From 3332ebbc1dc877a875acf69f481627b595268ef8 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Fri, 24 May 2024 15:32:43 +0200
Subject: [PATCH 01/41] WIP: restructure reference building

---
 conf/modules.config                    |   2 +-
 main.nf                                |  10 +-
 nextflow.config                        |   5 +-
 subworkflows/local/build_references.nf | 122 +++++++
 workflows/build_references.nf          |  89 -----
 workflows/rnafusion.nf                 | 436 +++++++++++++------------
 6 files changed, 347 insertions(+), 317 deletions(-)
 create mode 100644 subworkflows/local/build_references.nf
 delete mode 100644 workflows/build_references.nf

diff --git a/conf/modules.config b/conf/modules.config
index a1fe1702..44dec339 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -59,7 +59,7 @@ process {
 
     withName: 'FASTQC' {
         ext.args = '--quiet'
-        ext.when         = { !params.skip_qc }
+        ext.when = { !params.skip_qc }
         publishDir = [
             path: { "${params.outdir}/fastqc" },
             mode: params.publish_dir_mode,
diff --git a/main.nf b/main.nf
index ac96ab66..4c945cf8 100644
--- a/main.nf
+++ b/main.nf
@@ -20,7 +20,6 @@ nextflow.enable.dsl = 2
 include { PIPELINE_INITIALISATION } from './subworkflows/local/utils_nfcore_rnafusion_pipeline'
 include { PIPELINE_COMPLETION     } from './subworkflows/local/utils_nfcore_rnafusion_pipeline'
 include { getGenomeAttribute      } from './subworkflows/local/utils_nfcore_rnafusion_pipeline'
-include { BUILD_REFERENCES        } from './workflows/build_references'
 include { RNAFUSION               } from './workflows/rnafusion'
 
 
@@ -50,12 +49,9 @@ workflow NFCORE_RNAFUSION {
     //
     // WORKFLOW: Run pipeline
     //
-    if (params.build_references) {
-        BUILD_REFERENCES ()
-    } else {
-        ch_samplesheet = Channel.value(file(params.input, checkIfExists: true))
-        RNAFUSION(ch_samplesheet)
-    }
+
+    ch_samplesheet = Channel.value(file(params.input, checkIfExists: true))
+    RNAFUSION(ch_samplesheet)
 
 }
 /*
diff --git a/nextflow.config b/nextflow.config
index 14127c38..265c3c0b 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -33,11 +33,10 @@ params {
     genomes                    = [:]
 
     // Genomes options
-    fasta          = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.all.fa"
-    fai            = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.all.fa.fai"
+    fasta          = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.dna.primary_assembly.fa"
+    fai            = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.dna.primary_assembly.fa.fai"
     gtf            = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.gtf"
     chrgtf         = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.chr.gtf"
-    transcript     = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.cdna.all.fa.gz"
     refflat        = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.chr.gtf.refflat"
     rrna_intervals = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.interval_list"
 
diff --git a/subworkflows/local/build_references.nf b/subworkflows/local/build_references.nf
new file mode 100644
index 00000000..bb2acc4d
--- /dev/null
+++ b/subworkflows/local/build_references.nf
@@ -0,0 +1,122 @@
+/*
+========================================================================================
+    IMPORT LOCAL MODULES/SUBWORKFLOWS
+========================================================================================
+*/
+
+include { ARRIBA_DOWNLOAD }                 from '../../modules/local/arriba/download/main'
+include { ENSEMBL_DOWNLOAD }                from '../../modules/local/ensembl/main'
+include { FUSIONCATCHER_DOWNLOAD }          from '../../modules/local/fusioncatcher/download/main'
+include { FUSIONREPORT_DOWNLOAD }           from '../../modules/local/fusionreport/download/main'
+include { HGNC_DOWNLOAD }                   from '../../modules/local/hgnc/main'
+include { STARFUSION_BUILD }                from '../../modules/local/starfusion/build/main'
+include { STARFUSION_DOWNLOAD }             from '../../modules/local/starfusion/download/main'
+include { GTF_TO_REFFLAT }                  from '../../modules/local/uscs/custom_gtftogenepred/main'
+include { RRNA_TRANSCRIPTS }                from '../../modules/local/rrnatranscripts/main'
+include { CONVERT2BED }                     from '../../modules/local/convert2bed/main'
+/*
+========================================================================================
+    IMPORT NF-CORE MODULES/SUBWORKFLOWS
+========================================================================================
+*/
+
+include { SAMTOOLS_FAIDX }                  from '../../modules/nf-core/samtools/faidx/main'
+include { STAR_GENOMEGENERATE }             from '../../modules/nf-core/star/genomegenerate/main'
+include { GATK4_CREATESEQUENCEDICTIONARY }  from '../../modules/nf-core/gatk4/createsequencedictionary/main'
+include { GATK4_BEDTOINTERVALLIST }         from '../../modules/nf-core/gatk4/bedtointervallist/main'
+include { SALMON_INDEX }                    from '../../modules/nf-core/salmon/index/main'
+include { GFFREAD }                         from '../../modules/nf-core/gffread/main'
+
+/*
+========================================================================================
+    RUN MAIN WORKFLOW
+========================================================================================
+*/
+
+workflow BUILD_REFERENCES {
+
+
+    main:
+
+    ch_versions = Channel.empty()
+
+    def fake_meta = [:]
+    fake_meta.id = "Homo_sapiens.${params.genome}.${params.ensembl_version}"
+
+    if (!file(params.fasta).exists() || file(params.fasta).isEmpty() ||
+                    !file(params.chrgtf).exists() || file(params.chrgtf).isEmpty() ||
+                    !file(params.gtf).exists() || file(params.gtf).isEmpty()){
+        ENSEMBL_DOWNLOAD(params.ensembl_version, params.genome, fake_meta)}
+    ch_fasta = {(!file(params.fasta).exists() || file(params.fasta).isEmpty()) ? ENSEMBL_DOWNLOAD.out.primary_assembly : Channel.fromPath(params.fasta).map { that -> [[id:that.Name], that] }.collect()}
+
+    if (!file(params.hgnc_ref).exists() || file(params.hgnc_ref).isEmpty() ||
+                    !file(params.hgnc_date).exists() || file(params.hgnc_date).isEmpty()){
+        HGNC_DOWNLOAD( )}
+
+    if (!file(params.fai).exists() || file(params.fai).isEmpty(){
+        SAMTOOLS_FAIDX(ENSEMBL_DOWNLOAD.out.primary_assembly, [[],[]])}
+
+    if (!file(params.rrna_intervals).exists() || file(params.rrna_intervals).isEmpty(){
+        GATK4_CREATESEQUENCEDICTIONARY(ENSEMBL_DOWNLOAD.out.primary_assembly)
+        RRNA_TRANSCRIPTS(ENSEMBL_DOWNLOAD.out.gtf)
+        CONVERT2BED(RRNA_TRANSCRIPTS.out.rrna_gtf)
+        GATK4_BEDTOINTERVALLIST(CONVERT2BED.out.bed, GATK4_CREATESEQUENCEDICTIONARY.out.dict)
+        }
+
+    if (!file(params.salmon_index).exists() || file(params.salmon_index).isEmpty(){ // add condition for qc, check that dirs can also be checked with isEmpty()
+        GFFREAD(ENSEMBL_DOWNLOAD.out.gtf, ENSEMBL_DOWNLOAD.out.primary_assembly.map { meta, fasta -> [ fasta ] })
+        SALMON_INDEX(ENSEMBL_DOWNLOAD.out.primary_assembly.map{ meta, fasta -> [ fasta ] }, GFFREAD.out.gffread_fasta.map{ meta, gffread_fasta -> [ gffread_fasta ] })
+        }
+
+
+    if ((params.starindex || params.all || params.starfusion || params.arriba) &&
+            (!params.starindex_ref.exits() || params.starindex_ref.isEmpty())
+            ) {
+        STAR_GENOMEGENERATE( ENSEMBL_DOWNLOAD.out.primary_assembly, ENSEMBL_DOWNLOAD.out.gtf )
+    }
+    ch_starindex_ref = ...
+
+    // if (params.arriba || params.all) {
+    //     ARRIBA_DOWNLOAD()
+    // }
+
+    // if (params.fusioncatcher || params.all) {
+    //     FUSIONCATCHER_DOWNLOAD()
+    // }
+
+    // if (params.starfusion || params.all) {
+    //     if (params.starfusion_build){
+    //         STARFUSION_BUILD( ENSEMBL_DOWNLOAD.out.primary_assembly, ENSEMBL_DOWNLOAD.out.gtf )
+    //     } else {
+    //         STARFUSION_DOWNLOAD()
+    //     }
+    // }
+
+    // if (params.starfusion_build){
+    //     GTF_TO_REFFLAT(ENSEMBL_DOWNLOAD.out.gtf)
+    // } else {
+    //     GTF_TO_REFFLAT(STARFUSION_DOWNLOAD.out.gtf)
+    // }
+
+    // if (params.fusionreport || params.all) {
+    //     FUSIONREPORT_DOWNLOAD( params.cosmic_username, params.cosmic_passwd )
+    // }
+
+    emit:
+    ch_fasta
+    ch_chrgtf = {(!file(params.chrgtf).exists() || file(params.chrgtf).isEmpty()) ? ENSEMBL_DOWNLOAD.out.chrgtf : Channel.fromPath(params.chrgtf).map { that -> [[id:that.Name], that] }.collect()}
+    ch_gtf = {(!file(params.gtf).exists() || file(params.gtf).isEmpty()) ? ENSEMBL_DOWNLOAD.out.gtf : Channel.fromPath(params.gtf).map { that -> [[id:that.Name], that] }.collect()}
+    ch_hgnc_ref = Channel.fromPath(params.hgnc_ref).map { it -> [[id:it.Name], it] }.collect()
+    ch_hgnc_date = Channel.fromPath(params.hgnc_date).map { it -> [[id:it.Name], it] }.collect()
+    ch_fai = Channel.fromPath(params.fai).map { it -> [[id:it.Name], it] }.collect()
+    ch_rrna_interval = params.starfusion_build ?  Channel.fromPath(params.rrna_intervals).map { it -> [[id:it.Name], it] }.collect() : Channel.fromPath("${params.ensembl_ref}/ref_annot.interval_list").map { it -> [[id:it.Name], it] }.collect()
+    ch_salmon_index = Channel.fromPath(params.salmon_index).map { it -> [[id:it.Name], it] }.collect()
+
+
+}
+
+/*
+========================================================================================
+    THE END
+========================================================================================
+*/
diff --git a/workflows/build_references.nf b/workflows/build_references.nf
deleted file mode 100644
index 5b523db3..00000000
--- a/workflows/build_references.nf
+++ /dev/null
@@ -1,89 +0,0 @@
-/*
-========================================================================================
-    IMPORT LOCAL MODULES/SUBWORKFLOWS
-========================================================================================
-*/
-
-include { ARRIBA_DOWNLOAD }                 from '../modules/local/arriba/download/main'
-include { ENSEMBL_DOWNLOAD }                from '../modules/local/ensembl/main'
-include { FUSIONCATCHER_DOWNLOAD }          from '../modules/local/fusioncatcher/download/main'
-include { FUSIONREPORT_DOWNLOAD }           from '../modules/local/fusionreport/download/main'
-include { HGNC_DOWNLOAD }                   from '../modules/local/hgnc/main'
-include { STARFUSION_BUILD }                from '../modules/local/starfusion/build/main'
-include { STARFUSION_DOWNLOAD }             from '../modules/local/starfusion/download/main'
-include { GTF_TO_REFFLAT }                  from '../modules/local/uscs/custom_gtftogenepred/main'
-include { RRNA_TRANSCRIPTS }                from '../modules/local/rrnatranscripts/main'
-include { CONVERT2BED }                     from '../modules/local/convert2bed/main'
-/*
-========================================================================================
-    IMPORT NF-CORE MODULES/SUBWORKFLOWS
-========================================================================================
-*/
-
-include { SAMTOOLS_FAIDX }                  from '../modules/nf-core/samtools/faidx/main'
-include { STAR_GENOMEGENERATE }             from '../modules/nf-core/star/genomegenerate/main'
-include { GATK4_CREATESEQUENCEDICTIONARY }  from '../modules/nf-core/gatk4/createsequencedictionary/main'
-include { GATK4_BEDTOINTERVALLIST }         from '../modules/nf-core/gatk4/bedtointervallist/main'
-include { SALMON_INDEX }                    from '../modules/nf-core/salmon/index/main'
-include { GFFREAD }                         from '../modules/nf-core/gffread/main'
-
-/*
-========================================================================================
-    RUN MAIN WORKFLOW
-========================================================================================
-*/
-
-workflow BUILD_REFERENCES {
-
-    def fake_meta = [:]
-    fake_meta.id = "Homo_sapiens.${params.genome}.${params.ensembl_version}"
-    ENSEMBL_DOWNLOAD( params.ensembl_version, params.genome, fake_meta )
-    HGNC_DOWNLOAD( )
-    SAMTOOLS_FAIDX(ENSEMBL_DOWNLOAD.out.primary_assembly, [[],[]])
-    GATK4_CREATESEQUENCEDICTIONARY(ENSEMBL_DOWNLOAD.out.primary_assembly)
-
-    RRNA_TRANSCRIPTS(ENSEMBL_DOWNLOAD.out.gtf)
-    CONVERT2BED(RRNA_TRANSCRIPTS.out.rrna_gtf)
-
-    GATK4_BEDTOINTERVALLIST(CONVERT2BED.out.bed, GATK4_CREATESEQUENCEDICTIONARY.out.dict)
-
-    GFFREAD(ENSEMBL_DOWNLOAD.out.gtf, ENSEMBL_DOWNLOAD.out.primary_assembly.map { meta, fasta -> [ fasta ] })
-    SALMON_INDEX(ENSEMBL_DOWNLOAD.out.primary_assembly.map{ meta, fasta -> [ fasta ] }, GFFREAD.out.gffread_fasta.map{ meta, gffread_fasta -> [ gffread_fasta ] })
-
-    if (params.starindex || params.all || params.starfusion || params.arriba) {
-        STAR_GENOMEGENERATE( ENSEMBL_DOWNLOAD.out.primary_assembly, ENSEMBL_DOWNLOAD.out.gtf )
-    }
-
-    if (params.arriba || params.all) {
-        ARRIBA_DOWNLOAD()
-    }
-
-    if (params.fusioncatcher || params.all) {
-        FUSIONCATCHER_DOWNLOAD()
-    }
-
-    if (params.starfusion || params.all) {
-        if (params.starfusion_build){
-            STARFUSION_BUILD( ENSEMBL_DOWNLOAD.out.primary_assembly, ENSEMBL_DOWNLOAD.out.gtf )
-        } else {
-            STARFUSION_DOWNLOAD()
-        }
-    }
-
-    if (params.starfusion_build){
-        GTF_TO_REFFLAT(ENSEMBL_DOWNLOAD.out.gtf)
-    } else {
-        GTF_TO_REFFLAT(STARFUSION_DOWNLOAD.out.gtf)
-    }
-
-    if (params.fusionreport || params.all) {
-        FUSIONREPORT_DOWNLOAD( params.cosmic_username, params.cosmic_passwd )
-    }
-
-}
-
-/*
-========================================================================================
-    THE END
-========================================================================================
-*/
diff --git a/workflows/rnafusion.nf b/workflows/rnafusion.nf
index 45fd77eb..bf7fa1b8 100644
--- a/workflows/rnafusion.nf
+++ b/workflows/rnafusion.nf
@@ -12,25 +12,6 @@ include { softwareVersionsToYAML } from '../subworkflows/nf-core/utils_nfcore_pi
 include { methodsDescriptionText } from '../subworkflows/local/utils_nfcore_rnafusion_pipeline'
 include { paramsSummaryLog; paramsSummaryMap } from 'plugin/nf-validation'
 
-ch_chrgtf = params.starfusion_build ? Channel.fromPath(params.chrgtf).map { it -> [[id:it.Name], it] }.collect() : Channel.fromPath("${params.starfusion_ref}/ref_annot.gtf").map { it -> [[id:it.Name], it] }.collect()
-ch_starindex_ref = params.starfusion_build ? Channel.fromPath(params.starindex_ref).map { it -> [[id:it.Name], it] }.collect() : Channel.fromPath("${params.starfusion_ref}/ref_genome.fa.star.idx").map { it -> [[id:it.Name], it] }.collect()
-ch_starindex_ensembl_ref = Channel.fromPath(params.starindex_ref).map { it -> [[id:it.Name], it] }.collect()
-ch_refflat = params.starfusion_build ? Channel.fromPath(params.refflat).map { it -> [[id:it.Name], it] }.collect() : Channel.fromPath("${params.ensembl_ref}/ref_annot.gtf.refflat").map { it -> [[id:it.Name], it] }.collect()
-ch_rrna_interval = params.starfusion_build ?  Channel.fromPath(params.rrna_intervals).map { it -> [[id:it.Name], it] }.collect() : Channel.fromPath("${params.ensembl_ref}/ref_annot.interval_list").map { it -> [[id:it.Name], it] }.collect()
-ch_fusionreport_ref = Channel.fromPath(params.fusionreport_ref).map { it -> [[id:it.Name], it] }.collect()
-ch_arriba_ref_blacklist = Channel.fromPath(params.arriba_ref_blacklist).map { it -> [[id:it.Name], it] }.collect()
-ch_arriba_ref_known_fusions = Channel.fromPath(params.arriba_ref_known_fusions).map { it -> [[id:it.Name], it] }.collect()
-ch_arriba_ref_protein_domains = Channel.fromPath(params.arriba_ref_protein_domains).map { it -> [[id:it.Name], it] }.collect()
-ch_arriba_ref_cytobands = Channel.fromPath(params.arriba_ref_cytobands).map { it -> [[id:it.Name], it] }.collect()
-ch_hgnc_ref = Channel.fromPath(params.hgnc_ref).map { it -> [[id:it.Name], it] }.collect()
-ch_hgnc_date = Channel.fromPath(params.hgnc_date).map { it -> [[id:it.Name], it] }.collect()
-ch_fasta = Channel.fromPath(params.fasta).map { it -> [[id:it.Name], it] }.collect()
-ch_gtf = Channel.fromPath(params.gtf).map { it -> [[id:it.Name], it] }.collect()
-ch_salmon_index = Channel.fromPath(params.salmon_index).map { it -> [[id:it.Name], it] }.collect()
-ch_transcript = Channel.fromPath(params.transcript).map { it -> [[id:it.Name], it] }.collect()
-ch_fai = Channel.fromPath(params.fai).map { it -> [[id:it.Name], it] }.collect()
-
-
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     IMPORT LOCAL MODULES/SUBWORKFLOWS
@@ -40,7 +21,7 @@ ch_fai = Channel.fromPath(params.fai).map { it -> [[id:it.Name], it] }.collect()
 //
 // SUBWORKFLOW: Consisting of a mix of local and nf-core/modules
 //
-
+include { BUILD_REFERENCES              }   from '../subworkflows/local/build_references'
 include { TRIM_WORKFLOW                 }   from '../subworkflows/local/trim_workflow'
 include { ARRIBA_WORKFLOW               }   from '../subworkflows/local/arriba_workflow'
 include { QC_WORKFLOW                   }   from '../subworkflows/local/qc_workflow'
@@ -75,212 +56,233 @@ workflow RNAFUSION {
 
     main:
 
-    ch_versions = Channel.empty()
-    ch_multiqc_files = Channel.empty()
-
-    //
-    // Create channel from input file provided through params.input
-    //
-    Channel
-        .fromSamplesheet("input")
-        .map {
-            meta, fastq_1, fastq_2, strandedness ->
-                if (!fastq_2) {
-                    return [ meta.id, meta + [ single_end:true ], [ fastq_1 ] ]
-                } else {
-                    return [ meta.id, meta + [ single_end:false ], [ fastq_1, fastq_2 ] ]
-                }
-        }
-        .groupTuple()
-        .map {
-            validateInputSamplesheet(it)
-        }
-        .branch {
-            meta, fastqs ->
-                single  : fastqs.size() == 1
-                    return [ meta, fastqs.flatten() ]
-                multiple: fastqs.size() > 1
-                    return [ meta, fastqs.flatten() ]
-        }
-        .set { ch_fastq }
-
-    //
-    // MODULE: Concatenate FastQ files from same sample if required
-    //
-    CAT_FASTQ (
-        ch_fastq.multiple
-    )
-    .reads
-    .mix(ch_fastq.single)
-    .set { ch_cat_fastq }
-    ch_versions = ch_versions.mix(CAT_FASTQ.out.versions)
-
 
-    //
-    // MODULE: Run FastQC
-    //
-    FASTQC (
-        ch_cat_fastq
-    )
-    ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]})
-    ch_versions = ch_versions.mix(FASTQC.out.versions)
+    // Reference channels
+    // ch_starindex_ref = params.starfusion_build ? Channel.fromPath(params.starindex_ref).map { it -> [[id:it.Name], it] }.collect() : Channel.fromPath("${params.starfusion_ref}/ref_genome.fa.star.idx").map { it -> [[id:it.Name], it] }.collect()
+    // ch_starindex_ensembl_ref = Channel.fromPath(params.starindex_ref).map { it -> [[id:it.Name], it] }.collect()
+    // ch_refflat = params.starfusion_build ? Channel.fromPath(params.refflat).map { it -> [[id:it.Name], it] }.collect() : Channel.fromPath("${params.ensembl_ref}/ref_annot.gtf.refflat").map { it -> [[id:it.Name], it] }.collect()
+    // ch_fusionreport_ref = Channel.fromPath(params.fusionreport_ref).map { it -> [[id:it.Name], it] }.collect()
+    // ch_arriba_ref_blacklist = Channel.fromPath(params.arriba_ref_blacklist).map { it -> [[id:it.Name], it] }.collect()
+    // ch_arriba_ref_known_fusions = Channel.fromPath(params.arriba_ref_known_fusions).map { it -> [[id:it.Name], it] }.collect()
+    // ch_arriba_ref_protein_domains = Channel.fromPath(params.arriba_ref_protein_domains).map { it -> [[id:it.Name], it] }.collect()
+    // ch_arriba_ref_cytobands = Channel.fromPath(params.arriba_ref_cytobands).map { it -> [[id:it.Name], it] }.collect()
 
-    TRIM_WORKFLOW (
-        ch_cat_fastq
-    )
-    ch_reads_fusioncatcher = TRIM_WORKFLOW.out.ch_reads_fusioncatcher
-    ch_reads_all = TRIM_WORKFLOW.out.ch_reads_all
-    ch_versions = ch_versions.mix(TRIM_WORKFLOW.out.versions)
 
 
-    SALMON_QUANT( ch_reads_all, ch_salmon_index.map{ meta, index ->  index  }, ch_gtf.map{ meta, gtf ->  gtf  }, [], false, 'A')
+    ch_versions = Channel.empty()
+    ch_multiqc_files = Channel.empty()
 
 
     //
-    // SUBWORKFLOW:  Run STAR alignment and Arriba
+    // Create references if necessary
     //
-    ARRIBA_WORKFLOW (
-        ch_reads_all,
-        ch_gtf,
-        ch_fasta,
-        ch_starindex_ensembl_ref,
-        ch_arriba_ref_blacklist,
-        ch_arriba_ref_known_fusions,
-        ch_arriba_ref_protein_domains
-    )
-    ch_versions = ch_versions.mix(ARRIBA_WORKFLOW.out.versions)
-
-
-//Run STAR fusion
-    STARFUSION_WORKFLOW (
-        ch_reads_all,
-        ch_chrgtf,
-        ch_starindex_ref,
-        ch_fasta
-    )
-    ch_versions = ch_versions.mix(STARFUSION_WORKFLOW.out.versions)
-
-
-//Run fusioncatcher
-    FUSIONCATCHER_WORKFLOW (
-        ch_reads_fusioncatcher
-    )
-    ch_versions = ch_versions.mix(FUSIONCATCHER_WORKFLOW.out.versions)
-
-
-//Run stringtie
-    STRINGTIE_WORKFLOW (
-        STARFUSION_WORKFLOW.out.ch_bam_sorted,
-        ch_chrgtf
-    )
-    ch_versions = ch_versions.mix(STRINGTIE_WORKFLOW.out.versions)
-
-
-    //Run fusion-report
-    FUSIONREPORT_WORKFLOW (
-        ch_reads_all,
-        ch_fusionreport_ref,
-        ARRIBA_WORKFLOW.out.fusions,
-        STARFUSION_WORKFLOW.out.fusions,
-        FUSIONCATCHER_WORKFLOW.out.fusions
-    )
-    ch_versions = ch_versions.mix(FUSIONREPORT_WORKFLOW.out.versions)
-
-
-    //Run fusionInpector
-    FUSIONINSPECTOR_WORKFLOW (
-        ch_reads_all,
-        FUSIONREPORT_WORKFLOW.out.fusion_list,
-        FUSIONREPORT_WORKFLOW.out.fusion_list_filtered,
-        FUSIONREPORT_WORKFLOW.out.report,
-        FUSIONREPORT_WORKFLOW.out.csv,
-        STARFUSION_WORKFLOW.out.ch_bam_sorted_indexed,
-        ch_chrgtf,
-        ch_arriba_ref_protein_domains,
-        ch_arriba_ref_cytobands,
-        ch_hgnc_ref,
-        ch_hgnc_date
-    )
-    ch_versions = ch_versions.mix(FUSIONINSPECTOR_WORKFLOW.out.versions)
-
-
-    //QC
-    QC_WORKFLOW (
-        ch_reads_all,
-        STARFUSION_WORKFLOW.out.ch_bam_sorted,
-        STARFUSION_WORKFLOW.out.ch_bam_sorted_indexed,
-        ch_chrgtf,
-        ch_refflat,
-        ch_fasta,
-        ch_fai,
-        ch_rrna_interval
-    )
-    ch_versions = ch_versions.mix(QC_WORKFLOW.out.versions)
 
-    //
-    // Collate and save software versions
-    //
-    softwareVersionsToYAML(ch_versions)
-        .collectFile(
-            storeDir: "${params.outdir}/pipeline_info",
-            name: 'nf_core_pipeline_software_mqc_versions.yml',
-            sort: true,
-            newLine: true
-        ).set { ch_collated_versions }
-
-
-    //
-    // MODULE: MultiQC
-    //
-    ch_multiqc_config        = Channel.fromPath(
-        "$projectDir/assets/multiqc_config.yml", checkIfExists: true)
-    ch_multiqc_custom_config = params.multiqc_config ?
-        Channel.fromPath(params.multiqc_config, checkIfExists: true) :
-        Channel.empty()
-    ch_multiqc_logo          = params.multiqc_logo ?
-        Channel.fromPath(params.multiqc_logo, checkIfExists: true) :
-        Channel.empty()
-
-    summary_params      = paramsSummaryMap(
-        workflow, parameters_schema: "nextflow_schema.json")
-    ch_workflow_summary = Channel.value(paramsSummaryMultiqc(summary_params))
-
-    ch_multiqc_custom_methods_description = params.multiqc_methods_description ?
-        file(params.multiqc_methods_description, checkIfExists: true) :
-        file("$projectDir/assets/methods_description_template.yml", checkIfExists: true)
-    ch_methods_description                = Channel.value(
-        methodsDescriptionText(ch_multiqc_custom_methods_description))
-
-    ch_multiqc_files = ch_multiqc_files.mix(
-        ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml'))
-    ch_multiqc_files = ch_multiqc_files.mix(ch_collated_versions)
-    ch_multiqc_files = ch_multiqc_files.mix(
-        ch_methods_description.collectFile(
-            name: 'methods_description_mqc.yaml',
-            sort: true
-        )
-    )
-    ch_multiqc_files                      = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]}.ifEmpty([]))
-    ch_multiqc_files                      = ch_multiqc_files.mix(TRIM_WORKFLOW.out.ch_fastp_html.collect{it[1]}.ifEmpty([]))
-    ch_multiqc_files                      = ch_multiqc_files.mix(TRIM_WORKFLOW.out.ch_fastp_json.collect{it[1]}.ifEmpty([]))
-    ch_multiqc_files                      = ch_multiqc_files.mix(TRIM_WORKFLOW.out.ch_fastqc_trimmed.collect{it[1]}.ifEmpty([]))
-    ch_multiqc_files                      = ch_multiqc_files.mix(STARFUSION_WORKFLOW.out.star_stats.collect{it[1]}.ifEmpty([]))
-    ch_multiqc_files                      = ch_multiqc_files.mix(STARFUSION_WORKFLOW.out.star_gene_count.collect{it[1]}.ifEmpty([]))
-    ch_multiqc_files                      = ch_multiqc_files.mix(QC_WORKFLOW.out.rnaseq_metrics.collect{it[1]}.ifEmpty([]))
-    ch_multiqc_files                      = ch_multiqc_files.mix(QC_WORKFLOW.out.duplicate_metrics.collect{it[1]}.ifEmpty([]))
-    ch_multiqc_files                      = ch_multiqc_files.mix(QC_WORKFLOW.out.insertsize_metrics.collect{it[1]}.ifEmpty([]))
-    ch_multiqc_files                      = ch_multiqc_files.mix(FUSIONINSPECTOR_WORKFLOW.out.ch_arriba_visualisation.collect{it[1]}.ifEmpty([]))
-
-    MULTIQC (
-        ch_multiqc_files.collect(),
-        ch_multiqc_config.toList(),
-        ch_multiqc_custom_config.toList(),
-        ch_multiqc_logo.toList()
-    )
-
-    emit:
-    multiqc_report = MULTIQC.out.report.toList() // channel: /path/to/multiqc_report.html
-    versions       = ch_versions                 // channel: [ path(versions.yml) ]
+    BUILD_REFERENCES()
+
+
+//     //
+//     // Create channel from input file provided through params.input
+//     //
+//     Channel
+//         .fromSamplesheet("input")
+//         .map {
+//             meta, fastq_1, fastq_2, strandedness ->
+//                 if (!fastq_2) {
+//                     return [ meta.id, meta + [ single_end:true ], [ fastq_1 ] ]
+//                 } else {
+//                     return [ meta.id, meta + [ single_end:false ], [ fastq_1, fastq_2 ] ]
+//                 }
+//         }
+//         .groupTuple()
+//         .map {
+//             validateInputSamplesheet(it)
+//         }
+//         .branch {
+//             meta, fastqs ->
+//                 single  : fastqs.size() == 1
+//                     return [ meta, fastqs.flatten() ]
+//                 multiple: fastqs.size() > 1
+//                     return [ meta, fastqs.flatten() ]
+//         }
+//         .set { ch_fastq }
+
+//     //
+//     // MODULE: Concatenate FastQ files from same sample if required
+//     //
+//     CAT_FASTQ (
+//         ch_fastq.multiple
+//     )
+//     .reads
+//     .mix(ch_fastq.single)
+//     .set { ch_cat_fastq }
+//     ch_versions = ch_versions.mix(CAT_FASTQ.out.versions)
+
+
+//     //
+//     // MODULE: Run FastQC
+//     //
+//     FASTQC (
+//         ch_cat_fastq
+//     )
+//     ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]})
+//     ch_versions = ch_versions.mix(FASTQC.out.versions)
+
+//     TRIM_WORKFLOW (
+//         ch_cat_fastq
+//     )
+//     ch_reads_fusioncatcher = TRIM_WORKFLOW.out.ch_reads_fusioncatcher
+//     ch_reads_all = TRIM_WORKFLOW.out.ch_reads_all
+//     ch_versions = ch_versions.mix(TRIM_WORKFLOW.out.versions)
+
+
+//     SALMON_QUANT( ch_reads_all, ch_salmon_index.map{ meta, index ->  index  }, ch_gtf.map{ meta, gtf ->  gtf  }, [], false, 'A')
+
+
+//     //
+//     // SUBWORKFLOW:  Run STAR alignment and Arriba
+//     //
+//     ARRIBA_WORKFLOW (
+//         ch_reads_all,
+//         ch_gtf,
+//         ch_fasta,
+//         ch_starindex_ensembl_ref,
+//         ch_arriba_ref_blacklist,
+//         ch_arriba_ref_known_fusions,
+//         ch_arriba_ref_protein_domains
+//     )
+//     ch_versions = ch_versions.mix(ARRIBA_WORKFLOW.out.versions)
+
+
+// //Run STAR fusion
+//     STARFUSION_WORKFLOW (
+//         ch_reads_all,
+//         ch_chrgtf,
+//         ch_starindex_ref,
+//         ch_fasta
+//     )
+//     ch_versions = ch_versions.mix(STARFUSION_WORKFLOW.out.versions)
+
+
+// //Run fusioncatcher
+//     FUSIONCATCHER_WORKFLOW (
+//         ch_reads_fusioncatcher
+//     )
+//     ch_versions = ch_versions.mix(FUSIONCATCHER_WORKFLOW.out.versions)
+
+
+// //Run stringtie
+//     STRINGTIE_WORKFLOW (
+//         STARFUSION_WORKFLOW.out.ch_bam_sorted,
+//         ch_chrgtf
+//     )
+//     ch_versions = ch_versions.mix(STRINGTIE_WORKFLOW.out.versions)
+
+
+//     //Run fusion-report
+//     FUSIONREPORT_WORKFLOW (
+//         ch_reads_all,
+//         ch_fusionreport_ref,
+//         ARRIBA_WORKFLOW.out.fusions,
+//         STARFUSION_WORKFLOW.out.fusions,
+//         FUSIONCATCHER_WORKFLOW.out.fusions
+//     )
+//     ch_versions = ch_versions.mix(FUSIONREPORT_WORKFLOW.out.versions)
+
+
+//     //Run fusionInpector
+//     FUSIONINSPECTOR_WORKFLOW (
+//         ch_reads_all,
+//         FUSIONREPORT_WORKFLOW.out.fusion_list,
+//         FUSIONREPORT_WORKFLOW.out.fusion_list_filtered,
+//         FUSIONREPORT_WORKFLOW.out.report,
+//         FUSIONREPORT_WORKFLOW.out.csv,
+//         STARFUSION_WORKFLOW.out.ch_bam_sorted_indexed,
+//         ch_chrgtf,
+//         ch_arriba_ref_protein_domains,
+//         ch_arriba_ref_cytobands,
+//         ch_hgnc_ref,
+//         ch_hgnc_date
+//     )
+//     ch_versions = ch_versions.mix(FUSIONINSPECTOR_WORKFLOW.out.versions)
+
+
+//     //QC
+//     QC_WORKFLOW (
+//         ch_reads_all,
+//         STARFUSION_WORKFLOW.out.ch_bam_sorted,
+//         STARFUSION_WORKFLOW.out.ch_bam_sorted_indexed,
+//         ch_chrgtf,
+//         ch_refflat,
+//         ch_fasta,
+//         ch_fai,
+//         ch_rrna_interval
+//     )
+//     ch_versions = ch_versions.mix(QC_WORKFLOW.out.versions)
+
+//     //
+//     // Collate and save software versions
+//     //
+//     softwareVersionsToYAML(ch_versions)
+//         .collectFile(
+//             storeDir: "${params.outdir}/pipeline_info",
+//             name: 'nf_core_pipeline_software_mqc_versions.yml',
+//             sort: true,
+//             newLine: true
+//         ).set { ch_collated_versions }
+
+
+//     //
+//     // MODULE: MultiQC
+//     //
+//     ch_multiqc_config        = Channel.fromPath(
+//         "$projectDir/assets/multiqc_config.yml", checkIfExists: true)
+//     ch_multiqc_custom_config = params.multiqc_config ?
+//         Channel.fromPath(params.multiqc_config, checkIfExists: true) :
+//         Channel.empty()
+//     ch_multiqc_logo          = params.multiqc_logo ?
+//         Channel.fromPath(params.multiqc_logo, checkIfExists: true) :
+//         Channel.empty()
+
+//     summary_params      = paramsSummaryMap(
+//         workflow, parameters_schema: "nextflow_schema.json")
+//     ch_workflow_summary = Channel.value(paramsSummaryMultiqc(summary_params))
+
+//     ch_multiqc_custom_methods_description = params.multiqc_methods_description ?
+//         file(params.multiqc_methods_description, checkIfExists: true) :
+//         file("$projectDir/assets/methods_description_template.yml", checkIfExists: true)
+//     ch_methods_description                = Channel.value(
+//         methodsDescriptionText(ch_multiqc_custom_methods_description))
+
+//     ch_multiqc_files = ch_multiqc_files.mix(
+//         ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml'))
+//     ch_multiqc_files = ch_multiqc_files.mix(ch_collated_versions)
+//     ch_multiqc_files = ch_multiqc_files.mix(
+//         ch_methods_description.collectFile(
+//             name: 'methods_description_mqc.yaml',
+//             sort: true
+//         )
+//     )
+//     ch_multiqc_files                      = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]}.ifEmpty([]))
+//     ch_multiqc_files                      = ch_multiqc_files.mix(TRIM_WORKFLOW.out.ch_fastp_html.collect{it[1]}.ifEmpty([]))
+//     ch_multiqc_files                      = ch_multiqc_files.mix(TRIM_WORKFLOW.out.ch_fastp_json.collect{it[1]}.ifEmpty([]))
+//     ch_multiqc_files                      = ch_multiqc_files.mix(TRIM_WORKFLOW.out.ch_fastqc_trimmed.collect{it[1]}.ifEmpty([]))
+//     ch_multiqc_files                      = ch_multiqc_files.mix(STARFUSION_WORKFLOW.out.star_stats.collect{it[1]}.ifEmpty([]))
+//     ch_multiqc_files                      = ch_multiqc_files.mix(STARFUSION_WORKFLOW.out.star_gene_count.collect{it[1]}.ifEmpty([]))
+//     ch_multiqc_files                      = ch_multiqc_files.mix(QC_WORKFLOW.out.rnaseq_metrics.collect{it[1]}.ifEmpty([]))
+//     ch_multiqc_files                      = ch_multiqc_files.mix(QC_WORKFLOW.out.duplicate_metrics.collect{it[1]}.ifEmpty([]))
+//     ch_multiqc_files                      = ch_multiqc_files.mix(QC_WORKFLOW.out.insertsize_metrics.collect{it[1]}.ifEmpty([]))
+//     ch_multiqc_files                      = ch_multiqc_files.mix(FUSIONINSPECTOR_WORKFLOW.out.ch_arriba_visualisation.collect{it[1]}.ifEmpty([]))
+
+//     MULTIQC (
+//         ch_multiqc_files.collect(),
+//         ch_multiqc_config.toList(),
+//         ch_multiqc_custom_config.toList(),
+//         ch_multiqc_logo.toList()
+//     )
+
+//     emit:
+//     multiqc_report = MULTIQC.out.report.toList() // channel: /path/to/multiqc_report.html
+//     versions       = ch_versions                 // channel: [ path(versions.yml) ]
 
 }
 

From bf0c33e179290f060a661301e906cb3d24435951 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Tue, 28 May 2024 15:39:38 +0200
Subject: [PATCH 02/41] refactor downloading of references

---
 modules/local/fusioncatcher/build/main.nf     |  42 +++++
 modules/local/fusioncatcher/build/meta.yml    |  25 +++
 modules/local/fusioncatcher/download/main.nf  |  30 ++--
 .../local/uscs/custom_gtftogenepred/main.nf   |   1 +
 nextflow.config                               |  30 ++--
 nextflow_schema.json                          |  48 +++---
 subworkflows/local/build_references.nf        | 144 +++++++++++-------
 workflows/rnafusion.nf                        |   9 +-
 8 files changed, 220 insertions(+), 109 deletions(-)
 create mode 100644 modules/local/fusioncatcher/build/main.nf
 create mode 100644 modules/local/fusioncatcher/build/meta.yml

diff --git a/modules/local/fusioncatcher/build/main.nf b/modules/local/fusioncatcher/build/main.nf
new file mode 100644
index 00000000..afab999c
--- /dev/null
+++ b/modules/local/fusioncatcher/build/main.nf
@@ -0,0 +1,42 @@
+process FUSIONCATCHER_BUILD {
+    tag "fusioncatcher_build"
+    label 'process_medium'
+
+    conda "bioconda::fusioncatcher=1.33"
+    container "docker.io/clinicalgenomics/fusioncatcher:1.33"
+
+    input:
+    val ensembl_version
+
+    output:
+    path "*"                , emit: reference
+    path "versions.yml"     , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+
+    def args = task.ext.args ?: ''
+    """
+    fusioncatcher-build \\
+        -g homo_sapiens \\
+        -o human_${human_version} \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        fusioncatcher: \$(echo \$(fusioncatcher --version 2>&1))
+    END_VERSIONS
+    """
+
+    stub:
+    """
+    mkdir human_v${ensembl_version}
+    touch human_v${ensembl_version}/ensembl_fully_overlapping_genes.txt
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        fusioncatcher: \$(echo \$(fusioncatcher --version 2>&1))
+    END_VERSIONS
+    """
+}
diff --git a/modules/local/fusioncatcher/build/meta.yml b/modules/local/fusioncatcher/build/meta.yml
new file mode 100644
index 00000000..40421a4e
--- /dev/null
+++ b/modules/local/fusioncatcher/build/meta.yml
@@ -0,0 +1,25 @@
+name: fusioncatcher_download
+description: Build genome for fusioncatcher
+keywords:
+  - sort
+tools:
+  - fusioncatcher:
+      description: Build genome for fusioncatcher
+      homepage: https://github.com/ndaniel/fusioncatcher/
+      documentation: https://github.com/ndaniel/fusioncatcher/blob/master/doc/manual.md
+      tool_dev_url: https://github.com/ndaniel/fusioncatcher/
+      doi: "10.1101/011650"
+      licence: ["GPL v3"]
+
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - reference:
+      type: directory
+      description: Path to fusioncatcher references
+      pattern: "*"
+
+authors:
+  - "@praveenraj2018, @rannick"
diff --git a/modules/local/fusioncatcher/download/main.nf b/modules/local/fusioncatcher/download/main.nf
index 156e70b6..7f59d920 100644
--- a/modules/local/fusioncatcher/download/main.nf
+++ b/modules/local/fusioncatcher/download/main.nf
@@ -5,6 +5,10 @@ process FUSIONCATCHER_DOWNLOAD {
     conda "bioconda::fusioncatcher=1.33"
     container "docker.io/clinicalgenomics/fusioncatcher:1.33"
 
+
+    input:
+    val ensembl_version
+
     output:
     path "*"                , emit: reference
     path "versions.yml"     , emit: versions
@@ -16,22 +20,14 @@ process FUSIONCATCHER_DOWNLOAD {
 
     def args = task.ext.args ?: ''
     def args2 = task.ext.args2 ?: ''
-    def human_version = "v102"
-    def url = "http://sourceforge.net/projects/fusioncatcher/files/data/human_${human_version}.tar.gz.aa"
+    def url =
     """
-    if wget --spider "$url" 2>/dev/null; then
-        wget $args $url
-        wget $args http://sourceforge.net/projects/fusioncatcher/files/data/human_${human_version}.tar.gz.ab
-        wget $args http://sourceforge.net/projects/fusioncatcher/files/data/human_${human_version}.tar.gz.ac
-        wget $args http://sourceforge.net/projects/fusioncatcher/files/data/human_${human_version}.tar.gz.ad
-        cat human_${human_version}.tar.gz.* | tar xz
-        rm human_${human_version}.tar*
-    else
-        fusioncatcher-build \\
-            -g homo_sapiens \\
-            -o human_${human_version} \\
-            $args2
-    fi
+    wget $args http://sourceforge.net/projects/fusioncatcher/files/data/human_${ensembl_version}.tar.gz.aa
+    wget $args http://sourceforge.net/projects/fusioncatcher/files/data/human_${ensembl_version}.tar.gz.ab
+    wget $args http://sourceforge.net/projects/fusioncatcher/files/data/human_${ensembl_version}.tar.gz.ac
+    wget $args http://sourceforge.net/projects/fusioncatcher/files/data/human_${ensembl_version}.tar.gz.ad
+    cat human_${ensembl_version}.tar.gz.* | tar xz
+    rm human_${ensembl_version}.tar*
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
@@ -40,9 +36,9 @@ process FUSIONCATCHER_DOWNLOAD {
     """
 
     stub:
-    def human_version = "v102"
     """
-    mkdir human_${human_version}
+    mkdir human_v${ensembl_version}
+    touch human_v${ensembl_version}/ensembl_fully_overlapping_genes.txt
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
         fusioncatcher: \$(echo \$(fusioncatcher --version 2>&1))
diff --git a/modules/local/uscs/custom_gtftogenepred/main.nf b/modules/local/uscs/custom_gtftogenepred/main.nf
index 78fcbd29..53a74e3d 100644
--- a/modules/local/uscs/custom_gtftogenepred/main.nf
+++ b/modules/local/uscs/custom_gtftogenepred/main.nf
@@ -1,4 +1,5 @@
 process GTF_TO_REFFLAT {
+    tag "$meta.id"
     label 'process_low'
 
     conda "bioconda::ucsc-gtftogenepred=377"
diff --git a/nextflow.config b/nextflow.config
index 265c3c0b..fe2dd83d 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -27,19 +27,11 @@ params {
     // Genome
     genome                     = 'GRCh38'
     genomes_base               = "${params.outdir}/references"
-    ensembl_version            = 102
+    ensembl_version            = 112
     read_length                = 100
     starfusion_build           = true
     genomes                    = [:]
 
-    // Genomes options
-    fasta          = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.dna.primary_assembly.fa"
-    fai            = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.dna.primary_assembly.fa.fai"
-    gtf            = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.gtf"
-    chrgtf         = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.chr.gtf"
-    refflat        = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.chr.gtf.refflat"
-    rrna_intervals = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.interval_list"
-
     // Filtering
     tools_cutoff               = 1
 
@@ -72,14 +64,21 @@ params {
     skip_qc                    = false
     skip_vis                   = false
 
+    // Download references option
+    download_refs              = true
+
     // Path to references
+    fasta                         = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.dna.primary_assembly.fa"
+    fai                           = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.dna.primary_assembly.fa.fai"
+    gtf                           = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.gtf"
+    chrgtf                        = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.chr.gtf"
+    refflat                       = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.gtf.refflat"
+    rrna_intervals                = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.interval_list"
     ensembl_ref                   = "${params.genomes_base}/ensembl"
-    arriba_ref                    = "${params.genomes_base}/arriba"
     arriba_ref_blacklist          = "${params.genomes_base}/arriba/blacklist_hg38_GRCh38_v2.4.0.tsv.gz"
-    arriba_ref_cytobands          = "${params.genomes_base}/arriba/cytobands_hg38_GRCh38_v2.4.0.tsv"
     arriba_ref_known_fusions      = "${params.genomes_base}/arriba/known_fusions_hg38_GRCh38_v2.4.0.tsv.gz"
     arriba_ref_protein_domains    = "${params.genomes_base}/arriba/protein_domains_hg38_GRCh38_v2.4.0.gff3"
-    fusioncatcher_ref             = "${params.genomes_base}/fusioncatcher/human_v102"
+    fusioncatcher_ref             = "${params.genomes_base}/fusioncatcher/human_v${params.ensembl_version}"
     hgnc_ref                      = "${params.genomes_base}/hgnc/hgnc_complete_set.txt"
     hgnc_date                     = "${params.genomes_base}/hgnc/HGNC-DB-timestamp.txt"
     salmon_index                  = "${params.genomes_base}/salmon/salmon"
@@ -88,6 +87,13 @@ params {
     fusionreport_ref              = "${params.genomes_base}/fusion_report_db"
 
 
+    // Internal file presence checks
+    salmon_index_stub_check       = "${params.genomes_base}/salmon/salmon/complete_ref_lens.bin"
+    starindex_ref_stub_check      = "${params.genomes_base}/star/star/Genome"
+    fusionreport_ref_stub_check   = "${params.genomes_base}/fusion_report_db/mitelman.db"
+    fusioncatcher_ref_stub_check  = "${params.genomes_base}/fusioncatcher/human_v${params.ensembl_version}/ensembl_fully_overlapping_genes.txt"
+    starfusion_ref_stub_check     = "${params.genomes_base}/starfusion/Pfam-A.hmm"
+
     // Path to fusion outputs
     arriba_fusions                = null
     starfusion_fusions            = null
diff --git a/nextflow_schema.json b/nextflow_schema.json
index 69270631..0889caa2 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -105,21 +105,11 @@
                     "fa_icon": "far fa-file-code",
                     "description": "Build or run arriba references/analyses"
                 },
-                "arriba_ref": {
-                    "type": "string",
-                    "fa_icon": "far fa-file-code",
-                    "description": "Path to arriba references"
-                },
                 "arriba_ref_blacklist": {
                     "type": "string",
                     "fa_icon": "far fa-file-code",
                     "description": "Path to arriba reference blacklist"
                 },
-                "arriba_ref_cytobands": {
-                    "type": "string",
-                    "fa_icon": "far fa-file-code",
-                    "description": "Path to arriba reference cytobands"
-                },
                 "arriba_ref_known_fusions": {
                     "type": "string",
                     "fa_icon": "far fa-file-code",
@@ -135,6 +125,11 @@
                     "fa_icon": "far fa-file-code",
                     "description": "Path to arriba output"
                 },
+                "download_refs": {
+                    "type": "boolean",
+                    "fa_icon": "far fa-file-code",
+                    "description": "Download references instead of building them (for fusioncatcher and starfusion)"
+                },
                 "ensembl_ref": {
                     "type": "string",
                     "fa_icon": "far fa-file-code",
@@ -160,6 +155,11 @@
                     "fa_icon": "far fa-file-code",
                     "description": "Path to fusioncatcher references"
                 },
+                "fusioncatcher_ref_stub_check": {
+                    "type": "string",
+                    "fa_icon": "far fa-file-code",
+                    "description": "Path to file in fusioncatcher references"
+                },
                 "fusioninspector_limitSjdbInsertNsj": {
                     "type": "integer",
                     "fa_icon": "far fa-file-code",
@@ -185,6 +185,11 @@
                     "fa_icon": "far fa-file-code",
                     "description": "Path to fusionreport references"
                 },
+                "fusionreport_ref_stub_check": {
+                    "type": "string",
+                    "fa_icon": "far fa-file-code",
+                    "description": "Path to file in fusionreport references"
+                },
                 "hgnc_ref": {
                     "type": "string",
                     "fa_icon": "far fa-file-code",
@@ -205,6 +210,11 @@
                     "fa_icon": "far fa-file-code",
                     "description": "Path to salmon index"
                 },
+                "salmon_index_stub_check": {
+                    "type": "string",
+                    "fa_icon": "far fa-file-code",
+                    "description": "Path to file in salmon index"
+                },
                 "starfusion": {
                     "type": "boolean",
                     "fa_icon": "far fa-file-code",
@@ -220,6 +230,11 @@
                     "fa_icon": "far fa-file-code",
                     "description": "Path to starfusion references"
                 },
+                "starfusion_ref_stub_check": {
+                    "type": "string",
+                    "fa_icon": "far fa-file-code",
+                    "description": "Path to file in starfusion references"
+                },
                 "starindex": {
                     "type": "boolean",
                     "fa_icon": "far fa-file-code",
@@ -230,6 +245,11 @@
                     "fa_icon": "far fa-file-code",
                     "description": "Path to starindex references"
                 },
+                "starindex_ref_stub_check": {
+                    "type": "string",
+                    "fa_icon": "far fa-file-code",
+                    "description": "Path to file in starindex references"
+                },
                 "stringtie": {
                     "type": "boolean",
                     "fa_icon": "far fa-file-code",
@@ -326,14 +346,6 @@
                     "description": "Path to GTF genome file.",
                     "fa_icon": "far fa-file-code"
                 },
-                "transcript": {
-                    "type": "string",
-                    "format": "file-path",
-                    "mimetype": "text/plain",
-                    "pattern": "^\\S+\\.fn?a(sta)?(\\.gz)?$",
-                    "description": "Path to GTF genome file.",
-                    "fa_icon": "far fa-file-code"
-                },
                 "refflat": {
                     "type": "string",
                     "format": "file-path",
diff --git a/subworkflows/local/build_references.nf b/subworkflows/local/build_references.nf
index bb2acc4d..0101c4d3 100644
--- a/subworkflows/local/build_references.nf
+++ b/subworkflows/local/build_references.nf
@@ -7,6 +7,7 @@
 include { ARRIBA_DOWNLOAD }                 from '../../modules/local/arriba/download/main'
 include { ENSEMBL_DOWNLOAD }                from '../../modules/local/ensembl/main'
 include { FUSIONCATCHER_DOWNLOAD }          from '../../modules/local/fusioncatcher/download/main'
+include { FUSIONCATCHER_BUILD }             from '../../modules/local/fusioncatcher/build/main'
 include { FUSIONREPORT_DOWNLOAD }           from '../../modules/local/fusionreport/download/main'
 include { HGNC_DOWNLOAD }                   from '../../modules/local/hgnc/main'
 include { STARFUSION_BUILD }                from '../../modules/local/starfusion/build/main'
@@ -37,82 +38,117 @@ workflow BUILD_REFERENCES {
 
 
     main:
-
     ch_versions = Channel.empty()
 
-    def fake_meta = [:]
-    fake_meta.id = "Homo_sapiens.${params.genome}.${params.ensembl_version}"
 
     if (!file(params.fasta).exists() || file(params.fasta).isEmpty() ||
-                    !file(params.chrgtf).exists() || file(params.chrgtf).isEmpty() ||
-                    !file(params.gtf).exists() || file(params.gtf).isEmpty()){
+            !file(params.chrgtf).exists() || file(params.chrgtf).isEmpty() ||
+            !file(params.gtf).exists() || file(params.gtf).isEmpty()){
+        fake_meta = [:]
+        fake_meta.id = "Homo_sapiens.${params.genome}.${params.ensembl_version}"
         ENSEMBL_DOWNLOAD(params.ensembl_version, params.genome, fake_meta)}
-    ch_fasta = {(!file(params.fasta).exists() || file(params.fasta).isEmpty()) ? ENSEMBL_DOWNLOAD.out.primary_assembly : Channel.fromPath(params.fasta).map { that -> [[id:that.Name], that] }.collect()}
+    ch_fasta = Channel.fromPath(params.fasta).map { that -> [[id:that.Name], that] }
+    ch_chrgtf = Channel.fromPath(params.chrgtf).map { that -> [[id:that.Name], that] }
+    ch_gtf = Channel.fromPath(params.gtf).map { that -> [[id:that.Name], that] }
 
     if (!file(params.hgnc_ref).exists() || file(params.hgnc_ref).isEmpty() ||
-                    !file(params.hgnc_date).exists() || file(params.hgnc_date).isEmpty()){
+                !file(params.hgnc_date).exists() || file(params.hgnc_date).isEmpty()){
         HGNC_DOWNLOAD( )}
+    ch_hgnc_ref = Channel.fromPath(params.hgnc_ref).map { that -> [[id:that.Name], that] }
+    ch_hgnc_date = Channel.fromPath(params.hgnc_date).map { that -> [[id:that.Name], that] }
+
 
-    if (!file(params.fai).exists() || file(params.fai).isEmpty(){
-        SAMTOOLS_FAIDX(ENSEMBL_DOWNLOAD.out.primary_assembly, [[],[]])}
+    if (!file(params.fai).exists() || file(params.fai).isEmpty()){
+        SAMTOOLS_FAIDX(ch_fasta, [[],[]])}
+    ch_fai = Channel.fromPath(params.fai).map { that -> [[id:that.Name], that] }
 
-    if (!file(params.rrna_intervals).exists() || file(params.rrna_intervals).isEmpty(){
-        GATK4_CREATESEQUENCEDICTIONARY(ENSEMBL_DOWNLOAD.out.primary_assembly)
-        RRNA_TRANSCRIPTS(ENSEMBL_DOWNLOAD.out.gtf)
+
+    if (!file(params.rrna_intervals).exists() || file(params.rrna_intervals).isEmpty()){
+        GATK4_CREATESEQUENCEDICTIONARY(ch_fasta)
+        RRNA_TRANSCRIPTS(ch_gtf)
         CONVERT2BED(RRNA_TRANSCRIPTS.out.rrna_gtf)
         GATK4_BEDTOINTERVALLIST(CONVERT2BED.out.bed, GATK4_CREATESEQUENCEDICTIONARY.out.dict)
         }
+    ch_rrna_interval = Channel.fromPath(params.rrna_intervals).map { that -> [[id:that.Name], that] }
+
 
-    if (!file(params.salmon_index).exists() || file(params.salmon_index).isEmpty(){ // add condition for qc, check that dirs can also be checked with isEmpty()
-        GFFREAD(ENSEMBL_DOWNLOAD.out.gtf, ENSEMBL_DOWNLOAD.out.primary_assembly.map { meta, fasta -> [ fasta ] })
-        SALMON_INDEX(ENSEMBL_DOWNLOAD.out.primary_assembly.map{ meta, fasta -> [ fasta ] }, GFFREAD.out.gffread_fasta.map{ meta, gffread_fasta -> [ gffread_fasta ] })
+    if (!file(params.refflat).exists() || file(params.refflat).isEmpty()){
+        GTF_TO_REFFLAT(ch_gtf)}
+    ch_refflat = Channel.fromPath(params.refflat)
+
+
+    if (!file(params.salmon_index).exists() || file(params.salmon_index).isEmpty() ||
+        !file(params.salmon_index_stub_check).exists() || file(params.salmon_index_stub_check).isEmpty()){ // add condition for qc
+        GFFREAD(ch_gtf, ch_fasta.map{ meta, fasta -> [ fasta ] })
+        SALMON_INDEX(ch_fasta.map{ meta, fasta -> [ fasta ] }, GFFREAD.out.gffread_fasta.map{ meta, gffread_fasta -> [ gffread_fasta ] })
         }
+    ch_salmon_index = Channel.fromPath(params.salmon_index)
 
 
     if ((params.starindex || params.all || params.starfusion || params.arriba) &&
-            (!params.starindex_ref.exits() || params.starindex_ref.isEmpty())
-            ) {
-        STAR_GENOMEGENERATE( ENSEMBL_DOWNLOAD.out.primary_assembly, ENSEMBL_DOWNLOAD.out.gtf )
+            (!file(params.starindex_ref).exists() || file(params.starindex_ref).isEmpty() ||
+            !file(params.starindex_ref_stub_check).exists() || file(params.starindex_ref_stub_check).isEmpty() )) {
+        STAR_GENOMEGENERATE(ch_fasta, ch_gtf)
+    }
+    ch_starindex_ref = Channel.fromPath(params.starindex_ref).map { that -> [[id:that.Name], that] }
+
+
+    if ((params.arriba || params.all) &&
+            (!file(params.arriba_ref_blacklist).exists() || file(params.arriba_ref_blacklist).isEmpty() ||
+            !file(params.arriba_ref_known_fusions).exists() || file(params.arriba_ref_known_fusions).isEmpty() ||
+            !file(params.arriba_ref_protein_domains).exists() || file(params.arriba_ref_protein_domains).isEmpty())) {
+        ARRIBA_DOWNLOAD()}
+    ch_arriba_ref_blacklist = Channel.fromPath(params.arriba_ref_blacklist).map { that -> [[id:that.Name], that] }
+    ch_arriba_ref_known_fusions = Channel.fromPath(params.arriba_ref_known_fusions).map { that -> [[id:that.Name], that] }
+    ch_arriba_ref_protein_domains = Channel.fromPath(params.arriba_ref_protein_domains).map { that -> [[id:that.Name], that] }
+
+
+    if ((params.fusioncatcher || params.all) &&
+            (!file(params.fusioncatcher_ref).exists() || file(params.fusioncatcher_ref).isEmpty() ||
+            !file(params.fusioncatcher_ref_stub_check).exists() || file(params.fusioncatcher_ref_stub_check).isEmpty() )) {
+        if (params.download_refs) {
+            FUSIONCATCHER_DOWNLOAD(params.ensembl_version)}
+        else {
+            FUSIONCATCHER_BUILD(params.ensembl_version)}
     }
-    ch_starindex_ref = ...
-
-    // if (params.arriba || params.all) {
-    //     ARRIBA_DOWNLOAD()
-    // }
-
-    // if (params.fusioncatcher || params.all) {
-    //     FUSIONCATCHER_DOWNLOAD()
-    // }
-
-    // if (params.starfusion || params.all) {
-    //     if (params.starfusion_build){
-    //         STARFUSION_BUILD( ENSEMBL_DOWNLOAD.out.primary_assembly, ENSEMBL_DOWNLOAD.out.gtf )
-    //     } else {
-    //         STARFUSION_DOWNLOAD()
-    //     }
-    // }
-
-    // if (params.starfusion_build){
-    //     GTF_TO_REFFLAT(ENSEMBL_DOWNLOAD.out.gtf)
-    // } else {
-    //     GTF_TO_REFFLAT(STARFUSION_DOWNLOAD.out.gtf)
-    // }
-
-    // if (params.fusionreport || params.all) {
-    //     FUSIONREPORT_DOWNLOAD( params.cosmic_username, params.cosmic_passwd )
-    // }
+    ch_fusioncatcher_ref = Channel.fromPath(params.fusioncatcher_ref).map { that -> [[id:that.Name], that] }
 
-    emit:
-    ch_fasta
-    ch_chrgtf = {(!file(params.chrgtf).exists() || file(params.chrgtf).isEmpty()) ? ENSEMBL_DOWNLOAD.out.chrgtf : Channel.fromPath(params.chrgtf).map { that -> [[id:that.Name], that] }.collect()}
-    ch_gtf = {(!file(params.gtf).exists() || file(params.gtf).isEmpty()) ? ENSEMBL_DOWNLOAD.out.gtf : Channel.fromPath(params.gtf).map { that -> [[id:that.Name], that] }.collect()}
-    ch_hgnc_ref = Channel.fromPath(params.hgnc_ref).map { it -> [[id:it.Name], it] }.collect()
-    ch_hgnc_date = Channel.fromPath(params.hgnc_date).map { it -> [[id:it.Name], it] }.collect()
-    ch_fai = Channel.fromPath(params.fai).map { it -> [[id:it.Name], it] }.collect()
-    ch_rrna_interval = params.starfusion_build ?  Channel.fromPath(params.rrna_intervals).map { it -> [[id:it.Name], it] }.collect() : Channel.fromPath("${params.ensembl_ref}/ref_annot.interval_list").map { it -> [[id:it.Name], it] }.collect()
-    ch_salmon_index = Channel.fromPath(params.salmon_index).map { it -> [[id:it.Name], it] }.collect()
+
+    if ((params.starfusion || params.all) &&
+            (!file(params.starfusion_ref).exists() || file(params.starfusion_ref).isEmpty() ||
+            !file(params.starfusion_ref_stub_check).exists() || file(params.starfusion_ref_stub_check).isEmpty() )) {
+        if (params.download_refs) {
+            STARFUSION_DOWNLOAD( ch_fasta, ch_gtf )}
+        else {
+            STARFUSION_BUILD( ch_fasta, ch_gtf )}
+    }
+    ch_starfusion_ref = Channel.fromPath(params.starfusion_ref).map { that -> [[id:that.Name], that] }
 
 
+    if ((params.fusionreport || params.all) &&
+            (!file(params.fusionreport_ref).exists() || file(params.fusionreport_ref).isEmpty() ||
+            !file(params.fusionreport_ref_stub_check).exists() || file(params.fusionreport_ref_stub_check).isEmpty())) {
+        if (!params.cosmic_username || !params.cosmic_passwd) { exit 1, 'COSMIC username and/or password missing' }
+        FUSIONREPORT_DOWNLOAD( params.cosmic_username, params.cosmic_passwd )}
+    ch_fusionreport_ref = Channel.fromPath(params.fusionreport_ref).map { that -> [[id:that.Name], that] }
+
+    emit:
+    ch_fasta
+    ch_chrgtf
+    ch_gtf
+    ch_hgnc_ref
+    ch_hgnc_date
+    ch_fai
+    ch_rrna_interval
+    ch_refflat
+    ch_salmon_index
+    ch_starindex_ref
+    ch_arriba_ref_blacklist
+    ch_arriba_ref_known_fusions
+    ch_arriba_ref_protein_domains
+    ch_fusioncatcher_ref
+    ch_starfusion_ref
+    ch_fusionreport_ref
 }
 
 /*
diff --git a/workflows/rnafusion.nf b/workflows/rnafusion.nf
index bf7fa1b8..64bd3f99 100644
--- a/workflows/rnafusion.nf
+++ b/workflows/rnafusion.nf
@@ -58,14 +58,7 @@ workflow RNAFUSION {
 
 
     // Reference channels
-    // ch_starindex_ref = params.starfusion_build ? Channel.fromPath(params.starindex_ref).map { it -> [[id:it.Name], it] }.collect() : Channel.fromPath("${params.starfusion_ref}/ref_genome.fa.star.idx").map { it -> [[id:it.Name], it] }.collect()
-    // ch_starindex_ensembl_ref = Channel.fromPath(params.starindex_ref).map { it -> [[id:it.Name], it] }.collect()
-    // ch_refflat = params.starfusion_build ? Channel.fromPath(params.refflat).map { it -> [[id:it.Name], it] }.collect() : Channel.fromPath("${params.ensembl_ref}/ref_annot.gtf.refflat").map { it -> [[id:it.Name], it] }.collect()
-    // ch_fusionreport_ref = Channel.fromPath(params.fusionreport_ref).map { it -> [[id:it.Name], it] }.collect()
-    // ch_arriba_ref_blacklist = Channel.fromPath(params.arriba_ref_blacklist).map { it -> [[id:it.Name], it] }.collect()
-    // ch_arriba_ref_known_fusions = Channel.fromPath(params.arriba_ref_known_fusions).map { it -> [[id:it.Name], it] }.collect()
-    // ch_arriba_ref_protein_domains = Channel.fromPath(params.arriba_ref_protein_domains).map { it -> [[id:it.Name], it] }.collect()
-    // ch_arriba_ref_cytobands = Channel.fromPath(params.arriba_ref_cytobands).map { it -> [[id:it.Name], it] }.collect()
+
 
 
 

From a19abbde7f1268bf49b5e57a7485040fc592468d Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Tue, 28 May 2024 21:14:21 +0200
Subject: [PATCH 03/41] fix params

---
 modules/local/fusioncatcher/build/main.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/modules/local/fusioncatcher/build/main.nf b/modules/local/fusioncatcher/build/main.nf
index afab999c..c5eeeb45 100644
--- a/modules/local/fusioncatcher/build/main.nf
+++ b/modules/local/fusioncatcher/build/main.nf
@@ -21,7 +21,7 @@ process FUSIONCATCHER_BUILD {
     """
     fusioncatcher-build \\
         -g homo_sapiens \\
-        -o human_${human_version} \\
+        -o human_v${ensembl_version} \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

From 93fbfb8bc795c3fe405d9e98c6199469e213e203 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Tue, 28 May 2024 21:25:30 +0200
Subject: [PATCH 04/41] fix

---
 modules/local/fusioncatcher/build/main.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/modules/local/fusioncatcher/build/main.nf b/modules/local/fusioncatcher/build/main.nf
index c5eeeb45..51353556 100644
--- a/modules/local/fusioncatcher/build/main.nf
+++ b/modules/local/fusioncatcher/build/main.nf
@@ -19,7 +19,7 @@ process FUSIONCATCHER_BUILD {
 
     def args = task.ext.args ?: ''
     """
-    fusioncatcher-build \\
+    fusioncatcher-build.py \\
         -g homo_sapiens \\
         -o human_v${ensembl_version} \\
         $args

From b7dd1375cd74fa4c9b37edc415c665976b708930 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Thu, 13 Jun 2024 11:41:44 +0200
Subject: [PATCH 05/41] update refs generation

---
 conf/modules.config                          |  12 ++-
 modules/local/fusioncatcher/build/main.nf    |   4 +-
 modules/local/fusioncatcher/download/main.nf |   2 +-
 nextflow.config                              |   1 +
 nextflow_schema.json                         |   4 +
 subworkflows/local/build_references.nf       | 101 +++++++++++-------
 workflows/rnafusion.nf                       | 106 +++++++++----------
 7 files changed, 131 insertions(+), 99 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index 44dec339..e78f73db 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -45,6 +45,10 @@ process {
         ]
     }
 
+    withName: 'CAT_FASTQ' {
+        ext.when   = { !params.build_references }
+    }
+
     withName: 'ENSEMBL_DOWNLOAD' {
         publishDir = [
             path: { "${params.genomes_base}/ensembl" },
@@ -59,7 +63,7 @@ process {
 
     withName: 'FASTQC' {
         ext.args = '--quiet'
-        ext.when = { !params.skip_qc }
+        ext.when = { !params.skip_qc and not !params.build_references }
         publishDir = [
             path: { "${params.outdir}/fastqc" },
             mode: params.publish_dir_mode,
@@ -69,6 +73,7 @@ process {
 
     withName: 'FASTQC_FOR_FASTP' {
         ext.args = '--quiet'
+        ext.when = ( !params.skip_qc)
         ext.prefix = { "${meta.id}_trimmed" }
         publishDir = [
             path: { "${params.outdir}/fastqc_for_fastp" },
@@ -362,6 +367,11 @@ process {
         ]
     }
 
+    withName: 'TRIM_WORKFLOW:*' {
+        ext.when = { !params.build_references }
+
+    }
+
     withName: 'VCF_COLLECT' {
         ext.when = {!params.fusioninspector_only}
     }
diff --git a/modules/local/fusioncatcher/build/main.nf b/modules/local/fusioncatcher/build/main.nf
index 51353556..15f7afed 100644
--- a/modules/local/fusioncatcher/build/main.nf
+++ b/modules/local/fusioncatcher/build/main.nf
@@ -9,8 +9,8 @@ process FUSIONCATCHER_BUILD {
     val ensembl_version
 
     output:
-    path "*"                , emit: reference
-    path "versions.yml"     , emit: versions
+    path "human_v${ensembl_version}"  , emit: reference
+    path "versions.yml"               , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
diff --git a/modules/local/fusioncatcher/download/main.nf b/modules/local/fusioncatcher/download/main.nf
index 7f59d920..ff146c95 100644
--- a/modules/local/fusioncatcher/download/main.nf
+++ b/modules/local/fusioncatcher/download/main.nf
@@ -10,7 +10,7 @@ process FUSIONCATCHER_DOWNLOAD {
     val ensembl_version
 
     output:
-    path "*"                , emit: reference
+    path "human_v${ensembl_version}"                , emit: reference
     path "versions.yml"     , emit: versions
 
     when:
diff --git a/nextflow.config b/nextflow.config
index fe2dd83d..b7d78f7d 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -62,6 +62,7 @@ params {
 
     // Skip steps
     skip_qc                    = false
+    skip_vcf                   = false
     skip_vis                   = false
 
     // Download references option
diff --git a/nextflow_schema.json b/nextflow_schema.json
index 0889caa2..604e7b00 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -15,6 +15,10 @@
                     "type": "boolean",
                     "description": "Skip QC steps"
                 },
+                "skip_vcf": {
+                    "type": "boolean",
+                    "description": "Skip vcf creation step"
+                }
                 "skip_vis": {
                     "type": "boolean",
                     "description": "Skip visualisation steps"
diff --git a/subworkflows/local/build_references.nf b/subworkflows/local/build_references.nf
index 0101c4d3..32602cc1 100644
--- a/subworkflows/local/build_references.nf
+++ b/subworkflows/local/build_references.nf
@@ -46,21 +46,30 @@ workflow BUILD_REFERENCES {
             !file(params.gtf).exists() || file(params.gtf).isEmpty()){
         fake_meta = [:]
         fake_meta.id = "Homo_sapiens.${params.genome}.${params.ensembl_version}"
-        ENSEMBL_DOWNLOAD(params.ensembl_version, params.genome, fake_meta)}
-    ch_fasta = Channel.fromPath(params.fasta).map { that -> [[id:that.Name], that] }
-    ch_chrgtf = Channel.fromPath(params.chrgtf).map { that -> [[id:that.Name], that] }
-    ch_gtf = Channel.fromPath(params.gtf).map { that -> [[id:that.Name], that] }
+        ENSEMBL_DOWNLOAD(params.ensembl_version, params.genome, fake_meta)
+        ch_fasta = ENSEMBL_DOWNLOAD.out.primary_assembly
+        ch_chrgtf = ENSEMBL_DOWNLOAD.out.chrgtf
+        ch_gtf = ENSEMBL_DOWNLOAD.out.gtf
+    } else {
+        ch_fasta = Channel.fromPath(params.fasta).map { that -> [[id:that.Name], that] }
+        ch_chrgtf = Channel.fromPath(params.chrgtf).map { that -> [[id:that.Name], that] }
+        ch_gtf = Channel.fromPath(params.gtf).map { that -> [[id:that.Name], that] }
+    }
+
 
-    if (!file(params.hgnc_ref).exists() || file(params.hgnc_ref).isEmpty() ||
-                !file(params.hgnc_date).exists() || file(params.hgnc_date).isEmpty()){
-        HGNC_DOWNLOAD( )}
-    ch_hgnc_ref = Channel.fromPath(params.hgnc_ref).map { that -> [[id:that.Name], that] }
-    ch_hgnc_date = Channel.fromPath(params.hgnc_date).map { that -> [[id:that.Name], that] }
+    if ((!file(params.hgnc_ref).exists() || file(params.hgnc_ref).isEmpty() ||
+                !file(params.hgnc_date).exists() || file(params.hgnc_date).isEmpty()) and not params.skip_vcf){
+        HGNC_DOWNLOAD( )
+        ch_hgnc_ref = HGNC_DOWNLOAD.out.hgnc_ref
+        ch_hgnc_date =HGNC_DOWNLOAD.out.hgnc_date
 
+    } else {
+        ch_hgnc_ref = Channel.fromPath(params.hgnc_ref).map { that -> [[id:that.Name], that] }
+        ch_hgnc_date = Channel.fromPath(params.hgnc_date).map { that -> [[id:that.Name], that] }
+    }
 
-    if (!file(params.fai).exists() || file(params.fai).isEmpty()){
-        SAMTOOLS_FAIDX(ch_fasta, [[],[]])}
-    ch_fai = Channel.fromPath(params.fai).map { that -> [[id:that.Name], that] }
+
+    ch_fai = (!file(params.fai).exists() || file(params.fai).isEmpty()) ? SAMTOOLS_FAIDX(ch_fasta, [[],[]]).fai : Channel.fromPath(params.fai).map { that -> [[id:that.Name], that] }
 
 
     if (!file(params.rrna_intervals).exists() || file(params.rrna_intervals).isEmpty()){
@@ -68,69 +77,81 @@ workflow BUILD_REFERENCES {
         RRNA_TRANSCRIPTS(ch_gtf)
         CONVERT2BED(RRNA_TRANSCRIPTS.out.rrna_gtf)
         GATK4_BEDTOINTERVALLIST(CONVERT2BED.out.bed, GATK4_CREATESEQUENCEDICTIONARY.out.dict)
-        }
-    ch_rrna_interval = Channel.fromPath(params.rrna_intervals).map { that -> [[id:that.Name], that] }
+        ch_rrna_interval = GATK4_BEDTOINTERVALLIST.out.interval_list
+    } else {
+        ch_rrna_interval = Channel.fromPath(params.rrna_intervals).map { that -> [[id:that.Name], that] }
+    }
 
 
-    if (!file(params.refflat).exists() || file(params.refflat).isEmpty()){
-        GTF_TO_REFFLAT(ch_gtf)}
-    ch_refflat = Channel.fromPath(params.refflat)
+    ch_refflat = (!file(params.refflat).exists() || file(params.refflat).isEmpty()) ? GTF_TO_REFFLAT.refflat : Channel.fromPath(params.refflat)
 
 
     if (!file(params.salmon_index).exists() || file(params.salmon_index).isEmpty() ||
         !file(params.salmon_index_stub_check).exists() || file(params.salmon_index_stub_check).isEmpty()){ // add condition for qc
         GFFREAD(ch_gtf, ch_fasta.map{ meta, fasta -> [ fasta ] })
         SALMON_INDEX(ch_fasta.map{ meta, fasta -> [ fasta ] }, GFFREAD.out.gffread_fasta.map{ meta, gffread_fasta -> [ gffread_fasta ] })
+        ch_salmon_index = SALMON_INDEX.out.index
+    } else {
+        ch_salmon_index = Channel.fromPath(params.salmon_index)
         }
-    ch_salmon_index = Channel.fromPath(params.salmon_index)
 
 
     if ((params.starindex || params.all || params.starfusion || params.arriba) &&
             (!file(params.starindex_ref).exists() || file(params.starindex_ref).isEmpty() ||
             !file(params.starindex_ref_stub_check).exists() || file(params.starindex_ref_stub_check).isEmpty() )) {
         STAR_GENOMEGENERATE(ch_fasta, ch_gtf)
+        ch_starindex_ref = STAR_GENOMEGENERATE.out.index
+    } else {
+        ch_starindex_ref = Channel.fromPath(params.starindex_ref).map { that -> [[id:that.Name], that] }
     }
-    ch_starindex_ref = Channel.fromPath(params.starindex_ref).map { that -> [[id:that.Name], that] }
 
 
-    if ((params.arriba || params.all) &&
-            (!file(params.arriba_ref_blacklist).exists() || file(params.arriba_ref_blacklist).isEmpty() ||
-            !file(params.arriba_ref_known_fusions).exists() || file(params.arriba_ref_known_fusions).isEmpty() ||
-            !file(params.arriba_ref_protein_domains).exists() || file(params.arriba_ref_protein_domains).isEmpty())) {
-        ARRIBA_DOWNLOAD()}
-    ch_arriba_ref_blacklist = Channel.fromPath(params.arriba_ref_blacklist).map { that -> [[id:that.Name], that] }
-    ch_arriba_ref_known_fusions = Channel.fromPath(params.arriba_ref_known_fusions).map { that -> [[id:that.Name], that] }
-    ch_arriba_ref_protein_domains = Channel.fromPath(params.arriba_ref_protein_domains).map { that -> [[id:that.Name], that] }
+//     if ((params.arriba || params.all) &&
+//             (!file(params.arriba_ref_blacklist).exists() || file(params.arriba_ref_blacklist).isEmpty() ||
+//             !file(params.arriba_ref_known_fusions).exists() || file(params.arriba_ref_known_fusions).isEmpty() ||
+//             !file(params.arriba_ref_protein_domains).exists() || file(params.arriba_ref_protein_domains).isEmpty())) {
+//         ARRIBA_DOWNLOAD()
+//         ch_arriba_ref_blacklist = Channel.fromPath(params.arriba_ref_blacklist).map { that -> [[id:that.Name], that] }
+//         ch_arriba_ref_known_fusions = Channel.fromPath(params.arriba_ref_known_fusions).map { that -> [[id:that.Name], that] }
+//         ch_arriba_ref_protein_domains = Channel.fromPath(params.arriba_ref_protein_domains).map { that -> [[id:that.Name], that] }
+//     } else {
+// // need to update the module to emit blacklist,knownfusions etc
+//     }
 
 
     if ((params.fusioncatcher || params.all) &&
             (!file(params.fusioncatcher_ref).exists() || file(params.fusioncatcher_ref).isEmpty() ||
             !file(params.fusioncatcher_ref_stub_check).exists() || file(params.fusioncatcher_ref_stub_check).isEmpty() )) {
         if (params.download_refs) {
-            FUSIONCATCHER_DOWNLOAD(params.ensembl_version)}
+            FUSIONCATCHER_DOWNLOAD(params.ensembl_version)
+            ch_fusioncatcher_ref = FUSIONCATCHER_DOWNLOAD.out.reference}
         else {
-            FUSIONCATCHER_BUILD(params.ensembl_version)}
-    }
-    ch_fusioncatcher_ref = Channel.fromPath(params.fusioncatcher_ref).map { that -> [[id:that.Name], that] }
+            FUSIONCATCHER_BUILD(params.ensembl_version)
+            ch_fusioncatcher_ref = FUSIONCATCHER_BUILD.out.reference}
+        } else {
+            ch_fusioncatcher_ref = Channel.fromPath(params.fusioncatcher_ref).map { that -> [[id:that.Name], that] }
+        }
 
 
     if ((params.starfusion || params.all) &&
             (!file(params.starfusion_ref).exists() || file(params.starfusion_ref).isEmpty() ||
             !file(params.starfusion_ref_stub_check).exists() || file(params.starfusion_ref_stub_check).isEmpty() )) {
         if (params.download_refs) {
-            STARFUSION_DOWNLOAD( ch_fasta, ch_gtf )}
+            ch_starfusion_ref = STARFUSION_DOWNLOAD( ch_fasta, ch_gtf ).out.reference }
         else {
-            STARFUSION_BUILD( ch_fasta, ch_gtf )}
-    }
-    ch_starfusion_ref = Channel.fromPath(params.starfusion_ref).map { that -> [[id:that.Name], that] }
+            ch_starfusion_ref = STARFUSION_BUILD( ch_fasta, ch_gtf ).out.reference }
+    } else {
+        ch_starfusion_ref = Channel.fromPath(params.starfusion_ref).map { that -> [[id:that.Name], that] }}
 
 
     if ((params.fusionreport || params.all) &&
             (!file(params.fusionreport_ref).exists() || file(params.fusionreport_ref).isEmpty() ||
             !file(params.fusionreport_ref_stub_check).exists() || file(params.fusionreport_ref_stub_check).isEmpty())) {
         if (!params.cosmic_username || !params.cosmic_passwd) { exit 1, 'COSMIC username and/or password missing' }
-        FUSIONREPORT_DOWNLOAD( params.cosmic_username, params.cosmic_passwd )}
-    ch_fusionreport_ref = Channel.fromPath(params.fusionreport_ref).map { that -> [[id:that.Name], that] }
+        ch_fusionreport_ref = FUSIONREPORT_DOWNLOAD( params.cosmic_username, params.cosmic_passwd ).out.reference
+    } else {
+        ch_fusionreport_ref = Channel.fromPath(params.fusionreport_ref).map { that -> [[id:that.Name], that] }
+    }
 
     emit:
     ch_fasta
@@ -143,9 +164,9 @@ workflow BUILD_REFERENCES {
     ch_refflat
     ch_salmon_index
     ch_starindex_ref
-    ch_arriba_ref_blacklist
-    ch_arriba_ref_known_fusions
-    ch_arriba_ref_protein_domains
+    // ch_arriba_ref_blacklist
+    // ch_arriba_ref_known_fusions
+    // ch_arriba_ref_protein_domains
     ch_fusioncatcher_ref
     ch_starfusion_ref
     ch_fusionreport_ref
diff --git a/workflows/rnafusion.nf b/workflows/rnafusion.nf
index 64bd3f99..eb0e19f4 100644
--- a/workflows/rnafusion.nf
+++ b/workflows/rnafusion.nf
@@ -57,11 +57,6 @@ workflow RNAFUSION {
     main:
 
 
-    // Reference channels
-
-
-
-
     ch_versions = Channel.empty()
     ch_multiqc_files = Channel.empty()
 
@@ -73,59 +68,60 @@ workflow RNAFUSION {
     BUILD_REFERENCES()
 
 
-//     //
-//     // Create channel from input file provided through params.input
-//     //
-//     Channel
-//         .fromSamplesheet("input")
-//         .map {
-//             meta, fastq_1, fastq_2, strandedness ->
-//                 if (!fastq_2) {
-//                     return [ meta.id, meta + [ single_end:true ], [ fastq_1 ] ]
-//                 } else {
-//                     return [ meta.id, meta + [ single_end:false ], [ fastq_1, fastq_2 ] ]
-//                 }
-//         }
-//         .groupTuple()
-//         .map {
-//             validateInputSamplesheet(it)
-//         }
-//         .branch {
-//             meta, fastqs ->
-//                 single  : fastqs.size() == 1
-//                     return [ meta, fastqs.flatten() ]
-//                 multiple: fastqs.size() > 1
-//                     return [ meta, fastqs.flatten() ]
-//         }
-//         .set { ch_fastq }
-
-//     //
-//     // MODULE: Concatenate FastQ files from same sample if required
-//     //
-//     CAT_FASTQ (
-//         ch_fastq.multiple
-//     )
-//     .reads
-//     .mix(ch_fastq.single)
-//     .set { ch_cat_fastq }
-//     ch_versions = ch_versions.mix(CAT_FASTQ.out.versions)
+    //
+    // Create channel from input file provided through params.input
+    //
+    Channel
+        .fromSamplesheet("input")
+        .map {
+            meta, fastq_1, fastq_2, strandedness ->
+                if (!fastq_2) {
+                    return [ meta.id, meta + [ single_end:true ], [ fastq_1 ] ]
+                } else {
+                    return [ meta.id, meta + [ single_end:false ], [ fastq_1, fastq_2 ] ]
+                }
+        }
+        .groupTuple()
+        .map {
+            validateInputSamplesheet(it)
+        }
+        .branch {
+            meta, fastqs ->
+                single  : fastqs.size() == 1
+                    return [ meta, fastqs.flatten() ]
+                multiple: fastqs.size() > 1
+                    return [ meta, fastqs.flatten() ]
+        }
+        .set { ch_fastq }
 
+    //
+    // MODULE: Concatenate FastQ files from same sample if required
+    //
+    CAT_FASTQ (
+        ch_fastq.multiple
+    )
+    .reads
+    .mix(ch_fastq.single)
+    .set { ch_cat_fastq }
+    ch_versions = ch_versions.mix(CAT_FASTQ.out.versions)
 
-//     //
-//     // MODULE: Run FastQC
-//     //
-//     FASTQC (
-//         ch_cat_fastq
-//     )
-//     ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]})
-//     ch_versions = ch_versions.mix(FASTQC.out.versions)
 
-//     TRIM_WORKFLOW (
-//         ch_cat_fastq
-//     )
-//     ch_reads_fusioncatcher = TRIM_WORKFLOW.out.ch_reads_fusioncatcher
-//     ch_reads_all = TRIM_WORKFLOW.out.ch_reads_all
-//     ch_versions = ch_versions.mix(TRIM_WORKFLOW.out.versions)
+    //
+    // MODULE: Run FastQC
+    //
+    FASTQC (
+        ch_cat_fastq
+    )
+    ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]})
+    ch_versions = ch_versions.mix(FASTQC.out.versions)
+
+
+    TRIM_WORKFLOW (
+        ch_cat_fastq
+    )
+    ch_reads_fusioncatcher = TRIM_WORKFLOW.out.ch_reads_fusioncatcher
+    ch_reads_all = TRIM_WORKFLOW.out.ch_reads_all
+    ch_versions = ch_versions.mix(TRIM_WORKFLOW.out.versions)
 
 
 //     SALMON_QUANT( ch_reads_all, ch_salmon_index.map{ meta, index ->  index  }, ch_gtf.map{ meta, gtf ->  gtf  }, [], false, 'A')

From 89be7c1ab16c8a25dc7dedc8cdc7a18a3c36d75f Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Thu, 13 Jun 2024 12:15:12 +0200
Subject: [PATCH 06/41] fix small issues

---
 modules/local/fusioncatcher/build/main.nf |  2 +-
 nextflow_schema.json                      |  2 +-
 subworkflows/local/build_references.nf    |  5 ++---
 workflows/rnafusion.nf                    | 10 +++++-----
 4 files changed, 9 insertions(+), 10 deletions(-)

diff --git a/modules/local/fusioncatcher/build/main.nf b/modules/local/fusioncatcher/build/main.nf
index 15f7afed..0258a2cc 100644
--- a/modules/local/fusioncatcher/build/main.nf
+++ b/modules/local/fusioncatcher/build/main.nf
@@ -3,7 +3,7 @@ process FUSIONCATCHER_BUILD {
     label 'process_medium'
 
     conda "bioconda::fusioncatcher=1.33"
-    container "docker.io/clinicalgenomics/fusioncatcher:1.33"
+    container "docker.io/rannickscilifelab/fusioncatcher:1.33a"
 
     input:
     val ensembl_version
diff --git a/nextflow_schema.json b/nextflow_schema.json
index 604e7b00..95238d65 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -18,7 +18,7 @@
                 "skip_vcf": {
                     "type": "boolean",
                     "description": "Skip vcf creation step"
-                }
+                },
                 "skip_vis": {
                     "type": "boolean",
                     "description": "Skip visualisation steps"
diff --git a/subworkflows/local/build_references.nf b/subworkflows/local/build_references.nf
index 32602cc1..49a18ce2 100644
--- a/subworkflows/local/build_references.nf
+++ b/subworkflows/local/build_references.nf
@@ -58,11 +58,10 @@ workflow BUILD_REFERENCES {
 
 
     if ((!file(params.hgnc_ref).exists() || file(params.hgnc_ref).isEmpty() ||
-                !file(params.hgnc_date).exists() || file(params.hgnc_date).isEmpty()) and not params.skip_vcf){
+            !file(params.hgnc_date).exists() || file(params.hgnc_date).isEmpty()) && !params.skip_vcf){
         HGNC_DOWNLOAD( )
         ch_hgnc_ref = HGNC_DOWNLOAD.out.hgnc_ref
-        ch_hgnc_date =HGNC_DOWNLOAD.out.hgnc_date
-
+        ch_hgnc_date = HGNC_DOWNLOAD.out.hgnc_date
     } else {
         ch_hgnc_ref = Channel.fromPath(params.hgnc_ref).map { that -> [[id:that.Name], that] }
         ch_hgnc_date = Channel.fromPath(params.hgnc_date).map { that -> [[id:that.Name], that] }
diff --git a/workflows/rnafusion.nf b/workflows/rnafusion.nf
index eb0e19f4..8067210a 100644
--- a/workflows/rnafusion.nf
+++ b/workflows/rnafusion.nf
@@ -109,11 +109,11 @@ workflow RNAFUSION {
     //
     // MODULE: Run FastQC
     //
-    FASTQC (
-        ch_cat_fastq
-    )
-    ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]})
-    ch_versions = ch_versions.mix(FASTQC.out.versions)
+    // FASTQC (
+    //     ch_cat_fastq
+    // )
+    // ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]})
+    // ch_versions = ch_versions.mix(FASTQC.out.versions)
 
 
     TRIM_WORKFLOW (

From 0c6fe8283c61f0dc4557970ce576d08fc97ee909 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Thu, 12 Sep 2024 11:21:33 +0200
Subject: [PATCH 07/41] updates

---
 conf/base.config                             |  2 +-
 modules/local/fusioncatcher/build/main.nf    |  2 +-
 modules/local/fusioncatcher/download/main.nf |  1 +
 modules/local/starfusion/download/main.nf    |  1 +
 subworkflows/local/build_references.nf       | 30 ++++++++++----------
 subworkflows/local/trim_workflow.nf          | 18 ++++--------
 workflows/rnafusion.nf                       | 24 +++++++++-------
 7 files changed, 38 insertions(+), 40 deletions(-)

diff --git a/conf/base.config b/conf/base.config
index 5b2e6f36..62d8dbf1 100644
--- a/conf/base.config
+++ b/conf/base.config
@@ -31,7 +31,7 @@ process {
     }
     withLabel:process_medium {
         cpus   = { check_max( 6     * task.attempt, 'cpus'    ) }
-        memory = { check_max( 36.GB * task.attempt, 'memory'  ) }
+        memory = { check_max( 16.GB * task.attempt, 'memory'  ) }
         time   = { check_max( 8.h   * task.attempt, 'time'    ) }
     }
     withLabel:process_high {
diff --git a/modules/local/fusioncatcher/build/main.nf b/modules/local/fusioncatcher/build/main.nf
index 0258a2cc..15f7afed 100644
--- a/modules/local/fusioncatcher/build/main.nf
+++ b/modules/local/fusioncatcher/build/main.nf
@@ -3,7 +3,7 @@ process FUSIONCATCHER_BUILD {
     label 'process_medium'
 
     conda "bioconda::fusioncatcher=1.33"
-    container "docker.io/rannickscilifelab/fusioncatcher:1.33a"
+    container "docker.io/clinicalgenomics/fusioncatcher:1.33"
 
     input:
     val ensembl_version
diff --git a/modules/local/fusioncatcher/download/main.nf b/modules/local/fusioncatcher/download/main.nf
index ff146c95..aec16288 100644
--- a/modules/local/fusioncatcher/download/main.nf
+++ b/modules/local/fusioncatcher/download/main.nf
@@ -22,6 +22,7 @@ process FUSIONCATCHER_DOWNLOAD {
     def args2 = task.ext.args2 ?: ''
     def url =
     """
+    TODO: move to my sourceforge
     wget $args http://sourceforge.net/projects/fusioncatcher/files/data/human_${ensembl_version}.tar.gz.aa
     wget $args http://sourceforge.net/projects/fusioncatcher/files/data/human_${ensembl_version}.tar.gz.ab
     wget $args http://sourceforge.net/projects/fusioncatcher/files/data/human_${ensembl_version}.tar.gz.ac
diff --git a/modules/local/starfusion/download/main.nf b/modules/local/starfusion/download/main.nf
index 9c9b1482..e3a4b1b8 100644
--- a/modules/local/starfusion/download/main.nf
+++ b/modules/local/starfusion/download/main.nf
@@ -9,6 +9,7 @@ process STARFUSION_DOWNLOAD {
     path "ctat_genome_lib_build_dir/ref_annot.gtf", emit: chrgtf
 
 
+    TODO: move to my sourceforge
     script:
     """
     wget https://data.broadinstitute.org/Trinity/CTAT_RESOURCE_LIB/__genome_libs_StarFv1.10/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play.tar.gz --no-check-certificate
diff --git a/subworkflows/local/build_references.nf b/subworkflows/local/build_references.nf
index 49a18ce2..a1a64050 100644
--- a/subworkflows/local/build_references.nf
+++ b/subworkflows/local/build_references.nf
@@ -92,7 +92,7 @@ workflow BUILD_REFERENCES {
         ch_salmon_index = SALMON_INDEX.out.index
     } else {
         ch_salmon_index = Channel.fromPath(params.salmon_index)
-        }
+    }
 
 
     if ((params.starindex || params.all || params.starfusion || params.arriba) &&
@@ -105,17 +105,17 @@ workflow BUILD_REFERENCES {
     }
 
 
-//     if ((params.arriba || params.all) &&
-//             (!file(params.arriba_ref_blacklist).exists() || file(params.arriba_ref_blacklist).isEmpty() ||
-//             !file(params.arriba_ref_known_fusions).exists() || file(params.arriba_ref_known_fusions).isEmpty() ||
-//             !file(params.arriba_ref_protein_domains).exists() || file(params.arriba_ref_protein_domains).isEmpty())) {
-//         ARRIBA_DOWNLOAD()
-//         ch_arriba_ref_blacklist = Channel.fromPath(params.arriba_ref_blacklist).map { that -> [[id:that.Name], that] }
-//         ch_arriba_ref_known_fusions = Channel.fromPath(params.arriba_ref_known_fusions).map { that -> [[id:that.Name], that] }
-//         ch_arriba_ref_protein_domains = Channel.fromPath(params.arriba_ref_protein_domains).map { that -> [[id:that.Name], that] }
-//     } else {
-// // need to update the module to emit blacklist,knownfusions etc
-//     }
+    if ((params.arriba || params.all) &&
+            (!file(params.arriba_ref_blacklist).exists() || file(params.arriba_ref_blacklist).isEmpty() ||
+            !file(params.arriba_ref_known_fusions).exists() || file(params.arriba_ref_known_fusions).isEmpty() ||
+            !file(params.arriba_ref_protein_domains).exists() || file(params.arriba_ref_protein_domains).isEmpty())) {
+        ARRIBA_DOWNLOAD()
+        ch_arriba_ref_blacklist = Channel.fromPath(params.arriba_ref_blacklist).map { that -> [[id:that.Name], that] }
+        ch_arriba_ref_known_fusions = Channel.fromPath(params.arriba_ref_known_fusions).map { that -> [[id:that.Name], that] }
+        ch_arriba_ref_protein_domains = Channel.fromPath(params.arriba_ref_protein_domains).map { that -> [[id:that.Name], that] }
+    } else {
+// TODO need to update the module to emit blacklist,knownfusions etc
+    }
 
 
     if ((params.fusioncatcher || params.all) &&
@@ -163,9 +163,9 @@ workflow BUILD_REFERENCES {
     ch_refflat
     ch_salmon_index
     ch_starindex_ref
-    // ch_arriba_ref_blacklist
-    // ch_arriba_ref_known_fusions
-    // ch_arriba_ref_protein_domains
+    ch_arriba_ref_blacklist
+    ch_arriba_ref_known_fusions
+    ch_arriba_ref_protein_domains
     ch_fusioncatcher_ref
     ch_starfusion_ref
     ch_fusionreport_ref
diff --git a/subworkflows/local/trim_workflow.nf b/subworkflows/local/trim_workflow.nf
index ea21134d..f963451b 100644
--- a/subworkflows/local/trim_workflow.nf
+++ b/subworkflows/local/trim_workflow.nf
@@ -8,9 +8,6 @@ workflow TRIM_WORKFLOW {
 
     main:
         ch_versions = Channel.empty()
-        ch_fastp_html = Channel.empty()
-        ch_fastp_json = Channel.empty()
-        ch_fastqc_trimmed = Channel.empty()
 
         if (params.fastp_trim) {
             FASTP(reads, params.adapter_fasta, false, false)
@@ -19,24 +16,21 @@ workflow TRIM_WORKFLOW {
             FASTQC_FOR_FASTP(FASTP.out.reads)
             ch_versions = ch_versions.mix(FASTQC_FOR_FASTP.out.versions)
 
-            ch_reads_all = FASTP.out.reads
-            ch_reads_fusioncatcher = ch_reads_all
+            ch_reads = FASTP.out.reads
             ch_fastp_html = FASTP.out.html
             ch_fastp_json = FASTP.out.json
             ch_fastqc_trimmed = FASTQC_FOR_FASTP.out.zip
 
         }
         else {
-            ch_reads_all = reads
-            ch_reads_fusioncatcher = reads
+            ch_reads = reads
         }
 
     emit:
-        ch_reads_all
-        ch_reads_fusioncatcher
-        ch_fastp_html
-        ch_fastp_json
-        ch_fastqc_trimmed
+        trimmed_reads = ch_reads
+        fastp_html = ch_fastp_html.ifEmpty([])
+        fastp_json = ch_fastp_json.ifEmpty([])
+        fastqc_trimmed = ch_fastqc_trimmed.ifEmpty([])
         versions = ch_versions
     }
 
diff --git a/workflows/rnafusion.nf b/workflows/rnafusion.nf
index 8067210a..302f2829 100644
--- a/workflows/rnafusion.nf
+++ b/workflows/rnafusion.nf
@@ -107,26 +107,28 @@ workflow RNAFUSION {
 
 
     //
-    // MODULE: Run FastQC
+    // QC from FASTQ files
     //
-    // FASTQC (
-    //     ch_cat_fastq
-    // )
-    // ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]})
-    // ch_versions = ch_versions.mix(FASTQC.out.versions)
+    FASTQC (
+        ch_cat_fastq
+    )
+    ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]})
+    ch_versions = ch_versions.mix(FASTQC.out.versions)
 
+    SALMON_QUANT( ch_reads_all, ch_salmon_index.map{ meta, index ->  index  }, ch_gtf.map{ meta, gtf ->  gtf  }, [], false, 'A')
+    ch_multiqc_files = ch_multiqc_files.mix(SALMON_QUANT.out.zip.collect{it[1]})
+    ch_versions = ch_versions.mix(SALMON_QUANT.out.versions)
 
+    //
+    // Trimming
+    //
     TRIM_WORKFLOW (
         ch_cat_fastq
     )
-    ch_reads_fusioncatcher = TRIM_WORKFLOW.out.ch_reads_fusioncatcher
-    ch_reads_all = TRIM_WORKFLOW.out.ch_reads_all
+    ch_reads = TRIM_WORKFLOW.out.trimmed_reads
     ch_versions = ch_versions.mix(TRIM_WORKFLOW.out.versions)
 
 
-//     SALMON_QUANT( ch_reads_all, ch_salmon_index.map{ meta, index ->  index  }, ch_gtf.map{ meta, gtf ->  gtf  }, [], false, 'A')
-
-
 //     //
 //     // SUBWORKFLOW:  Run STAR alignment and Arriba
 //     //

From eb6e354c180f6c533cbb862678403984e79275b2 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Mon, 23 Sep 2024 21:15:42 +0200
Subject: [PATCH 08/41] change strategy

---
 conf/modules.config                    |  3 ++-
 modules/local/ensembl/main.nf          | 22 +++++++++--------
 nextflow.config                        |  2 +-
 subworkflows/local/build_references.nf |  7 +++++-
 workflows/rnafusion.nf                 | 34 ++++++++++++++++++++++++--
 5 files changed, 53 insertions(+), 15 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index e78f73db..bbafa80d 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -49,7 +49,8 @@ process {
         ext.when   = { !params.build_references }
     }
 
-    withName: 'ENSEMBL_DOWNLOAD' {
+    withName: '.*BUILD_REFERENCES:ENSEMBL_DOWNLOAD' {
+        ext.when = { !params.fasta || ! params.gtf }
         publishDir = [
             path: { "${params.genomes_base}/ensembl" },
             mode: params.publish_dir_mode,
diff --git a/modules/local/ensembl/main.nf b/modules/local/ensembl/main.nf
index 8297e290..695ab312 100644
--- a/modules/local/ensembl/main.nf
+++ b/modules/local/ensembl/main.nf
@@ -14,20 +14,23 @@ process ENSEMBL_DOWNLOAD {
 
     output:
     tuple val(meta), path("Homo_sapiens.${genome}.${ensembl_version}.gtf")                       , emit: gtf
-    tuple val(meta), path("Homo_sapiens.${genome}.${ensembl_version}.dna.primary_assembly.fa")   , emit: primary_assembly
-    tuple val(meta), path("Homo_sapiens.${genome}.${ensembl_version}.chr.gtf")                   , emit: chrgtf
+    tuple val(meta), path("Homo_sapiens.${genome}.${ensembl_version}.dna.primary_assembly.fa")   , emit: fasta
     path "versions.yml"                                                                          , emit: versions
 
 
     script:
     """
-    wget ftp://ftp.ensembl.org/pub/release-${ensembl_version}/gtf/homo_sapiens/Homo_sapiens.${params.genome}.${ensembl_version}.gtf.gz
-    wget ftp://ftp.ensembl.org/pub/release-${ensembl_version}/fasta/homo_sapiens/dna/Homo_sapiens.${params.genome}.dna.primary_assembly.fa.gz -O Homo_sapiens.${params.genome}.${ensembl_version}.dna.primary_assembly.fa.gz
-    wget ftp://ftp.ensembl.org/pub/release-${ensembl_version}/gtf/homo_sapiens/Homo_sapiens.${params.genome}.${ensembl_version}.chr.gtf.gz
+    if [ ${genome} == 'GRCh37' ]; then
+        wget ftp://ftp.ensembl.org/pub/grch37/release-${ensembl_version}/gtf/homo_sapiens/Homo_sapiens.${genome}.87.gtf.gz -O Homo_sapiens.${genome}.${ensembl_version}.gtf.gz
+        wget ftp://ftp.ensembl.org/pub/grch37/release-${ensembl_version}/fasta/homo_sapiens/dna/Homo_sapiens.${genome}.dna.primary_assembly.fa.gz -O Homo_sapiens.${genome}.${ensembl_version}.dna.primary_assembly.fa.gz
 
-    gunzip Homo_sapiens.${params.genome}.${ensembl_version}.gtf.gz
-    gunzip Homo_sapiens.${params.genome}.${ensembl_version}.dna.primary_assembly.fa.gz
-    gunzip Homo_sapiens.${params.genome}.${ensembl_version}.chr.gtf.gz
+
+    else:
+        wget ftp://ftp.ensembl.org/pub/release-${ensembl_version}/gtf/homo_sapiens/Homo_sapiens.${genome}.${ensembl_version}.gtf.gz
+        wget ftp://ftp.ensembl.org/pub/release-${ensembl_version}/fasta/homo_sapiens/dna/Homo_sapiens.${genome}.dna.primary_assembly.fa.gz -O Homo_sapiens.${genome}.${ensembl_version}.dna.primary_assembly.fa.gz
+
+    gunzip Homo_sapiens.${genome}.${ensembl_version}.gtf.gz
+    gunzip Homo_sapiens.${genome}.${ensembl_version}.dna.primary_assembly.fa.gz
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
@@ -40,8 +43,7 @@ process ENSEMBL_DOWNLOAD {
     stub:
     """
     touch "Homo_sapiens.${genome}.${ensembl_version}.gtf"
-    touch "Homo_sapiens.${params.genome}.${ensembl_version}.dna.primary_assembly.fa"
-    touch "Homo_sapiens.${params.genome}.${ensembl_version}.chr.gtf"
+    touch "Homo_sapiens.${genome}.${ensembl_version}.dna.primary_assembly.fa"
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
diff --git a/nextflow.config b/nextflow.config
index b7d78f7d..ccaf0348 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -27,7 +27,7 @@ params {
     // Genome
     genome                     = 'GRCh38'
     genomes_base               = "${params.outdir}/references"
-    ensembl_version            = 112
+    ensembl_version            = 111
     read_length                = 100
     starfusion_build           = true
     genomes                    = [:]
diff --git a/subworkflows/local/build_references.nf b/subworkflows/local/build_references.nf
index a1a64050..c7a62033 100644
--- a/subworkflows/local/build_references.nf
+++ b/subworkflows/local/build_references.nf
@@ -35,12 +35,17 @@ include { GFFREAD }                         from '../../modules/nf-core/gffread/
 */
 
 workflow BUILD_REFERENCES {
-
+    take:
+        genome                           // channel: [mandatory]  val(genome)
+        ensembl_version                  // channel: [mandatory]  val(ensembl_version)
 
     main:
     ch_versions = Channel.empty()
 
 
+
+
+
     if (!file(params.fasta).exists() || file(params.fasta).isEmpty() ||
             !file(params.chrgtf).exists() || file(params.chrgtf).isEmpty() ||
             !file(params.gtf).exists() || file(params.gtf).isEmpty()){
diff --git a/workflows/rnafusion.nf b/workflows/rnafusion.nf
index 302f2829..36865840 100644
--- a/workflows/rnafusion.nf
+++ b/workflows/rnafusion.nf
@@ -65,8 +65,38 @@ workflow RNAFUSION {
     // Create references if necessary
     //
 
-    BUILD_REFERENCES()
-
+    BUILD_REFERENCES(params.genome, params.ensembl_version)
+    ch_versions = ch_versions.mix(BUILD_REFERENCES.out.versions)
+
+    // Optional
+    ch_fasta                      = params.fasta                        ? Channel.fromPath(params.fasta).map {it -> [[id:it[0].simpleName], it]}.collect()
+                                                                        : BUILD_REFERENCES.out.fasta.map {it -> [[id:it[0].simpleName], it]}.collect()
+    ch_gtf                        = params.gtf                          ? Channel.fromPath(params.gtf).map {it -> [[id:it[0].simpleName], it]}.collect()
+                                                                        : downloads.gtf.map {it -> [[id:it[0].simpleName], it]}.collect()
+    ch_vep_cache_unprocessed      = params.vep_cache                    ? Channel.fromPath(params.vep_cache)
+                                                                        : Channel.empty().mix(downloads.vep_cache)
+    ch_vep_extra_files_unsplit    = params.vep_plugin_files             ? Channel.fromPath(params.vep_plugin_files)
+                                                                        : Channel.empty().mix(downloads.vep_plugin)
+    ch_fai                        = params.fai                          ? Channel.fromPath(params.fai).map {it -> [[id:it[0].simpleName], it]}.collect()
+                                                                        : Channel.empty()
+    ch_gene_panel_clinical_filter = params.gene_panel_clinical_filter   ? Channel.fromPath(params.gene_panel_clinical_filter).collect()
+                                                                        : Channel.empty()
+    ch_ref_drop_annot_file        = params.reference_drop_annot_file    ? Channel.fromPath(params.reference_drop_annot_file).collect()
+                                                                        : Channel.empty()
+    ch_ref_drop_count_file        = params.reference_drop_count_file    ? Channel.fromPath(params.reference_drop_count_file).collect()
+                                                                        : Channel.empty()
+    ch_ref_drop_splice_folder     = params.reference_drop_splice_folder ? Channel.fromPath(params.reference_drop_splice_folder).collect()
+                                                                        : Channel.empty()
+    ch_salmon_index               = params.salmon_index                 ? Channel.fromPath(params.salmon_index)
+                                                                        : Channel.empty()
+    ch_star_index                 = params.star_index                   ? Channel.fromPath(params.star_index).map {it -> [[id:it[0].simpleName], it]}.collect()
+                                                                        : Channel.empty()
+    ch_transcript_fasta           = params.transcript_fasta             ? Channel.fromPath(params.transcript_fasta)
+                                                                        : Channel.empty()
+    ch_sequence_dict              = params.sequence_dict                ? Channel.fromPath(params.sequence_dict).map{ it -> [[id:it[0].simpleName], it] }.collect()
+                                                                        : Channel.empty()
+    ch_subsample_bed              = params.subsample_bed                ? Channel.fromPath(params.subsample_bed).collect()
+                                                                        : Channel.empty()
 
     //
     // Create channel from input file provided through params.input

From 40fbd83d3d45d009af01dda1eea44ef9af44fe24 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Mon, 7 Oct 2024 14:41:49 +0200
Subject: [PATCH 09/41] intermediate state

---
 modules/local/fusioncatcher/download/main.nf |   5 +-
 modules/local/starfusion/download/main.nf    |   2 +-
 nextflow.config                              |   3 +-
 subworkflows/local/build_references.nf       |  63 ++++---
 workflows/rnafusion.nf                       | 170 +++++++++----------
 5 files changed, 121 insertions(+), 122 deletions(-)

diff --git a/modules/local/fusioncatcher/download/main.nf b/modules/local/fusioncatcher/download/main.nf
index aec16288..916b4673 100644
--- a/modules/local/fusioncatcher/download/main.nf
+++ b/modules/local/fusioncatcher/download/main.nf
@@ -20,9 +20,10 @@ process FUSIONCATCHER_DOWNLOAD {
 
     def args = task.ext.args ?: ''
     def args2 = task.ext.args2 ?: ''
-    def url =
+        // TODO: move to my sourceforge
+
+    // def url =
     """
-    TODO: move to my sourceforge
     wget $args http://sourceforge.net/projects/fusioncatcher/files/data/human_${ensembl_version}.tar.gz.aa
     wget $args http://sourceforge.net/projects/fusioncatcher/files/data/human_${ensembl_version}.tar.gz.ab
     wget $args http://sourceforge.net/projects/fusioncatcher/files/data/human_${ensembl_version}.tar.gz.ac
diff --git a/modules/local/starfusion/download/main.nf b/modules/local/starfusion/download/main.nf
index e3a4b1b8..fedadfa0 100644
--- a/modules/local/starfusion/download/main.nf
+++ b/modules/local/starfusion/download/main.nf
@@ -9,7 +9,7 @@ process STARFUSION_DOWNLOAD {
     path "ctat_genome_lib_build_dir/ref_annot.gtf", emit: chrgtf
 
 
-    TODO: move to my sourceforge
+    // TODO: move to my sourceforge
     script:
     """
     wget https://data.broadinstitute.org/Trinity/CTAT_RESOURCE_LIB/__genome_libs_StarFv1.10/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play.tar.gz --no-check-certificate
diff --git a/nextflow.config b/nextflow.config
index ccaf0348..db5a3f63 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -27,7 +27,7 @@ params {
     // Genome
     genome                     = 'GRCh38'
     genomes_base               = "${params.outdir}/references"
-    ensembl_version            = 111
+    ensembl_version            = 112
     read_length                = 100
     starfusion_build           = true
     genomes                    = [:]
@@ -72,7 +72,6 @@ params {
     fasta                         = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.dna.primary_assembly.fa"
     fai                           = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.dna.primary_assembly.fa.fai"
     gtf                           = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.gtf"
-    chrgtf                        = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.chr.gtf"
     refflat                       = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.gtf.refflat"
     rrna_intervals                = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.interval_list"
     ensembl_ref                   = "${params.genomes_base}/ensembl"
diff --git a/subworkflows/local/build_references.nf b/subworkflows/local/build_references.nf
index c7a62033..cfb4258b 100644
--- a/subworkflows/local/build_references.nf
+++ b/subworkflows/local/build_references.nf
@@ -42,25 +42,26 @@ workflow BUILD_REFERENCES {
     main:
     ch_versions = Channel.empty()
 
-
-
-
-
     if (!file(params.fasta).exists() || file(params.fasta).isEmpty() ||
-            !file(params.chrgtf).exists() || file(params.chrgtf).isEmpty() ||
             !file(params.gtf).exists() || file(params.gtf).isEmpty()){
         fake_meta = [:]
         fake_meta.id = "Homo_sapiens.${params.genome}.${params.ensembl_version}"
         ENSEMBL_DOWNLOAD(params.ensembl_version, params.genome, fake_meta)
+        ch_versions = ENSEMBL_DOWNLOAD.out.versions
         ch_fasta = ENSEMBL_DOWNLOAD.out.primary_assembly
-        ch_chrgtf = ENSEMBL_DOWNLOAD.out.chrgtf
         ch_gtf = ENSEMBL_DOWNLOAD.out.gtf
     } else {
         ch_fasta = Channel.fromPath(params.fasta).map { that -> [[id:that.Name], that] }
-        ch_chrgtf = Channel.fromPath(params.chrgtf).map { that -> [[id:that.Name], that] }
         ch_gtf = Channel.fromPath(params.gtf).map { that -> [[id:that.Name], that] }
     }
 
+    if (!file(params.fai).exists() || file(params.fai).isEmpty()){
+        SAMTOOLS_FAIDX(ch_fasta, [[],[]]).fai
+        ch_versions = SAMTOOLS_FAIDX.out.versions
+        ch_fai = SAMTOOLS_FAIDX.out.fai
+    } else {
+        ch_fai = Channel.fromPath(params.fai).map { that -> [[id:that.Name], that] }
+    }
 
     if ((!file(params.hgnc_ref).exists() || file(params.hgnc_ref).isEmpty() ||
             !file(params.hgnc_date).exists() || file(params.hgnc_date).isEmpty()) && !params.skip_vcf){
@@ -72,10 +73,6 @@ workflow BUILD_REFERENCES {
         ch_hgnc_date = Channel.fromPath(params.hgnc_date).map { that -> [[id:that.Name], that] }
     }
 
-
-    ch_fai = (!file(params.fai).exists() || file(params.fai).isEmpty()) ? SAMTOOLS_FAIDX(ch_fasta, [[],[]]).fai : Channel.fromPath(params.fai).map { that -> [[id:that.Name], that] }
-
-
     if (!file(params.rrna_intervals).exists() || file(params.rrna_intervals).isEmpty()){
         GATK4_CREATESEQUENCEDICTIONARY(ch_fasta)
         RRNA_TRANSCRIPTS(ch_gtf)
@@ -86,9 +83,12 @@ workflow BUILD_REFERENCES {
         ch_rrna_interval = Channel.fromPath(params.rrna_intervals).map { that -> [[id:that.Name], that] }
     }
 
-
-    ch_refflat = (!file(params.refflat).exists() || file(params.refflat).isEmpty()) ? GTF_TO_REFFLAT.refflat : Channel.fromPath(params.refflat)
-
+    if (!file(params.refflat).exists() || file(params.refflat).isEmpty()){
+        GTF_TO_REFFLAT(ch_gtf)
+        ch_refflat = GTF_TO_REFFLAT.out.refflat
+    } else {
+        ch_refflat = Channel.fromPath(params.refflat).map { that -> [[id:that.Name], that] }
+    }
 
     if (!file(params.salmon_index).exists() || file(params.salmon_index).isEmpty() ||
         !file(params.salmon_index_stub_check).exists() || file(params.salmon_index_stub_check).isEmpty()){ // add condition for qc
@@ -99,7 +99,6 @@ workflow BUILD_REFERENCES {
         ch_salmon_index = Channel.fromPath(params.salmon_index)
     }
 
-
     if ((params.starindex || params.all || params.starfusion || params.arriba) &&
             (!file(params.starindex_ref).exists() || file(params.starindex_ref).isEmpty() ||
             !file(params.starindex_ref_stub_check).exists() || file(params.starindex_ref_stub_check).isEmpty() )) {
@@ -109,18 +108,17 @@ workflow BUILD_REFERENCES {
         ch_starindex_ref = Channel.fromPath(params.starindex_ref).map { that -> [[id:that.Name], that] }
     }
 
-
-    if ((params.arriba || params.all) &&
-            (!file(params.arriba_ref_blacklist).exists() || file(params.arriba_ref_blacklist).isEmpty() ||
-            !file(params.arriba_ref_known_fusions).exists() || file(params.arriba_ref_known_fusions).isEmpty() ||
-            !file(params.arriba_ref_protein_domains).exists() || file(params.arriba_ref_protein_domains).isEmpty())) {
-        ARRIBA_DOWNLOAD()
-        ch_arriba_ref_blacklist = Channel.fromPath(params.arriba_ref_blacklist).map { that -> [[id:that.Name], that] }
-        ch_arriba_ref_known_fusions = Channel.fromPath(params.arriba_ref_known_fusions).map { that -> [[id:that.Name], that] }
-        ch_arriba_ref_protein_domains = Channel.fromPath(params.arriba_ref_protein_domains).map { that -> [[id:that.Name], that] }
-    } else {
-// TODO need to update the module to emit blacklist,knownfusions etc
-    }
+//     if ((params.arriba || params.all) &&
+//             (!file(params.arriba_ref_blacklist).exists() || file(params.arriba_ref_blacklist).isEmpty() ||
+//             !file(params.arriba_ref_known_fusions).exists() || file(params.arriba_ref_known_fusions).isEmpty() ||
+//             !file(params.arriba_ref_protein_domains).exists() || file(params.arriba_ref_protein_domains).isEmpty())) {
+//         ARRIBA_DOWNLOAD()
+//         ch_arriba_ref_blacklist = Channel.fromPath(params.arriba_ref_blacklist).map { that -> [[id:that.Name], that] }
+//         ch_arriba_ref_known_fusions = Channel.fromPath(params.arriba_ref_known_fusions).map { that -> [[id:that.Name], that] }
+//         ch_arriba_ref_protein_domains = Channel.fromPath(params.arriba_ref_protein_domains).map { that -> [[id:that.Name], that] }
+//     } else {
+// // TODO need to update the module to emit blacklist,knownfusions etc
+//     }
 
 
     if ((params.fusioncatcher || params.all) &&
@@ -159,21 +157,22 @@ workflow BUILD_REFERENCES {
 
     emit:
     ch_fasta
-    ch_chrgtf
     ch_gtf
+    ch_fai
+
     ch_hgnc_ref
     ch_hgnc_date
-    ch_fai
     ch_rrna_interval
     ch_refflat
     ch_salmon_index
     ch_starindex_ref
-    ch_arriba_ref_blacklist
-    ch_arriba_ref_known_fusions
-    ch_arriba_ref_protein_domains
+    // ch_arriba_ref_blacklist
+    // ch_arriba_ref_known_fusions
+    // ch_arriba_ref_protein_domains
     ch_fusioncatcher_ref
     ch_starfusion_ref
     ch_fusionreport_ref
+    versions        = ch_versions
 }
 
 /*
diff --git a/workflows/rnafusion.nf b/workflows/rnafusion.nf
index 36865840..67dedb4b 100644
--- a/workflows/rnafusion.nf
+++ b/workflows/rnafusion.nf
@@ -68,95 +68,95 @@ workflow RNAFUSION {
     BUILD_REFERENCES(params.genome, params.ensembl_version)
     ch_versions = ch_versions.mix(BUILD_REFERENCES.out.versions)
 
-    // Optional
-    ch_fasta                      = params.fasta                        ? Channel.fromPath(params.fasta).map {it -> [[id:it[0].simpleName], it]}.collect()
-                                                                        : BUILD_REFERENCES.out.fasta.map {it -> [[id:it[0].simpleName], it]}.collect()
-    ch_gtf                        = params.gtf                          ? Channel.fromPath(params.gtf).map {it -> [[id:it[0].simpleName], it]}.collect()
-                                                                        : downloads.gtf.map {it -> [[id:it[0].simpleName], it]}.collect()
-    ch_vep_cache_unprocessed      = params.vep_cache                    ? Channel.fromPath(params.vep_cache)
-                                                                        : Channel.empty().mix(downloads.vep_cache)
-    ch_vep_extra_files_unsplit    = params.vep_plugin_files             ? Channel.fromPath(params.vep_plugin_files)
-                                                                        : Channel.empty().mix(downloads.vep_plugin)
-    ch_fai                        = params.fai                          ? Channel.fromPath(params.fai).map {it -> [[id:it[0].simpleName], it]}.collect()
-                                                                        : Channel.empty()
-    ch_gene_panel_clinical_filter = params.gene_panel_clinical_filter   ? Channel.fromPath(params.gene_panel_clinical_filter).collect()
-                                                                        : Channel.empty()
-    ch_ref_drop_annot_file        = params.reference_drop_annot_file    ? Channel.fromPath(params.reference_drop_annot_file).collect()
-                                                                        : Channel.empty()
-    ch_ref_drop_count_file        = params.reference_drop_count_file    ? Channel.fromPath(params.reference_drop_count_file).collect()
-                                                                        : Channel.empty()
-    ch_ref_drop_splice_folder     = params.reference_drop_splice_folder ? Channel.fromPath(params.reference_drop_splice_folder).collect()
-                                                                        : Channel.empty()
-    ch_salmon_index               = params.salmon_index                 ? Channel.fromPath(params.salmon_index)
-                                                                        : Channel.empty()
-    ch_star_index                 = params.star_index                   ? Channel.fromPath(params.star_index).map {it -> [[id:it[0].simpleName], it]}.collect()
-                                                                        : Channel.empty()
-    ch_transcript_fasta           = params.transcript_fasta             ? Channel.fromPath(params.transcript_fasta)
-                                                                        : Channel.empty()
-    ch_sequence_dict              = params.sequence_dict                ? Channel.fromPath(params.sequence_dict).map{ it -> [[id:it[0].simpleName], it] }.collect()
-                                                                        : Channel.empty()
-    ch_subsample_bed              = params.subsample_bed                ? Channel.fromPath(params.subsample_bed).collect()
-                                                                        : Channel.empty()
+    // // Optional
+    // ch_fasta                      = params.fasta                        ? Channel.fromPath(params.fasta).map {it -> [[id:it[0].simpleName], it]}.collect()
+    //                                                                     : BUILD_REFERENCES.out.fasta.map {it -> [[id:it[0].simpleName], it]}.collect()
+    // ch_gtf                        = params.gtf                          ? Channel.fromPath(params.gtf).map {it -> [[id:it[0].simpleName], it]}.collect()
+    //                                                                     : downloads.gtf.map {it -> [[id:it[0].simpleName], it]}.collect()
+    // ch_vep_cache_unprocessed      = params.vep_cache                    ? Channel.fromPath(params.vep_cache)
+    //                                                                     : Channel.empty().mix(downloads.vep_cache)
+    // ch_vep_extra_files_unsplit    = params.vep_plugin_files             ? Channel.fromPath(params.vep_plugin_files)
+    //                                                                     : Channel.empty().mix(downloads.vep_plugin)
+    // ch_fai                        = params.fai                          ? Channel.fromPath(params.fai).map {it -> [[id:it[0].simpleName], it]}.collect()
+    //                                                                     : Channel.empty()
+    // ch_gene_panel_clinical_filter = params.gene_panel_clinical_filter   ? Channel.fromPath(params.gene_panel_clinical_filter).collect()
+    //                                                                     : Channel.empty()
+    // ch_ref_drop_annot_file        = params.reference_drop_annot_file    ? Channel.fromPath(params.reference_drop_annot_file).collect()
+    //                                                                     : Channel.empty()
+    // ch_ref_drop_count_file        = params.reference_drop_count_file    ? Channel.fromPath(params.reference_drop_count_file).collect()
+    //                                                                     : Channel.empty()
+    // ch_ref_drop_splice_folder     = params.reference_drop_splice_folder ? Channel.fromPath(params.reference_drop_splice_folder).collect()
+    //                                                                     : Channel.empty()
+    // ch_salmon_index               = params.salmon_index                 ? Channel.fromPath(params.salmon_index)
+    //                                                                     : Channel.empty()
+    // ch_star_index                 = params.star_index                   ? Channel.fromPath(params.star_index).map {it -> [[id:it[0].simpleName], it]}.collect()
+    //                                                                     : Channel.empty()
+    // ch_transcript_fasta           = params.transcript_fasta             ? Channel.fromPath(params.transcript_fasta)
+    //                                                                     : Channel.empty()
+    // ch_sequence_dict              = params.sequence_dict                ? Channel.fromPath(params.sequence_dict).map{ it -> [[id:it[0].simpleName], it] }.collect()
+    //                                                                     : Channel.empty()
+    // ch_subsample_bed              = params.subsample_bed                ? Channel.fromPath(params.subsample_bed).collect()
+    //                                                                     : Channel.empty()
 
     //
     // Create channel from input file provided through params.input
     //
-    Channel
-        .fromSamplesheet("input")
-        .map {
-            meta, fastq_1, fastq_2, strandedness ->
-                if (!fastq_2) {
-                    return [ meta.id, meta + [ single_end:true ], [ fastq_1 ] ]
-                } else {
-                    return [ meta.id, meta + [ single_end:false ], [ fastq_1, fastq_2 ] ]
-                }
-        }
-        .groupTuple()
-        .map {
-            validateInputSamplesheet(it)
-        }
-        .branch {
-            meta, fastqs ->
-                single  : fastqs.size() == 1
-                    return [ meta, fastqs.flatten() ]
-                multiple: fastqs.size() > 1
-                    return [ meta, fastqs.flatten() ]
-        }
-        .set { ch_fastq }
-
-    //
-    // MODULE: Concatenate FastQ files from same sample if required
-    //
-    CAT_FASTQ (
-        ch_fastq.multiple
-    )
-    .reads
-    .mix(ch_fastq.single)
-    .set { ch_cat_fastq }
-    ch_versions = ch_versions.mix(CAT_FASTQ.out.versions)
-
-
-    //
-    // QC from FASTQ files
-    //
-    FASTQC (
-        ch_cat_fastq
-    )
-    ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]})
-    ch_versions = ch_versions.mix(FASTQC.out.versions)
-
-    SALMON_QUANT( ch_reads_all, ch_salmon_index.map{ meta, index ->  index  }, ch_gtf.map{ meta, gtf ->  gtf  }, [], false, 'A')
-    ch_multiqc_files = ch_multiqc_files.mix(SALMON_QUANT.out.zip.collect{it[1]})
-    ch_versions = ch_versions.mix(SALMON_QUANT.out.versions)
-
-    //
-    // Trimming
-    //
-    TRIM_WORKFLOW (
-        ch_cat_fastq
-    )
-    ch_reads = TRIM_WORKFLOW.out.trimmed_reads
-    ch_versions = ch_versions.mix(TRIM_WORKFLOW.out.versions)
+    // Channel
+    //     .fromSamplesheet("input")
+    //     .map {
+    //         meta, fastq_1, fastq_2, strandedness ->
+    //             if (!fastq_2) {
+    //                 return [ meta.id, meta + [ single_end:true ], [ fastq_1 ] ]
+    //             } else {
+    //                 return [ meta.id, meta + [ single_end:false ], [ fastq_1, fastq_2 ] ]
+    //             }
+    //     }
+    //     .groupTuple()
+    //     .map {
+    //         validateInputSamplesheet(it)
+    //     }
+    //     .branch {
+    //         meta, fastqs ->
+    //             single  : fastqs.size() == 1
+    //                 return [ meta, fastqs.flatten() ]
+    //             multiple: fastqs.size() > 1
+    //                 return [ meta, fastqs.flatten() ]
+    //     }
+    //     .set { ch_fastq }
+
+    // //
+    // // MODULE: Concatenate FastQ files from same sample if required
+    // //
+    // CAT_FASTQ (
+    //     ch_fastq.multiple
+    // )
+    // .reads
+    // .mix(ch_fastq.single)
+    // .set { ch_cat_fastq }
+    // ch_versions = ch_versions.mix(CAT_FASTQ.out.versions)
+
+
+    // //
+    // // QC from FASTQ files
+    // //
+    // FASTQC (
+    //     ch_cat_fastq
+    // )
+    // ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]})
+    // ch_versions = ch_versions.mix(FASTQC.out.versions)
+
+    // SALMON_QUANT( ch_reads_all, BUILD_REFERENCES.out.ch_salmon_index.map{ meta, index ->  index  }, BUILD_REFERENCES.out.ch_gtf.map{ meta, gtf ->  gtf  }, [], false, 'A')
+    // ch_multiqc_files = ch_multiqc_files.mix(SALMON_QUANT.out.zip.collect{it[1]})
+    // ch_versions = ch_versions.mix(SALMON_QUANT.out.versions)
+
+    // //
+    // // Trimming
+    // //
+    // TRIM_WORKFLOW (
+    //     ch_cat_fastq
+    // )
+    // ch_reads = TRIM_WORKFLOW.out.trimmed_reads
+    // ch_versions = ch_versions.mix(TRIM_WORKFLOW.out.versions)
 
 
 //     //

From 7a889713da5ee69696daf159cb45d94e577cc483 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Wed, 16 Oct 2024 09:27:26 +0200
Subject: [PATCH 10/41] ensembl to gencode, removing chrgtf

---
 conf/modules.config                           |  11 +-
 modules.json                                  |  10 ++
 modules/local/ensembl/main.nf                 |  55 -------
 modules/local/fusioncatcher/build/main.nf     |  12 +-
 modules/local/gencode_download/main.nf        |  49 +++++++
 modules/local/hgnc/main.nf                    |   2 +-
 modules/local/starfusion/download/main.nf     |   1 -
 .../nf-core/arriba/download/environment.yml   |   5 +
 modules/nf-core/arriba/download/main.nf       |  46 ++++++
 modules/nf-core/arriba/download/meta.yml      |  30 ++++
 .../arriba/download/tests/main.nf.test        |  35 +++++
 .../arriba/download/tests/main.nf.test.snap   |  35 +++++
 modules/nf-core/gunzip/environment.yml        |   7 +
 modules/nf-core/gunzip/main.nf                |  55 +++++++
 modules/nf-core/gunzip/meta.yml               |  47 ++++++
 modules/nf-core/gunzip/tests/main.nf.test     | 121 ++++++++++++++++
 .../nf-core/gunzip/tests/main.nf.test.snap    | 134 ++++++++++++++++++
 modules/nf-core/gunzip/tests/nextflow.config  |   5 +
 modules/nf-core/gunzip/tests/tags.yml         |   2 +
 nextflow.config                               |  19 ++-
 nextflow_schema.json                          |  19 +--
 subworkflows/local/build_references.nf        |  96 ++++++-------
 subworkflows/local/qc_workflow.nf             |   2 +-
 subworkflows/local/starfusion_workflow.nf     |   4 +-
 subworkflows/local/stringtie_workflow.nf      |   6 +-
 workflows/rnafusion.nf                        |  10 +-
 26 files changed, 663 insertions(+), 155 deletions(-)
 delete mode 100644 modules/local/ensembl/main.nf
 create mode 100644 modules/local/gencode_download/main.nf
 create mode 100644 modules/nf-core/arriba/download/environment.yml
 create mode 100644 modules/nf-core/arriba/download/main.nf
 create mode 100644 modules/nf-core/arriba/download/meta.yml
 create mode 100644 modules/nf-core/arriba/download/tests/main.nf.test
 create mode 100644 modules/nf-core/arriba/download/tests/main.nf.test.snap
 create mode 100644 modules/nf-core/gunzip/environment.yml
 create mode 100644 modules/nf-core/gunzip/main.nf
 create mode 100644 modules/nf-core/gunzip/meta.yml
 create mode 100644 modules/nf-core/gunzip/tests/main.nf.test
 create mode 100644 modules/nf-core/gunzip/tests/main.nf.test.snap
 create mode 100644 modules/nf-core/gunzip/tests/nextflow.config
 create mode 100644 modules/nf-core/gunzip/tests/tags.yml

diff --git a/conf/modules.config b/conf/modules.config
index bbafa80d..af832498 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -49,10 +49,9 @@ process {
         ext.when   = { !params.build_references }
     }
 
-    withName: '.*BUILD_REFERENCES:ENSEMBL_DOWNLOAD' {
-        ext.when = { !params.fasta || ! params.gtf }
+    withName: 'GENCODE_DOWNLOAD' {
         publishDir = [
-            path: { "${params.genomes_base}/ensembl" },
+            path: { "${params.genomes_base}/gencode" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]
@@ -122,7 +121,7 @@ process {
 
     withName: 'GATK4_BEDTOINTERVALLIST' {
         publishDir = [
-            path: { "${params.genomes_base}/ensembl" },
+            path: { "${params.genomes_base}/gencode" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]
@@ -139,7 +138,7 @@ process {
 
     withName: 'GTF_TO_REFFLAT' {
         publishDir = [
-            path: { "${params.genomes_base}/ensembl" },
+            path: { "${params.genomes_base}/gencode" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
         ]
@@ -209,7 +208,7 @@ process {
 
     withName: 'SAMTOOLS_FAIDX' {
         publishDir = [
-            path: { "${params.genomes_base}/ensembl" },
+            path: { "${params.genomes_base}/gencode" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
         ]
diff --git a/modules.json b/modules.json
index 7f4cf0ef..886af975 100644
--- a/modules.json
+++ b/modules.json
@@ -15,6 +15,11 @@
                         "git_sha": "bbaeb3a3149def237b9d0acb9ab749ae98088e29",
                         "installed_by": ["modules"]
                     },
+                    "arriba/download": {
+                        "branch": "master",
+                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
+                        "installed_by": ["modules"]
+                    },
                     "cat/cat": {
                         "branch": "master",
                         "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",
@@ -55,6 +60,11 @@
                         "git_sha": "6c996d7fbe0816dcbb68ce587ad5f873313682a1",
                         "installed_by": ["modules"]
                     },
+                    "gunzip": {
+                        "branch": "master",
+                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
+                        "installed_by": ["modules"]
+                    },
                     "multiqc": {
                         "branch": "master",
                         "git_sha": "b7ebe95761cd389603f9cc0e0dc384c0f663815a",
diff --git a/modules/local/ensembl/main.nf b/modules/local/ensembl/main.nf
deleted file mode 100644
index 695ab312..00000000
--- a/modules/local/ensembl/main.nf
+++ /dev/null
@@ -1,55 +0,0 @@
-process ENSEMBL_DOWNLOAD {
-    tag "ensembl"
-    label 'process_low'
-
-    conda "bioconda::gnu-wget=1.18"
-    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gnu-wget:1.18--h5bf99c6_5' :
-        'quay.io/biocontainers/gnu-wget:1.18--h5bf99c6_5' }"
-
-    input:
-    val ensembl_version
-    val genome
-    val meta
-
-    output:
-    tuple val(meta), path("Homo_sapiens.${genome}.${ensembl_version}.gtf")                       , emit: gtf
-    tuple val(meta), path("Homo_sapiens.${genome}.${ensembl_version}.dna.primary_assembly.fa")   , emit: fasta
-    path "versions.yml"                                                                          , emit: versions
-
-
-    script:
-    """
-    if [ ${genome} == 'GRCh37' ]; then
-        wget ftp://ftp.ensembl.org/pub/grch37/release-${ensembl_version}/gtf/homo_sapiens/Homo_sapiens.${genome}.87.gtf.gz -O Homo_sapiens.${genome}.${ensembl_version}.gtf.gz
-        wget ftp://ftp.ensembl.org/pub/grch37/release-${ensembl_version}/fasta/homo_sapiens/dna/Homo_sapiens.${genome}.dna.primary_assembly.fa.gz -O Homo_sapiens.${genome}.${ensembl_version}.dna.primary_assembly.fa.gz
-
-
-    else:
-        wget ftp://ftp.ensembl.org/pub/release-${ensembl_version}/gtf/homo_sapiens/Homo_sapiens.${genome}.${ensembl_version}.gtf.gz
-        wget ftp://ftp.ensembl.org/pub/release-${ensembl_version}/fasta/homo_sapiens/dna/Homo_sapiens.${genome}.dna.primary_assembly.fa.gz -O Homo_sapiens.${genome}.${ensembl_version}.dna.primary_assembly.fa.gz
-
-    gunzip Homo_sapiens.${genome}.${ensembl_version}.gtf.gz
-    gunzip Homo_sapiens.${genome}.${ensembl_version}.dna.primary_assembly.fa.gz
-
-    cat <<-END_VERSIONS > versions.yml
-    "${task.process}":
-        wget: \$(echo wget -V 2>&1 | grep "GNU Wget" | cut -d" " -f3 > versions.yml)
-        gunzip: \$(echo \$(gunzip --version 2>&1) | sed 's/^.*(gzip) //; s/ Copyright.*\$//')
-
-    END_VERSIONS
-    """
-
-    stub:
-    """
-    touch "Homo_sapiens.${genome}.${ensembl_version}.gtf"
-    touch "Homo_sapiens.${genome}.${ensembl_version}.dna.primary_assembly.fa"
-
-    cat <<-END_VERSIONS > versions.yml
-    "${task.process}":
-        wget: \$(echo wget -V 2>&1 | grep "GNU Wget" | cut -d" " -f3 > versions.yml)
-        gunzip: \$(echo \$(gunzip --version 2>&1) | sed 's/^.*(gzip) //; s/ Copyright.*\$//')
-    END_VERSIONS
-    """
-
-}
diff --git a/modules/local/fusioncatcher/build/main.nf b/modules/local/fusioncatcher/build/main.nf
index 15f7afed..51153253 100644
--- a/modules/local/fusioncatcher/build/main.nf
+++ b/modules/local/fusioncatcher/build/main.nf
@@ -6,11 +6,11 @@ process FUSIONCATCHER_BUILD {
     container "docker.io/clinicalgenomics/fusioncatcher:1.33"
 
     input:
-    val ensembl_version
+    val genome_gencode_version
 
     output:
-    path "human_v${ensembl_version}"  , emit: reference
-    path "versions.yml"               , emit: versions
+    path "human_v${genome_gencode_version}"  , emit: reference
+    path "versions.yml"                      , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
@@ -21,7 +21,7 @@ process FUSIONCATCHER_BUILD {
     """
     fusioncatcher-build.py \\
         -g homo_sapiens \\
-        -o human_v${ensembl_version} \\
+        -o human_v${genome_gencode_version} \\
         $args
 
     cat <<-END_VERSIONS > versions.yml
@@ -32,8 +32,8 @@ process FUSIONCATCHER_BUILD {
 
     stub:
     """
-    mkdir human_v${ensembl_version}
-    touch human_v${ensembl_version}/ensembl_fully_overlapping_genes.txt
+    mkdir human_v${genome_gencode_version}
+    touch human_v${genome_gencode_version}/ensembl_fully_overlapping_genes.txt
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
         fusioncatcher: \$(echo \$(fusioncatcher --version 2>&1))
diff --git a/modules/local/gencode_download/main.nf b/modules/local/gencode_download/main.nf
new file mode 100644
index 00000000..e9416cf4
--- /dev/null
+++ b/modules/local/gencode_download/main.nf
@@ -0,0 +1,49 @@
+process GENCODE_DOWNLOAD {
+    tag "gencode_download"
+    label 'process_low'
+
+    conda "bioconda::gnu-wget=1.18"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/gnu-wget:1.18--h5bf99c6_5' :
+        'quay.io/biocontainers/gnu-wget:1.18--h5bf99c6_5' }"
+
+    input:
+    val genome_gencode_version
+    val genome
+
+    output:
+    path "*.fa"        , emit: fasta
+    path "*.gtf"       , emit: gtf
+    path "versions.yml", emit: versions
+
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def folder_gencode = genome.contains("38") ? "" : "/${genome}_mapping"
+    def gtf_file_name = genome.contains("38") ? "gencode.v${genome_gencode_version}.primary_assembly.annotation.gtf.gz" : "gencode.v${genome_gencode_version}lift${genome_gencode_version}.annotation.gtf.gz"
+    """
+    wget ftp://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_${genome_gencode_version}/${folder_gencode}${genome}.primary_assembly.genome.fa.gz -O Homo_sapiens_${genome}_${genome_gencode_version}_dna_primary_assembly.fa.gz
+    gunzip Homo_sapiens_${genome}_${genome_gencode_version}_dna_primary_assembly.fa.gz
+    wget ftp://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_${genome_gencode_version}/${folder_gencode}${gtf_file_name} -O Homo_sapiens_${genome}_${genome_gencode_version}.gtf.gz
+    gunzip  Homo_sapiens_${genome}_${genome_gencode_version}.gtf.gz
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        wget: \$(echo wget -V 2>&1 | grep "GNU Wget" | cut -d" " -f3 > versions.yml)
+    END_VERSIONS
+    """
+
+    stub:
+    """
+    touch Homo_sapiens.${genome}.${genome_gencode_version}_dna_primary_assembly.fa
+    touch Homo_sapiens.${genome}.${genome_gencode_version}.gtf
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        wget: \$(echo wget -V 2>&1 | grep "GNU Wget" | cut -d" " -f3 > versions.yml)
+    END_VERSIONS
+    """
+
+}
diff --git a/modules/local/hgnc/main.nf b/modules/local/hgnc/main.nf
index 1b3808f6..6a055631 100644
--- a/modules/local/hgnc/main.nf
+++ b/modules/local/hgnc/main.nf
@@ -18,7 +18,7 @@ process HGNC_DOWNLOAD {
 
     script:
     """
-    wget https://ftp.ebi.ac.uk/pub/databases/genenames/hgnc/tsv/hgnc_complete_set.txt
+    wget https://ftp.ebi.ac.uk/pub/databases/genenames/out_of_date_hgnc/tsv/hgnc_complete_set.txt
     date +%Y-%m-%d/%H:%M  > HGNC-DB-timestamp.txt
 
     cat <<-END_VERSIONS > versions.yml
diff --git a/modules/local/starfusion/download/main.nf b/modules/local/starfusion/download/main.nf
index fedadfa0..17bfa72e 100644
--- a/modules/local/starfusion/download/main.nf
+++ b/modules/local/starfusion/download/main.nf
@@ -6,7 +6,6 @@ process STARFUSION_DOWNLOAD {
 
     output:
     path "ctat_genome_lib_build_dir/*"            , emit: reference
-    path "ctat_genome_lib_build_dir/ref_annot.gtf", emit: chrgtf
 
 
     // TODO: move to my sourceforge
diff --git a/modules/nf-core/arriba/download/environment.yml b/modules/nf-core/arriba/download/environment.yml
new file mode 100644
index 00000000..d0883a0d
--- /dev/null
+++ b/modules/nf-core/arriba/download/environment.yml
@@ -0,0 +1,5 @@
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::arriba=2.4.0
diff --git a/modules/nf-core/arriba/download/main.nf b/modules/nf-core/arriba/download/main.nf
new file mode 100644
index 00000000..96a4e336
--- /dev/null
+++ b/modules/nf-core/arriba/download/main.nf
@@ -0,0 +1,46 @@
+process ARRIBA_DOWNLOAD {
+    tag "arriba"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/arriba:2.4.0--h0033a41_2' :
+        'biocontainers/arriba:2.4.0--h0033a41_2' }"
+
+    input:
+
+    output:
+    path "*"              , emit: reference
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    """
+    wget https://github.com/suhrig/arriba/releases/download/v2.4.0/arriba_v2.4.0.tar.gz -O arriba_v2.4.0.tar.gz
+    tar -xzvf arriba_v2.4.0.tar.gz
+    rm arriba_v2.4.0.tar.gz
+    mv arriba_v2.4.0/database/* .
+    rm -r arriba_v2.4.0
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        arriba_download: \$(arriba -h | grep 'Version:' 2>&1 |  sed 's/Version:\s//')
+    END_VERSIONS
+    """
+
+    stub:
+    """
+    touch blacklist_hg38_GRCh38_v2.4.0.tsv.gz
+    touch protein_domains_hg38_GRCh38_v2.4.0.gff3
+    touch cytobands_hg38_GRCh38_v2.4.0.tsv
+    touch known_fusions_hg38_GRCh38_v2.4.0.tsv.gz
+    touch protein_domains_hg38_GRCh38_v2.4.0.gff3
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        arriba_download: \$(arriba -h | grep 'Version:' 2>&1 |  sed 's/Version:\s//')
+    END_VERSIONS
+    """
+}
diff --git a/modules/nf-core/arriba/download/meta.yml b/modules/nf-core/arriba/download/meta.yml
new file mode 100644
index 00000000..531c66c2
--- /dev/null
+++ b/modules/nf-core/arriba/download/meta.yml
@@ -0,0 +1,30 @@
+name: arriba_download
+description: Arriba is a command-line tool for the detection of gene fusions from
+  RNA-Seq data.
+keywords:
+  - fusion
+  - arriba
+  - reference
+tools:
+  - arriba:
+      description: Fast and accurate gene fusion detection from RNA-Seq data
+      homepage: https://github.com/suhrig/arriba
+      documentation: https://arriba.readthedocs.io/en/latest/
+      tool_dev_url: https://github.com/suhrig/arriba
+      doi: "10.1101/gr.257246.119"
+      licence: ["MIT"]
+      identifier: biotools:Arriba
+
+output:
+  - reference:
+      - "*":
+          type: directory
+          description: Folder with arriba references
+          pattern: "*"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+authors:
+  - "@peterpru"
diff --git a/modules/nf-core/arriba/download/tests/main.nf.test b/modules/nf-core/arriba/download/tests/main.nf.test
new file mode 100644
index 00000000..cccc95db
--- /dev/null
+++ b/modules/nf-core/arriba/download/tests/main.nf.test
@@ -0,0 +1,35 @@
+
+nextflow_process {
+
+    name "Test Process ARRIBA_DOWNLOAD"
+    script "../main.nf"
+    process "ARRIBA_DOWNLOAD"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "arriba"
+    tag "arriba/download"
+
+    test("test-arriba-download") {
+
+        when {
+            process {
+                """
+
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    process.out.reference[0].collect { file(it).name }.toSorted(),
+                    process.out.versions
+                    ).match()
+                }
+            )
+        }
+    }
+
+}
diff --git a/modules/nf-core/arriba/download/tests/main.nf.test.snap b/modules/nf-core/arriba/download/tests/main.nf.test.snap
new file mode 100644
index 00000000..eda3f706
--- /dev/null
+++ b/modules/nf-core/arriba/download/tests/main.nf.test.snap
@@ -0,0 +1,35 @@
+{
+    "test-arriba-download": {
+        "content": [
+            [
+                "CREDITS",
+                "RefSeq_viral_genomes_v2.4.0.fa.gz",
+                "blacklist_hg19_hs37d5_GRCh37_v2.4.0.tsv.gz",
+                "blacklist_hg38_GRCh38_v2.4.0.tsv.gz",
+                "blacklist_mm10_GRCm38_v2.4.0.tsv.gz",
+                "blacklist_mm39_GRCm39_v2.4.0.tsv.gz",
+                "cytobands_hg19_hs37d5_GRCh37_v2.4.0.tsv",
+                "cytobands_hg38_GRCh38_v2.4.0.tsv",
+                "cytobands_mm10_GRCm38_v2.4.0.tsv",
+                "cytobands_mm39_GRCm39_v2.4.0.tsv",
+                "known_fusions_hg19_hs37d5_GRCh37_v2.4.0.tsv.gz",
+                "known_fusions_hg38_GRCh38_v2.4.0.tsv.gz",
+                "known_fusions_mm10_GRCm38_v2.4.0.tsv.gz",
+                "known_fusions_mm39_GRCm39_v2.4.0.tsv.gz",
+                "protein_domains_hg19_hs37d5_GRCh37_v2.4.0.gff3",
+                "protein_domains_hg38_GRCh38_v2.4.0.gff3",
+                "protein_domains_mm10_GRCm38_v2.4.0.gff3",
+                "protein_domains_mm39_GRCm39_v2.4.0.gff3",
+                "versions.yml"
+            ],
+            [
+                "versions.yml:md5,98c69df5eaea5caf0b4af7b8d7af4893"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-08-22T17:00:38.086459"
+    }
+}
\ No newline at end of file
diff --git a/modules/nf-core/gunzip/environment.yml b/modules/nf-core/gunzip/environment.yml
new file mode 100644
index 00000000..c7794856
--- /dev/null
+++ b/modules/nf-core/gunzip/environment.yml
@@ -0,0 +1,7 @@
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - conda-forge::grep=3.11
+  - conda-forge::sed=4.8
+  - conda-forge::tar=1.34
diff --git a/modules/nf-core/gunzip/main.nf b/modules/nf-core/gunzip/main.nf
new file mode 100644
index 00000000..5e67e3b9
--- /dev/null
+++ b/modules/nf-core/gunzip/main.nf
@@ -0,0 +1,55 @@
+process GUNZIP {
+    tag "$archive"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/ubuntu:22.04' :
+        'nf-core/ubuntu:22.04' }"
+
+    input:
+    tuple val(meta), path(archive)
+
+    output:
+    tuple val(meta), path("$gunzip"), emit: gunzip
+    path "versions.yml"             , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args        = task.ext.args ?: ''
+    def extension   = ( archive.toString() - '.gz' ).tokenize('.')[-1]
+    def name        = archive.toString() - '.gz' - ".$extension"
+    def prefix      = task.ext.prefix ?: name
+    gunzip          = prefix + ".$extension"
+    """
+    # Not calling gunzip itself because it creates files
+    # with the original group ownership rather than the
+    # default one for that user / the work directory
+    gzip \\
+        -cd \\
+        $args \\
+        $archive \\
+        > $gunzip
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        gunzip: \$(echo \$(gunzip --version 2>&1) | sed 's/^.*(gzip) //; s/ Copyright.*\$//')
+    END_VERSIONS
+    """
+
+    stub:
+    def args        = task.ext.args ?: ''
+    def extension   = ( archive.toString() - '.gz' ).tokenize('.')[-1]
+    def name        = archive.toString() - '.gz' - ".$extension"
+    def prefix      = task.ext.prefix ?: name
+    gunzip          = prefix + ".$extension"
+    """
+    touch $gunzip
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        gunzip: \$(echo \$(gunzip --version 2>&1) | sed 's/^.*(gzip) //; s/ Copyright.*\$//')
+    END_VERSIONS
+    """
+}
diff --git a/modules/nf-core/gunzip/meta.yml b/modules/nf-core/gunzip/meta.yml
new file mode 100644
index 00000000..9066c035
--- /dev/null
+++ b/modules/nf-core/gunzip/meta.yml
@@ -0,0 +1,47 @@
+name: gunzip
+description: Compresses and decompresses files.
+keywords:
+  - gunzip
+  - compression
+  - decompression
+tools:
+  - gunzip:
+      description: |
+        gzip is a file format and a software application used for file compression and decompression.
+      documentation: https://www.gnu.org/software/gzip/manual/gzip.html
+      licence: ["GPL-3.0-or-later"]
+      identifier: ""
+input:
+  - - meta:
+        type: map
+        description: |
+          Optional groovy Map containing meta information
+          e.g. [ id:'test', single_end:false ]
+    - archive:
+        type: file
+        description: File to be compressed/uncompressed
+        pattern: "*.*"
+output:
+  - gunzip:
+      - meta:
+          type: file
+          description: Compressed/uncompressed file
+          pattern: "*.*"
+      - $gunzip:
+          type: file
+          description: Compressed/uncompressed file
+          pattern: "*.*"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+authors:
+  - "@joseespinosa"
+  - "@drpatelh"
+  - "@jfy133"
+maintainers:
+  - "@joseespinosa"
+  - "@drpatelh"
+  - "@jfy133"
+  - "@gallvp"
diff --git a/modules/nf-core/gunzip/tests/main.nf.test b/modules/nf-core/gunzip/tests/main.nf.test
new file mode 100644
index 00000000..776211ad
--- /dev/null
+++ b/modules/nf-core/gunzip/tests/main.nf.test
@@ -0,0 +1,121 @@
+nextflow_process {
+
+    name "Test Process GUNZIP"
+    script "../main.nf"
+    process "GUNZIP"
+    tag "gunzip"
+    tag "modules_nfcore"
+    tag "modules"
+
+    test("Should run without failures") {
+
+        when {
+            params {
+                outdir = "$outputDir"
+            }
+            process {
+                """
+                input[0] = Channel.of([
+                        [],
+                        file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true)
+                    ]
+                )
+                """
+            }
+        }
+
+        then {
+            assertAll(
+            { assert process.success },
+            { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+    test("Should run without failures - prefix") {
+
+        config './nextflow.config'
+
+        when {
+            params {
+                outdir = "$outputDir"
+            }
+            process {
+                """
+                input[0] = Channel.of([
+                        [ id: 'test' ],
+                        file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true)
+                    ]
+                )
+                """
+            }
+        }
+
+        then {
+            assertAll(
+            { assert process.success },
+            { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+    test("Should run without failures - stub") {
+
+        options '-stub'
+
+        when {
+            params {
+                outdir = "$outputDir"
+            }
+            process {
+                """
+                input[0] = Channel.of([
+                        [],
+                        file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true)
+                    ]
+                )
+                """
+            }
+        }
+
+        then {
+            assertAll(
+            { assert process.success },
+            { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+    test("Should run without failures - prefix - stub") {
+
+        options '-stub'
+        config './nextflow.config'
+
+        when {
+            params {
+                outdir = "$outputDir"
+            }
+            process {
+                """
+                input[0] = Channel.of([
+                        [ id: 'test' ],
+                        file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true)
+                    ]
+                )
+                """
+            }
+        }
+
+        then {
+            assertAll(
+            { assert process.success },
+            { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+}
diff --git a/modules/nf-core/gunzip/tests/main.nf.test.snap b/modules/nf-core/gunzip/tests/main.nf.test.snap
new file mode 100644
index 00000000..069967e7
--- /dev/null
+++ b/modules/nf-core/gunzip/tests/main.nf.test.snap
@@ -0,0 +1,134 @@
+{
+    "Should run without failures - prefix - stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.xyz.fastq:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,54376d32aca20e937a4ec26dac228e84"
+                ],
+                "gunzip": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.xyz.fastq:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,54376d32aca20e937a4ec26dac228e84"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "24.04.2"
+        },
+        "timestamp": "2024-06-25T11:35:10.861293"
+    },
+    "Should run without failures - stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        [
+                            
+                        ],
+                        "test_1.fastq:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,54376d32aca20e937a4ec26dac228e84"
+                ],
+                "gunzip": [
+                    [
+                        [
+                            
+                        ],
+                        "test_1.fastq:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,54376d32aca20e937a4ec26dac228e84"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "24.04.2"
+        },
+        "timestamp": "2024-06-25T11:35:05.857145"
+    },
+    "Should run without failures": {
+        "content": [
+            {
+                "0": [
+                    [
+                        [
+                            
+                        ],
+                        "test_1.fastq:md5,4161df271f9bfcd25d5845a1e220dbec"
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,54376d32aca20e937a4ec26dac228e84"
+                ],
+                "gunzip": [
+                    [
+                        [
+                            
+                        ],
+                        "test_1.fastq:md5,4161df271f9bfcd25d5845a1e220dbec"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,54376d32aca20e937a4ec26dac228e84"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "24.04.2"
+        },
+        "timestamp": "2023-10-17T15:35:37.690477896"
+    },
+    "Should run without failures - prefix": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.xyz.fastq:md5,4161df271f9bfcd25d5845a1e220dbec"
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,54376d32aca20e937a4ec26dac228e84"
+                ],
+                "gunzip": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.xyz.fastq:md5,4161df271f9bfcd25d5845a1e220dbec"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,54376d32aca20e937a4ec26dac228e84"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "24.04.2"
+        },
+        "timestamp": "2024-06-25T11:33:32.921739"
+    }
+}
\ No newline at end of file
diff --git a/modules/nf-core/gunzip/tests/nextflow.config b/modules/nf-core/gunzip/tests/nextflow.config
new file mode 100644
index 00000000..dec77642
--- /dev/null
+++ b/modules/nf-core/gunzip/tests/nextflow.config
@@ -0,0 +1,5 @@
+process {
+    withName: GUNZIP {
+        ext.prefix = { "${meta.id}.xyz" }
+    }
+}
diff --git a/modules/nf-core/gunzip/tests/tags.yml b/modules/nf-core/gunzip/tests/tags.yml
new file mode 100644
index 00000000..fd3f6915
--- /dev/null
+++ b/modules/nf-core/gunzip/tests/tags.yml
@@ -0,0 +1,2 @@
+gunzip:
+  - modules/nf-core/gunzip/**
diff --git a/nextflow.config b/nextflow.config
index db5a3f63..63369d6c 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -12,7 +12,6 @@ params {
     // Input options
     input                      = 'https://raw.githubusercontent.com/nf-core/test-datasets/rnafusion/testdata/human/samplesheet_valid.csv'
 
-    build_references           = false
     cosmic_username            = null
     cosmic_passwd              = null
     qiagen                     = false
@@ -27,7 +26,7 @@ params {
     // Genome
     genome                     = 'GRCh38'
     genomes_base               = "${params.outdir}/references"
-    ensembl_version            = 112
+    genome_gencode_version     = 46
     read_length                = 100
     starfusion_build           = true
     genomes                    = [:]
@@ -69,16 +68,16 @@ params {
     download_refs              = true
 
     // Path to references
-    fasta                         = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.dna.primary_assembly.fa"
-    fai                           = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.dna.primary_assembly.fa.fai"
-    gtf                           = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.gtf"
-    refflat                       = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.gtf.refflat"
-    rrna_intervals                = "${params.genomes_base}/ensembl/Homo_sapiens.${params.genome}.${params.ensembl_version}.interval_list"
-    ensembl_ref                   = "${params.genomes_base}/ensembl"
+    fasta                         = "${params.genomes_base}/gencode/Homo_sapiens_${params.genome}_${params.genome_gencode_version}_dna_primary_assembly.fa"
+    fai                           = "${params.genomes_base}/gencode/Homo_sapiens_${params.genome}_${params.genome_gencode_version}_dna_primary_assembly.fa.fai"
+    gtf                           = "${params.genomes_base}/gencode/Homo_sapiens_${params.genome}_${params.genome_gencode_version}.gtf"
+    refflat                       = "${params.genomes_base}/gencode/Homo_sapiens_${params.genome}_${params.genome_gencode_version}.gtf.refflat"
+    rrna_intervals                = "${params.genomes_base}/gencode/Homo_sapiens_${params.genome}_${params.genome_gencode_version}.interval_list"
+    gencode_ref                   = "${params.genomes_base}/gencode"
     arriba_ref_blacklist          = "${params.genomes_base}/arriba/blacklist_hg38_GRCh38_v2.4.0.tsv.gz"
     arriba_ref_known_fusions      = "${params.genomes_base}/arriba/known_fusions_hg38_GRCh38_v2.4.0.tsv.gz"
     arriba_ref_protein_domains    = "${params.genomes_base}/arriba/protein_domains_hg38_GRCh38_v2.4.0.gff3"
-    fusioncatcher_ref             = "${params.genomes_base}/fusioncatcher/human_v${params.ensembl_version}"
+    fusioncatcher_ref             = "${params.genomes_base}/fusioncatcher/human_v${params.genome_gencode_version}"
     hgnc_ref                      = "${params.genomes_base}/hgnc/hgnc_complete_set.txt"
     hgnc_date                     = "${params.genomes_base}/hgnc/HGNC-DB-timestamp.txt"
     salmon_index                  = "${params.genomes_base}/salmon/salmon"
@@ -91,7 +90,7 @@ params {
     salmon_index_stub_check       = "${params.genomes_base}/salmon/salmon/complete_ref_lens.bin"
     starindex_ref_stub_check      = "${params.genomes_base}/star/star/Genome"
     fusionreport_ref_stub_check   = "${params.genomes_base}/fusion_report_db/mitelman.db"
-    fusioncatcher_ref_stub_check  = "${params.genomes_base}/fusioncatcher/human_v${params.ensembl_version}/ensembl_fully_overlapping_genes.txt"
+    fusioncatcher_ref_stub_check  = "${params.genomes_base}/fusioncatcher/human_v${params.genome_gencode_version}/ensembl_fully_overlapping_genes.txt"
     starfusion_ref_stub_check     = "${params.genomes_base}/starfusion/Pfam-A.hmm"
 
     // Path to fusion outputs
diff --git a/nextflow_schema.json b/nextflow_schema.json
index 95238d65..be31bcc3 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -62,11 +62,6 @@
                     "description": "MultiQC report title. Printed as page header, used for filename if not otherwise specified.",
                     "fa_icon": "fas fa-file-signature"
                 },
-                "build_references": {
-                    "type": "boolean",
-                    "fa_icon": "far fa-file-code",
-                    "description": "Specifies which analysis type for the pipeline - either build references or analyse data"
-                },
                 "cosmic_username": {
                     "type": "string",
                     "fa_icon": "far fa-file-code",
@@ -82,7 +77,7 @@
                     "fa_icon": "far fa-file-code",
                     "description": "Path to reference folder"
                 },
-                "ensembl_version": {
+                "genome_gencode_version": {
                     "type": "integer",
                     "fa_icon": "far fa-file-code",
                     "description": "ensembl version",
@@ -134,10 +129,10 @@
                     "fa_icon": "far fa-file-code",
                     "description": "Download references instead of building them (for fusioncatcher and starfusion)"
                 },
-                "ensembl_ref": {
+                "gencode_ref": {
                     "type": "string",
                     "fa_icon": "far fa-file-code",
-                    "description": "Path to ensembl references"
+                    "description": "Path to gencode references"
                 },
                 "fusioncatcher": {
                     "type": "boolean",
@@ -342,14 +337,6 @@
                     "description": "Path to GTF genome file.",
                     "fa_icon": "far fa-file-code"
                 },
-                "chrgtf": {
-                    "type": "string",
-                    "format": "file-path",
-                    "mimetype": "text/plain",
-                    "pattern": "^\\S+\\.gtf?(\\.gz)?$",
-                    "description": "Path to GTF genome file.",
-                    "fa_icon": "far fa-file-code"
-                },
                 "refflat": {
                     "type": "string",
                     "format": "file-path",
diff --git a/subworkflows/local/build_references.nf b/subworkflows/local/build_references.nf
index cfb4258b..8017f634 100644
--- a/subworkflows/local/build_references.nf
+++ b/subworkflows/local/build_references.nf
@@ -5,7 +5,7 @@
 */
 
 include { ARRIBA_DOWNLOAD }                 from '../../modules/local/arriba/download/main'
-include { ENSEMBL_DOWNLOAD }                from '../../modules/local/ensembl/main'
+include { GENCODE_DOWNLOAD }                from '../../modules/local/gencode_download/main'
 include { FUSIONCATCHER_DOWNLOAD }          from '../../modules/local/fusioncatcher/download/main'
 include { FUSIONCATCHER_BUILD }             from '../../modules/local/fusioncatcher/build/main'
 include { FUSIONREPORT_DOWNLOAD }           from '../../modules/local/fusionreport/download/main'
@@ -37,26 +37,24 @@ include { GFFREAD }                         from '../../modules/nf-core/gffread/
 workflow BUILD_REFERENCES {
     take:
         genome                           // channel: [mandatory]  val(genome)
-        ensembl_version                  // channel: [mandatory]  val(ensembl_version)
+        genome_gencode_version           // channel: [mandatory]  val(genome_gencode_version)
 
     main:
     ch_versions = Channel.empty()
 
     if (!file(params.fasta).exists() || file(params.fasta).isEmpty() ||
             !file(params.gtf).exists() || file(params.gtf).isEmpty()){
-        fake_meta = [:]
-        fake_meta.id = "Homo_sapiens.${params.genome}.${params.ensembl_version}"
-        ENSEMBL_DOWNLOAD(params.ensembl_version, params.genome, fake_meta)
-        ch_versions = ENSEMBL_DOWNLOAD.out.versions
-        ch_fasta = ENSEMBL_DOWNLOAD.out.primary_assembly
-        ch_gtf = ENSEMBL_DOWNLOAD.out.gtf
+        GENCODE_DOWNLOAD(params.genome_gencode_version, params.genome)
+        ch_versions = GENCODE_DOWNLOAD.out.versions
+        ch_fasta = GENCODE_DOWNLOAD.out.fasta.map { that -> [[id:that.Name], that] }
+        ch_gtf = GENCODE_DOWNLOAD.out.gtf.map { that -> [[id:that.Name], that] }
     } else {
         ch_fasta = Channel.fromPath(params.fasta).map { that -> [[id:that.Name], that] }
         ch_gtf = Channel.fromPath(params.gtf).map { that -> [[id:that.Name], that] }
     }
 
     if (!file(params.fai).exists() || file(params.fai).isEmpty()){
-        SAMTOOLS_FAIDX(ch_fasta, [[],[]]).fai
+        SAMTOOLS_FAIDX(ch_fasta, [[],[]])
         ch_versions = SAMTOOLS_FAIDX.out.versions
         ch_fai = SAMTOOLS_FAIDX.out.fai
     } else {
@@ -121,39 +119,39 @@ workflow BUILD_REFERENCES {
 //     }
 
 
-    if ((params.fusioncatcher || params.all) &&
-            (!file(params.fusioncatcher_ref).exists() || file(params.fusioncatcher_ref).isEmpty() ||
-            !file(params.fusioncatcher_ref_stub_check).exists() || file(params.fusioncatcher_ref_stub_check).isEmpty() )) {
-        if (params.download_refs) {
-            FUSIONCATCHER_DOWNLOAD(params.ensembl_version)
-            ch_fusioncatcher_ref = FUSIONCATCHER_DOWNLOAD.out.reference}
-        else {
-            FUSIONCATCHER_BUILD(params.ensembl_version)
-            ch_fusioncatcher_ref = FUSIONCATCHER_BUILD.out.reference}
-        } else {
-            ch_fusioncatcher_ref = Channel.fromPath(params.fusioncatcher_ref).map { that -> [[id:that.Name], that] }
-        }
-
-
-    if ((params.starfusion || params.all) &&
-            (!file(params.starfusion_ref).exists() || file(params.starfusion_ref).isEmpty() ||
-            !file(params.starfusion_ref_stub_check).exists() || file(params.starfusion_ref_stub_check).isEmpty() )) {
-        if (params.download_refs) {
-            ch_starfusion_ref = STARFUSION_DOWNLOAD( ch_fasta, ch_gtf ).out.reference }
-        else {
-            ch_starfusion_ref = STARFUSION_BUILD( ch_fasta, ch_gtf ).out.reference }
-    } else {
-        ch_starfusion_ref = Channel.fromPath(params.starfusion_ref).map { that -> [[id:that.Name], that] }}
-
-
-    if ((params.fusionreport || params.all) &&
-            (!file(params.fusionreport_ref).exists() || file(params.fusionreport_ref).isEmpty() ||
-            !file(params.fusionreport_ref_stub_check).exists() || file(params.fusionreport_ref_stub_check).isEmpty())) {
-        if (!params.cosmic_username || !params.cosmic_passwd) { exit 1, 'COSMIC username and/or password missing' }
-        ch_fusionreport_ref = FUSIONREPORT_DOWNLOAD( params.cosmic_username, params.cosmic_passwd ).out.reference
-    } else {
-        ch_fusionreport_ref = Channel.fromPath(params.fusionreport_ref).map { that -> [[id:that.Name], that] }
-    }
+    // if ((params.fusioncatcher || params.all) &&
+    //         (!file(params.fusioncatcher_ref).exists() || file(params.fusioncatcher_ref).isEmpty() ||
+    //         !file(params.fusioncatcher_ref_stub_check).exists() || file(params.fusioncatcher_ref_stub_check).isEmpty() )) {
+    //     if (params.download_refs) {
+    //         FUSIONCATCHER_DOWNLOAD(params.genome_gencode_version)
+    //         ch_fusioncatcher_ref = FUSIONCATCHER_DOWNLOAD.out.reference}
+    //     else {
+    //         FUSIONCATCHER_BUILD(params.genome_gencode_version)
+    //         ch_fusioncatcher_ref = FUSIONCATCHER_BUILD.out.reference}
+    //     } else {
+    //         ch_fusioncatcher_ref = Channel.fromPath(params.fusioncatcher_ref).map { that -> [[id:that.Name], that] }
+    //     }
+
+
+    // if ((params.starfusion || params.all) &&
+    //         (!file(params.starfusion_ref).exists() || file(params.starfusion_ref).isEmpty() ||
+    //         !file(params.starfusion_ref_stub_check).exists() || file(params.starfusion_ref_stub_check).isEmpty() )) {
+    //     if (params.download_refs) {
+    //         ch_starfusion_ref = STARFUSION_DOWNLOAD( ch_fasta, ch_gtf ).out.reference }
+    //     else {
+    //         ch_starfusion_ref = STARFUSION_BUILD( ch_fasta, ch_gtf ).out.reference }
+    // } else {
+    //     ch_starfusion_ref = Channel.fromPath(params.starfusion_ref).map { that -> [[id:that.Name], that] }}
+
+
+    // if ((params.fusionreport || params.all) &&
+    //         (!file(params.fusionreport_ref).exists() || file(params.fusionreport_ref).isEmpty() ||
+    //         !file(params.fusionreport_ref_stub_check).exists() || file(params.fusionreport_ref_stub_check).isEmpty())) {
+    //     if (!params.cosmic_username || !params.cosmic_passwd) { exit 1, 'COSMIC username and/or password missing' }
+    //     ch_fusionreport_ref = FUSIONREPORT_DOWNLOAD( params.cosmic_username, params.cosmic_passwd ).out.reference
+    // } else {
+    //     ch_fusionreport_ref = Channel.fromPath(params.fusionreport_ref).map { that -> [[id:that.Name], that] }
+    // }
 
     emit:
     ch_fasta
@@ -162,16 +160,16 @@ workflow BUILD_REFERENCES {
 
     ch_hgnc_ref
     ch_hgnc_date
-    ch_rrna_interval
-    ch_refflat
-    ch_salmon_index
-    ch_starindex_ref
+    // ch_rrna_interval
+    // ch_refflat
+    // ch_salmon_index
+    // ch_starindex_ref
     // ch_arriba_ref_blacklist
     // ch_arriba_ref_known_fusions
     // ch_arriba_ref_protein_domains
-    ch_fusioncatcher_ref
-    ch_starfusion_ref
-    ch_fusionreport_ref
+    // ch_fusioncatcher_ref
+    // ch_starfusion_ref
+    // ch_fusionreport_ref
     versions        = ch_versions
 }
 
diff --git a/subworkflows/local/qc_workflow.nf b/subworkflows/local/qc_workflow.nf
index d7958fec..177f42d2 100644
--- a/subworkflows/local/qc_workflow.nf
+++ b/subworkflows/local/qc_workflow.nf
@@ -11,7 +11,7 @@ workflow QC_WORKFLOW {
         ch_reads_all
         ch_bam_sorted
         ch_bam_sorted_indexed
-        ch_chrgtf
+        ch_gtf
         ch_refflat
         ch_fasta
         ch_fai
diff --git a/subworkflows/local/starfusion_workflow.nf b/subworkflows/local/starfusion_workflow.nf
index de99d8e5..d6a0668a 100644
--- a/subworkflows/local/starfusion_workflow.nf
+++ b/subworkflows/local/starfusion_workflow.nf
@@ -7,7 +7,7 @@ include { STARFUSION }                                           from '../../mod
 workflow STARFUSION_WORKFLOW {
     take:
         reads
-        ch_chrgtf
+        ch_gtf
         ch_starindex_ref
         ch_fasta
 
@@ -23,7 +23,7 @@ workflow STARFUSION_WORKFLOW {
                 ch_starfusion_fusions = reads.combine(Channel.value(file(params.starfusion_fusions, checkIfExists:true)))
                                         .map { meta, reads, fusions -> [ meta, fusions ] }
             } else {
-                STAR_FOR_STARFUSION( reads, ch_starindex_ref, ch_chrgtf, params.star_ignore_sjdbgtf, '', params.seq_center ?: '')
+                STAR_FOR_STARFUSION( reads, ch_starindex_ref, ch_gtf, params.star_ignore_sjdbgtf, '', params.seq_center ?: '')
                 ch_versions = ch_versions.mix(STAR_FOR_STARFUSION.out.versions)
                 ch_align = STAR_FOR_STARFUSION.out.bam_sorted
 
diff --git a/subworkflows/local/stringtie_workflow.nf b/subworkflows/local/stringtie_workflow.nf
index 60bd4f38..d66ec0ee 100644
--- a/subworkflows/local/stringtie_workflow.nf
+++ b/subworkflows/local/stringtie_workflow.nf
@@ -5,14 +5,14 @@ include { STRINGTIE_MERGE }        from '../../modules/nf-core/stringtie/merge/m
 workflow STRINGTIE_WORKFLOW {
     take:
         bam_sorted
-        ch_chrgtf
+        ch_gtf
 
     main:
         ch_versions = Channel.empty()
         ch_stringtie_gtf = Channel.empty()
 
         if ((params.stringtie || params.all) && !params.fusioninspector_only) {
-            STRINGTIE_STRINGTIE(bam_sorted, ch_chrgtf.map { meta, gtf -> [ gtf ]})
+            STRINGTIE_STRINGTIE(bam_sorted, ch_gtf.map { meta, gtf -> [ gtf ]})
             ch_versions = ch_versions.mix(STRINGTIE_STRINGTIE.out.versions)
 
             STRINGTIE_STRINGTIE
@@ -23,7 +23,7 @@ workflow STRINGTIE_WORKFLOW {
             ch_versions = ch_versions.mix(STRINGTIE_STRINGTIE.out.versions)
 
 
-            STRINGTIE_MERGE (stringtie_gtf, ch_chrgtf.map { meta, gtf -> [ gtf ]})
+            STRINGTIE_MERGE (stringtie_gtf, ch_gtf.map { meta, gtf -> [ gtf ]})
             ch_versions = ch_versions.mix(STRINGTIE_MERGE.out.versions)
             ch_stringtie_gtf = STRINGTIE_MERGE.out.gtf
         }
diff --git a/workflows/rnafusion.nf b/workflows/rnafusion.nf
index 67dedb4b..bb24df1f 100644
--- a/workflows/rnafusion.nf
+++ b/workflows/rnafusion.nf
@@ -65,7 +65,7 @@ workflow RNAFUSION {
     // Create references if necessary
     //
 
-    BUILD_REFERENCES(params.genome, params.ensembl_version)
+    BUILD_REFERENCES(params.genome, params.genome_gencode_version)
     ch_versions = ch_versions.mix(BUILD_REFERENCES.out.versions)
 
     // // Optional
@@ -177,7 +177,7 @@ workflow RNAFUSION {
 // //Run STAR fusion
 //     STARFUSION_WORKFLOW (
 //         ch_reads_all,
-//         ch_chrgtf,
+//         ch_gtf,
 //         ch_starindex_ref,
 //         ch_fasta
 //     )
@@ -194,7 +194,7 @@ workflow RNAFUSION {
 // //Run stringtie
 //     STRINGTIE_WORKFLOW (
 //         STARFUSION_WORKFLOW.out.ch_bam_sorted,
-//         ch_chrgtf
+//         ch_gtf
 //     )
 //     ch_versions = ch_versions.mix(STRINGTIE_WORKFLOW.out.versions)
 
@@ -218,7 +218,7 @@ workflow RNAFUSION {
 //         FUSIONREPORT_WORKFLOW.out.report,
 //         FUSIONREPORT_WORKFLOW.out.csv,
 //         STARFUSION_WORKFLOW.out.ch_bam_sorted_indexed,
-//         ch_chrgtf,
+//         ch_gtf,
 //         ch_arriba_ref_protein_domains,
 //         ch_arriba_ref_cytobands,
 //         ch_hgnc_ref,
@@ -232,7 +232,7 @@ workflow RNAFUSION {
 //         ch_reads_all,
 //         STARFUSION_WORKFLOW.out.ch_bam_sorted,
 //         STARFUSION_WORKFLOW.out.ch_bam_sorted_indexed,
-//         ch_chrgtf,
+//         ch_gtf,
 //         ch_refflat,
 //         ch_fasta,
 //         ch_fai,

From 0b1a0672a59a31918c9fddb54fdffc883768800d Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Wed, 13 Nov 2024 10:03:44 +0100
Subject: [PATCH 11/41] syntax

---
 conf/modules.config                        |  2 +-
 modules/local/arriba/visualisation/main.nf |  8 ++++----
 modules/local/hgnc/main.nf                 |  2 --
 modules/nf-core/arriba/download/main.nf    |  2 --
 modules/nf-core/arriba/main.nf             | 20 ++++++++++----------
 subworkflows/local/build_references.nf     | 18 +++++++++---------
 6 files changed, 24 insertions(+), 28 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index af832498..232efdd1 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -63,7 +63,7 @@ process {
 
     withName: 'FASTQC' {
         ext.args = '--quiet'
-        ext.when = { !params.skip_qc and not !params.build_references }
+        ext.when = { !params.skip_qc && !params.build_references }
         publishDir = [
             path: { "${params.outdir}/fastqc" },
             mode: params.publish_dir_mode,
diff --git a/modules/local/arriba/visualisation/main.nf b/modules/local/arriba/visualisation/main.nf
index cc120119..f1aa097b 100644
--- a/modules/local/arriba/visualisation/main.nf
+++ b/modules/local/arriba/visualisation/main.nf
@@ -22,17 +22,17 @@ process ARRIBA_VISUALISATION {
 
     script:
     def args = task.ext.args ?: ''
-    def cytobands = cytobands ? " --cytobands=$cytobands" : ""
+    def arg_cytobands = cytobands ? " --cytobands=$cytobands" : ""
+    def arg_protein_domains = protein_domains ? "--proteinDomains=$protein_domains" : ""
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def protein_domains = protein_domains ? "--proteinDomains=$protein_domains" : ""
     """
     draw_fusions.R \\
         --fusions=$fusions \\
         --alignments=$bam \\
         --output=${prefix}.pdf \\
         --annotation=${gtf} \\
-        $cytobands \\
-        $protein_domains \\
+        $arg_cytobands \\
+        $arg_protein_domains \\
         $args
 
     cat <<-END_VERSIONS > versions.yml
diff --git a/modules/local/hgnc/main.nf b/modules/local/hgnc/main.nf
index 6a055631..5a250f0f 100644
--- a/modules/local/hgnc/main.nf
+++ b/modules/local/hgnc/main.nf
@@ -7,8 +7,6 @@ process HGNC_DOWNLOAD {
         'https://depot.galaxyproject.org/singularity/gnu-wget:1.18--h5bf99c6_5' :
         'quay.io/biocontainers/gnu-wget:1.18--h5bf99c6_5' }"
 
-    input:
-
     output:
     path "hgnc_complete_set.txt"        , emit: hgnc_ref
     path "HGNC-DB-timestamp.txt"        , emit: hgnc_date
diff --git a/modules/nf-core/arriba/download/main.nf b/modules/nf-core/arriba/download/main.nf
index 96a4e336..7f11898b 100644
--- a/modules/nf-core/arriba/download/main.nf
+++ b/modules/nf-core/arriba/download/main.nf
@@ -7,8 +7,6 @@ process ARRIBA_DOWNLOAD {
         'https://depot.galaxyproject.org/singularity/arriba:2.4.0--h0033a41_2' :
         'biocontainers/arriba:2.4.0--h0033a41_2' }"
 
-    input:
-
     output:
     path "*"              , emit: reference
     path "versions.yml"           , emit: versions
diff --git a/modules/nf-core/arriba/main.nf b/modules/nf-core/arriba/main.nf
index 2537d05b..66809530 100644
--- a/modules/nf-core/arriba/main.nf
+++ b/modules/nf-core/arriba/main.nf
@@ -28,11 +28,11 @@ process ARRIBA {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def blacklist = blacklist ? "-b $blacklist" : "-f blacklist"
-    def known_fusions = known_fusions ? "-k $known_fusions" : ""
-    def structural_variants = structural_variants ? "-d $structual_variants" : ""
-    def tags = tags ? "-t $tags" : ""
-    def protein_domains = protein_domains ? "-p $protein_domains" : ""
+    def arg_blacklist = blacklist ? "-b $blacklist" : "-f blacklist"
+    def arg_known_fusions = known_fusions ? "-k $known_fusions" : ""
+    def arg_structural_variants = structural_variants ? "-d $structural_variants" : ""
+    def arg_tags = tags ? "-t $tags" : ""
+    def arg_protein_domains = protein_domains ? "-p $protein_domains" : ""
 
     """
     arriba \\
@@ -41,11 +41,11 @@ process ARRIBA {
         -g $gtf \\
         -o ${prefix}.fusions.tsv \\
         -O ${prefix}.fusions.discarded.tsv \\
-        $blacklist \\
-        $known_fusions \\
-        $structural_variants \\
-        $tags \\
-        $protein_domains \\
+        $arg_blacklist \\
+        $arg_known_fusions \\
+        $arg_structural_variants \\
+        $arg_tags \\
+        $arg_protein_domains \\
         $args
 
     cat <<-END_VERSIONS > versions.yml
diff --git a/subworkflows/local/build_references.nf b/subworkflows/local/build_references.nf
index 8017f634..1d45e74c 100644
--- a/subworkflows/local/build_references.nf
+++ b/subworkflows/local/build_references.nf
@@ -133,15 +133,15 @@ workflow BUILD_REFERENCES {
     //     }
 
 
-    // if ((params.starfusion || params.all) &&
-    //         (!file(params.starfusion_ref).exists() || file(params.starfusion_ref).isEmpty() ||
-    //         !file(params.starfusion_ref_stub_check).exists() || file(params.starfusion_ref_stub_check).isEmpty() )) {
-    //     if (params.download_refs) {
-    //         ch_starfusion_ref = STARFUSION_DOWNLOAD( ch_fasta, ch_gtf ).out.reference }
-    //     else {
-    //         ch_starfusion_ref = STARFUSION_BUILD( ch_fasta, ch_gtf ).out.reference }
-    // } else {
-    //     ch_starfusion_ref = Channel.fromPath(params.starfusion_ref).map { that -> [[id:that.Name], that] }}
+    if ((params.starfusion || params.all) &&
+            (!file(params.starfusion_ref).exists() || file(params.starfusion_ref).isEmpty() ||
+            !file(params.starfusion_ref_stub_check).exists() || file(params.starfusion_ref_stub_check).isEmpty() )) {
+        if (params.download_refs) {
+            ch_starfusion_ref = STARFUSION_DOWNLOAD( ch_fasta, ch_gtf ).out.reference }
+        else {
+            ch_starfusion_ref = STARFUSION_BUILD( ch_fasta, ch_gtf ).out.reference }
+    } else {
+        ch_starfusion_ref = Channel.fromPath(params.starfusion_ref).map { that -> [[id:that.Name], that] }}
 
 
     // if ((params.fusionreport || params.all) &&

From f134b84c8a5977cee935aa5396eef504f6c278fd Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Wed, 13 Nov 2024 10:35:46 +0100
Subject: [PATCH 12/41] merging

---
 conf/modules.config                  | 14 --------------
 modules/nf-core/salmon/quant/main.nf |  2 +-
 workflows/rnafusion.nf               |  1 +
 3 files changed, 2 insertions(+), 15 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index 7afa2817..113c406c 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -127,7 +127,6 @@ process {
         ]
     }
 
-<<<<<<< HEAD
     withName: 'GFFREAD' {
         ext.args = { '-w' }
         publishDir = [
@@ -145,8 +144,6 @@ process {
         ]
     }
 
-=======
->>>>>>> 22d0e803ca87786359cf582bfb4ac8114adde8fd
     withName: 'HGNC_DOWNLOAD' {
         publishDir = [
             path: { "${params.genomes_base}/hgnc" },
@@ -369,20 +366,9 @@ process {
         ]
     }
 
-<<<<<<< HEAD
     withName: 'TRIM_WORKFLOW:*' {
         ext.when = { !params.build_references }
 
-=======
-    withName: 'UCSC_GTFTOGENEPRED' {
-        ext.args   = "-genePredExt -geneNameAsName2"
-        publishDir = [
-            path: { "${params.genomes_base}/ensembl" },
-            mode: params.publish_dir_mode,
-            saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
-        ]
->>>>>>> 22d0e803ca87786359cf582bfb4ac8114adde8fd
-    }
 
     withName: 'VCF_COLLECT' {
         ext.when = {!params.fusioninspector_only}
diff --git a/modules/nf-core/salmon/quant/main.nf b/modules/nf-core/salmon/quant/main.nf
index 6c528b24..6d624e75 100644
--- a/modules/nf-core/salmon/quant/main.nf
+++ b/modules/nf-core/salmon/quant/main.nf
@@ -28,7 +28,7 @@ process SALMON_QUANT {
     def args = task.ext.args   ?: ''
     prefix   = task.ext.prefix ?: "${meta.id}"
 
-    def reference   = "--index $index"
+    def reference = "--index $index"
     def reads1 = [], reads2 = []
     meta.single_end ? [reads].flatten().each{reads1 << it} : reads.eachWithIndex{ v, ix -> ( ix & 1 ? reads2 : reads1) << v }
     def input_reads = meta.single_end ? "-r ${reads1.join(" ")}" : "-1 ${reads1.join(" ")} -2 ${reads2.join(" ")}"
diff --git a/workflows/rnafusion.nf b/workflows/rnafusion.nf
index 9b615d40..8f7f8ae8 100644
--- a/workflows/rnafusion.nf
+++ b/workflows/rnafusion.nf
@@ -39,6 +39,7 @@ include { CAT_FASTQ              } from '../modules/nf-core/cat/fastq/main'
 include { FASTQC                 } from '../modules/nf-core/fastqc/main'
 include { MULTIQC                } from '../modules/nf-core/multiqc/main'
 include { SALMON_QUANT           } from '../modules/nf-core/salmon/quant/main'
+
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     RUN MAIN WORKFLOW

From 7a5a91700ad963723a0a837d7f8cdb212947e8fd Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Wed, 13 Nov 2024 14:20:16 +0100
Subject: [PATCH 13/41] cleanup

---
 conf/modules.config                           |   2 +-
 main.nf                                       |   7 +-
 modules.json                                  | 142 ++++++++++++------
 modules/local/fusioncatcher/build/main.nf     |   1 -
 modules/local/fusioncatcher/download/main.nf  |  20 +--
 modules/local/gencode_download/main.nf        |   4 +-
 modules/local/get_rrna_transcripts.nf         |  43 ++++++
 modules/nf-core/arriba/arriba/environment.yml |   3 +
 modules/nf-core/arriba/arriba/main.nf         |  29 ++--
 modules/nf-core/arriba/arriba/meta.yml        |  39 +----
 .../nf-core/arriba/arriba/tests/main.nf.test  | 107 +++++++++++++
 .../arriba/arriba/tests/main.nf.test.snap     |  55 +++++++
 .../arriba/arriba/tests/nextflow.config       |   8 +
 modules/nf-core/arriba/download/main.nf       |  13 +-
 modules/nf-core/arriba/download/meta.yml      |  32 +++-
 .../arriba/download/tests/main.nf.test        |  29 +++-
 .../arriba/download/tests/main.nf.test.snap   |  62 ++++----
 .../nf-core/arriba/download/tests/tags.yml    |   2 +
 modules/nf-core/gunzip/environment.yml        |   7 -
 modules/nf-core/gunzip/main.nf                |  55 -------
 modules/nf-core/gunzip/meta.yml               |  47 ------
 modules/nf-core/gunzip/tests/main.nf.test     | 121 ---------------
 .../nf-core/gunzip/tests/main.nf.test.snap    | 134 -----------------
 modules/nf-core/gunzip/tests/nextflow.config  |   5 -
 modules/nf-core/gunzip/tests/tags.yml         |   2 -
 modules/nf-core/salmon/quant/environment.yml  |   2 +-
 modules/nf-core/salmon/quant/main.nf          |   6 +-
 .../salmon/quant/tests/main.nf.test.snap      |  64 ++++----
 nextflow.config                               |   3 +-
 nextflow_schema.json                          |  19 ++-
 subworkflows/local/build_references.nf        | 102 +++++++------
 workflows/rnafusion.nf                        |  52 ++-----
 32 files changed, 564 insertions(+), 653 deletions(-)
 create mode 100644 modules/local/get_rrna_transcripts.nf
 create mode 100644 modules/nf-core/arriba/arriba/tests/main.nf.test
 create mode 100644 modules/nf-core/arriba/arriba/tests/main.nf.test.snap
 create mode 100644 modules/nf-core/arriba/arriba/tests/nextflow.config
 create mode 100644 modules/nf-core/arriba/download/tests/tags.yml
 delete mode 100644 modules/nf-core/gunzip/environment.yml
 delete mode 100644 modules/nf-core/gunzip/main.nf
 delete mode 100644 modules/nf-core/gunzip/meta.yml
 delete mode 100644 modules/nf-core/gunzip/tests/main.nf.test
 delete mode 100644 modules/nf-core/gunzip/tests/main.nf.test.snap
 delete mode 100644 modules/nf-core/gunzip/tests/nextflow.config
 delete mode 100644 modules/nf-core/gunzip/tests/tags.yml

diff --git a/conf/modules.config b/conf/modules.config
index 113c406c..123e02b0 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -368,7 +368,7 @@ process {
 
     withName: 'TRIM_WORKFLOW:*' {
         ext.when = { !params.build_references }
-
+    }
 
     withName: 'VCF_COLLECT' {
         ext.when = {!params.fusioninspector_only}
diff --git a/main.nf b/main.nf
index ce7352f1..09216f56 100644
--- a/main.nf
+++ b/main.nf
@@ -41,6 +41,8 @@ include { RNAFUSION               } from './workflows/rnafusion'
 // WORKFLOW: Run main analysis pipeline depending on type of input
 //
 workflow NFCORE_RNAFUSION {
+    take:
+    samplesheet
 
     main:
 
@@ -48,8 +50,7 @@ workflow NFCORE_RNAFUSION {
     // WORKFLOW: Run pipeline
     //
 
-    ch_samplesheet = Channel.value(file(params.input, checkIfExists: true))
-    RNAFUSION(ch_samplesheet)
+    RNAFUSION(samplesheet)
 }
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -75,7 +76,7 @@ workflow {
     //
     // WORKFLOW: Run main workflow
     //
-    NFCORE_RNAFUSION ()
+    NFCORE_RNAFUSION (PIPELINE_INITIALISATION.out.samplesheet)
 
     //
     // SUBWORKFLOW: Run completion tasks
diff --git a/modules.json b/modules.json
index e71954a6..7e506548 100644
--- a/modules.json
+++ b/modules.json
@@ -8,152 +8,198 @@
                     "agat/convertspgff2tsv": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "arriba/arriba": {
                         "branch": "master",
-                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "git_sha": "7741dfc830e77a8ead2fcb50b01461ee09d0cdfe",
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "arriba/download": {
                         "branch": "master",
-                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "git_sha": "467c202a876d26af544fa8c4b22a050a535462a7",
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "bedops/convert2bed": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
-                    },
-                    "arriba/download": {
-                        "branch": "master",
-                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "cat/cat": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "cat/fastq": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "fastp": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "fastqc": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "gatk4/bedtointervallist": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "gatk4/createsequencedictionary": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "gatk4/markduplicates": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "gffread": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
-                    },
-                    "gunzip": {
-                        "branch": "master",
-                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "multiqc": {
                         "branch": "master",
                         "git_sha": "cf17ca47590cc578dfb47db1c2a44ef86f89976d",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "picard/collectinsertsizemetrics": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "picard/collectrnaseqmetrics": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "picard/collectwgsmetrics": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "rrnatranscripts": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "salmon/index": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "salmon/quant": {
                         "branch": "master",
-                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "git_sha": "49f4e50534fe4b64101e62ea41d5dc43b1324358",
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "samtools/faidx": {
                         "branch": "master",
                         "git_sha": "b13f07be4c508d6ff6312d354d09f2493243e208",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "samtools/index": {
                         "branch": "master",
                         "git_sha": "b13f07be4c508d6ff6312d354d09f2493243e208",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "samtools/sort": {
                         "branch": "master",
                         "git_sha": "b13f07be4c508d6ff6312d354d09f2493243e208",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "samtools/view": {
                         "branch": "master",
                         "git_sha": "b13f07be4c508d6ff6312d354d09f2493243e208",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "star/align": {
                         "branch": "master",
                         "git_sha": "30a97c755895b7dfe40a730b0695c554a10f1cdd",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "star/genomegenerate": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "stringtie/merge": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "stringtie/stringtie": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "ucsc/gtftogenepred": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     }
                 }
             },
@@ -162,20 +208,26 @@
                     "utils_nextflow_pipeline": {
                         "branch": "master",
                         "git_sha": "3aa0aec1d52d492fe241919f0c6100ebf0074082",
-                        "installed_by": ["subworkflows"]
+                        "installed_by": [
+                            "subworkflows"
+                        ]
                     },
                     "utils_nfcore_pipeline": {
                         "branch": "master",
                         "git_sha": "1b6b9a3338d011367137808b49b923515080e3ba",
-                        "installed_by": ["subworkflows"]
+                        "installed_by": [
+                            "subworkflows"
+                        ]
                     },
                     "utils_nfschema_plugin": {
                         "branch": "master",
                         "git_sha": "bbd5a41f4535a8defafe6080e00ea74c45f4f96c",
-                        "installed_by": ["subworkflows"]
+                        "installed_by": [
+                            "subworkflows"
+                        ]
                     }
                 }
             }
         }
     }
-}
+}
\ No newline at end of file
diff --git a/modules/local/fusioncatcher/build/main.nf b/modules/local/fusioncatcher/build/main.nf
index 51153253..f6ff0987 100644
--- a/modules/local/fusioncatcher/build/main.nf
+++ b/modules/local/fusioncatcher/build/main.nf
@@ -2,7 +2,6 @@ process FUSIONCATCHER_BUILD {
     tag "fusioncatcher_build"
     label 'process_medium'
 
-    conda "bioconda::fusioncatcher=1.33"
     container "docker.io/clinicalgenomics/fusioncatcher:1.33"
 
     input:
diff --git a/modules/local/fusioncatcher/download/main.nf b/modules/local/fusioncatcher/download/main.nf
index 916b4673..20e3681f 100644
--- a/modules/local/fusioncatcher/download/main.nf
+++ b/modules/local/fusioncatcher/download/main.nf
@@ -7,10 +7,10 @@ process FUSIONCATCHER_DOWNLOAD {
 
 
     input:
-    val ensembl_version
+    val genome_gencode_version
 
     output:
-    path "human_v${ensembl_version}"                , emit: reference
+    path "human_v${genome_gencode_version}"                , emit: reference
     path "versions.yml"     , emit: versions
 
     when:
@@ -24,12 +24,12 @@ process FUSIONCATCHER_DOWNLOAD {
 
     // def url =
     """
-    wget $args http://sourceforge.net/projects/fusioncatcher/files/data/human_${ensembl_version}.tar.gz.aa
-    wget $args http://sourceforge.net/projects/fusioncatcher/files/data/human_${ensembl_version}.tar.gz.ab
-    wget $args http://sourceforge.net/projects/fusioncatcher/files/data/human_${ensembl_version}.tar.gz.ac
-    wget $args http://sourceforge.net/projects/fusioncatcher/files/data/human_${ensembl_version}.tar.gz.ad
-    cat human_${ensembl_version}.tar.gz.* | tar xz
-    rm human_${ensembl_version}.tar*
+    wget $args http://sourceforge.net/projects/fusioncatcher/files/data/human_${genome_gencode_version}.tar.gz.aa
+    wget $args http://sourceforge.net/projects/fusioncatcher/files/data/human_${genome_gencode_version}.tar.gz.ab
+    wget $args http://sourceforge.net/projects/fusioncatcher/files/data/human_${genome_gencode_version}.tar.gz.ac
+    wget $args http://sourceforge.net/projects/fusioncatcher/files/data/human_${genome_gencode_version}.tar.gz.ad
+    cat human_${genome_gencode_version}.tar.gz.* | tar xz
+    rm human_${genome_gencode_version}.tar*
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
@@ -39,8 +39,8 @@ process FUSIONCATCHER_DOWNLOAD {
 
     stub:
     """
-    mkdir human_v${ensembl_version}
-    touch human_v${ensembl_version}/ensembl_fully_overlapping_genes.txt
+    mkdir human_v${genome_gencode_version}
+    touch human_v${genome_gencode_version}/ensembl_fully_overlapping_genes.txt
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
         fusioncatcher: \$(echo \$(fusioncatcher --version 2>&1))
diff --git a/modules/local/gencode_download/main.nf b/modules/local/gencode_download/main.nf
index e9416cf4..1f466d26 100644
--- a/modules/local/gencode_download/main.nf
+++ b/modules/local/gencode_download/main.nf
@@ -31,7 +31,7 @@ process GENCODE_DOWNLOAD {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        wget: \$(echo wget -V 2>&1 | grep "GNU Wget" | cut -d" " -f3 > versions.yml)
+        wget: \$(echo wget -V 2>&1 | grep "GNU Wget" | cut -d" " -f3)
     END_VERSIONS
     """
 
@@ -42,7 +42,7 @@ process GENCODE_DOWNLOAD {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        wget: \$(echo wget -V 2>&1 | grep "GNU Wget" | cut -d" " -f3 > versions.yml)
+        wget: \$(echo wget -V 2>&1 | grep "GNU Wget" | cut -d" " -f3)
     END_VERSIONS
     """
 
diff --git a/modules/local/get_rrna_transcripts.nf b/modules/local/get_rrna_transcripts.nf
new file mode 100644
index 00000000..cb39b3e4
--- /dev/null
+++ b/modules/local/get_rrna_transcripts.nf
@@ -0,0 +1,43 @@
+process GET_RRNA_TRANSCRIPTS {
+    tag 'get_rrna_bed'
+    label 'process_low'
+
+    conda "bioconda::pirate=1.0.4 bioconda::perl-bioperl=1.7.2"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/pirate:1.0.4--hdfd78af_2' :
+        'biocontainers/pirate:1.0.4--hdfd78af_2' }"
+
+    input:
+    tuple val(meta), path(gtf)
+
+    output:
+    path('rrna.gtf')    , emit: rrnagtf
+    path('rrna.bed')    , emit: bed
+    path "versions.yml" , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    """
+    $baseDir/bin/get_rrna_transcripts.py --gtf ${gtf} --output rrna.gtf
+
+    $baseDir/bin/gtf2bed rrna.gtf > rrna.bed
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        get_rrna_transcripts: v1.0
+    END_VERSIONS
+    """
+
+    stub:
+    """
+    touch rrna.gtf
+    touch rrna.bed
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        get_rrna_transcripts: v1.0
+    END_VERSIONS
+    """
+}
diff --git a/modules/nf-core/arriba/arriba/environment.yml b/modules/nf-core/arriba/arriba/environment.yml
index d0883a0d..c3a88ffb 100644
--- a/modules/nf-core/arriba/arriba/environment.yml
+++ b/modules/nf-core/arriba/arriba/environment.yml
@@ -1,5 +1,8 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
 channels:
   - conda-forge
   - bioconda
+
 dependencies:
   - bioconda::arriba=2.4.0
diff --git a/modules/nf-core/arriba/arriba/main.nf b/modules/nf-core/arriba/arriba/main.nf
index df6d4e39..75dbf93a 100644
--- a/modules/nf-core/arriba/arriba/main.nf
+++ b/modules/nf-core/arriba/arriba/main.nf
@@ -8,14 +8,13 @@ process ARRIBA_ARRIBA {
         'biocontainers/arriba:2.4.0--h0033a41_2' }"
 
     input:
-    tuple val(meta), path(bam)
+    tuple val(meta),  path(bam)
     tuple val(meta2), path(fasta)
     tuple val(meta3), path(gtf)
-    tuple val(meta4), path(blacklist)
-    tuple val(meta5), path(known_fusions)
-    tuple val(meta6), path(structural_variants)
-    tuple val(meta7), path(tags)
-    tuple val(meta8), path(protein_domains)
+    path(blacklist)
+    path(known_fusions)
+    path(cytobands)
+    path(protein_domains)
 
     output:
     tuple val(meta), path("*.fusions.tsv")          , emit: fusions
@@ -28,11 +27,10 @@ process ARRIBA_ARRIBA {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def arg_blacklist = blacklist ? "-b $blacklist" : "-f blacklist"
-    def arg_known_fusions = known_fusions ? "-k $known_fusions" : ""
-    def arg_structural_variants = structural_variants ? "-d $structural_variants" : ""
-    def arg_tags = tags ? "-t $tags" : ""
-    def arg_protein_domains = protein_domains ? "-p $protein_domains" : ""
+    def blacklist = blacklist ? "-b $blacklist" : "-f blacklist"
+    def known_fusions = known_fusions ? "-k $known_fusions" : ""
+    def cytobands = cytobands ? "-d $cytobands" : ""
+    def protein_domains = protein_domains ? "-p $protein_domains" : ""
 
     """
     arriba \\
@@ -41,11 +39,10 @@ process ARRIBA_ARRIBA {
         -g $gtf \\
         -o ${prefix}.fusions.tsv \\
         -O ${prefix}.fusions.discarded.tsv \\
-        $arg_blacklist \\
-        $arg_known_fusions \\
-        $arg_structural_variants \\
-        $arg_tags \\
-        $arg_protein_domains \\
+        $blacklist \\
+        $known_fusions \\
+        $cytobands \\
+        $protein_domains \\
         $args
 
     cat <<-END_VERSIONS > versions.yml
diff --git a/modules/nf-core/arriba/arriba/meta.yml b/modules/nf-core/arriba/arriba/meta.yml
index f230dda1..91ba2103 100644
--- a/modules/nf-core/arriba/arriba/meta.yml
+++ b/modules/nf-core/arriba/arriba/meta.yml
@@ -43,48 +43,19 @@ input:
         type: file
         description: Annotation GTF file
         pattern: "*.{gtf}"
-  - - meta4:
-        type: map
-        description: |
-          Groovy Map containing reference information
-          e.g. [ id:'test' ]
-    - blacklist:
+  - - blacklist:
         type: file
         description: Blacklist file
         pattern: "*.{tsv}"
-  - - meta5:
-        type: map
-        description: |
-          Groovy Map containing reference information
-          e.g. [ id:'test' ]
-    - known_fusions:
+  - - known_fusions:
         type: file
         description: Known fusions file
         pattern: "*.{tsv}"
-  - - meta6:
-        type: map
-        description: |
-          Groovy Map containing reference information
-          e.g. [ id:'test' ]
-    - structural_variants:
-        type: file
-        description: Structural variants file
-        pattern: "*.{tsv}"
-  - - meta7:
-        type: map
-        description: |
-          Groovy Map containing reference information
-          e.g. [ id:'test' ]
-    - tags:
+  - - cytobands:
         type: file
-        description: Tags file
+        description: Cytobands file
         pattern: "*.{tsv}"
-  - - meta8:
-        type: map
-        description: |
-          Groovy Map containing reference information
-          e.g. [ id:'test' ]
-    - protein_domains:
+  - - protein_domains:
         type: file
         description: Protein domains file
         pattern: "*.{gff3}"
diff --git a/modules/nf-core/arriba/arriba/tests/main.nf.test b/modules/nf-core/arriba/arriba/tests/main.nf.test
new file mode 100644
index 00000000..4cff86e5
--- /dev/null
+++ b/modules/nf-core/arriba/arriba/tests/main.nf.test
@@ -0,0 +1,107 @@
+
+nextflow_process {
+
+    name "Test Process ARRIBA_ARRIBA"
+    script "../main.nf"
+    process "ARRIBA_ARRIBA"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "arriba"
+    tag "arriba/arriba"
+    tag "arriba/download"
+    tag "star/genomegenerate"
+    tag "star/align"
+
+    setup {
+        config "./nextflow.config"
+        options "-stub"
+        run("ARRIBA_DOWNLOAD") {
+            script "../../../arriba/download/main.nf"
+            process {
+                """
+                input[0] = 'GRCh38'
+                """
+            }
+        }
+        run("STAR_GENOMEGENERATE") {
+            script "../../../star/genomegenerate/main.nf"
+            options "-stub"
+            process {
+                """
+                input[0] = Channel.of([
+                    [ id:'test_fasta' ],
+                    [ file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta', checkIfExists: true) ]
+                ])
+                input[1] = Channel.of([
+                    [ id:'test_gtf' ],
+                    [ file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.gtf', checkIfExists: true) ]
+                ])
+                """
+            }
+        }
+        run("STAR_ALIGN") {
+            script "../../../star/align/main.nf"
+            options "-stub"
+            process {
+                """
+                input[0] = Channel.of([
+                    [ id:'test', single_end:false ], // meta map
+                    [
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/fastq/test_rnaseq_1.fastq.gz', checkIfExists: true),
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/fastq/test_rnaseq_2.fastq.gz', checkIfExists: true)
+                    ]
+                ])
+                input[1] = STAR_GENOMEGENERATE.out.index
+                input[2] = Channel.of([
+                    [ id:'test_gtf' ],
+                    [ file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.gtf', checkIfExists: true) ]
+                ])
+                input[3] = false
+                input[4] = 'illumina'
+                input[5] = false
+                """
+            }
+        }
+    }
+
+    test("homo_sapiens - paired_end - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = Channel.of([
+                    [ id:'test', single_end:false ], // meta map
+                    [ file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/test.rna.paired_end.sorted.bam', checkIfExists: true) ]
+                ])
+                input[1] = Channel.of([
+                    [ id:'test_fasta' ],
+                    [ file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta', checkIfExists: true) ]
+                ])
+                input[2] = Channel.of([
+                    [ id:'test_gtf' ],
+                    [ file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.gtf', checkIfExists: true) ]
+                ])
+                input[3] = []
+
+                input[4] = []
+
+                input[5] = []
+
+                input[6] = []
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+}
diff --git a/modules/nf-core/arriba/arriba/tests/main.nf.test.snap b/modules/nf-core/arriba/arriba/tests/main.nf.test.snap
new file mode 100644
index 00000000..14d46f6b
--- /dev/null
+++ b/modules/nf-core/arriba/arriba/tests/main.nf.test.snap
@@ -0,0 +1,55 @@
+{
+    "homo_sapiens - paired_end - stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.fusions.tsv:md5,f50b84b1db4b83ba62ec1deacc69c260"
+                    ]
+                ],
+                "1": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.fusions.discarded.tsv:md5,f50b84b1db4b83ba62ec1deacc69c260"
+                    ]
+                ],
+                "2": [
+                    "versions.yml:md5,d323796555db4a58fe4c6bc08d1dec30"
+                ],
+                "fusions": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.fusions.tsv:md5,f50b84b1db4b83ba62ec1deacc69c260"
+                    ]
+                ],
+                "fusions_fail": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.fusions.discarded.tsv:md5,f50b84b1db4b83ba62ec1deacc69c260"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,d323796555db4a58fe4c6bc08d1dec30"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-10-08T15:41:23.945072"
+    }
+}
\ No newline at end of file
diff --git a/modules/nf-core/arriba/arriba/tests/nextflow.config b/modules/nf-core/arriba/arriba/tests/nextflow.config
new file mode 100644
index 00000000..d3d5b00f
--- /dev/null
+++ b/modules/nf-core/arriba/arriba/tests/nextflow.config
@@ -0,0 +1,8 @@
+process {
+    withName: STAR_GENOMEGENERATE {
+        ext.args = '--genomeSAindexNbases 11'
+    }
+    withName: STAR_ALIGN {
+        ext.args = '--readFilesCommand zcat --outSAMtype BAM Unsorted --outSAMunmapped Within --outBAMcompression 0 --outFilterMultimapNmax 50 --peOverlapNbasesMin 10 --alignSplicedMateMapLminOverLmate 0.5 --alignSJstitchMismatchNmax 5 -1 5 5 --chimSegmentMin 10 --chimOutType WithinBAM HardClip --chimJunctionOverhangMin 10 --chimScoreDropMax 30 --chimScoreJunctionNonGTAG 0 --chimScoreSeparation 1 --chimSegmentReadGapMax 3 --chimMultimapNmax 50'
+    }
+}
diff --git a/modules/nf-core/arriba/download/main.nf b/modules/nf-core/arriba/download/main.nf
index 7f11898b..c45120ad 100644
--- a/modules/nf-core/arriba/download/main.nf
+++ b/modules/nf-core/arriba/download/main.nf
@@ -7,16 +7,22 @@ process ARRIBA_DOWNLOAD {
         'https://depot.galaxyproject.org/singularity/arriba:2.4.0--h0033a41_2' :
         'biocontainers/arriba:2.4.0--h0033a41_2' }"
 
+    input:
+    val(genome)
+
     output:
-    path "*"              , emit: reference
-    path "versions.yml"           , emit: versions
+    path "blacklist*${genome}*.tsv.gz"       , emit: blacklist
+    path "cytobands*${genome}*.tsv"          , emit: cytobands
+    path "protein_domains*${genome}*.gff3"   , emit: protein_domains
+    path "known_fusions*${genome}*.tsv.gz"   , emit: known_fusions
+    path "versions.yml"                      , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
 
     script:
     """
-    wget https://github.com/suhrig/arriba/releases/download/v2.4.0/arriba_v2.4.0.tar.gz -O arriba_v2.4.0.tar.gz
+    wget https://github.com/suhrig/arriba/releases/download/v2.4.0/arriba_v2.4.0.tar.gz -O arriba_v2.4.0.tar.gz --no-check-certificate
     tar -xzvf arriba_v2.4.0.tar.gz
     rm arriba_v2.4.0.tar.gz
     mv arriba_v2.4.0/database/* .
@@ -34,7 +40,6 @@ process ARRIBA_DOWNLOAD {
     touch protein_domains_hg38_GRCh38_v2.4.0.gff3
     touch cytobands_hg38_GRCh38_v2.4.0.tsv
     touch known_fusions_hg38_GRCh38_v2.4.0.tsv.gz
-    touch protein_domains_hg38_GRCh38_v2.4.0.gff3
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
diff --git a/modules/nf-core/arriba/download/meta.yml b/modules/nf-core/arriba/download/meta.yml
index 531c66c2..bdf542eb 100644
--- a/modules/nf-core/arriba/download/meta.yml
+++ b/modules/nf-core/arriba/download/meta.yml
@@ -15,12 +15,34 @@ tools:
       licence: ["MIT"]
       identifier: biotools:Arriba
 
+input:
+  - - genome:
+        type: string
+        description: hg38, hg19, GRCh38, GRCh37 for humans are accepted
 output:
-  - reference:
-      - "*":
-          type: directory
-          description: Folder with arriba references
-          pattern: "*"
+  - blacklist:
+      - blacklist*${genome}*.tsv.gz:
+          type: string
+          description: The blacklist removes recurrent alignment artifacts and transcripts
+            which are present in healthy tissue
+          pattern: ".tsv.gz"
+  - cytobands:
+      - cytobands*${genome}*.tsv:
+          type: file
+          description: Coordinates of the Giemsa staining bands. This information is used
+            to draw ideograms
+          pattern: ".tsv"
+  - protein_domains:
+      - protein_domains*${genome}*.gff3:
+          type: file
+          description: Protein domain annotations
+          patter: "*.gff3"
+  - known_fusions:
+      - known_fusions*${genome}*.tsv.gz:
+          type: file
+          description: Arriba is more sensitive to those fusions to improve the detection
+            rate of expected or highly relevant events, such as recurrent fusions
+          patter: "*.tsv.gz"
   - versions:
       - versions.yml:
           type: file
diff --git a/modules/nf-core/arriba/download/tests/main.nf.test b/modules/nf-core/arriba/download/tests/main.nf.test
index cccc95db..2c32c7a0 100644
--- a/modules/nf-core/arriba/download/tests/main.nf.test
+++ b/modules/nf-core/arriba/download/tests/main.nf.test
@@ -11,11 +11,10 @@ nextflow_process {
     tag "arriba/download"
 
     test("test-arriba-download") {
-
         when {
             process {
                 """
-
+                input[0] = 'GRCh38'
                 """
             }
         }
@@ -23,11 +22,27 @@ nextflow_process {
         then {
             assertAll(
                 { assert process.success },
-                { assert snapshot(
-                    process.out.reference[0].collect { file(it).name }.toSorted(),
-                    process.out.versions
-                    ).match()
-                }
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+    test("download - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = 'GRCh38'
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success }
             )
         }
     }
diff --git a/modules/nf-core/arriba/download/tests/main.nf.test.snap b/modules/nf-core/arriba/download/tests/main.nf.test.snap
index eda3f706..fe9b18b9 100644
--- a/modules/nf-core/arriba/download/tests/main.nf.test.snap
+++ b/modules/nf-core/arriba/download/tests/main.nf.test.snap
@@ -1,35 +1,43 @@
 {
-    "test-arriba-download": {
+    "download": {
         "content": [
-            [
-                "CREDITS",
-                "RefSeq_viral_genomes_v2.4.0.fa.gz",
-                "blacklist_hg19_hs37d5_GRCh37_v2.4.0.tsv.gz",
-                "blacklist_hg38_GRCh38_v2.4.0.tsv.gz",
-                "blacklist_mm10_GRCm38_v2.4.0.tsv.gz",
-                "blacklist_mm39_GRCm39_v2.4.0.tsv.gz",
-                "cytobands_hg19_hs37d5_GRCh37_v2.4.0.tsv",
-                "cytobands_hg38_GRCh38_v2.4.0.tsv",
-                "cytobands_mm10_GRCm38_v2.4.0.tsv",
-                "cytobands_mm39_GRCm39_v2.4.0.tsv",
-                "known_fusions_hg19_hs37d5_GRCh37_v2.4.0.tsv.gz",
-                "known_fusions_hg38_GRCh38_v2.4.0.tsv.gz",
-                "known_fusions_mm10_GRCm38_v2.4.0.tsv.gz",
-                "known_fusions_mm39_GRCm39_v2.4.0.tsv.gz",
-                "protein_domains_hg19_hs37d5_GRCh37_v2.4.0.gff3",
-                "protein_domains_hg38_GRCh38_v2.4.0.gff3",
-                "protein_domains_mm10_GRCm38_v2.4.0.gff3",
-                "protein_domains_mm39_GRCm39_v2.4.0.gff3",
-                "versions.yml"
-            ],
-            [
-                "versions.yml:md5,98c69df5eaea5caf0b4af7b8d7af4893"
-            ]
+            {
+                "0": [
+                    "blacklist_hg38_GRCh38_v2.4.0.tsv.gz:md5,e3098a4be51aece78aede64b55c39318"
+                ],
+                "1": [
+                    "cytobands_hg38_GRCh38_v2.4.0.tsv:md5,7bd504feefb33fcfc9be0517439a423c"
+                ],
+                "2": [
+                    "protein_domains_hg38_GRCh38_v2.4.0.gff3:md5,43c387a784ebeed71b4147076cebf978"
+                ],
+                "3": [
+                    "known_fusions_hg38_GRCh38_v2.4.0.tsv.gz:md5,4f00f81ccb5f4db283f1a22b8b0da67c"
+                ],
+                "4": [
+                    "versions.yml:md5,98c69df5eaea5caf0b4af7b8d7af4893"
+                ],
+                "blacklist": [
+                    "blacklist_hg38_GRCh38_v2.4.0.tsv.gz:md5,e3098a4be51aece78aede64b55c39318"
+                ],
+                "cytobands": [
+                    "cytobands_hg38_GRCh38_v2.4.0.tsv:md5,7bd504feefb33fcfc9be0517439a423c"
+                ],
+                "known_fusions": [
+                    "known_fusions_hg38_GRCh38_v2.4.0.tsv.gz:md5,4f00f81ccb5f4db283f1a22b8b0da67c"
+                ],
+                "protein_domains": [
+                    "protein_domains_hg38_GRCh38_v2.4.0.gff3:md5,43c387a784ebeed71b4147076cebf978"
+                ],
+                "versions": [
+                    "versions.yml:md5,98c69df5eaea5caf0b4af7b8d7af4893"
+                ]
+            }
         ],
         "meta": {
-            "nf-test": "0.8.4",
+            "nf-test": "0.9.0",
             "nextflow": "24.04.4"
         },
-        "timestamp": "2024-08-22T17:00:38.086459"
+        "timestamp": "2024-10-08T11:12:17.010496"
     }
 }
\ No newline at end of file
diff --git a/modules/nf-core/arriba/download/tests/tags.yml b/modules/nf-core/arriba/download/tests/tags.yml
new file mode 100644
index 00000000..f510bbf1
--- /dev/null
+++ b/modules/nf-core/arriba/download/tests/tags.yml
@@ -0,0 +1,2 @@
+arriba/download:
+  - "modules/nf-core/arriba/download/**"
diff --git a/modules/nf-core/gunzip/environment.yml b/modules/nf-core/gunzip/environment.yml
deleted file mode 100644
index c7794856..00000000
--- a/modules/nf-core/gunzip/environment.yml
+++ /dev/null
@@ -1,7 +0,0 @@
-channels:
-  - conda-forge
-  - bioconda
-dependencies:
-  - conda-forge::grep=3.11
-  - conda-forge::sed=4.8
-  - conda-forge::tar=1.34
diff --git a/modules/nf-core/gunzip/main.nf b/modules/nf-core/gunzip/main.nf
deleted file mode 100644
index 5e67e3b9..00000000
--- a/modules/nf-core/gunzip/main.nf
+++ /dev/null
@@ -1,55 +0,0 @@
-process GUNZIP {
-    tag "$archive"
-    label 'process_single'
-
-    conda "${moduleDir}/environment.yml"
-    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/ubuntu:22.04' :
-        'nf-core/ubuntu:22.04' }"
-
-    input:
-    tuple val(meta), path(archive)
-
-    output:
-    tuple val(meta), path("$gunzip"), emit: gunzip
-    path "versions.yml"             , emit: versions
-
-    when:
-    task.ext.when == null || task.ext.when
-
-    script:
-    def args        = task.ext.args ?: ''
-    def extension   = ( archive.toString() - '.gz' ).tokenize('.')[-1]
-    def name        = archive.toString() - '.gz' - ".$extension"
-    def prefix      = task.ext.prefix ?: name
-    gunzip          = prefix + ".$extension"
-    """
-    # Not calling gunzip itself because it creates files
-    # with the original group ownership rather than the
-    # default one for that user / the work directory
-    gzip \\
-        -cd \\
-        $args \\
-        $archive \\
-        > $gunzip
-
-    cat <<-END_VERSIONS > versions.yml
-    "${task.process}":
-        gunzip: \$(echo \$(gunzip --version 2>&1) | sed 's/^.*(gzip) //; s/ Copyright.*\$//')
-    END_VERSIONS
-    """
-
-    stub:
-    def args        = task.ext.args ?: ''
-    def extension   = ( archive.toString() - '.gz' ).tokenize('.')[-1]
-    def name        = archive.toString() - '.gz' - ".$extension"
-    def prefix      = task.ext.prefix ?: name
-    gunzip          = prefix + ".$extension"
-    """
-    touch $gunzip
-    cat <<-END_VERSIONS > versions.yml
-    "${task.process}":
-        gunzip: \$(echo \$(gunzip --version 2>&1) | sed 's/^.*(gzip) //; s/ Copyright.*\$//')
-    END_VERSIONS
-    """
-}
diff --git a/modules/nf-core/gunzip/meta.yml b/modules/nf-core/gunzip/meta.yml
deleted file mode 100644
index 9066c035..00000000
--- a/modules/nf-core/gunzip/meta.yml
+++ /dev/null
@@ -1,47 +0,0 @@
-name: gunzip
-description: Compresses and decompresses files.
-keywords:
-  - gunzip
-  - compression
-  - decompression
-tools:
-  - gunzip:
-      description: |
-        gzip is a file format and a software application used for file compression and decompression.
-      documentation: https://www.gnu.org/software/gzip/manual/gzip.html
-      licence: ["GPL-3.0-or-later"]
-      identifier: ""
-input:
-  - - meta:
-        type: map
-        description: |
-          Optional groovy Map containing meta information
-          e.g. [ id:'test', single_end:false ]
-    - archive:
-        type: file
-        description: File to be compressed/uncompressed
-        pattern: "*.*"
-output:
-  - gunzip:
-      - meta:
-          type: file
-          description: Compressed/uncompressed file
-          pattern: "*.*"
-      - $gunzip:
-          type: file
-          description: Compressed/uncompressed file
-          pattern: "*.*"
-  - versions:
-      - versions.yml:
-          type: file
-          description: File containing software versions
-          pattern: "versions.yml"
-authors:
-  - "@joseespinosa"
-  - "@drpatelh"
-  - "@jfy133"
-maintainers:
-  - "@joseespinosa"
-  - "@drpatelh"
-  - "@jfy133"
-  - "@gallvp"
diff --git a/modules/nf-core/gunzip/tests/main.nf.test b/modules/nf-core/gunzip/tests/main.nf.test
deleted file mode 100644
index 776211ad..00000000
--- a/modules/nf-core/gunzip/tests/main.nf.test
+++ /dev/null
@@ -1,121 +0,0 @@
-nextflow_process {
-
-    name "Test Process GUNZIP"
-    script "../main.nf"
-    process "GUNZIP"
-    tag "gunzip"
-    tag "modules_nfcore"
-    tag "modules"
-
-    test("Should run without failures") {
-
-        when {
-            params {
-                outdir = "$outputDir"
-            }
-            process {
-                """
-                input[0] = Channel.of([
-                        [],
-                        file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true)
-                    ]
-                )
-                """
-            }
-        }
-
-        then {
-            assertAll(
-            { assert process.success },
-            { assert snapshot(process.out).match() }
-            )
-        }
-
-    }
-
-    test("Should run without failures - prefix") {
-
-        config './nextflow.config'
-
-        when {
-            params {
-                outdir = "$outputDir"
-            }
-            process {
-                """
-                input[0] = Channel.of([
-                        [ id: 'test' ],
-                        file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true)
-                    ]
-                )
-                """
-            }
-        }
-
-        then {
-            assertAll(
-            { assert process.success },
-            { assert snapshot(process.out).match() }
-            )
-        }
-
-    }
-
-    test("Should run without failures - stub") {
-
-        options '-stub'
-
-        when {
-            params {
-                outdir = "$outputDir"
-            }
-            process {
-                """
-                input[0] = Channel.of([
-                        [],
-                        file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true)
-                    ]
-                )
-                """
-            }
-        }
-
-        then {
-            assertAll(
-            { assert process.success },
-            { assert snapshot(process.out).match() }
-            )
-        }
-
-    }
-
-    test("Should run without failures - prefix - stub") {
-
-        options '-stub'
-        config './nextflow.config'
-
-        when {
-            params {
-                outdir = "$outputDir"
-            }
-            process {
-                """
-                input[0] = Channel.of([
-                        [ id: 'test' ],
-                        file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true)
-                    ]
-                )
-                """
-            }
-        }
-
-        then {
-            assertAll(
-            { assert process.success },
-            { assert snapshot(process.out).match() }
-            )
-        }
-
-    }
-
-}
diff --git a/modules/nf-core/gunzip/tests/main.nf.test.snap b/modules/nf-core/gunzip/tests/main.nf.test.snap
deleted file mode 100644
index 069967e7..00000000
--- a/modules/nf-core/gunzip/tests/main.nf.test.snap
+++ /dev/null
@@ -1,134 +0,0 @@
-{
-    "Should run without failures - prefix - stub": {
-        "content": [
-            {
-                "0": [
-                    [
-                        {
-                            "id": "test"
-                        },
-                        "test.xyz.fastq:md5,d41d8cd98f00b204e9800998ecf8427e"
-                    ]
-                ],
-                "1": [
-                    "versions.yml:md5,54376d32aca20e937a4ec26dac228e84"
-                ],
-                "gunzip": [
-                    [
-                        {
-                            "id": "test"
-                        },
-                        "test.xyz.fastq:md5,d41d8cd98f00b204e9800998ecf8427e"
-                    ]
-                ],
-                "versions": [
-                    "versions.yml:md5,54376d32aca20e937a4ec26dac228e84"
-                ]
-            }
-        ],
-        "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "24.04.2"
-        },
-        "timestamp": "2024-06-25T11:35:10.861293"
-    },
-    "Should run without failures - stub": {
-        "content": [
-            {
-                "0": [
-                    [
-                        [
-                            
-                        ],
-                        "test_1.fastq:md5,d41d8cd98f00b204e9800998ecf8427e"
-                    ]
-                ],
-                "1": [
-                    "versions.yml:md5,54376d32aca20e937a4ec26dac228e84"
-                ],
-                "gunzip": [
-                    [
-                        [
-                            
-                        ],
-                        "test_1.fastq:md5,d41d8cd98f00b204e9800998ecf8427e"
-                    ]
-                ],
-                "versions": [
-                    "versions.yml:md5,54376d32aca20e937a4ec26dac228e84"
-                ]
-            }
-        ],
-        "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "24.04.2"
-        },
-        "timestamp": "2024-06-25T11:35:05.857145"
-    },
-    "Should run without failures": {
-        "content": [
-            {
-                "0": [
-                    [
-                        [
-                            
-                        ],
-                        "test_1.fastq:md5,4161df271f9bfcd25d5845a1e220dbec"
-                    ]
-                ],
-                "1": [
-                    "versions.yml:md5,54376d32aca20e937a4ec26dac228e84"
-                ],
-                "gunzip": [
-                    [
-                        [
-                            
-                        ],
-                        "test_1.fastq:md5,4161df271f9bfcd25d5845a1e220dbec"
-                    ]
-                ],
-                "versions": [
-                    "versions.yml:md5,54376d32aca20e937a4ec26dac228e84"
-                ]
-            }
-        ],
-        "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "24.04.2"
-        },
-        "timestamp": "2023-10-17T15:35:37.690477896"
-    },
-    "Should run without failures - prefix": {
-        "content": [
-            {
-                "0": [
-                    [
-                        {
-                            "id": "test"
-                        },
-                        "test.xyz.fastq:md5,4161df271f9bfcd25d5845a1e220dbec"
-                    ]
-                ],
-                "1": [
-                    "versions.yml:md5,54376d32aca20e937a4ec26dac228e84"
-                ],
-                "gunzip": [
-                    [
-                        {
-                            "id": "test"
-                        },
-                        "test.xyz.fastq:md5,4161df271f9bfcd25d5845a1e220dbec"
-                    ]
-                ],
-                "versions": [
-                    "versions.yml:md5,54376d32aca20e937a4ec26dac228e84"
-                ]
-            }
-        ],
-        "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "24.04.2"
-        },
-        "timestamp": "2024-06-25T11:33:32.921739"
-    }
-}
\ No newline at end of file
diff --git a/modules/nf-core/gunzip/tests/nextflow.config b/modules/nf-core/gunzip/tests/nextflow.config
deleted file mode 100644
index dec77642..00000000
--- a/modules/nf-core/gunzip/tests/nextflow.config
+++ /dev/null
@@ -1,5 +0,0 @@
-process {
-    withName: GUNZIP {
-        ext.prefix = { "${meta.id}.xyz" }
-    }
-}
diff --git a/modules/nf-core/gunzip/tests/tags.yml b/modules/nf-core/gunzip/tests/tags.yml
deleted file mode 100644
index fd3f6915..00000000
--- a/modules/nf-core/gunzip/tests/tags.yml
+++ /dev/null
@@ -1,2 +0,0 @@
-gunzip:
-  - modules/nf-core/gunzip/**
diff --git a/modules/nf-core/salmon/quant/environment.yml b/modules/nf-core/salmon/quant/environment.yml
index 471164fa..b3f75777 100644
--- a/modules/nf-core/salmon/quant/environment.yml
+++ b/modules/nf-core/salmon/quant/environment.yml
@@ -2,4 +2,4 @@ channels:
   - conda-forge
   - bioconda
 dependencies:
-  - bioconda::salmon=1.10.1
+  - bioconda::salmon=1.10.3
diff --git a/modules/nf-core/salmon/quant/main.nf b/modules/nf-core/salmon/quant/main.nf
index 6d624e75..f1e3b5cd 100644
--- a/modules/nf-core/salmon/quant/main.nf
+++ b/modules/nf-core/salmon/quant/main.nf
@@ -4,8 +4,8 @@ process SALMON_QUANT {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/salmon:1.10.1--h7e5ed60_0' :
-        'biocontainers/salmon:1.10.1--h7e5ed60_0' }"
+        'https://depot.galaxyproject.org/singularity/salmon:1.10.3--h6dccd9a_2' :
+        'biocontainers/salmon:1.10.3--h6dccd9a_2' }"
 
     input:
     tuple val(meta), path(reads)
@@ -28,7 +28,7 @@ process SALMON_QUANT {
     def args = task.ext.args   ?: ''
     prefix   = task.ext.prefix ?: "${meta.id}"
 
-    def reference = "--index $index"
+    def reference   = "--index $index"
     def reads1 = [], reads2 = []
     meta.single_end ? [reads].flatten().each{reads1 << it} : reads.eachWithIndex{ v, ix -> ( ix & 1 ? reads2 : reads1) << v }
     def input_reads = meta.single_end ? "-r ${reads1.join(" ")}" : "-1 ${reads1.join(" ")} -2 ${reads2.join(" ")}"
diff --git a/modules/nf-core/salmon/quant/tests/main.nf.test.snap b/modules/nf-core/salmon/quant/tests/main.nf.test.snap
index 547ce2de..ea22a80c 100644
--- a/modules/nf-core/salmon/quant/tests/main.nf.test.snap
+++ b/modules/nf-core/salmon/quant/tests/main.nf.test.snap
@@ -2,7 +2,7 @@
     "sarscov2 - single_end": {
         "content": [
             [
-                "versions.yml:md5,80eb3d2ad36960c7e9263f81ede9d263"
+                "versions.yml:md5,0d510d5db6398e2c8ca9443330740607"
             ],
             [
                 [
@@ -15,15 +15,15 @@
             ]
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-06-14T09:51:22.424672"
+        "timestamp": "2024-10-18T10:01:16.989080539"
     },
     "sarscov2 - single_end stub": {
         "content": [
             [
-                "versions.yml:md5,80eb3d2ad36960c7e9263f81ede9d263"
+                "versions.yml:md5,0d510d5db6398e2c8ca9443330740607"
             ],
             [
                 [
@@ -36,15 +36,15 @@
             ]
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-06-14T09:51:32.292277"
+        "timestamp": "2024-10-18T10:01:29.340996235"
     },
     "sarscov2 - single_end lib type A": {
         "content": [
             [
-                "versions.yml:md5,80eb3d2ad36960c7e9263f81ede9d263"
+                "versions.yml:md5,0d510d5db6398e2c8ca9443330740607"
             ],
             [
                 [
@@ -57,15 +57,15 @@
             ]
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-06-14T09:51:42.656382"
+        "timestamp": "2024-10-18T10:01:43.056167576"
     },
     "sarscov2 - pair_end multiple": {
         "content": [
             [
-                "versions.yml:md5,80eb3d2ad36960c7e9263f81ede9d263"
+                "versions.yml:md5,0d510d5db6398e2c8ca9443330740607"
             ],
             [
                 [
@@ -78,15 +78,15 @@
             ]
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-06-14T09:52:33.03647"
+        "timestamp": "2024-10-18T10:03:05.500792631"
     },
     "sarscov2 - pair_end multiple stub": {
         "content": [
             [
-                "versions.yml:md5,80eb3d2ad36960c7e9263f81ede9d263"
+                "versions.yml:md5,0d510d5db6398e2c8ca9443330740607"
             ],
             [
                 [
@@ -99,15 +99,15 @@
             ]
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-06-14T09:52:43.388379"
+        "timestamp": "2024-10-18T10:03:26.428959203"
     },
     "sarscov2 - single_end lib type A stub": {
         "content": [
             [
-                "versions.yml:md5,80eb3d2ad36960c7e9263f81ede9d263"
+                "versions.yml:md5,0d510d5db6398e2c8ca9443330740607"
             ],
             [
                 [
@@ -120,15 +120,15 @@
             ]
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-06-14T09:51:52.612664"
+        "timestamp": "2024-10-18T10:02:03.420850208"
     },
     "sarscov2 - pair_end": {
         "content": [
             [
-                "versions.yml:md5,80eb3d2ad36960c7e9263f81ede9d263"
+                "versions.yml:md5,0d510d5db6398e2c8ca9443330740607"
             ],
             [
                 [
@@ -141,15 +141,15 @@
             ]
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-06-14T09:52:05.577881"
+        "timestamp": "2024-10-18T10:02:16.130074696"
     },
     "sarscov2 - pair_end stub": {
         "content": [
             [
-                "versions.yml:md5,80eb3d2ad36960c7e9263f81ede9d263"
+                "versions.yml:md5,0d510d5db6398e2c8ca9443330740607"
             ],
             [
                 [
@@ -162,9 +162,9 @@
             ]
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-06-14T09:52:15.286461"
+        "timestamp": "2024-10-18T10:02:39.470004547"
     }
 }
\ No newline at end of file
diff --git a/nextflow.config b/nextflow.config
index 3e4e4b4d..98535a01 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -11,7 +11,7 @@ params {
 
     // Input options
     input                      = 'https://raw.githubusercontent.com/nf-core/test-datasets/rnafusion/testdata/human/samplesheet_valid.csv'
-    build_references           = false
+    references_only            = false
     cosmic_username            = null
     cosmic_passwd              = null
     qiagen                     = false
@@ -75,6 +75,7 @@ params {
     rrna_intervals                = "${params.genomes_base}/gencode/Homo_sapiens_${params.genome}_${params.genome_gencode_version}.interval_list"
     gencode_ref                   = "${params.genomes_base}/gencode"
     arriba_ref_blacklist          = "${params.genomes_base}/arriba/blacklist_hg38_GRCh38_v2.4.0.tsv.gz"
+    arriba_ref_cytobands          = "${params.genomes_base}/arriba/cytobands_hg38_GRCh38_v2.4.0.tsv"
     arriba_ref_known_fusions      = "${params.genomes_base}/arriba/known_fusions_hg38_GRCh38_v2.4.0.tsv.gz"
     arriba_ref_protein_domains    = "${params.genomes_base}/arriba/protein_domains_hg38_GRCh38_v2.4.0.gff3"
     fusioncatcher_ref             = "${params.genomes_base}/fusioncatcher/human_v${params.genome_gencode_version}"
diff --git a/nextflow_schema.json b/nextflow_schema.json
index 480aa091..15915510 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -79,8 +79,7 @@
                 "genome_gencode_version": {
                     "type": "integer",
                     "fa_icon": "far fa-file-code",
-                    "description": "ensembl version",
-                    "default": 102
+                    "description": "gencode version"
                 },
                 "starfusion_build": {
                     "type": "boolean",
@@ -108,6 +107,11 @@
                     "fa_icon": "far fa-file-code",
                     "description": "Path to arriba reference blacklist"
                 },
+                "arriba_ref_cytobands": {
+                    "type": "string",
+                    "fa_icon": "far fa-file-code",
+                    "description": "Path to arriba reference cytobands"
+                },
                 "arriba_ref_known_fusions": {
                     "type": "string",
                     "fa_icon": "far fa-file-code",
@@ -307,9 +311,9 @@
             "fa_icon": "fas fa-dna",
             "description": "Reference genome related files and options required for the workflow.",
             "properties": {
-                "genome": {
-                    "type": "string",
-                    "description": "Name of iGenomes reference.",
+                "references_only": {
+                    "type": "boolean",
+                    "description": "Skip running the analysis, only builds the references",
                     "fa_icon": "fas fa-book"
                 },
                 "fasta": {
@@ -328,6 +332,11 @@
                     "description": "Path to FASTA genome index file.",
                     "fa_icon": "far fa-file-code"
                 },
+                "genome": {
+                    "type": "string",
+                    "description": "Name of iGenomes reference.",
+                    "fa_icon": "fas fa-book"
+                },
                 "gtf": {
                     "type": "string",
                     "format": "file-path",
diff --git a/subworkflows/local/build_references.nf b/subworkflows/local/build_references.nf
index 1d45e74c..0c6c9916 100644
--- a/subworkflows/local/build_references.nf
+++ b/subworkflows/local/build_references.nf
@@ -4,7 +4,6 @@
 ========================================================================================
 */
 
-include { ARRIBA_DOWNLOAD }                 from '../../modules/local/arriba/download/main'
 include { GENCODE_DOWNLOAD }                from '../../modules/local/gencode_download/main'
 include { FUSIONCATCHER_DOWNLOAD }          from '../../modules/local/fusioncatcher/download/main'
 include { FUSIONCATCHER_BUILD }             from '../../modules/local/fusioncatcher/build/main'
@@ -14,13 +13,14 @@ include { STARFUSION_BUILD }                from '../../modules/local/starfusion
 include { STARFUSION_DOWNLOAD }             from '../../modules/local/starfusion/download/main'
 include { GTF_TO_REFFLAT }                  from '../../modules/local/uscs/custom_gtftogenepred/main'
 include { RRNA_TRANSCRIPTS }                from '../../modules/local/rrnatranscripts/main'
-include { CONVERT2BED }                     from '../../modules/local/convert2bed/main'
+include { GET_RRNA_TRANSCRIPTS }            from '../../modules/local/get_rrna_transcripts'
+// include { CONVERT2BED }                     from '../../modules/local/convert2bed/main'
 /*
 ========================================================================================
     IMPORT NF-CORE MODULES/SUBWORKFLOWS
 ========================================================================================
 */
-
+include { ARRIBA_DOWNLOAD }                 from '../../modules/nf-core/arriba/download/main'
 include { SAMTOOLS_FAIDX }                  from '../../modules/nf-core/samtools/faidx/main'
 include { STAR_GENOMEGENERATE }             from '../../modules/nf-core/star/genomegenerate/main'
 include { GATK4_CREATESEQUENCEDICTIONARY }  from '../../modules/nf-core/gatk4/createsequencedictionary/main'
@@ -73,9 +73,8 @@ workflow BUILD_REFERENCES {
 
     if (!file(params.rrna_intervals).exists() || file(params.rrna_intervals).isEmpty()){
         GATK4_CREATESEQUENCEDICTIONARY(ch_fasta)
-        RRNA_TRANSCRIPTS(ch_gtf)
-        CONVERT2BED(RRNA_TRANSCRIPTS.out.rrna_gtf)
-        GATK4_BEDTOINTERVALLIST(CONVERT2BED.out.bed, GATK4_CREATESEQUENCEDICTIONARY.out.dict)
+        GET_RRNA_TRANSCRIPTS(ch_gtf)
+        GATK4_BEDTOINTERVALLIST(GET_RRNA_TRANSCRIPTS.out.bed.map { it -> [ [id:it.name], it ] }, GATK4_CREATESEQUENCEDICTIONARY.out.dict )
         ch_rrna_interval = GATK4_BEDTOINTERVALLIST.out.interval_list
     } else {
         ch_rrna_interval = Channel.fromPath(params.rrna_intervals).map { that -> [[id:that.Name], that] }
@@ -106,31 +105,35 @@ workflow BUILD_REFERENCES {
         ch_starindex_ref = Channel.fromPath(params.starindex_ref).map { that -> [[id:that.Name], that] }
     }
 
-//     if ((params.arriba || params.all) &&
-//             (!file(params.arriba_ref_blacklist).exists() || file(params.arriba_ref_blacklist).isEmpty() ||
-//             !file(params.arriba_ref_known_fusions).exists() || file(params.arriba_ref_known_fusions).isEmpty() ||
-//             !file(params.arriba_ref_protein_domains).exists() || file(params.arriba_ref_protein_domains).isEmpty())) {
-//         ARRIBA_DOWNLOAD()
-//         ch_arriba_ref_blacklist = Channel.fromPath(params.arriba_ref_blacklist).map { that -> [[id:that.Name], that] }
-//         ch_arriba_ref_known_fusions = Channel.fromPath(params.arriba_ref_known_fusions).map { that -> [[id:that.Name], that] }
-//         ch_arriba_ref_protein_domains = Channel.fromPath(params.arriba_ref_protein_domains).map { that -> [[id:that.Name], that] }
-//     } else {
-// // TODO need to update the module to emit blacklist,knownfusions etc
-//     }
-
-
-    // if ((params.fusioncatcher || params.all) &&
-    //         (!file(params.fusioncatcher_ref).exists() || file(params.fusioncatcher_ref).isEmpty() ||
-    //         !file(params.fusioncatcher_ref_stub_check).exists() || file(params.fusioncatcher_ref_stub_check).isEmpty() )) {
-    //     if (params.download_refs) {
-    //         FUSIONCATCHER_DOWNLOAD(params.genome_gencode_version)
-    //         ch_fusioncatcher_ref = FUSIONCATCHER_DOWNLOAD.out.reference}
-    //     else {
-    //         FUSIONCATCHER_BUILD(params.genome_gencode_version)
-    //         ch_fusioncatcher_ref = FUSIONCATCHER_BUILD.out.reference}
-    //     } else {
-    //         ch_fusioncatcher_ref = Channel.fromPath(params.fusioncatcher_ref).map { that -> [[id:that.Name], that] }
-    //     }
+    if ((params.arriba || params.all) &&
+            (!file(params.arriba_ref_blacklist).exists() || file(params.arriba_ref_blacklist).isEmpty() ||
+            !file(params.arriba_ref_known_fusions).exists() || file(params.arriba_ref_known_fusions).isEmpty() ||
+            !file(params.arriba_ref_protein_domains).exists() || file(params.arriba_ref_protein_domains).isEmpty())) {
+        ARRIBA_DOWNLOAD(genome)
+        ch_arriba_ref_blacklist = ARRIBA_DOWNLOAD.out.blacklist
+        ch_arriba_ref_cytobands = ARRIBA_DOWNLOAD.out.cytobands
+        ch_arriba_ref_known_fusions = ARRIBA_DOWNLOAD.out.known_fusions
+        ch_arriba_ref_protein_domains = ARRIBA_DOWNLOAD.out.protein_domains
+    } else {
+        ch_arriba_ref_blacklist = Channel.fromPath(params.arriba_ref_blacklist).map { that -> [[id:that.Name], that] }
+        ch_arriba_ref_cytobands = Channel.fromPath(params.arriba_ref_cytobands).map { that -> [[id:that.Name], that] }
+        ch_arriba_ref_known_fusions = Channel.fromPath(params.arriba_ref_known_fusions).map { that -> [[id:that.Name], that] }
+        ch_arriba_ref_protein_domains = Channel.fromPath(params.arriba_ref_protein_domains).map { that -> [[id:that.Name], that] }
+    }
+
+
+    if ((params.fusioncatcher || params.all) &&
+            (!file(params.fusioncatcher_ref).exists() || file(params.fusioncatcher_ref).isEmpty() ||
+            !file(params.fusioncatcher_ref_stub_check).exists() || file(params.fusioncatcher_ref_stub_check).isEmpty() )) {
+        if (params.download_refs) {
+            FUSIONCATCHER_DOWNLOAD(params.genome_gencode_version)
+            ch_fusioncatcher_ref = FUSIONCATCHER_DOWNLOAD.out.reference}
+        else {
+            FUSIONCATCHER_BUILD(params.genome_gencode_version)
+            ch_fusioncatcher_ref = FUSIONCATCHER_BUILD.out.reference}
+        } else {
+            ch_fusioncatcher_ref = Channel.fromPath(params.fusioncatcher_ref).map { that -> [[id:that.Name], that] }
+        }
 
 
     if ((params.starfusion || params.all) &&
@@ -144,14 +147,14 @@ workflow BUILD_REFERENCES {
         ch_starfusion_ref = Channel.fromPath(params.starfusion_ref).map { that -> [[id:that.Name], that] }}
 
 
-    // if ((params.fusionreport || params.all) &&
-    //         (!file(params.fusionreport_ref).exists() || file(params.fusionreport_ref).isEmpty() ||
-    //         !file(params.fusionreport_ref_stub_check).exists() || file(params.fusionreport_ref_stub_check).isEmpty())) {
-    //     if (!params.cosmic_username || !params.cosmic_passwd) { exit 1, 'COSMIC username and/or password missing' }
-    //     ch_fusionreport_ref = FUSIONREPORT_DOWNLOAD( params.cosmic_username, params.cosmic_passwd ).out.reference
-    // } else {
-    //     ch_fusionreport_ref = Channel.fromPath(params.fusionreport_ref).map { that -> [[id:that.Name], that] }
-    // }
+    if ((params.fusionreport || params.all) &&
+            (!file(params.fusionreport_ref).exists() || file(params.fusionreport_ref).isEmpty() ||
+            !file(params.fusionreport_ref_stub_check).exists() || file(params.fusionreport_ref_stub_check).isEmpty())) {
+        if (!params.cosmic_username || !params.cosmic_passwd) { exit 1, 'COSMIC username and/or password missing' }
+        ch_fusionreport_ref = FUSIONREPORT_DOWNLOAD( params.cosmic_username, params.cosmic_passwd ).out.reference
+    } else {
+        ch_fusionreport_ref = Channel.fromPath(params.fusionreport_ref).map { that -> [[id:that.Name], that] }
+    }
 
     emit:
     ch_fasta
@@ -160,16 +163,17 @@ workflow BUILD_REFERENCES {
 
     ch_hgnc_ref
     ch_hgnc_date
-    // ch_rrna_interval
-    // ch_refflat
-    // ch_salmon_index
-    // ch_starindex_ref
-    // ch_arriba_ref_blacklist
-    // ch_arriba_ref_known_fusions
-    // ch_arriba_ref_protein_domains
-    // ch_fusioncatcher_ref
-    // ch_starfusion_ref
-    // ch_fusionreport_ref
+    ch_rrna_interval
+    ch_refflat
+    ch_salmon_index
+    ch_starindex_ref
+    ch_arriba_ref_blacklist
+    ch_arriba_ref_cytobands
+    ch_arriba_ref_known_fusions
+    ch_arriba_ref_protein_domains
+    ch_fusioncatcher_ref
+    ch_starfusion_ref
+    ch_fusionreport_ref
     versions        = ch_versions
 }
 
diff --git a/workflows/rnafusion.nf b/workflows/rnafusion.nf
index 8f7f8ae8..5e34db97 100644
--- a/workflows/rnafusion.nf
+++ b/workflows/rnafusion.nf
@@ -4,41 +4,21 @@
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 */
 
-
-
-/*
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-    IMPORT LOCAL MODULES/SUBWORKFLOWS
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-*/
-
-//
-// SUBWORKFLOW: Consisting of a mix of local and nf-core/modules
-//
 include { BUILD_REFERENCES              }   from '../subworkflows/local/build_references'
-include { TRIM_WORKFLOW                 }   from '../subworkflows/local/trim_workflow'
-include { ARRIBA_WORKFLOW               }   from '../subworkflows/local/arriba_workflow'
-include { QC_WORKFLOW                   }   from '../subworkflows/local/qc_workflow'
-include { STARFUSION_WORKFLOW           }   from '../subworkflows/local/starfusion_workflow'
-include { STRINGTIE_WORKFLOW            }   from '../subworkflows/local/stringtie_workflow'
-include { FUSIONCATCHER_WORKFLOW        }   from '../subworkflows/local/fusioncatcher_workflow'
-include { FUSIONINSPECTOR_WORKFLOW      }   from '../subworkflows/local/fusioninspector_workflow'
-include { FUSIONREPORT_WORKFLOW         }   from '../subworkflows/local/fusionreport_workflow'
-include { validateInputSamplesheet      }   from '../subworkflows/local/utils_nfcore_rnafusion_pipeline'
-
-/*
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-    IMPORT NF-CORE MODULES/SUBWORKFLOWS
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-*/
-
-//
-// MODULE: Installed directly from nf-core/modules
-//
-include { CAT_FASTQ              } from '../modules/nf-core/cat/fastq/main'
-include { FASTQC                 } from '../modules/nf-core/fastqc/main'
-include { MULTIQC                } from '../modules/nf-core/multiqc/main'
-include { SALMON_QUANT           } from '../modules/nf-core/salmon/quant/main'
+// include { TRIM_WORKFLOW                 }   from '../subworkflows/local/trim_workflow'
+// include { ARRIBA_WORKFLOW               }   from '../subworkflows/local/arriba_workflow'
+// include { QC_WORKFLOW                   }   from '../subworkflows/local/qc_workflow'
+// include { STARFUSION_WORKFLOW           }   from '../subworkflows/local/starfusion_workflow'
+// include { STRINGTIE_WORKFLOW            }   from '../subworkflows/local/stringtie_workflow'
+// include { FUSIONCATCHER_WORKFLOW        }   from '../subworkflows/local/fusioncatcher_workflow'
+// include { FUSIONINSPECTOR_WORKFLOW      }   from '../subworkflows/local/fusioninspector_workflow'
+// include { FUSIONREPORT_WORKFLOW         }   from '../subworkflows/local/fusionreport_workflow'
+// include { validateInputSamplesheet      }   from '../subworkflows/local/utils_nfcore_rnafusion_pipeline'
+
+include { CAT_FASTQ                     }   from '../modules/nf-core/cat/fastq/main'
+include { FASTQC                        }   from '../modules/nf-core/fastqc/main'
+include { MULTIQC                       }   from '../modules/nf-core/multiqc/main'
+// include { SALMON_QUANT                  }   from '../modules/nf-core/salmon/quant/main'
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -54,7 +34,7 @@ workflow RNAFUSION {
 
 
     ch_versions = Channel.empty()
-    ch_multiqc_files = Channel.empty()
+    // ch_multiqc_files = Channel.empty()
 
     //
     // Create references if necessary
@@ -268,7 +248,7 @@ workflow RNAFUSION {
     // QC_WORKFLOW (
     //     ch_reads_all,
     //     STARFUSION_WORKFLOW.out.ch_bam_sorted,
-    //     ch_chrgtf,
+    //     ch_gtf,
     //     ch_refflat,
     //     ch_fasta,
     //     ch_fai,

From d18b303eb7a1644405fe877bc7a2a80f88197f19 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Thu, 14 Nov 2024 15:45:10 +0100
Subject: [PATCH 14/41] update modules, remove chrgtf, adapt with meta/no meta

---
 .github/workflows/awsfulltest.yml             |  18 +-
 .github/workflows/awstest.yml                 |  26 --
 .github/workflows/ci.yml                      |   9 +-
 AAA_BBB.html                                  |   0
 README.md                                     |   6 +-
 conf/modules.config                           |   6 +-
 docs/usage.md                                 |  16 +-
 modules.json                                  | 146 +++------
 modules/local/fusionreport/detect/main.nf     |  12 +-
 modules/nf-core/cat/fastq/environment.yml     |   2 +-
 modules/nf-core/cat/fastq/main.nf             |   4 +-
 .../nf-core/cat/fastq/tests/main.nf.test.snap | 100 +++---
 .../collectinsertsizemetrics/environment.yml  |   2 +-
 .../picard/collectinsertsizemetrics/main.nf   |   4 +-
 .../tests/main.nf.test.snap                   |  14 +-
 .../collectrnaseqmetrics/environment.yml      |   2 +-
 .../picard/collectrnaseqmetrics/main.nf       |   4 +-
 .../collectrnaseqmetrics/tests/main.nf.test   |  81 +++++
 .../tests/main.nf.test.snap                   |  60 ++++
 .../tests/nextflow.config                     |  13 +
 .../picard/collectwgsmetrics/environment.yml  |   4 +-
 .../nf-core/picard/collectwgsmetrics/main.nf  |   4 +-
 .../collectwgsmetrics/tests/main.nf.test.snap |  12 +-
 modules/nf-core/salmon/index/environment.yml  |   2 +-
 modules/nf-core/salmon/index/main.nf          |   4 +-
 .../salmon/index/tests/main.nf.test.snap      |  16 +-
 modules/nf-core/salmon/quant/main.nf          |   3 +-
 modules/nf-core/samtools/sort/main.nf         |  10 +-
 .../nf-core/samtools/sort/tests/main.nf.test  |  64 ++++
 .../samtools/sort/tests/main.nf.test.snap     |  99 +++++-
 modules/nf-core/samtools/view/environment.yml |   2 +
 modules/nf-core/samtools/view/main.nf         |   4 +-
 modules/nf-core/star/align/environment.yml    |   6 +-
 modules/nf-core/star/align/main.nf            |   4 +-
 modules/nf-core/star/align/meta.yml           | 111 ++++---
 modules/nf-core/star/align/tests/main.nf.test |  36 +-
 .../star/align/tests/main.nf.test.snap        | 190 +++--------
 .../star/genomegenerate/environment.yml       |   6 +-
 modules/nf-core/star/genomegenerate/main.nf   |   4 +-
 .../genomegenerate/tests/main.nf.test.snap    |  28 +-
 .../stringtie/stringtie/environment.yml       |   2 +-
 modules/nf-core/stringtie/stringtie/main.nf   |   4 +-
 .../stringtie/tests/main.nf.test.snap         |  64 ++--
 subworkflows/local/arriba_workflow.nf         |   3 +-
 subworkflows/local/build_references.nf        |  46 ++-
 subworkflows/local/fusionreport_workflow.nf   |   2 +-
 test.fusionreport.tsv                         |   0
 test.fusionreport_filtered.tsv                |   0
 test.fusions.csv                              |   0
 test.fusions.json                             |   0
 test_fusionreport_index.html                  |   0
 tests/main.nf.test                            |  22 +-
 workflows/rnafusion.nf                        | 307 ++++++------------
 53 files changed, 785 insertions(+), 799 deletions(-)
 create mode 100644 AAA_BBB.html
 create mode 100644 modules/nf-core/picard/collectrnaseqmetrics/tests/main.nf.test
 create mode 100644 modules/nf-core/picard/collectrnaseqmetrics/tests/main.nf.test.snap
 create mode 100644 modules/nf-core/picard/collectrnaseqmetrics/tests/nextflow.config
 create mode 100644 test.fusionreport.tsv
 create mode 100644 test.fusionreport_filtered.tsv
 create mode 100644 test.fusions.csv
 create mode 100644 test.fusions.json
 create mode 100644 test_fusionreport_index.html

diff --git a/.github/workflows/awsfulltest.yml b/.github/workflows/awsfulltest.yml
index fe30ca56..d1492d8b 100644
--- a/.github/workflows/awsfulltest.yml
+++ b/.github/workflows/awsfulltest.yml
@@ -46,7 +46,6 @@ jobs:
               "cosmic_username": "${{ secrets.cosmic_username }}",
               "cosmic_passwd": "${{ secrets.cosmic_passwd }}",
               "all": true,
-              "build_references": true
             }
           profiles: test_full,aws_tower
       - uses: actions/upload-artifact@v4
@@ -55,19 +54,4 @@ jobs:
           path: |
             seqera_platform_action_*.log
             seqera_platform_action_*.json
-      - name: Launch run workflow via tower
-        uses: seqeralabs/action-tower-launch@v2
-        with:
-          workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }}
-          access_token: ${{ secrets.TOWER_ACCESS_TOKEN }}
-          compute_env: ${{ secrets.TOWER_COMPUTE_ENV }}
-          workdir: s3://${{ secrets.AWS_S3_BUCKET }}/work/rnafusion/work-${{ github.sha }}
-          parameters: |
-            {
-              "outdir": "s3://${{ secrets.AWS_S3_BUCKET }}/rnafusion/results-${{ github.sha }}",
-              "genomes_base": "s3://${{ secrets.AWS_S3_BUCKET }}/rnafusion/results-${{ github.sha }}/references",
-              "cosmic_username": "${{ secrets.cosmic_username }}",
-              "cosmic_passwd": "${{ secrets.cosmic_passwd }}",
-              "all": true,
-            }
-          profiles: test_full,aws_tower
+
diff --git a/.github/workflows/awstest.yml b/.github/workflows/awstest.yml
index 8f6bfb01..78bdb317 100644
--- a/.github/workflows/awstest.yml
+++ b/.github/workflows/awstest.yml
@@ -26,8 +26,6 @@ jobs:
               "cosmic_username": "${{ secrets.cosmic_username }}",
               "cosmic_passwd": "${{ secrets.cosmic_passwd }}",
               "all": true,
-              "stub": true,
-              "build_references": true
             }
           profiles: test,aws_tower
       - uses: actions/upload-artifact@v4
@@ -36,27 +34,3 @@ jobs:
           path: |
             tower_action_*.log
             tower_action_*.json
-
-      - name: Launch workflow via tower
-        uses: seqeralabs/action-tower-launch@v2
-        with:
-          workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }}
-          access_token: ${{ secrets.TOWER_ACCESS_TOKEN }}
-          compute_env: ${{ secrets.TOWER_COMPUTE_ENV }}
-          workdir: s3://${{ secrets.AWS_S3_BUCKET }}/work/rnafusion/work-${{ github.sha }}
-          parameters: |
-            {
-              "outdir": "s3://${{ secrets.AWS_S3_BUCKET }}/rnafusion/results-${{ github.sha }}",
-              "genomes_base": "s3://${{ secrets.AWS_S3_BUCKET }}/rnafusion/results-${{ github.sha }}/references",
-              "cosmic_username": "${{ secrets.cosmic_username }}",
-              "cosmic_passwd": "${{ secrets.cosmic_passwd }}",
-              "all": true,
-              "stub": true
-            }
-          profiles: test,aws_tower
-      - uses: actions/upload-artifact@v4
-        with:
-          name: Seqera Platform debug log file
-          path: |
-            seqera_platform_action_*.log
-            seqera_platform_action_*.json
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index e1028ed8..2a87529d 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -83,16 +83,11 @@ jobs:
       - name: Clean up Disk space
         uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1
 
-      - name: "Run pipeline build with test data ${{ matrix.NXF_VER }} | ${{ matrix.test_name }} | ${{ matrix.profile }}"
+      - name: "Run pipeline with test data ${{ matrix.NXF_VER }} | ${{ matrix.test_name }} | ${{ matrix.profile }}"
         run: |
           nextflow run ${GITHUB_WORKSPACE} -profile ${{ matrix.test_name }},${{ matrix.profile }} \
-          -stub --build_references \
+          -stub \
           --outdir /home/runner/work/rnafusion/rnafusion/results --all \
           --genomes_base /home/runner/work/rnafusion/rnafusion/results/references \
           --cosmic_username ${{ secrets.COSMIC_USERNAME }} --cosmic_passwd ${{ secrets.COSMIC_PASSWD }}
 
-      - name: "Run pipeline with test data ${{ matrix.NXF_VER }} | ${{ matrix.test_name }} | ${{ matrix.profile }}"
-        run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile ${{ matrix.test_name }},${{ matrix.profile }} -stub \
-          --outdir /home/runner/work/rnafusion/rnafusion/results --all ${{ matrix.trim_parameters }} \
-          --genomes_base /home/runner/work/rnafusion/rnafusion/results/references
diff --git a/AAA_BBB.html b/AAA_BBB.html
new file mode 100644
index 00000000..e69de29b
diff --git a/README.md b/README.md
index 41e2bc96..a5210091 100644
--- a/README.md
+++ b/README.md
@@ -31,9 +31,9 @@ In rnafusion the full-sized test includes reference building and fusion detectio
 
 ### Build references
 
-`--build_references` triggers a parallel workflow to build references, which is a prerequisite to running the pipeline:
+`--references_only` triggers a workflow to ONLY build references, otherwise the references are built with the analysis run:
 
-1. Download ensembl fasta and gtf files
+1. Download gencode fasta and gtf files
 2. Create [STAR](https://github.com/alexdobin/STAR) index
 3. Download [Arriba](https://github.com/suhrig/arriba) references
 4. Download [FusionCatcher](https://github.com/ndaniel/fusioncatcher) references
@@ -78,7 +78,7 @@ First, build the references:
 nextflow run nf-core/rnafusion \
    -profile test,<docker/singularity/.../institute> \
    --outdir <OUTDIR>\
-   --build_references \
+   --references_only \
    -stub
 ```
 
diff --git a/conf/modules.config b/conf/modules.config
index 123e02b0..b07f5333 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -46,7 +46,7 @@ process {
     }
 
     withName: 'CAT_FASTQ' {
-        ext.when   = { !params.build_references }
+        ext.when   = { !params.references_only }
     }
 
     withName: 'GENCODE_DOWNLOAD' {
@@ -63,7 +63,7 @@ process {
 
     withName: 'FASTQC' {
         ext.args = '--quiet'
-        ext.when = { !params.skip_qc && !params.build_references }
+        ext.when = { !params.skip_qc && !params.references_only }
         publishDir = [
             path: { "${params.outdir}/fastqc" },
             mode: params.publish_dir_mode,
@@ -367,7 +367,7 @@ process {
     }
 
     withName: 'TRIM_WORKFLOW:*' {
-        ext.when = { !params.build_references }
+        ext.when = { !params.references_only }
     }
 
     withName: 'VCF_COLLECT' {
diff --git a/docs/usage.md b/docs/usage.md
index b7bc6794..86ede4dd 100644
--- a/docs/usage.md
+++ b/docs/usage.md
@@ -10,7 +10,7 @@ The pipeline is divided into two parts:
 
 1. Download and build references
 
-- specified with `--build_references` parameter
+- specified with `--references_only` parameter
 - required only once before running the pipeline
 - **Important**: has to be run with each new release
 
@@ -32,7 +32,7 @@ The rnafusion pipeline needs references for the fusion detection tools, so downl
 ```bash
 nextflow run nf-core/rnafusion \
   -profile <docker/singularity/.../institute> \
-  --build_references --all \
+  --references_only --all \
   --cosmic_username <EMAIL> --cosmic_passwd <PASSWORD> \
   --genomes_base <PATH/TO/REFERENCES> \
   --outdir <PATH/TO/REFERENCES>
@@ -43,7 +43,7 @@ References for each tools can also be downloaded separately with:
 ```bash
 nextflow run nf-core/rnafusion \
   -profile <docker/singularity/.../institute> \
-  --build_references --<tool1> --<tool2> ... \
+  --references_only --<tool1> --<tool2> ... \
   --cosmic_username <EMAIL> --cosmic_passwd <PASSWORD> \
   --genomes_base <PATH/TO/REFERENCES> \
   --outdir <OUTPUT/PATH>
@@ -62,7 +62,7 @@ Use credentials from QIAGEN and add `--qiagen`
 ```bash
 nextflow run nf-core/rnafusion \
   -profile <docker/singularity/.../institute> \
-  --build_references --<tool1> --<tool2> ... \
+  --references_only --<tool1> --<tool2> ... \
   --cosmic_username <EMAIL> --cosmic_passwd <PASSWORD> \
   --genomes_base <PATH/TO/REFERENCES> \
   --outdir <OUTPUT/PATH> --qiagen
@@ -79,7 +79,7 @@ If process `FUSIONREPORT_DOWNLOAD` times out, it could be due to network restric
 ```bash
 nextflow run nf-core/rnafusion  \
   -profile <docker/singularity/.../institute> \
-  --build_references \
+  --references_only \
   --cosmic_username <EMAIL> --cosmic_passwd <PASSWORD> \
   --fusionreport \
   --genomes_base <PATH/TO/REFERENCES> \
@@ -91,7 +91,7 @@ Where the custom configuration could look like (adaptation to local machine nece
 
 ```text
 process {
-  withName:  'NFCORE_RNAFUSION:BUILD_REFERENCES:FUSIONREPORT_DOWNLOAD' {
+  withName:  'NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:FUSIONREPORT_DOWNLOAD' {
     memory = '8.GB'
     cpus = 4
   }
@@ -158,7 +158,7 @@ nextflow run nf-core/rnafusion \
 
 > **IMPORTANT: Either `--all` or `--<tool>`** is necessary to run detection tools
 
-`--genomes_base` should be the path to the directory containing the folder `references/` that was built with `--build_references`.
+`--genomes_base` should be the path to the directory containing the folder `references/` that was built with `--references_only`.
 
 Note that the pipeline will create the following files in your working directory:
 
@@ -393,7 +393,7 @@ If `-profile` is not specified, the pipeline will run locally and expect all sof
 - `test`
   - A profile with a complete configuration for automated testing
   - Includes links to test data so needs no other parameters
-  - Needs to run in two steps: with `--build_references` first and then without `--build_references` to run the analysis
+  - Needs to run in two steps: with `--references_only` first and then without `--references_only` to run the analysis
   - !!!! Run with `-stub` as all references need to be downloaded otherwise !!!!
 
 ### `-resume`
diff --git a/modules.json b/modules.json
index 7e506548..358910d4 100644
--- a/modules.json
+++ b/modules.json
@@ -8,198 +8,142 @@
                     "agat/convertspgff2tsv": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "installed_by": ["modules"]
                     },
                     "arriba/arriba": {
                         "branch": "master",
                         "git_sha": "7741dfc830e77a8ead2fcb50b01461ee09d0cdfe",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "installed_by": ["modules"]
                     },
                     "arriba/download": {
                         "branch": "master",
                         "git_sha": "467c202a876d26af544fa8c4b22a050a535462a7",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "installed_by": ["modules"]
                     },
                     "bedops/convert2bed": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "installed_by": ["modules"]
                     },
                     "cat/cat": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "installed_by": ["modules"]
                     },
                     "cat/fastq": {
                         "branch": "master",
-                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "git_sha": "a1abf90966a2a4016d3c3e41e228bfcbd4811ccc",
+                        "installed_by": ["modules"]
                     },
                     "fastp": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "installed_by": ["modules"]
                     },
                     "fastqc": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "installed_by": ["modules"]
                     },
                     "gatk4/bedtointervallist": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "installed_by": ["modules"]
                     },
                     "gatk4/createsequencedictionary": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "installed_by": ["modules"]
                     },
                     "gatk4/markduplicates": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "installed_by": ["modules"]
                     },
                     "gffread": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "installed_by": ["modules"]
                     },
                     "multiqc": {
                         "branch": "master",
                         "git_sha": "cf17ca47590cc578dfb47db1c2a44ef86f89976d",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "installed_by": ["modules"]
                     },
                     "picard/collectinsertsizemetrics": {
                         "branch": "master",
-                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "git_sha": "49f4e50534fe4b64101e62ea41d5dc43b1324358",
+                        "installed_by": ["modules"]
                     },
                     "picard/collectrnaseqmetrics": {
                         "branch": "master",
-                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "git_sha": "49f4e50534fe4b64101e62ea41d5dc43b1324358",
+                        "installed_by": ["modules"]
                     },
                     "picard/collectwgsmetrics": {
                         "branch": "master",
-                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "git_sha": "49f4e50534fe4b64101e62ea41d5dc43b1324358",
+                        "installed_by": ["modules"]
                     },
                     "rrnatranscripts": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "installed_by": ["modules"]
                     },
                     "salmon/index": {
                         "branch": "master",
-                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "git_sha": "49f4e50534fe4b64101e62ea41d5dc43b1324358",
+                        "installed_by": ["modules"]
                     },
                     "salmon/quant": {
                         "branch": "master",
                         "git_sha": "49f4e50534fe4b64101e62ea41d5dc43b1324358",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "installed_by": ["modules"]
                     },
                     "samtools/faidx": {
                         "branch": "master",
                         "git_sha": "b13f07be4c508d6ff6312d354d09f2493243e208",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "installed_by": ["modules"]
                     },
                     "samtools/index": {
                         "branch": "master",
                         "git_sha": "b13f07be4c508d6ff6312d354d09f2493243e208",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "installed_by": ["modules"]
                     },
                     "samtools/sort": {
                         "branch": "master",
-                        "git_sha": "b13f07be4c508d6ff6312d354d09f2493243e208",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "git_sha": "b7800db9b069ed505db3f9d91b8c72faea9be17b",
+                        "installed_by": ["modules"]
                     },
                     "samtools/view": {
                         "branch": "master",
-                        "git_sha": "b13f07be4c508d6ff6312d354d09f2493243e208",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "git_sha": "669eb24fd82a9d3cb18ad0e73673ecb26827f683",
+                        "installed_by": ["modules"]
                     },
                     "star/align": {
                         "branch": "master",
-                        "git_sha": "30a97c755895b7dfe40a730b0695c554a10f1cdd",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "git_sha": "a5ad53288c79fa52c5ae708c317e09ec2dd149ab",
+                        "installed_by": ["modules"]
                     },
                     "star/genomegenerate": {
                         "branch": "master",
-                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "git_sha": "a5ad53288c79fa52c5ae708c317e09ec2dd149ab",
+                        "installed_by": ["modules"]
                     },
                     "stringtie/merge": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "installed_by": ["modules"]
                     },
                     "stringtie/stringtie": {
                         "branch": "master",
-                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "git_sha": "49f4e50534fe4b64101e62ea41d5dc43b1324358",
+                        "installed_by": ["modules"]
                     },
                     "ucsc/gtftogenepred": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "installed_by": ["modules"]
                     }
                 }
             },
@@ -208,26 +152,20 @@
                     "utils_nextflow_pipeline": {
                         "branch": "master",
                         "git_sha": "3aa0aec1d52d492fe241919f0c6100ebf0074082",
-                        "installed_by": [
-                            "subworkflows"
-                        ]
+                        "installed_by": ["subworkflows"]
                     },
                     "utils_nfcore_pipeline": {
                         "branch": "master",
                         "git_sha": "1b6b9a3338d011367137808b49b923515080e3ba",
-                        "installed_by": [
-                            "subworkflows"
-                        ]
+                        "installed_by": ["subworkflows"]
                     },
                     "utils_nfschema_plugin": {
                         "branch": "master",
                         "git_sha": "bbd5a41f4535a8defafe6080e00ea74c45f4f96c",
-                        "installed_by": [
-                            "subworkflows"
-                        ]
+                        "installed_by": ["subworkflows"]
                     }
                 }
             }
         }
     }
-}
\ No newline at end of file
+}
diff --git a/modules/local/fusionreport/detect/main.nf b/modules/local/fusionreport/detect/main.nf
index 8024d8f8..f2557bf0 100644
--- a/modules/local/fusionreport/detect/main.nf
+++ b/modules/local/fusionreport/detect/main.nf
@@ -8,17 +8,17 @@ process FUSIONREPORT {
 
     input:
     tuple val(meta), path(reads), path(arriba_fusions), path(starfusion_fusions),  path(fusioncatcher_fusions)
-    tuple val(meta2), path(fusionreport_ref)
+    path(fusionreport_ref)
     val(tools_cutoff)
 
     output:
-    path "versions.yml"                                                 , emit: versions
     tuple val(meta), path("*fusionreport.tsv")                          , emit: fusion_list
     tuple val(meta), path("*fusionreport_filtered.tsv")                 , emit: fusion_list_filtered
-    tuple val(meta), path("*index.html")                                 , emit: report
+    tuple val(meta), path("*index.html")                                , emit: report
     tuple val(meta), path("*_*.html")                    , optional:true, emit: html
     tuple val(meta), path("*.csv")                       , optional:true, emit: csv
     tuple val(meta), path("*.json")                      , optional:true, emit: json
+    path "versions.yml"                                                 , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
@@ -58,7 +58,11 @@ process FUSIONREPORT {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        fusion_report: \$(fusion_report --version | sed 's/fusion-report //')
+        fusion_report: sth
     END_VERSIONS
     """
 }
+    // cat <<-END_VERSIONS > versions.yml
+    // "${task.process}":
+    //     fusion_report: \$(fusion_report --version 2>&1 | sed 's/fusion-report //')
+    // END_VERSIONS
diff --git a/modules/nf-core/cat/fastq/environment.yml b/modules/nf-core/cat/fastq/environment.yml
index c7eb9bd1..71e04c3d 100644
--- a/modules/nf-core/cat/fastq/environment.yml
+++ b/modules/nf-core/cat/fastq/environment.yml
@@ -2,4 +2,4 @@ channels:
   - conda-forge
   - bioconda
 dependencies:
-  - conda-forge::coreutils=8.30
+  - conda-forge::coreutils=9.5
diff --git a/modules/nf-core/cat/fastq/main.nf b/modules/nf-core/cat/fastq/main.nf
index b68e5f91..4364a389 100644
--- a/modules/nf-core/cat/fastq/main.nf
+++ b/modules/nf-core/cat/fastq/main.nf
@@ -4,8 +4,8 @@ process CAT_FASTQ {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/ubuntu:20.04' :
-        'nf-core/ubuntu:20.04' }"
+        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/c2/c262fc09eca59edb5a724080eeceb00fb06396f510aefb229c2d2c6897e63975/data' :
+        'community.wave.seqera.io/library/coreutils:9.5--ae99c88a9b28c264' }"
 
     input:
     tuple val(meta), path(reads, stageAs: "input*/*")
diff --git a/modules/nf-core/cat/fastq/tests/main.nf.test.snap b/modules/nf-core/cat/fastq/tests/main.nf.test.snap
index aec119a9..f8689a1c 100644
--- a/modules/nf-core/cat/fastq/tests/main.nf.test.snap
+++ b/modules/nf-core/cat/fastq/tests/main.nf.test.snap
@@ -12,7 +12,7 @@
                     ]
                 ],
                 "1": [
-                    "versions.yml:md5,d42d6e24d67004608495883e00bd501b"
+                    "versions.yml:md5,6ef4fd28546a005865b9454bbedbf81a"
                 ],
                 "reads": [
                     [
@@ -24,15 +24,15 @@
                     ]
                 ],
                 "versions": [
-                    "versions.yml:md5,d42d6e24d67004608495883e00bd501b"
+                    "versions.yml:md5,6ef4fd28546a005865b9454bbedbf81a"
                 ]
             }
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "24.04.2"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-01-17T17:30:39.816981"
+        "timestamp": "2024-10-19T20:02:07.519211144"
     },
     "test_cat_fastq_single_end_same_name": {
         "content": [
@@ -47,7 +47,7 @@
                     ]
                 ],
                 "1": [
-                    "versions.yml:md5,d42d6e24d67004608495883e00bd501b"
+                    "versions.yml:md5,6ef4fd28546a005865b9454bbedbf81a"
                 ],
                 "reads": [
                     [
@@ -59,15 +59,15 @@
                     ]
                 ],
                 "versions": [
-                    "versions.yml:md5,d42d6e24d67004608495883e00bd501b"
+                    "versions.yml:md5,6ef4fd28546a005865b9454bbedbf81a"
                 ]
             }
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "24.04.2"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-01-17T17:32:35.229332"
+        "timestamp": "2024-10-19T20:02:31.618628921"
     },
     "test_cat_fastq_single_end_single_file": {
         "content": [
@@ -82,7 +82,7 @@
                     ]
                 ],
                 "1": [
-                    "versions.yml:md5,d42d6e24d67004608495883e00bd501b"
+                    "versions.yml:md5,6ef4fd28546a005865b9454bbedbf81a"
                 ],
                 "reads": [
                     [
@@ -94,15 +94,15 @@
                     ]
                 ],
                 "versions": [
-                    "versions.yml:md5,d42d6e24d67004608495883e00bd501b"
+                    "versions.yml:md5,6ef4fd28546a005865b9454bbedbf81a"
                 ]
             }
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "24.04.2"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-01-17T17:34:00.058829"
+        "timestamp": "2024-10-19T20:02:57.904149581"
     },
     "test_cat_fastq_paired_end_same_name": {
         "content": [
@@ -120,7 +120,7 @@
                     ]
                 ],
                 "1": [
-                    "versions.yml:md5,d42d6e24d67004608495883e00bd501b"
+                    "versions.yml:md5,6ef4fd28546a005865b9454bbedbf81a"
                 ],
                 "reads": [
                     [
@@ -135,15 +135,15 @@
                     ]
                 ],
                 "versions": [
-                    "versions.yml:md5,d42d6e24d67004608495883e00bd501b"
+                    "versions.yml:md5,6ef4fd28546a005865b9454bbedbf81a"
                 ]
             }
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "24.04.2"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-01-17T17:33:33.031555"
+        "timestamp": "2024-10-19T20:02:44.577183829"
     },
     "test_cat_fastq_single_end - stub": {
         "content": [
@@ -158,7 +158,7 @@
                     ]
                 ],
                 "1": [
-                    "versions.yml:md5,d42d6e24d67004608495883e00bd501b"
+                    "versions.yml:md5,6ef4fd28546a005865b9454bbedbf81a"
                 ],
                 "reads": [
                     [
@@ -170,15 +170,15 @@
                     ]
                 ],
                 "versions": [
-                    "versions.yml:md5,d42d6e24d67004608495883e00bd501b"
+                    "versions.yml:md5,6ef4fd28546a005865b9454bbedbf81a"
                 ]
             }
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "24.04.2"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-07-05T12:07:28.244999"
+        "timestamp": "2024-10-19T20:03:10.603734777"
     },
     "test_cat_fastq_paired_end_same_name - stub": {
         "content": [
@@ -196,7 +196,7 @@
                     ]
                 ],
                 "1": [
-                    "versions.yml:md5,d42d6e24d67004608495883e00bd501b"
+                    "versions.yml:md5,6ef4fd28546a005865b9454bbedbf81a"
                 ],
                 "reads": [
                     [
@@ -211,15 +211,15 @@
                     ]
                 ],
                 "versions": [
-                    "versions.yml:md5,d42d6e24d67004608495883e00bd501b"
+                    "versions.yml:md5,6ef4fd28546a005865b9454bbedbf81a"
                 ]
             }
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "24.04.2"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-07-05T12:07:57.070911"
+        "timestamp": "2024-10-19T20:03:46.041808828"
     },
     "test_cat_fastq_single_end_same_name - stub": {
         "content": [
@@ -234,7 +234,7 @@
                     ]
                 ],
                 "1": [
-                    "versions.yml:md5,d42d6e24d67004608495883e00bd501b"
+                    "versions.yml:md5,6ef4fd28546a005865b9454bbedbf81a"
                 ],
                 "reads": [
                     [
@@ -246,15 +246,15 @@
                     ]
                 ],
                 "versions": [
-                    "versions.yml:md5,d42d6e24d67004608495883e00bd501b"
+                    "versions.yml:md5,6ef4fd28546a005865b9454bbedbf81a"
                 ]
             }
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "24.04.2"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-07-05T12:07:46.796254"
+        "timestamp": "2024-10-19T20:03:34.13865402"
     },
     "test_cat_fastq_paired_end": {
         "content": [
@@ -272,7 +272,7 @@
                     ]
                 ],
                 "1": [
-                    "versions.yml:md5,d42d6e24d67004608495883e00bd501b"
+                    "versions.yml:md5,6ef4fd28546a005865b9454bbedbf81a"
                 ],
                 "reads": [
                     [
@@ -287,15 +287,15 @@
                     ]
                 ],
                 "versions": [
-                    "versions.yml:md5,d42d6e24d67004608495883e00bd501b"
+                    "versions.yml:md5,6ef4fd28546a005865b9454bbedbf81a"
                 ]
             }
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "24.04.2"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-01-17T17:32:02.270935"
+        "timestamp": "2024-10-19T20:02:19.64383573"
     },
     "test_cat_fastq_paired_end - stub": {
         "content": [
@@ -313,7 +313,7 @@
                     ]
                 ],
                 "1": [
-                    "versions.yml:md5,d42d6e24d67004608495883e00bd501b"
+                    "versions.yml:md5,6ef4fd28546a005865b9454bbedbf81a"
                 ],
                 "reads": [
                     [
@@ -328,15 +328,15 @@
                     ]
                 ],
                 "versions": [
-                    "versions.yml:md5,d42d6e24d67004608495883e00bd501b"
+                    "versions.yml:md5,6ef4fd28546a005865b9454bbedbf81a"
                 ]
             }
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "24.04.2"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-07-05T12:07:37.807553"
+        "timestamp": "2024-10-19T20:03:22.597246066"
     },
     "test_cat_fastq_single_end_single_file - stub": {
         "content": [
@@ -351,7 +351,7 @@
                     ]
                 ],
                 "1": [
-                    "versions.yml:md5,d42d6e24d67004608495883e00bd501b"
+                    "versions.yml:md5,6ef4fd28546a005865b9454bbedbf81a"
                 ],
                 "reads": [
                     [
@@ -363,14 +363,14 @@
                     ]
                 ],
                 "versions": [
-                    "versions.yml:md5,d42d6e24d67004608495883e00bd501b"
+                    "versions.yml:md5,6ef4fd28546a005865b9454bbedbf81a"
                 ]
             }
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "24.04.2"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-07-05T12:14:51.861264"
+        "timestamp": "2024-10-19T20:03:58.44849001"
     }
 }
\ No newline at end of file
diff --git a/modules/nf-core/picard/collectinsertsizemetrics/environment.yml b/modules/nf-core/picard/collectinsertsizemetrics/environment.yml
index ff4a85ed..1d715d56 100644
--- a/modules/nf-core/picard/collectinsertsizemetrics/environment.yml
+++ b/modules/nf-core/picard/collectinsertsizemetrics/environment.yml
@@ -2,4 +2,4 @@ channels:
   - conda-forge
   - bioconda
 dependencies:
-  - bioconda::picard=3.2.0
+  - bioconda::picard=3.3.0
diff --git a/modules/nf-core/picard/collectinsertsizemetrics/main.nf b/modules/nf-core/picard/collectinsertsizemetrics/main.nf
index 1a49a7f0..c3014d80 100644
--- a/modules/nf-core/picard/collectinsertsizemetrics/main.nf
+++ b/modules/nf-core/picard/collectinsertsizemetrics/main.nf
@@ -4,8 +4,8 @@ process PICARD_COLLECTINSERTSIZEMETRICS {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/picard:3.2.0--hdfd78af_0' :
-        'biocontainers/picard:3.2.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/picard:3.3.0--hdfd78af_0' :
+        'biocontainers/picard:3.3.0--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(bam)
diff --git a/modules/nf-core/picard/collectinsertsizemetrics/tests/main.nf.test.snap b/modules/nf-core/picard/collectinsertsizemetrics/tests/main.nf.test.snap
index bcb5b455..cbe9329d 100644
--- a/modules/nf-core/picard/collectinsertsizemetrics/tests/main.nf.test.snap
+++ b/modules/nf-core/picard/collectinsertsizemetrics/tests/main.nf.test.snap
@@ -9,14 +9,14 @@
             ],
             "test.pdf",
             [
-                "versions.yml:md5,4423bfe2194f61d919c382d2225b0835"
+                "versions.yml:md5,38d39e9882afe7ac015213c286745056"
             ]
         ],
         "meta": {
-            "nf-test": "0.8.4",
+            "nf-test": "0.9.0",
             "nextflow": "24.04.4"
         },
-        "timestamp": "2024-08-30T12:23:29.392944"
+        "timestamp": "2024-10-18T10:55:45.769771444"
     },
     "test-picard-collectinsertsizemetrics-stub": {
         "content": [
@@ -40,7 +40,7 @@
                     ]
                 ],
                 "2": [
-                    "versions.yml:md5,4423bfe2194f61d919c382d2225b0835"
+                    "versions.yml:md5,38d39e9882afe7ac015213c286745056"
                 ],
                 "histogram": [
                     [
@@ -61,14 +61,14 @@
                     ]
                 ],
                 "versions": [
-                    "versions.yml:md5,4423bfe2194f61d919c382d2225b0835"
+                    "versions.yml:md5,38d39e9882afe7ac015213c286745056"
                 ]
             }
         ],
         "meta": {
-            "nf-test": "0.8.4",
+            "nf-test": "0.9.0",
             "nextflow": "24.04.4"
         },
-        "timestamp": "2024-08-30T12:20:03.841884"
+        "timestamp": "2024-10-18T10:56:09.914953495"
     }
 }
\ No newline at end of file
diff --git a/modules/nf-core/picard/collectrnaseqmetrics/environment.yml b/modules/nf-core/picard/collectrnaseqmetrics/environment.yml
index ff4a85ed..1d715d56 100644
--- a/modules/nf-core/picard/collectrnaseqmetrics/environment.yml
+++ b/modules/nf-core/picard/collectrnaseqmetrics/environment.yml
@@ -2,4 +2,4 @@ channels:
   - conda-forge
   - bioconda
 dependencies:
-  - bioconda::picard=3.2.0
+  - bioconda::picard=3.3.0
diff --git a/modules/nf-core/picard/collectrnaseqmetrics/main.nf b/modules/nf-core/picard/collectrnaseqmetrics/main.nf
index 0c8f2cfa..eb80fdc7 100644
--- a/modules/nf-core/picard/collectrnaseqmetrics/main.nf
+++ b/modules/nf-core/picard/collectrnaseqmetrics/main.nf
@@ -4,8 +4,8 @@ process PICARD_COLLECTRNASEQMETRICS {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/picard:3.2.0--hdfd78af_0' :
-        'biocontainers/picard:3.2.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/picard:3.3.0--hdfd78af_0' :
+        'biocontainers/picard:3.3.0--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(bam)
diff --git a/modules/nf-core/picard/collectrnaseqmetrics/tests/main.nf.test b/modules/nf-core/picard/collectrnaseqmetrics/tests/main.nf.test
new file mode 100644
index 00000000..9ab18552
--- /dev/null
+++ b/modules/nf-core/picard/collectrnaseqmetrics/tests/main.nf.test
@@ -0,0 +1,81 @@
+nextflow_process {
+
+    name "Test Process PICARD_COLLECTRNASEQMETRICS"
+    script "../main.nf"
+    process "PICARD_COLLECTRNASEQMETRICS"
+    config "./nextflow.config"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "picard"
+    tag "picard/collectrnaseqmetrics"
+    tag "ucsc/gtftogenepred"
+
+    setup {
+        run("UCSC_GTFTOGENEPRED") {
+            script "../../../ucsc/gtftogenepred/main.nf"
+            process {
+                """
+                input[0] = Channel.of([
+                    [ id:'test' ],
+                    [ file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.gtf', checkIfExists: true) ]
+                ])
+                """
+            }
+        }
+    }
+
+    test("sarscov2 - fasta - gtf") {
+        
+        when {
+            process {
+                """
+                input[0] = [
+        	    [ id:'test', single_end:false, strandedness:'forward' ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/bam/test.paired_end.sorted.bam', checkIfExists: true)
+                ]
+                input[1] = UCSC_GTFTOGENEPRED.out.refflat.map{ it[1] }
+                input[2] = file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
+                input[3] = []
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert file(process.out.metrics[0][1]).text.contains('CollectRnaSeqMetrics') },
+                { assert snapshot(
+                    process.out.versions,
+                    process.out.pdf
+                ).match() }
+            )
+        }
+    }
+    
+    test("sarscov2 - fasta - gtf - stub") {
+        
+        options "-stub"
+        
+        when {
+            process {
+                """
+                input[0] = [
+        	    [ id:'test', single_end:false, strandedness:'forward' ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/bam/test.paired_end.sorted.bam', checkIfExists: true)
+                ]
+                input[1] = UCSC_GTFTOGENEPRED.out.refflat.map{ it[1] }
+                input[2] = file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
+                input[3] = []
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+}
diff --git a/modules/nf-core/picard/collectrnaseqmetrics/tests/main.nf.test.snap b/modules/nf-core/picard/collectrnaseqmetrics/tests/main.nf.test.snap
new file mode 100644
index 00000000..ad6503af
--- /dev/null
+++ b/modules/nf-core/picard/collectrnaseqmetrics/tests/main.nf.test.snap
@@ -0,0 +1,60 @@
+{
+    "sarscov2 - fasta - gtf": {
+        "content": [
+            [
+                "versions.yml:md5,8d0867f89947c081711de09338138c2e"
+            ],
+            [
+                
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-10-18T16:10:39.199344417"
+    },
+    "sarscov2 - fasta - gtf - stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false,
+                            "strandedness": "forward"
+                        },
+                        "test.rna_metrics:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "1": [
+                    
+                ],
+                "2": [
+                    "versions.yml:md5,8d0867f89947c081711de09338138c2e"
+                ],
+                "metrics": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false,
+                            "strandedness": "forward"
+                        },
+                        "test.rna_metrics:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "pdf": [
+                    
+                ],
+                "versions": [
+                    "versions.yml:md5,8d0867f89947c081711de09338138c2e"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-10-18T16:10:57.248132065"
+    }
+}
\ No newline at end of file
diff --git a/modules/nf-core/picard/collectrnaseqmetrics/tests/nextflow.config b/modules/nf-core/picard/collectrnaseqmetrics/tests/nextflow.config
new file mode 100644
index 00000000..bc82e10c
--- /dev/null
+++ b/modules/nf-core/picard/collectrnaseqmetrics/tests/nextflow.config
@@ -0,0 +1,13 @@
+process {
+    withName:UCSC_GTFTOGENEPRED {
+        ext.args = "-genePredExt -geneNameAsName2 -ignoreGroupsWithoutExons"
+    }
+    withName:PICARD_COLLECTRNASEQMETRICS {
+        ext.args = { ( meta.strandedness == "forward" || meta.single_end ) ?
+            "--STRAND_SPECIFICITY FIRST_READ_TRANSCRIPTION_STRAND" :
+        meta.strandedness == "reverse" ?
+        "--STRAND_SPECIFICITY SECOND_READ_TRANSCRIPTION_STRAND" :
+        "--STRAND_SPECIFICITY NONE"
+    }
+    }
+}
diff --git a/modules/nf-core/picard/collectwgsmetrics/environment.yml b/modules/nf-core/picard/collectwgsmetrics/environment.yml
index 58d52581..13265842 100644
--- a/modules/nf-core/picard/collectwgsmetrics/environment.yml
+++ b/modules/nf-core/picard/collectwgsmetrics/environment.yml
@@ -2,5 +2,5 @@ channels:
   - conda-forge
   - bioconda
 dependencies:
-  - bioconda::picard=3.2.0
-  - r::r-base
+  - bioconda::picard=3.3.0
+  - conda-forge::r-base=4.4.1
diff --git a/modules/nf-core/picard/collectwgsmetrics/main.nf b/modules/nf-core/picard/collectwgsmetrics/main.nf
index 6002a7ca..39cf7d2b 100644
--- a/modules/nf-core/picard/collectwgsmetrics/main.nf
+++ b/modules/nf-core/picard/collectwgsmetrics/main.nf
@@ -4,8 +4,8 @@ process PICARD_COLLECTWGSMETRICS {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/picard:3.2.0--hdfd78af_0' :
-        'biocontainers/picard:3.2.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/picard:3.3.0--hdfd78af_0' :
+        'biocontainers/picard:3.3.0--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(bam), path(bai)
diff --git a/modules/nf-core/picard/collectwgsmetrics/tests/main.nf.test.snap b/modules/nf-core/picard/collectwgsmetrics/tests/main.nf.test.snap
index f188382b..1958fcde 100644
--- a/modules/nf-core/picard/collectwgsmetrics/tests/main.nf.test.snap
+++ b/modules/nf-core/picard/collectwgsmetrics/tests/main.nf.test.snap
@@ -3,26 +3,26 @@
         "content": [
             true,
             [
-                "versions.yml:md5,06b5898fb06823b736c90e1dcebe75fe"
+                "versions.yml:md5,9927db69fdd55176be5cdbd427d000c2"
             ]
         ],
         "meta": {
-            "nf-test": "0.8.4",
+            "nf-test": "0.9.0",
             "nextflow": "24.04.4"
         },
-        "timestamp": "2024-08-23T11:02:46.301176"
+        "timestamp": "2024-10-18T10:15:18.13771243"
     },
     "test-picard-collectwgsmetrics": {
         "content": [
             true,
             [
-                "versions.yml:md5,06b5898fb06823b736c90e1dcebe75fe"
+                "versions.yml:md5,9927db69fdd55176be5cdbd427d000c2"
             ]
         ],
         "meta": {
-            "nf-test": "0.8.4",
+            "nf-test": "0.9.0",
             "nextflow": "24.04.4"
         },
-        "timestamp": "2024-08-23T11:02:25.132069"
+        "timestamp": "2024-10-18T10:14:57.786056996"
     }
 }
\ No newline at end of file
diff --git a/modules/nf-core/salmon/index/environment.yml b/modules/nf-core/salmon/index/environment.yml
index 471164fa..b3f75777 100644
--- a/modules/nf-core/salmon/index/environment.yml
+++ b/modules/nf-core/salmon/index/environment.yml
@@ -2,4 +2,4 @@ channels:
   - conda-forge
   - bioconda
 dependencies:
-  - bioconda::salmon=1.10.1
+  - bioconda::salmon=1.10.3
diff --git a/modules/nf-core/salmon/index/main.nf b/modules/nf-core/salmon/index/main.nf
index e755d9a3..3d653c0d 100644
--- a/modules/nf-core/salmon/index/main.nf
+++ b/modules/nf-core/salmon/index/main.nf
@@ -4,8 +4,8 @@ process SALMON_INDEX {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/salmon:1.10.1--h7e5ed60_0' :
-        'biocontainers/salmon:1.10.1--h7e5ed60_0' }"
+        'https://depot.galaxyproject.org/singularity/salmon:1.10.3--h6dccd9a_2' :
+        'biocontainers/salmon:1.10.3--h6dccd9a_2' }"
 
     input:
     path genome_fasta
diff --git a/modules/nf-core/salmon/index/tests/main.nf.test.snap b/modules/nf-core/salmon/index/tests/main.nf.test.snap
index 703e455c..e5899b51 100644
--- a/modules/nf-core/salmon/index/tests/main.nf.test.snap
+++ b/modules/nf-core/salmon/index/tests/main.nf.test.snap
@@ -2,25 +2,25 @@
     "versions": {
         "content": [
             [
-                "versions.yml:md5,563eeafb4577be0b13801d7021c0bf42"
+                "versions.yml:md5,85337fa0a286ea35073ee5260974e307"
             ]
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2023-11-22T14:26:33.32036"
+        "timestamp": "2024-10-18T10:00:47.087293189"
     },
     "versions stub": {
         "content": [
             [
-                "versions.yml:md5,563eeafb4577be0b13801d7021c0bf42"
+                "versions.yml:md5,85337fa0a286ea35073ee5260974e307"
             ]
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-04-23T09:47:58.828124"
+        "timestamp": "2024-10-18T10:01:03.89824494"
     }
 }
\ No newline at end of file
diff --git a/modules/nf-core/salmon/quant/main.nf b/modules/nf-core/salmon/quant/main.nf
index f1e3b5cd..e2d27352 100644
--- a/modules/nf-core/salmon/quant/main.nf
+++ b/modules/nf-core/salmon/quant/main.nf
@@ -29,7 +29,8 @@ process SALMON_QUANT {
     prefix   = task.ext.prefix ?: "${meta.id}"
 
     def reference   = "--index $index"
-    def reads1 = [], reads2 = []
+    def reads1 = []
+    def reads2 = []
     meta.single_end ? [reads].flatten().each{reads1 << it} : reads.eachWithIndex{ v, ix -> ( ix & 1 ? reads2 : reads1) << v }
     def input_reads = meta.single_end ? "-r ${reads1.join(" ")}" : "-1 ${reads1.join(" ")} -2 ${reads2.join(" ")}"
     if (alignment_mode) {
diff --git a/modules/nf-core/samtools/sort/main.nf b/modules/nf-core/samtools/sort/main.nf
index acfd9252..caf3c61a 100644
--- a/modules/nf-core/samtools/sort/main.nf
+++ b/modules/nf-core/samtools/sort/main.nf
@@ -12,11 +12,11 @@ process SAMTOOLS_SORT {
     tuple val(meta2), path(fasta)
 
     output:
-    tuple val(meta), path("*.bam"),     emit: bam,  optional: true
-    tuple val(meta), path("*.cram"),    emit: cram, optional: true
-    tuple val(meta), path("*.crai"),    emit: crai, optional: true
-    tuple val(meta), path("*.csi"),     emit: csi,  optional: true
-    path  "versions.yml"          , emit: versions
+    tuple val(meta), path("*.bam"),  emit: bam,  optional: true
+    tuple val(meta), path("*.cram"), emit: cram, optional: true
+    tuple val(meta), path("*.crai"), emit: crai, optional: true
+    tuple val(meta), path("*.csi"),  emit: csi,  optional: true
+    path  "versions.yml",            emit: versions
 
     when:
     task.ext.when == null || task.ext.when
diff --git a/modules/nf-core/samtools/sort/tests/main.nf.test b/modules/nf-core/samtools/sort/tests/main.nf.test
index c2ea9c72..b05e6691 100644
--- a/modules/nf-core/samtools/sort/tests/main.nf.test
+++ b/modules/nf-core/samtools/sort/tests/main.nf.test
@@ -39,6 +39,40 @@ nextflow_process {
         }
     }
 
+    test("multiple bam") {
+
+        config "./nextflow.config"
+
+        when {
+            process {
+                """
+                input[0] = Channel.of([
+                    [ id:'test', single_end:false ], // meta map
+                    [
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/test.paired_end.sorted.bam', checkIfExists: true),
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/test2.paired_end.sorted.bam', checkIfExists: true)
+                    ]
+                ])
+                input[1] = Channel.of([
+                    [ id:'fasta' ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta', checkIfExists: true)
+                ])
+                """
+            }
+        }
+
+        then {
+            assertAll (
+                { assert process.success },
+                { assert snapshot(
+                        process.out.bam,
+                        process.out.csi.collect { it.collect { it instanceof Map ? it : file(it).name } },
+                        process.out.versions
+                ).match()}
+            )
+        }
+    }
+
     test("cram") {
 
         config "./nextflow_cram.config"
@@ -98,6 +132,36 @@ nextflow_process {
         }
     }
 
+    test("multiple bam - stub") {
+
+        config "./nextflow.config"
+
+        when {
+            process {
+                """
+                input[0] = Channel.of([
+                    [ id:'test', single_end:false ], // meta map
+                    [
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/test.paired_end.sorted.bam', checkIfExists: true),
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/test2.paired_end.sorted.bam', checkIfExists: true)
+                    ]
+                ])
+                input[1] = Channel.of([
+                    [ id:'fasta' ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta', checkIfExists: true)
+                ])
+                """
+            }
+        }
+
+        then {
+            assertAll (
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
     test("cram - stub") {
 
         options "-stub"
diff --git a/modules/nf-core/samtools/sort/tests/main.nf.test.snap b/modules/nf-core/samtools/sort/tests/main.nf.test.snap
index 2d6b2900..469891fe 100644
--- a/modules/nf-core/samtools/sort/tests/main.nf.test.snap
+++ b/modules/nf-core/samtools/sort/tests/main.nf.test.snap
@@ -159,6 +159,101 @@
         },
         "timestamp": "2024-09-16T08:50:19.061912443"
     },
+    "multiple bam": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test",
+                        "single_end": false
+                    },
+                    "test.sorted.bam:md5,8a16ba90c7d294cbb4c33ac0f7127a12"
+                ]
+            ],
+            [
+                [
+                    {
+                        "id": "test",
+                        "single_end": false
+                    },
+                    "test.sorted.bam.csi"
+                ]
+            ],
+            [
+                "versions.yml:md5,2659b187d681241451539d4c53500b9f"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.09.0"
+        },
+        "timestamp": "2024-10-08T11:59:55.479443"
+    },
+    "multiple bam - stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.sorted.bam:md5,8a16ba90c7d294cbb4c33ac0f7127a12"
+                    ]
+                ],
+                "1": [
+                    
+                ],
+                "2": [
+                    
+                ],
+                "3": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.sorted.bam.csi:md5,d185916eaff9afeb4d0aeab3310371f9"
+                    ]
+                ],
+                "4": [
+                    "versions.yml:md5,2659b187d681241451539d4c53500b9f"
+                ],
+                "bam": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.sorted.bam:md5,8a16ba90c7d294cbb4c33ac0f7127a12"
+                    ]
+                ],
+                "crai": [
+                    
+                ],
+                "cram": [
+                    
+                ],
+                "csi": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.sorted.bam.csi:md5,d185916eaff9afeb4d0aeab3310371f9"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,2659b187d681241451539d4c53500b9f"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.09.0"
+        },
+        "timestamp": "2024-10-08T11:36:13.781404"
+    },
     "bam": {
         "content": [
             [
@@ -185,8 +280,8 @@
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.04.4"
+            "nextflow": "24.09.0"
         },
-        "timestamp": "2024-09-16T08:49:43.971158333"
+        "timestamp": "2024-10-08T11:59:46.372244"
     }
 }
\ No newline at end of file
diff --git a/modules/nf-core/samtools/view/environment.yml b/modules/nf-core/samtools/view/environment.yml
index 62054fc9..02cda6e6 100644
--- a/modules/nf-core/samtools/view/environment.yml
+++ b/modules/nf-core/samtools/view/environment.yml
@@ -4,5 +4,7 @@ channels:
   - conda-forge
   - bioconda
 dependencies:
+  # renovate: datasource=conda depName=bioconda/htslib
   - bioconda::htslib=1.21
+  # renovate: datasource=conda depName=bioconda/samtools
   - bioconda::samtools=1.21
diff --git a/modules/nf-core/samtools/view/main.nf b/modules/nf-core/samtools/view/main.nf
index 37e05cec..41fa3d6a 100644
--- a/modules/nf-core/samtools/view/main.nf
+++ b/modules/nf-core/samtools/view/main.nf
@@ -4,8 +4,8 @@ process SAMTOOLS_VIEW {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/samtools:1.21--h50ea8bc_0' :
-        'biocontainers/samtools:1.21--h50ea8bc_0' }"
+        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/9e/9edc2564215d5cd137a8b25ca8a311600987186d406b092022444adf3c4447f7/data' :
+        'community​.wave​.seqera​.io/library/htslib_samtools:1​.21--6cb89bfd40cbaabf' }"
 
     input:
     tuple val(meta), path(input), path(index)
diff --git a/modules/nf-core/star/align/environment.yml b/modules/nf-core/star/align/environment.yml
index 1debc4c9..7c57530a 100644
--- a/modules/nf-core/star/align/environment.yml
+++ b/modules/nf-core/star/align/environment.yml
@@ -3,7 +3,7 @@ channels:
   - bioconda
 
 dependencies:
-  - bioconda::htslib=1.18
-  - bioconda::samtools=1.18
-  - bioconda::star=2.7.10a
+  - bioconda::htslib=1.20
+  - bioconda::samtools=1.20
+  - bioconda::star=2.7.11b
   - conda-forge::gawk=5.1.0
diff --git a/modules/nf-core/star/align/main.nf b/modules/nf-core/star/align/main.nf
index b5bc9ddf..417071ba 100644
--- a/modules/nf-core/star/align/main.nf
+++ b/modules/nf-core/star/align/main.nf
@@ -4,8 +4,8 @@ process STAR_ALIGN {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:ded3841da0194af2701c780e9b3d653a85d27489-0' :
-        'biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:ded3841da0194af2701c780e9b3d653a85d27489-0' }"
+        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/b4/b425bc2a95806d878993f9a66dae3ae80ac2dafff4c208c5ae01b7a90a32fa91/data' :
+        'community.wave.seqera.io/library/star_samtools_htslib_gawk:10c6e8c834460019' }"
 
     input:
     tuple val(meta), path(reads, stageAs: "input*/*")
diff --git a/modules/nf-core/star/align/meta.yml b/modules/nf-core/star/align/meta.yml
index d9cba2aa..5cfe763e 100644
--- a/modules/nf-core/star/align/meta.yml
+++ b/modules/nf-core/star/align/meta.yml
@@ -56,27 +56,30 @@ input:
 output:
   - log_final:
       - meta:
-          type: file
-          description: STAR final log file
-          pattern: "*Log.final.out"
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
       - "*Log.final.out":
           type: file
           description: STAR final log file
           pattern: "*Log.final.out"
   - log_out:
       - meta:
-          type: file
-          description: STAR lot out file
-          pattern: "*Log.out"
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
       - "*Log.out":
           type: file
           description: STAR lot out file
           pattern: "*Log.out"
   - log_progress:
       - meta:
-          type: file
-          description: STAR log progress file
-          pattern: "*Log.progress.out"
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
       - "*Log.progress.out":
           type: file
           description: STAR log progress file
@@ -88,57 +91,70 @@ output:
           pattern: "versions.yml"
   - bam:
       - meta:
-          type: file
-          description: Output BAM file containing read alignments
-          pattern: "*.{bam}"
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
       - "*d.out.bam":
           type: file
           description: Output BAM file containing read alignments
           pattern: "*.{bam}"
   - bam_sorted:
       - meta:
-          type: file
-          description: Sorted BAM file of read alignments (optional)
-          pattern: "*sortedByCoord.out.bam"
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
       - ${prefix}.sortedByCoord.out.bam:
           type: file
           description: Sorted BAM file of read alignments (optional)
           pattern: "*sortedByCoord.out.bam"
   - bam_sorted_aligned:
-      - meta: {}
-      - ${prefix}.Aligned.sortedByCoord.out.bam: {}
-  - bam_transcript:
       - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - ${prefix}.Aligned.sortedByCoord.out.bam:
           type: file
-          description: Output BAM file of transcriptome alignment (optional)
-          pattern: "*toTranscriptome.out.bam"
+          description: Sorted BAM file of read alignments (optional)
+          pattern: "*.Aligned.sortedByCoord.out.bam"
+  - bam_transcript:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
       - "*toTranscriptome.out.bam":
           type: file
           description: Output BAM file of transcriptome alignment (optional)
           pattern: "*toTranscriptome.out.bam"
   - bam_unsorted:
       - meta:
-          type: file
-          description: Unsorted BAM file of read alignments (optional)
-          pattern: "*Aligned.unsort.out.bam"
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
       - "*Aligned.unsort.out.bam":
           type: file
           description: Unsorted BAM file of read alignments (optional)
           pattern: "*Aligned.unsort.out.bam"
   - fastq:
       - meta:
-          type: file
-          description: Unmapped FastQ files (optional)
-          pattern: "*fastq.gz"
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
       - "*fastq.gz":
           type: file
           description: Unmapped FastQ files (optional)
           pattern: "*fastq.gz"
   - tab:
       - meta:
-          type: file
-          description: STAR output tab file(s) (optional)
-          pattern: "*.tab"
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
       - "*.tab":
           type: file
           description: STAR output tab file(s) (optional)
@@ -149,12 +165,9 @@ output:
           description: |
             Groovy Map containing sample information
             e.g. [ id:'test', single_end:false ]
-          pattern: "*.SJ.out.tab"
       - "*.SJ.out.tab":
-          type: map
-          description: |
-            Groovy Map containing sample information
-            e.g. [ id:'test', single_end:false ]
+          type: file
+          description: STAR output splice junction tab file
           pattern: "*.SJ.out.tab"
   - read_per_gene_tab:
       - meta:
@@ -162,18 +175,16 @@ output:
           description: |
             Groovy Map containing sample information
             e.g. [ id:'test', single_end:false ]
-          pattern: "*.ReadsPerGene.out.tab"
       - "*.ReadsPerGene.out.tab":
+          type: file
+          description: STAR output read per gene tab file
+          pattern: "*.ReadsPerGene.out.tab"
+  - junction:
+      - meta:
           type: map
           description: |
             Groovy Map containing sample information
             e.g. [ id:'test', single_end:false ]
-          pattern: "*.ReadsPerGene.out.tab"
-  - junction:
-      - meta:
-          type: file
-          description: STAR chimeric junction output file (optional)
-          pattern: "*.out.junction"
       - "*.out.junction":
           type: file
           description: STAR chimeric junction output file (optional)
@@ -186,25 +197,25 @@ output:
             e.g. [ id:'test', single_end:false ]
           pattern: "*.out.sam"
       - "*.out.sam":
+          type: file
+          description: STAR output SAM file(s) (optional)
+          pattern: "*.out.sam"
+  - wig:
+      - meta:
           type: map
           description: |
             Groovy Map containing sample information
             e.g. [ id:'test', single_end:false ]
-          pattern: "*.out.sam"
-  - wig:
-      - meta:
-          type: file
-          description: STAR output wiggle format file(s) (optional)
-          pattern: "*.wig"
       - "*.wig":
           type: file
           description: STAR output wiggle format file(s) (optional)
           pattern: "*.wig"
   - bedgraph:
       - meta:
-          type: file
-          description: STAR output bedGraph format file(s) (optional)
-          pattern: "*.bg"
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
       - "*.bg":
           type: file
           description: STAR output bedGraph format file(s) (optional)
diff --git a/modules/nf-core/star/align/tests/main.nf.test b/modules/nf-core/star/align/tests/main.nf.test
index 2d9f72dd..a62c17db 100644
--- a/modules/nf-core/star/align/tests/main.nf.test
+++ b/modules/nf-core/star/align/tests/main.nf.test
@@ -56,13 +56,10 @@ nextflow_process {
                     file(process.out.log_final[0][1]).name,
                     file(process.out.log_out[0][1]).name,
                     file(process.out.log_progress[0][1]).name,
-                    process.out.bam,
-                    process.out.bam_sorted,
-                    process.out.bam_transcript,
-                    process.out.bam_unsorted,
+                    bam(process.out.bam[0][1]).getReadsMD5(),
+                    bam(process.out.bam_sorted_aligned[0][1]).getReadsMD5(),
                     process.out.bedgraph,
                     process.out.fastq,
-                    process.out.junction,
                     process.out.read_per_gene_tab,
                     process.out.sam,
                     process.out.spl_junc_tab,
@@ -124,13 +121,10 @@ nextflow_process {
                     file(process.out.log_final[0][1]).name,
                     file(process.out.log_out[0][1]).name,
                     file(process.out.log_progress[0][1]).name,
-                    process.out.bam,
-                    process.out.bam_sorted,
-                    process.out.bam_transcript,
-                    process.out.bam_unsorted,
+                    bam(process.out.bam[0][1]).getReadsMD5(),
+                    bam(process.out.bam_sorted_aligned[0][1]).getReadsMD5(),
                     process.out.bedgraph,
                     process.out.fastq,
-                    process.out.junction,
                     process.out.read_per_gene_tab,
                     process.out.sam,
                     process.out.spl_junc_tab,
@@ -192,13 +186,9 @@ nextflow_process {
                     file(process.out.log_final[0][1]).name,
                     file(process.out.log_out[0][1]).name,
                     file(process.out.log_progress[0][1]).name,
-                    process.out.bam,
-                    process.out.bam_sorted,
-                    process.out.bam_transcript,
-                    process.out.bam_unsorted,
+                    bam(process.out.bam[0][1]).getReadsMD5(),
                     process.out.bedgraph,
                     process.out.fastq,
-                    process.out.junction,
                     process.out.read_per_gene_tab,
                     process.out.sam,
                     process.out.spl_junc_tab,
@@ -260,13 +250,10 @@ nextflow_process {
                     file(process.out.log_final[0][1]).name,
                     file(process.out.log_out[0][1]).name,
                     file(process.out.log_progress[0][1]).name,
-                    process.out.bam,
-                    process.out.bam_sorted,
-                    process.out.bam_transcript,
-                    process.out.bam_unsorted,
+                    file(process.out.junction[0][1]).name,
+                    bam(process.out.bam[0][1]).getReadsMD5(),
                     process.out.bedgraph,
                     process.out.fastq,
-                    process.out.junction,
                     process.out.read_per_gene_tab,
                     process.out.sam,
                     process.out.spl_junc_tab,
@@ -330,13 +317,10 @@ nextflow_process {
                     file(process.out.log_final[0][1]).name,
                     file(process.out.log_out[0][1]).name,
                     file(process.out.log_progress[0][1]).name,
-                    process.out.bam,
-                    process.out.bam_sorted,
-                    process.out.bam_transcript,
-                    process.out.bam_unsorted,
+                    bam(process.out.bam[0][1]).getReadsMD5(),
+                    bam(process.out.bam_sorted_aligned[0][1]).getReadsMD5(),
                     process.out.bedgraph,
                     process.out.fastq,
-                    process.out.junction,
                     process.out.read_per_gene_tab,
                     process.out.sam,
                     process.out.spl_junc_tab,
@@ -606,4 +590,4 @@ nextflow_process {
             )
         }
     }
-}
\ No newline at end of file
+}
diff --git a/modules/nf-core/star/align/tests/main.nf.test.snap b/modules/nf-core/star/align/tests/main.nf.test.snap
index 0da28d37..b533fb8b 100644
--- a/modules/nf-core/star/align/tests/main.nf.test.snap
+++ b/modules/nf-core/star/align/tests/main.nf.test.snap
@@ -97,7 +97,7 @@
                     ]
                 ],
                 "3": [
-                    "versions.yml:md5,2e6b6d8809f5a17f38f4d27c45dcb22f"
+                    "versions.yml:md5,a149bba1dbb5194560abdd813c7848e3"
                 ],
                 "4": [
                     [
@@ -307,7 +307,7 @@
                     ]
                 ],
                 "versions": [
-                    "versions.yml:md5,2e6b6d8809f5a17f38f4d27c45dcb22f"
+                    "versions.yml:md5,a149bba1dbb5194560abdd813c7848e3"
                 ],
                 "wig": [
                     [
@@ -322,9 +322,9 @@
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.04.3"
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-10-01T11:39:15.440397"
+        "timestamp": "2024-10-20T17:09:08.738074176"
     },
     "homo_sapiens - paired_end - arriba - stub": {
         "content": [
@@ -424,7 +424,7 @@
                     ]
                 ],
                 "3": [
-                    "versions.yml:md5,2e6b6d8809f5a17f38f4d27c45dcb22f"
+                    "versions.yml:md5,a149bba1dbb5194560abdd813c7848e3"
                 ],
                 "4": [
                     [
@@ -634,7 +634,7 @@
                     ]
                 ],
                 "versions": [
-                    "versions.yml:md5,2e6b6d8809f5a17f38f4d27c45dcb22f"
+                    "versions.yml:md5,a149bba1dbb5194560abdd813c7848e3"
                 ],
                 "wig": [
                     [
@@ -649,33 +649,17 @@
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.04.3"
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-10-01T11:40:15.472109"
+        "timestamp": "2024-10-20T17:09:36.122131869"
     },
     "homo_sapiens - single_end": {
         "content": [
             "test.Log.final.out",
             "test.Log.out",
             "test.Log.progress.out",
-            [
-                [
-                    {
-                        "id": "test",
-                        "single_end": true
-                    },
-                    "test.Aligned.sortedByCoord.out.bam:md5,c6cfaccaf91bc7fdabed3cfe236d4535"
-                ]
-            ],
-            [
-                
-            ],
-            [
-                
-            ],
-            [
-                
-            ],
+            "9f76be49a6607613a64f760101bdddce",
+            "9f76be49a6607613a64f760101bdddce",
             [
                 [
                     {
@@ -696,9 +680,6 @@
             ],
             [
                 
-            ],
-            [
-                
             ],
             [
                 [
@@ -722,38 +703,22 @@
                 
             ],
             [
-                "versions.yml:md5,2e6b6d8809f5a17f38f4d27c45dcb22f"
+                "versions.yml:md5,a149bba1dbb5194560abdd813c7848e3"
             ]
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.04.3"
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-10-01T11:23:08.001162"
+        "timestamp": "2024-10-20T17:01:22.197991909"
     },
     "homo_sapiens - paired_end": {
         "content": [
             "test.Log.final.out",
             "test.Log.out",
             "test.Log.progress.out",
-            [
-                [
-                    {
-                        "id": "test",
-                        "single_end": false
-                    },
-                    "test.Aligned.sortedByCoord.out.bam:md5,b9ee1c607e07323bc1652ef3babb543f"
-                ]
-            ],
-            [
-                
-            ],
-            [
-                
-            ],
-            [
-                
-            ],
+            "db9a8324b5163b025bcc0c33e848486",
+            "db9a8324b5163b025bcc0c33e848486",
             [
                 [
                     {
@@ -774,9 +739,6 @@
             ],
             [
                 
-            ],
-            [
-                
             ],
             [
                 [
@@ -800,14 +762,14 @@
                 
             ],
             [
-                "versions.yml:md5,2e6b6d8809f5a17f38f4d27c45dcb22f"
+                "versions.yml:md5,a149bba1dbb5194560abdd813c7848e3"
             ]
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.04.3"
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-10-01T11:24:46.295219"
+        "timestamp": "2024-10-20T17:02:06.988663857"
     },
     "homo_sapiens - paired_end - multiple - stub": {
         "content": [
@@ -907,7 +869,7 @@
                     ]
                 ],
                 "3": [
-                    "versions.yml:md5,2e6b6d8809f5a17f38f4d27c45dcb22f"
+                    "versions.yml:md5,a149bba1dbb5194560abdd813c7848e3"
                 ],
                 "4": [
                     [
@@ -1117,7 +1079,7 @@
                     ]
                 ],
                 "versions": [
-                    "versions.yml:md5,2e6b6d8809f5a17f38f4d27c45dcb22f"
+                    "versions.yml:md5,a149bba1dbb5194560abdd813c7848e3"
                 ],
                 "wig": [
                     [
@@ -1132,33 +1094,17 @@
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.04.3"
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-10-01T11:41:07.310866"
+        "timestamp": "2024-10-20T17:10:12.005468781"
     },
     "homo_sapiens - paired_end - multiple": {
         "content": [
             "test.Log.final.out",
             "test.Log.out",
             "test.Log.progress.out",
-            [
-                [
-                    {
-                        "id": "test",
-                        "single_end": false
-                    },
-                    "test.Aligned.sortedByCoord.out.bam:md5,ab07c21d63ab0a6c07d171d213c81d5a"
-                ]
-            ],
-            [
-                
-            ],
-            [
-                
-            ],
-            [
-                
-            ],
+            "3e54e45f5dc3e9c1f2fc55bc41531a87",
+            "3e54e45f5dc3e9c1f2fc55bc41531a87",
             [
                 [
                     {
@@ -1179,9 +1125,6 @@
             ],
             [
                 
-            ],
-            [
-                
             ],
             [
                 [
@@ -1205,14 +1148,14 @@
                 
             ],
             [
-                "versions.yml:md5,2e6b6d8809f5a17f38f4d27c45dcb22f"
+                "versions.yml:md5,a149bba1dbb5194560abdd813c7848e3"
             ]
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.04.3"
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-10-01T11:38:46.605044"
+        "timestamp": "2024-10-20T17:08:54.877286681"
     },
     "homo_sapiens - paired_end - stub": {
         "content": [
@@ -1312,7 +1255,7 @@
                     ]
                 ],
                 "3": [
-                    "versions.yml:md5,2e6b6d8809f5a17f38f4d27c45dcb22f"
+                    "versions.yml:md5,a149bba1dbb5194560abdd813c7848e3"
                 ],
                 "4": [
                     [
@@ -1522,7 +1465,7 @@
                     ]
                 ],
                 "versions": [
-                    "versions.yml:md5,2e6b6d8809f5a17f38f4d27c45dcb22f"
+                    "versions.yml:md5,a149bba1dbb5194560abdd813c7848e3"
                 ],
                 "wig": [
                     [
@@ -1537,24 +1480,17 @@
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.04.3"
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-10-01T11:39:51.595873"
+        "timestamp": "2024-10-20T17:09:20.911466345"
     },
     "homo_sapiens - paired_end - starfusion": {
         "content": [
             "test.Log.final.out",
             "test.Log.out",
             "test.Log.progress.out",
-            [
-                [
-                    {
-                        "id": "test",
-                        "single_end": false
-                    },
-                    "test.Aligned.out.bam:md5,bcad07b838f6762fc01eea52b5cd3f84"
-                ]
-            ],
+            "test.Chimeric.out.junction",
+            "caee9dcda13882d4913456973c25b57a",
             [
                 
             ],
@@ -1566,24 +1502,6 @@
             ],
             [
                 
-            ],
-            [
-                
-            ],
-            [
-                [
-                    {
-                        "id": "test",
-                        "single_end": false
-                    },
-                    "test.Chimeric.out.junction:md5,c10ef219f4a30e83711b995bc5e40dba"
-                ]
-            ],
-            [
-                
-            ],
-            [
-                
             ],
             [
                 [
@@ -1607,41 +1525,21 @@
                 
             ],
             [
-                "versions.yml:md5,2e6b6d8809f5a17f38f4d27c45dcb22f"
+                "versions.yml:md5,a149bba1dbb5194560abdd813c7848e3"
             ]
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.04.3"
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-10-01T11:35:43.874508"
+        "timestamp": "2024-10-20T17:07:25.0639914"
     },
     "homo_sapiens - paired_end - arriba": {
         "content": [
             "test.Log.final.out",
             "test.Log.out",
             "test.Log.progress.out",
-            [
-                [
-                    {
-                        "id": "test",
-                        "single_end": false
-                    },
-                    "test.Aligned.out.bam:md5,c1b1747f5873f2d17762725636e891d5"
-                ]
-            ],
-            [
-                
-            ],
-            [
-                
-            ],
-            [
-                
-            ],
-            [
-                
-            ],
+            "1a3abe88fb2490589c58497d39921bcc",
             [
                 
             ],
@@ -1676,14 +1574,14 @@
                 
             ],
             [
-                "versions.yml:md5,2e6b6d8809f5a17f38f4d27c45dcb22f"
+                "versions.yml:md5,a149bba1dbb5194560abdd813c7848e3"
             ]
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.04.3"
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-10-01T11:28:32.599223"
+        "timestamp": "2024-10-20T17:04:00.685784211"
     },
     "homo_sapiens - paired_end - starfusion - stub": {
         "content": [
@@ -1783,7 +1681,7 @@
                     ]
                 ],
                 "3": [
-                    "versions.yml:md5,2e6b6d8809f5a17f38f4d27c45dcb22f"
+                    "versions.yml:md5,a149bba1dbb5194560abdd813c7848e3"
                 ],
                 "4": [
                     [
@@ -1993,7 +1891,7 @@
                     ]
                 ],
                 "versions": [
-                    "versions.yml:md5,2e6b6d8809f5a17f38f4d27c45dcb22f"
+                    "versions.yml:md5,a149bba1dbb5194560abdd813c7848e3"
                 ],
                 "wig": [
                     [
@@ -2008,8 +1906,8 @@
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.04.3"
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-10-01T11:40:42.29249"
+        "timestamp": "2024-10-20T17:09:53.173671551"
     }
 }
\ No newline at end of file
diff --git a/modules/nf-core/star/genomegenerate/environment.yml b/modules/nf-core/star/genomegenerate/environment.yml
index 1debc4c9..7c57530a 100644
--- a/modules/nf-core/star/genomegenerate/environment.yml
+++ b/modules/nf-core/star/genomegenerate/environment.yml
@@ -3,7 +3,7 @@ channels:
   - bioconda
 
 dependencies:
-  - bioconda::htslib=1.18
-  - bioconda::samtools=1.18
-  - bioconda::star=2.7.10a
+  - bioconda::htslib=1.20
+  - bioconda::samtools=1.20
+  - bioconda::star=2.7.11b
   - conda-forge::gawk=5.1.0
diff --git a/modules/nf-core/star/genomegenerate/main.nf b/modules/nf-core/star/genomegenerate/main.nf
index b8855715..8f0c67e7 100644
--- a/modules/nf-core/star/genomegenerate/main.nf
+++ b/modules/nf-core/star/genomegenerate/main.nf
@@ -4,8 +4,8 @@ process STAR_GENOMEGENERATE {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:ded3841da0194af2701c780e9b3d653a85d27489-0' :
-        'biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:ded3841da0194af2701c780e9b3d653a85d27489-0' }"
+        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/b4/b425bc2a95806d878993f9a66dae3ae80ac2dafff4c208c5ae01b7a90a32fa91/data' :
+        'community.wave.seqera.io/library/star_samtools_htslib_gawk:10c6e8c834460019' }"
 
     input:
     tuple val(meta), path(fasta)
diff --git a/modules/nf-core/star/genomegenerate/tests/main.nf.test.snap b/modules/nf-core/star/genomegenerate/tests/main.nf.test.snap
index 207f4b4f..3db25678 100644
--- a/modules/nf-core/star/genomegenerate/tests/main.nf.test.snap
+++ b/modules/nf-core/star/genomegenerate/tests/main.nf.test.snap
@@ -3,14 +3,14 @@
         "content": [
             "[Genome, Log.out, SA, SAindex, chrLength.txt, chrName.txt, chrNameLength.txt, chrStart.txt, exonGeTrInfo.tab, exonInfo.tab, geneInfo.tab, genomeParameters.txt, sjdbInfo.txt, sjdbList.fromGTF.out.tab, sjdbList.out.tab, transcriptInfo.tab]",
             [
-                "versions.yml:md5,46b8f1f34bb7f23892cd1eb249ed4d7f"
+                "versions.yml:md5,14b05d04c9eca568e9ed4888aaf26fa6"
             ]
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.04.3"
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-07-22T14:55:35.478401"
+        "timestamp": "2024-10-19T20:37:47.410432728"
     },
     "fasta_gtf_stub": {
         "content": [
@@ -41,7 +41,7 @@
                     ]
                 ],
                 "1": [
-                    "versions.yml:md5,46b8f1f34bb7f23892cd1eb249ed4d7f"
+                    "versions.yml:md5,14b05d04c9eca568e9ed4888aaf26fa6"
                 ],
                 "index": [
                     [
@@ -69,15 +69,15 @@
                     ]
                 ],
                 "versions": [
-                    "versions.yml:md5,46b8f1f34bb7f23892cd1eb249ed4d7f"
+                    "versions.yml:md5,14b05d04c9eca568e9ed4888aaf26fa6"
                 ]
             }
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.04.3"
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-07-22T14:55:57.247585"
+        "timestamp": "2024-10-19T20:38:09.165234795"
     },
     "fasta_stub": {
         "content": [
@@ -101,7 +101,7 @@
                     ]
                 ],
                 "1": [
-                    "versions.yml:md5,46b8f1f34bb7f23892cd1eb249ed4d7f"
+                    "versions.yml:md5,14b05d04c9eca568e9ed4888aaf26fa6"
                 ],
                 "index": [
                     [
@@ -122,27 +122,27 @@
                     ]
                 ],
                 "versions": [
-                    "versions.yml:md5,46b8f1f34bb7f23892cd1eb249ed4d7f"
+                    "versions.yml:md5,14b05d04c9eca568e9ed4888aaf26fa6"
                 ]
             }
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.04.3"
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-07-22T14:56:07.01742"
+        "timestamp": "2024-10-19T20:38:19.530862664"
     },
     "fasta": {
         "content": [
             "[Genome, Log.out, SA, SAindex, chrLength.txt, chrName.txt, chrNameLength.txt, chrStart.txt, genomeParameters.txt]",
             [
-                "versions.yml:md5,46b8f1f34bb7f23892cd1eb249ed4d7f"
+                "versions.yml:md5,14b05d04c9eca568e9ed4888aaf26fa6"
             ]
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.04.3"
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-07-22T14:55:45.48784"
+        "timestamp": "2024-10-19T20:37:58.667436398"
     }
 }
\ No newline at end of file
diff --git a/modules/nf-core/stringtie/stringtie/environment.yml b/modules/nf-core/stringtie/stringtie/environment.yml
index 0556de41..906b7486 100644
--- a/modules/nf-core/stringtie/stringtie/environment.yml
+++ b/modules/nf-core/stringtie/stringtie/environment.yml
@@ -2,4 +2,4 @@ channels:
   - conda-forge
   - bioconda
 dependencies:
-  - bioconda::stringtie=2.2.1
+  - bioconda::stringtie=2.2.3
diff --git a/modules/nf-core/stringtie/stringtie/main.nf b/modules/nf-core/stringtie/stringtie/main.nf
index 6e25ba27..4635c8c5 100644
--- a/modules/nf-core/stringtie/stringtie/main.nf
+++ b/modules/nf-core/stringtie/stringtie/main.nf
@@ -4,8 +4,8 @@ process STRINGTIE_STRINGTIE {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/stringtie:2.2.1--hecb563c_2' :
-        'biocontainers/stringtie:2.2.1--hecb563c_2' }"
+        'https://depot.galaxyproject.org/singularity/stringtie:2.2.3--h43eeafb_0' :
+        'biocontainers/stringtie:2.2.3--h43eeafb_0' }"
 
     input:
     tuple val(meta), path(bam)
diff --git a/modules/nf-core/stringtie/stringtie/tests/main.nf.test.snap b/modules/nf-core/stringtie/stringtie/tests/main.nf.test.snap
index 124dd4cb..d4645de3 100644
--- a/modules/nf-core/stringtie/stringtie/tests/main.nf.test.snap
+++ b/modules/nf-core/stringtie/stringtie/tests/main.nf.test.snap
@@ -31,18 +31,18 @@
                         "id": "test",
                         "strandedness": "forward"
                     },
-                    "test.transcripts.gtf:md5,f56cf8aba2c4a5673bc7963ba5f12d04"
+                    "test.transcripts.gtf:md5,37154e7bda96544f24506ee902bb561d"
                 ]
             ],
             [
-                "versions.yml:md5,3410e8ac349d18c85ddee89337851d38"
+                "versions.yml:md5,06593ea00cc35bf06f2de2753e0c3913"
             ]
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.04.3"
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-07-22T12:33:44.299962"
+        "timestamp": "2024-10-18T09:56:50.294157199"
     },
     "sarscov2 [bam] - forward strandedness": {
         "content": [
@@ -61,18 +61,18 @@
                         "id": "test",
                         "strandedness": "forward"
                     },
-                    "test.transcripts.gtf:md5,569137af5be452413086b50653a97203"
+                    "test.transcripts.gtf:md5,6087dfc9700a52d9e4a1ae3fcd1d1dfd"
                 ]
             ],
             [
-                "versions.yml:md5,3410e8ac349d18c85ddee89337851d38"
+                "versions.yml:md5,06593ea00cc35bf06f2de2753e0c3913"
             ]
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.04.3"
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-07-22T12:33:35.177738"
+        "timestamp": "2024-10-18T09:56:39.4249133"
     },
     "sarscov2 [bam] - forward strandedness - stub": {
         "content": [
@@ -114,7 +114,7 @@
                     ]
                 ],
                 "4": [
-                    "versions.yml:md5,3410e8ac349d18c85ddee89337851d38"
+                    "versions.yml:md5,06593ea00cc35bf06f2de2753e0c3913"
                 ],
                 "abundance": [
                     [
@@ -153,15 +153,15 @@
                     ]
                 ],
                 "versions": [
-                    "versions.yml:md5,3410e8ac349d18c85ddee89337851d38"
+                    "versions.yml:md5,06593ea00cc35bf06f2de2753e0c3913"
                 ]
             }
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.04.3"
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-07-22T12:36:32.885078"
+        "timestamp": "2024-10-18T09:57:23.008470065"
     },
     "sarscov2 [bam] - forward strandedness + reference annotation - stub": {
         "content": [
@@ -203,7 +203,7 @@
                     ]
                 ],
                 "4": [
-                    "versions.yml:md5,3410e8ac349d18c85ddee89337851d38"
+                    "versions.yml:md5,06593ea00cc35bf06f2de2753e0c3913"
                 ],
                 "abundance": [
                     [
@@ -242,15 +242,15 @@
                     ]
                 ],
                 "versions": [
-                    "versions.yml:md5,3410e8ac349d18c85ddee89337851d38"
+                    "versions.yml:md5,06593ea00cc35bf06f2de2753e0c3913"
                 ]
             }
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.04.3"
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-07-22T12:36:43.325777"
+        "timestamp": "2024-10-18T09:57:33.622824981"
     },
     "sarscov2 [bam] - reverse strandedness + reference annotation - stub": {
         "content": [
@@ -292,7 +292,7 @@
                     ]
                 ],
                 "4": [
-                    "versions.yml:md5,3410e8ac349d18c85ddee89337851d38"
+                    "versions.yml:md5,06593ea00cc35bf06f2de2753e0c3913"
                 ],
                 "abundance": [
                     [
@@ -331,15 +331,15 @@
                     ]
                 ],
                 "versions": [
-                    "versions.yml:md5,3410e8ac349d18c85ddee89337851d38"
+                    "versions.yml:md5,06593ea00cc35bf06f2de2753e0c3913"
                 ]
             }
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.04.3"
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-07-22T12:37:06.085936"
+        "timestamp": "2024-10-18T09:57:55.803421433"
     },
     "sarscov2 [bam] - reverse strandedness - stub": {
         "content": [
@@ -381,7 +381,7 @@
                     ]
                 ],
                 "4": [
-                    "versions.yml:md5,3410e8ac349d18c85ddee89337851d38"
+                    "versions.yml:md5,06593ea00cc35bf06f2de2753e0c3913"
                 ],
                 "abundance": [
                     [
@@ -420,15 +420,15 @@
                     ]
                 ],
                 "versions": [
-                    "versions.yml:md5,3410e8ac349d18c85ddee89337851d38"
+                    "versions.yml:md5,06593ea00cc35bf06f2de2753e0c3913"
                 ]
             }
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.04.3"
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-07-22T12:36:53.837578"
+        "timestamp": "2024-10-18T09:57:44.825389635"
     },
     "sarscov2 [bam] - reverse strandedness + reference annotation": {
         "content": [
@@ -462,18 +462,18 @@
                         "id": "test",
                         "strandedness": "reverse"
                     },
-                    "test.transcripts.gtf:md5,bb346053a8c156b803b055133376c7fa"
+                    "test.transcripts.gtf:md5,fbabb4e3888bbede67f11f692e484880"
                 ]
             ],
             [
-                "versions.yml:md5,3410e8ac349d18c85ddee89337851d38"
+                "versions.yml:md5,06593ea00cc35bf06f2de2753e0c3913"
             ]
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.04.3"
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-07-22T12:34:03.114695"
+        "timestamp": "2024-10-18T09:57:11.793664242"
     },
     "sarscov2 [bam] - reverse strandedness": {
         "content": [
@@ -492,17 +492,17 @@
                         "id": "test",
                         "strandedness": "reverse"
                     },
-                    "test.transcripts.gtf:md5,31c34aec2bf36bb0ea3c16c2afeeeb1f"
+                    "test.transcripts.gtf:md5,01d6da00a3c458420841e57427297183"
                 ]
             ],
             [
-                "versions.yml:md5,3410e8ac349d18c85ddee89337851d38"
+                "versions.yml:md5,06593ea00cc35bf06f2de2753e0c3913"
             ]
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.04.3"
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-07-22T12:33:52.874479"
+        "timestamp": "2024-10-18T09:57:01.166309777"
     }
 }
\ No newline at end of file
diff --git a/subworkflows/local/arriba_workflow.nf b/subworkflows/local/arriba_workflow.nf
index ce142a74..fd2ec963 100644
--- a/subworkflows/local/arriba_workflow.nf
+++ b/subworkflows/local/arriba_workflow.nf
@@ -11,6 +11,7 @@ workflow ARRIBA_WORKFLOW {
         ch_fasta
         ch_starindex_ref
         ch_arriba_ref_blacklist
+        ch_arriba_ref_cytobands
         ch_arriba_ref_known_fusions
         ch_arriba_ref_protein_domains
 
@@ -28,7 +29,7 @@ workflow ARRIBA_WORKFLOW {
                     .map { meta, reads, fusions -> [ meta, fusions ] }
                 ch_arriba_fusion_fail = ch_dummy_file
             } else {
-                ARRIBA_ARRIBA ( STAR_FOR_ARRIBA.out.bam, ch_fasta, ch_gtf, ch_arriba_ref_blacklist, ch_arriba_ref_known_fusions, [[],[]], [[],[]], ch_arriba_ref_protein_domains )
+                ARRIBA_ARRIBA ( STAR_FOR_ARRIBA.out.bam, ch_fasta, ch_gtf, ch_arriba_ref_blacklist, ch_arriba_ref_known_fusions, ch_arriba_ref_cytobands, ch_arriba_ref_protein_domains )
                 ch_versions = ch_versions.mix(ARRIBA_ARRIBA.out.versions)
 
                 ch_arriba_fusions     = ARRIBA_ARRIBA.out.fusions
diff --git a/subworkflows/local/build_references.nf b/subworkflows/local/build_references.nf
index 0c6c9916..3de5af74 100644
--- a/subworkflows/local/build_references.nf
+++ b/subworkflows/local/build_references.nf
@@ -35,9 +35,6 @@ include { GFFREAD }                         from '../../modules/nf-core/gffread/
 */
 
 workflow BUILD_REFERENCES {
-    take:
-        genome                           // channel: [mandatory]  val(genome)
-        genome_gencode_version           // channel: [mandatory]  val(genome_gencode_version)
 
     main:
     ch_versions = Channel.empty()
@@ -82,7 +79,7 @@ workflow BUILD_REFERENCES {
 
     if (!file(params.refflat).exists() || file(params.refflat).isEmpty()){
         GTF_TO_REFFLAT(ch_gtf)
-        ch_refflat = GTF_TO_REFFLAT.out.refflat
+        ch_refflat = GTF_TO_REFFLAT.out.refflat.map { that -> [[id:that.Name], that] }
     } else {
         ch_refflat = Channel.fromPath(params.refflat).map { that -> [[id:that.Name], that] }
     }
@@ -109,58 +106,55 @@ workflow BUILD_REFERENCES {
             (!file(params.arriba_ref_blacklist).exists() || file(params.arriba_ref_blacklist).isEmpty() ||
             !file(params.arriba_ref_known_fusions).exists() || file(params.arriba_ref_known_fusions).isEmpty() ||
             !file(params.arriba_ref_protein_domains).exists() || file(params.arriba_ref_protein_domains).isEmpty())) {
-        ARRIBA_DOWNLOAD(genome)
+        ARRIBA_DOWNLOAD(params.genome)
         ch_arriba_ref_blacklist = ARRIBA_DOWNLOAD.out.blacklist
         ch_arriba_ref_cytobands = ARRIBA_DOWNLOAD.out.cytobands
         ch_arriba_ref_known_fusions = ARRIBA_DOWNLOAD.out.known_fusions
         ch_arriba_ref_protein_domains = ARRIBA_DOWNLOAD.out.protein_domains
     } else {
-        ch_arriba_ref_blacklist = Channel.fromPath(params.arriba_ref_blacklist).map { that -> [[id:that.Name], that] }
-        ch_arriba_ref_cytobands = Channel.fromPath(params.arriba_ref_cytobands).map { that -> [[id:that.Name], that] }
-        ch_arriba_ref_known_fusions = Channel.fromPath(params.arriba_ref_known_fusions).map { that -> [[id:that.Name], that] }
-        ch_arriba_ref_protein_domains = Channel.fromPath(params.arriba_ref_protein_domains).map { that -> [[id:that.Name], that] }
+        ch_arriba_ref_blacklist = Channel.fromPath(params.arriba_ref_blacklist)
+        ch_arriba_ref_cytobands = Channel.fromPath(params.arriba_ref_cytobands)
+        ch_arriba_ref_known_fusions = Channel.fromPath(params.arriba_ref_known_fusions)
+        ch_arriba_ref_protein_domains = Channel.fromPath(params.arriba_ref_protein_domains)
     }
 
 
     if ((params.fusioncatcher || params.all) &&
             (!file(params.fusioncatcher_ref).exists() || file(params.fusioncatcher_ref).isEmpty() ||
             !file(params.fusioncatcher_ref_stub_check).exists() || file(params.fusioncatcher_ref_stub_check).isEmpty() )) {
-        if (params.download_refs) {
-            FUSIONCATCHER_DOWNLOAD(params.genome_gencode_version)
-            ch_fusioncatcher_ref = FUSIONCATCHER_DOWNLOAD.out.reference}
-        else {
             FUSIONCATCHER_BUILD(params.genome_gencode_version)
-            ch_fusioncatcher_ref = FUSIONCATCHER_BUILD.out.reference}
-        } else {
-            ch_fusioncatcher_ref = Channel.fromPath(params.fusioncatcher_ref).map { that -> [[id:that.Name], that] }
-        }
+            ch_fusioncatcher_ref = FUSIONCATCHER_BUILD.out.reference
+    }
+    else {
+        ch_fusioncatcher_ref = Channel.fromPath(params.fusioncatcher_ref)
+    }
 
 
     if ((params.starfusion || params.all) &&
             (!file(params.starfusion_ref).exists() || file(params.starfusion_ref).isEmpty() ||
             !file(params.starfusion_ref_stub_check).exists() || file(params.starfusion_ref_stub_check).isEmpty() )) {
-        if (params.download_refs) {
-            ch_starfusion_ref = STARFUSION_DOWNLOAD( ch_fasta, ch_gtf ).out.reference }
-        else {
-            ch_starfusion_ref = STARFUSION_BUILD( ch_fasta, ch_gtf ).out.reference }
-    } else {
-        ch_starfusion_ref = Channel.fromPath(params.starfusion_ref).map { that -> [[id:that.Name], that] }}
+            STARFUSION_BUILD(ch_fasta, ch_gtf)
+            ch_starfusion_ref = STARFUSION_BUILD.out.reference
+    }
+    else {
+        ch_starfusion_ref = Channel.fromPath(params.starfusion_ref)
+    }
 
 
     if ((params.fusionreport || params.all) &&
             (!file(params.fusionreport_ref).exists() || file(params.fusionreport_ref).isEmpty() ||
             !file(params.fusionreport_ref_stub_check).exists() || file(params.fusionreport_ref_stub_check).isEmpty())) {
         if (!params.cosmic_username || !params.cosmic_passwd) { exit 1, 'COSMIC username and/or password missing' }
-        ch_fusionreport_ref = FUSIONREPORT_DOWNLOAD( params.cosmic_username, params.cosmic_passwd ).out.reference
+        FUSIONREPORT_DOWNLOAD(params.cosmic_username, params.cosmic_passwd)
+        ch_fusionreport_ref = FUSIONREPORT_DOWNLOAD.out.reference
     } else {
-        ch_fusionreport_ref = Channel.fromPath(params.fusionreport_ref).map { that -> [[id:that.Name], that] }
+        ch_fusionreport_ref = Channel.fromPath(params.fusionreport_ref)
     }
 
     emit:
     ch_fasta
     ch_gtf
     ch_fai
-
     ch_hgnc_ref
     ch_hgnc_date
     ch_rrna_interval
diff --git a/subworkflows/local/fusionreport_workflow.nf b/subworkflows/local/fusionreport_workflow.nf
index 09ec9965..f8fc90dc 100644
--- a/subworkflows/local/fusionreport_workflow.nf
+++ b/subworkflows/local/fusionreport_workflow.nf
@@ -23,7 +23,7 @@ workflow FUSIONREPORT_WORKFLOW {
             FUSIONREPORT(reads_fusions, fusionreport_ref, params.tools_cutoff)
             ch_fusion_list = FUSIONREPORT.out.fusion_list
             ch_fusion_list_filtered = FUSIONREPORT.out.fusion_list_filtered
-            ch_versions = ch_versions.mix(FUSIONREPORT.out.versions)
+            // ch_versions = ch_versions.mix(FUSIONREPORT.out.versions)
             ch_report = FUSIONREPORT.out.report
             ch_csv = FUSIONREPORT.out.csv
         } else {
diff --git a/test.fusionreport.tsv b/test.fusionreport.tsv
new file mode 100644
index 00000000..e69de29b
diff --git a/test.fusionreport_filtered.tsv b/test.fusionreport_filtered.tsv
new file mode 100644
index 00000000..e69de29b
diff --git a/test.fusions.csv b/test.fusions.csv
new file mode 100644
index 00000000..e69de29b
diff --git a/test.fusions.json b/test.fusions.json
new file mode 100644
index 00000000..e69de29b
diff --git a/test_fusionreport_index.html b/test_fusionreport_index.html
new file mode 100644
index 00000000..e69de29b
diff --git a/tests/main.nf.test b/tests/main.nf.test
index 715335d8..31c71b6f 100644
--- a/tests/main.nf.test
+++ b/tests/main.nf.test
@@ -5,11 +5,10 @@ nextflow_pipeline {
     tag "pipeline"
     tag "pipeline_rnafusion"
 
-    test("Run build references with profile test") {
+    test("Run fusion detection with profile test") {
 
         when {
             params {
-                build_references             = true
                 outdir                       = "results"
                 genome_base                  = "references"
                 max_cpus                     = 2
@@ -21,25 +20,6 @@ nextflow_pipeline {
             }
         }
 
-        then {
-            assertAll(
-                { assert workflow.success }
-            )
-        }
-    }
-    test("Run fusion detection with profile test") {
-
-        when {
-            params {
-                outdir                       = "results"
-                genome_base                  = "references"
-                max_cpus                     = 2
-                max_memory                   = '6.GB'
-                max_time                     = '6.h'
-                input                        = 'https://raw.githubusercontent.com/nf-core/test-datasets/rnafusion/testdata/human/samplesheet_valid.csv'
-            }
-        }
-
         then {
             assertAll(
                 { assert workflow.success }
diff --git a/workflows/rnafusion.nf b/workflows/rnafusion.nf
index 5e34db97..238bcc3a 100644
--- a/workflows/rnafusion.nf
+++ b/workflows/rnafusion.nf
@@ -5,20 +5,20 @@
 */
 
 include { BUILD_REFERENCES              }   from '../subworkflows/local/build_references'
-// include { TRIM_WORKFLOW                 }   from '../subworkflows/local/trim_workflow'
-// include { ARRIBA_WORKFLOW               }   from '../subworkflows/local/arriba_workflow'
-// include { QC_WORKFLOW                   }   from '../subworkflows/local/qc_workflow'
-// include { STARFUSION_WORKFLOW           }   from '../subworkflows/local/starfusion_workflow'
-// include { STRINGTIE_WORKFLOW            }   from '../subworkflows/local/stringtie_workflow'
-// include { FUSIONCATCHER_WORKFLOW        }   from '../subworkflows/local/fusioncatcher_workflow'
-// include { FUSIONINSPECTOR_WORKFLOW      }   from '../subworkflows/local/fusioninspector_workflow'
-// include { FUSIONREPORT_WORKFLOW         }   from '../subworkflows/local/fusionreport_workflow'
-// include { validateInputSamplesheet      }   from '../subworkflows/local/utils_nfcore_rnafusion_pipeline'
+include { TRIM_WORKFLOW                 }   from '../subworkflows/local/trim_workflow'
+include { ARRIBA_WORKFLOW               }   from '../subworkflows/local/arriba_workflow'
+include { QC_WORKFLOW                   }   from '../subworkflows/local/qc_workflow'
+include { STARFUSION_WORKFLOW           }   from '../subworkflows/local/starfusion_workflow'
+include { STRINGTIE_WORKFLOW            }   from '../subworkflows/local/stringtie_workflow'
+include { FUSIONCATCHER_WORKFLOW        }   from '../subworkflows/local/fusioncatcher_workflow'
+include { FUSIONINSPECTOR_WORKFLOW      }   from '../subworkflows/local/fusioninspector_workflow'
+include { FUSIONREPORT_WORKFLOW         }   from '../subworkflows/local/fusionreport_workflow'
+include { validateInputSamplesheet      }   from '../subworkflows/local/utils_nfcore_rnafusion_pipeline'
 
 include { CAT_FASTQ                     }   from '../modules/nf-core/cat/fastq/main'
 include { FASTQC                        }   from '../modules/nf-core/fastqc/main'
 include { MULTIQC                       }   from '../modules/nf-core/multiqc/main'
-// include { SALMON_QUANT                  }   from '../modules/nf-core/salmon/quant/main'
+include { SALMON_QUANT                  }   from '../modules/nf-core/salmon/quant/main'
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -34,204 +34,123 @@ workflow RNAFUSION {
 
 
     ch_versions = Channel.empty()
-    // ch_multiqc_files = Channel.empty()
+    ch_multiqc_files = Channel.empty()
 
     //
     // Create references if necessary
     //
 
-    BUILD_REFERENCES(params.genome, params.genome_gencode_version)
+    BUILD_REFERENCES()
     ch_versions = ch_versions.mix(BUILD_REFERENCES.out.versions)
 
-    // // Optional
-    // ch_fasta                      = params.fasta                        ? Channel.fromPath(params.fasta).map {it -> [[id:it[0].simpleName], it]}.collect()
-    //                                                                     : BUILD_REFERENCES.out.fasta.map {it -> [[id:it[0].simpleName], it]}.collect()
-    // ch_gtf                        = params.gtf                          ? Channel.fromPath(params.gtf).map {it -> [[id:it[0].simpleName], it]}.collect()
-    //                                                                     : downloads.gtf.map {it -> [[id:it[0].simpleName], it]}.collect()
-    // ch_vep_cache_unprocessed      = params.vep_cache                    ? Channel.fromPath(params.vep_cache)
-    //                                                                     : Channel.empty().mix(downloads.vep_cache)
-    // ch_vep_extra_files_unsplit    = params.vep_plugin_files             ? Channel.fromPath(params.vep_plugin_files)
-    //                                                                     : Channel.empty().mix(downloads.vep_plugin)
-    // ch_fai                        = params.fai                          ? Channel.fromPath(params.fai).map {it -> [[id:it[0].simpleName], it]}.collect()
-    //                                                                     : Channel.empty()
-    // ch_gene_panel_clinical_filter = params.gene_panel_clinical_filter   ? Channel.fromPath(params.gene_panel_clinical_filter).collect()
-    //                                                                     : Channel.empty()
-    // ch_ref_drop_annot_file        = params.reference_drop_annot_file    ? Channel.fromPath(params.reference_drop_annot_file).collect()
-    //                                                                     : Channel.empty()
-    // ch_ref_drop_count_file        = params.reference_drop_count_file    ? Channel.fromPath(params.reference_drop_count_file).collect()
-    //                                                                     : Channel.empty()
-    // ch_ref_drop_splice_folder     = params.reference_drop_splice_folder ? Channel.fromPath(params.reference_drop_splice_folder).collect()
-    //                                                                     : Channel.empty()
-    // ch_salmon_index               = params.salmon_index                 ? Channel.fromPath(params.salmon_index)
-    //                                                                     : Channel.empty()
-    // ch_star_index                 = params.star_index                   ? Channel.fromPath(params.star_index).map {it -> [[id:it[0].simpleName], it]}.collect()
-    //                                                                     : Channel.empty()
-    // ch_transcript_fasta           = params.transcript_fasta             ? Channel.fromPath(params.transcript_fasta)
-    //                                                                     : Channel.empty()
-    // ch_sequence_dict              = params.sequence_dict                ? Channel.fromPath(params.sequence_dict).map{ it -> [[id:it[0].simpleName], it] }.collect()
-    //                                                                     : Channel.empty()
-    // ch_subsample_bed              = params.subsample_bed                ? Channel.fromPath(params.subsample_bed).collect()
-    //                                                                     : Channel.empty()
 
     //
-    // Create channel from input file provided through params.input
+    // QC from FASTQ files
     //
-    // Channel
-    //     .fromSamplesheet("input")
-    //     .map {
-    //         meta, fastq_1, fastq_2, strandedness ->
-    //             if (!fastq_2) {
-    //                 return [ meta.id, meta + [ single_end:true ], [ fastq_1 ] ]
-    //             } else {
-    //                 return [ meta.id, meta + [ single_end:false ], [ fastq_1, fastq_2 ] ]
-    //             }
-    //     }
-    //     .groupTuple()
-    //     .map {
-    //         validateInputSamplesheet(it)
-    //     }
-    //     .branch {
-    //         meta, fastqs ->
-    //             single  : fastqs.size() == 1
-    //                 return [ meta, fastqs.flatten() ]
-    //             multiple: fastqs.size() > 1
-    //                 return [ meta, fastqs.flatten() ]
-    //     }
-    //     .set { ch_fastq }
+    FASTQC (
+        ch_samplesheet
+    )
+    ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]})
+    ch_versions = ch_versions.mix(FASTQC.out.versions)
 
-    // //
-    // // MODULE: Concatenate FastQ files from same sample if required
-    // //
-    // CAT_FASTQ (
-    //     ch_fastq.multiple
-    // )
-    // .reads
-    // .mix(ch_fastq.single)
-    // .set { ch_cat_fastq }
-    // ch_versions = ch_versions.mix(CAT_FASTQ.out.versions)
-
-
-    // //
-    // // QC from FASTQ files
-    // //
-    // FASTQC (
-    //     ch_cat_fastq
-    // )
-    // ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]})
-    // ch_versions = ch_versions.mix(FASTQC.out.versions)
 
-    // SALMON_QUANT( ch_reads_all, BUILD_REFERENCES.out.ch_salmon_index.map{ meta, index ->  index  }, BUILD_REFERENCES.out.ch_gtf.map{ meta, gtf ->  gtf  }, [], false, 'A')
-    // ch_multiqc_files = ch_multiqc_files.mix(SALMON_QUANT.out.zip.collect{it[1]})
+    //
+    // Trimming
+    //
+    TRIM_WORKFLOW (
+        ch_samplesheet
+    )
+    ch_reads = TRIM_WORKFLOW.out.trimmed_reads
+    ch_versions = ch_versions.mix(TRIM_WORKFLOW.out.versions)
+
+    // SALMON_QUANT( ch_reads, BUILD_REFERENCES.out.ch_salmon_index.map{ meta, index ->  index  }, BUILD_REFERENCES.out.ch_gtf.map{ meta, gtf ->  gtf  }, [], false, 'A')
+    // ch_multiqc_files = ch_multiqc_files.mix(SALMON_QUANT.out.zi.collect{it[1]})
     // ch_versions = ch_versions.mix(SALMON_QUANT.out.versions)
 
-    // //
-    // // Trimming
-    // //
-    // TRIM_WORKFLOW (
-    //     ch_cat_fastq
-    // )
-    // ch_reads = TRIM_WORKFLOW.out.trimmed_reads
-    // ch_versions = ch_versions.mix(TRIM_WORKFLOW.out.versions)
+
     //
-    // MODULE: Run FastQC
+    // SUBWORKFLOW:  Run STAR alignment and Arriba
     //
-    // FASTQC (
-    //     ch_samplesheet
-    // )
-    // ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]})
-    // ch_versions = ch_versions.mix(FASTQC.out.versions.first())
 
+    ARRIBA_WORKFLOW (
+        ch_reads,
+        BUILD_REFERENCES.out.ch_gtf,
+        BUILD_REFERENCES.out.ch_fasta,
+        BUILD_REFERENCES.out.ch_starindex_ref,
+        BUILD_REFERENCES.out.ch_arriba_ref_blacklist,
+        BUILD_REFERENCES.out.ch_arriba_ref_cytobands,
+        BUILD_REFERENCES.out.ch_arriba_ref_known_fusions,
+        BUILD_REFERENCES.out.ch_arriba_ref_protein_domains
+    )
+    ch_versions = ch_versions.mix(ARRIBA_WORKFLOW.out.versions)
+
+
+//Run STAR fusion
+    STARFUSION_WORKFLOW (
+        ch_reads,
+        BUILD_REFERENCES.out.ch_gtf,
+        BUILD_REFERENCES.out.ch_starindex_ref,
+        BUILD_REFERENCES.out.ch_fasta
+    )
+    ch_versions = ch_versions.mix(STARFUSION_WORKFLOW.out.versions)
+
+
+//Run fusioncatcher
+    FUSIONCATCHER_WORKFLOW (
+        ch_reads
+    )
+    ch_versions = ch_versions.mix(FUSIONCATCHER_WORKFLOW.out.versions)
+
+
+//Run stringtie
+    STRINGTIE_WORKFLOW (
+        STARFUSION_WORKFLOW.out.ch_bam_sorted,
+        BUILD_REFERENCES.out.ch_gtf
+    )
+    ch_versions = ch_versions.mix(STRINGTIE_WORKFLOW.out.versions)
+
+
+    //Run fusion-report
+    FUSIONREPORT_WORKFLOW (
+        ch_reads,
+        BUILD_REFERENCES.out.ch_fusionreport_ref,
+        ARRIBA_WORKFLOW.out.fusions,
+        STARFUSION_WORKFLOW.out.fusions,
+        FUSIONCATCHER_WORKFLOW.out.fusions
+    )
+    ch_versions = ch_versions.mix(FUSIONREPORT_WORKFLOW.out.versions)
+
+
+
+    //Run fusionInpector
+    FUSIONINSPECTOR_WORKFLOW (
+        ch_reads,
+        FUSIONREPORT_WORKFLOW.out.fusion_list,
+        FUSIONREPORT_WORKFLOW.out.fusion_list_filtered,
+        FUSIONREPORT_WORKFLOW.out.report,
+        FUSIONREPORT_WORKFLOW.out.csv,
+        STARFUSION_WORKFLOW.out.ch_bam_sorted_indexed,
+        BUILD_REFERENCES.out.ch_gtf,
+        BUILD_REFERENCES.out.ch_arriba_ref_protein_domains,
+        BUILD_REFERENCES.out.ch_arriba_ref_cytobands,
+        BUILD_REFERENCES.out.ch_hgnc_ref,
+        BUILD_REFERENCES.out.ch_hgnc_date
+    )
+    ch_versions = ch_versions.mix(FUSIONINSPECTOR_WORKFLOW.out.versions)
 
 
-    // TRIM_WORKFLOW (
-    //     ch_samplesheet
+    // //QC
+    // QC_WORKFLOW (
+    //     ch_reads,
+    //     STARFUSION_WORKFLOW.out.ch_bam_sorted,
+    //     STARFUSION_WORKFLOW.out.ch_bam_sorted_indexed,
+    //     BUILD_REFERENCES.out.ch_gtf,
+    //     BUILD_REFERENCES.out.ch_refflat,
+    //     BUILD_REFERENCES.out.ch_fasta,
+    //     BUILD_REFERENCES.out.ch_fai,
+    //     BUILD_REFERENCES.out.ch_rrna_interval
     // )
-    // ch_reads_fusioncatcher = TRIM_WORKFLOW.out.ch_reads_fusioncatcher
-    // ch_reads_all = TRIM_WORKFLOW.out.ch_reads_all
-    // ch_versions = ch_versions.mix(TRIM_WORKFLOW.out.versions)
-
-
-//     //
-//     // SUBWORKFLOW:  Run STAR alignment and Arriba
-//     //
-//     ARRIBA_WORKFLOW (
-//         ch_reads_all,
-//         ch_gtf,
-//         ch_fasta,
-//         ch_starindex_ensembl_ref,
-//         ch_arriba_ref_blacklist,
-//         ch_arriba_ref_known_fusions,
-//         ch_arriba_ref_protein_domains
-//     )
-//     ch_versions = ch_versions.mix(ARRIBA_WORKFLOW.out.versions)
-
-
-// //Run STAR fusion
-//     STARFUSION_WORKFLOW (
-//         ch_reads_all,
-//         ch_gtf,
-//         ch_starindex_ref,
-//         ch_fasta
-//     )
-//     ch_versions = ch_versions.mix(STARFUSION_WORKFLOW.out.versions)
-
-
-// //Run fusioncatcher
-//     FUSIONCATCHER_WORKFLOW (
-//         ch_reads_fusioncatcher
-//     )
-//     ch_versions = ch_versions.mix(FUSIONCATCHER_WORKFLOW.out.versions)
-
-
-// //Run stringtie
-//     STRINGTIE_WORKFLOW (
-//         STARFUSION_WORKFLOW.out.ch_bam_sorted,
-//         ch_gtf
-//     )
-//     ch_versions = ch_versions.mix(STRINGTIE_WORKFLOW.out.versions)
-
-
-//     //Run fusion-report
-//     FUSIONREPORT_WORKFLOW (
-//         ch_reads_all,
-//         ch_fusionreport_ref,
-//         ARRIBA_WORKFLOW.out.fusions,
-//         STARFUSION_WORKFLOW.out.fusions,
-//         FUSIONCATCHER_WORKFLOW.out.fusions
-//     )
-//     ch_versions = ch_versions.mix(FUSIONREPORT_WORKFLOW.out.versions)
-
-
-
-//     //Run fusionInpector
-//     FUSIONINSPECTOR_WORKFLOW (
-//         ch_reads_all,
-//         FUSIONREPORT_WORKFLOW.out.fusion_list,
-//         FUSIONREPORT_WORKFLOW.out.fusion_list_filtered,
-//         FUSIONREPORT_WORKFLOW.out.report,
-//         FUSIONREPORT_WORKFLOW.out.csv,
-//         STARFUSION_WORKFLOW.out.ch_bam_sorted_indexed,
-//         ch_gtf,
-//         ch_arriba_ref_protein_domains,
-//         ch_arriba_ref_cytobands,
-//         ch_hgnc_ref,
-//         ch_hgnc_date
-//     )
-//     ch_versions = ch_versions.mix(FUSIONINSPECTOR_WORKFLOW.out.versions)
-
-
-//     //QC
-//     QC_WORKFLOW (
-//         ch_reads_all,
-//         STARFUSION_WORKFLOW.out.ch_bam_sorted,
-//         STARFUSION_WORKFLOW.out.ch_bam_sorted_indexed,
-//         ch_gtf,
-//         ch_refflat,
-//         ch_fasta,
-//         ch_fai,
-//         ch_rrna_interval
-//     )
-//     ch_versions = ch_versions.mix(QC_WORKFLOW.out.versions)
+    // ch_versions = ch_versions.mix(QC_WORKFLOW.out.versions)
 
 //     //
 //     // Collate and save software versions
@@ -244,18 +163,6 @@ workflow RNAFUSION {
 //             newLine: true
 //         ).set { ch_collated_versions }
 
-    // //QC
-    // QC_WORKFLOW (
-    //     ch_reads_all,
-    //     STARFUSION_WORKFLOW.out.ch_bam_sorted,
-    //     ch_gtf,
-    //     ch_refflat,
-    //     ch_fasta,
-    //     ch_fai,
-    //     ch_rrna_interval
-    // )
-    // ch_versions = ch_versions.mix(QC_WORKFLOW.out.versions)
-
 
     // //
     // // Collate and save software versions

From 786b9bf4ec84fd6e2571ddd034b9923151cd4128 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Thu, 14 Nov 2024 15:45:31 +0100
Subject: [PATCH 15/41] remove unnecessary file

---
 AAA_BBB.html | 0
 1 file changed, 0 insertions(+), 0 deletions(-)
 delete mode 100644 AAA_BBB.html

diff --git a/AAA_BBB.html b/AAA_BBB.html
deleted file mode 100644
index e69de29b..00000000

From 460b6450ced2459dc4f2ce8abc5368dc5bc872c3 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Fri, 29 Nov 2024 09:18:26 +0100
Subject: [PATCH 16/41] add parameter interpretation in modules.config

---
 conf/modules.config                           |  18 +-
 main.nf                                       |   6 +-
 modules/local/fusionreport/detect/main.nf     |   6 +-
 modules/local/fusionreport/download/main.nf   |   2 +-
 .../utils_nfcore_rnafusion_pipeline/main.nf   |   3 +-
 workflows/rnafusion.nf                        | 182 +++++++++---------
 6 files changed, 104 insertions(+), 113 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index b07f5333..3b176c87 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -36,7 +36,7 @@ process {
     }
 
     withName: 'ARRIBA_VISUALISATION' {
-        ext.when   = { !params.fusioninspector_only && (params.starfusion || params.all) }
+        ext.when   = { {!params.fusioninspector_only} && ({params.starfusion} || {params.all}) }
         ext.prefix = { "${meta.id}_combined_fusions_arriba_visualisation" }
         publishDir = [
             path: { "${params.outdir}/arriba_visualisation" },
@@ -63,7 +63,7 @@ process {
 
     withName: 'FASTQC' {
         ext.args = '--quiet'
-        ext.when = { !params.skip_qc && !params.references_only }
+        ext.when = { {!params.skip_qc} && {!params.references_only} }
         publishDir = [
             path: { "${params.outdir}/fastqc" },
             mode: params.publish_dir_mode,
@@ -73,7 +73,7 @@ process {
 
     withName: 'FASTQC_FOR_FASTP' {
         ext.args = '--quiet'
-        ext.when = ( !params.skip_qc)
+        ext.when = { !params.skip_qc }
         ext.prefix = { "${meta.id}_trimmed" }
         publishDir = [
             path: { "${params.outdir}/fastqc_for_fastp" },
@@ -96,7 +96,7 @@ process {
 
     withName: 'FUSIONINSPECTOR' {
         ext.when = { !params.skip_vis }
-        ext.args = { params.fusioninspector_limitSjdbInsertNsj != 1000000 ? "--STAR_xtra_params \"--limitSjdbInsertNsj ${params.fusioninspector_limitSjdbInsertNsj}\"" : '' }
+        ext.args = { ${params.fusioninspector_limitSjdbInsertNsj} != 1000000 ? "--STAR_xtra_params \"--limitSjdbInsertNsj ${params.fusioninspector_limitSjdbInsertNsj}\"" : '' }
         ext.args2 = '--annotate --examine_coding_effect'
     }
 
@@ -111,7 +111,7 @@ process {
     }
 
     withName: 'FUSIONREPORT_DOWNLOAD' {
-        ext.args        = { params.qiagen ? "--qiagen" : "" }
+        ext.args        = { ${params.qiagen} ? "--qiagen" : "" }
         publishDir = [
             path: { "${params.genomes_base}/fusion_report_db" },
             mode: params.publish_dir_mode,
@@ -153,7 +153,7 @@ process {
     }
     withName: 'MULTIQC' {
         ext.when         = { !params.skip_qc }
-        ext.args   = params.multiqc_title ? "--title \"$params.multiqc_title\"" : ''
+        ext.args   = {params.multiqc_title} ? "--title \"$params.multiqc_title\"" : ''
         publishDir = [
             path: { "${params.outdir}/multiqc" },
             mode: params.publish_dir_mode,
@@ -162,12 +162,12 @@ process {
     }
 
     withName: 'PICARD_COLLECTRNASEQMETRICS' {
-        ext.when         = { !params.skip_qc && !params.fusioninspector_only && (params.starfusion || params.all) }
+        ext.when         = { {!params.skip_qc} && {!params.fusioninspector_only} && ( {params.starfusion} || {params.all}) }
 
     }
 
     withName: 'GATK4_MARKDUPLICATES' {
-        ext.when         = { !params.skip_qc && !params.fusioninspector_only && (params.starfusion || params.all) }
+        ext.when         = { {!params.skip_qc} && {!params.fusioninspector_only} && ( {params.starfusion}|| {params.all}) }
         publishDir = [
             path: { "${params.outdir}/picard" },
             mode: params.publish_dir_mode,
@@ -176,7 +176,7 @@ process {
     }
 
     withName: 'PICARD_COLLECTINSERTSIZEMETRICS' {
-        ext.when         = { !params.skip_qc && !params.fusioninspector_only && (params.starfusion || params.all) }
+        ext.when         = { ${!params.skip_qc} && ${!params.fusioninspector_only} && (${params.starfusion} || ${params.all}) }
         ext.prefix       = { "${meta.id}_collectinsertsize"}
         publishDir = [
             path: { "${params.outdir}/picard" },
diff --git a/main.nf b/main.nf
index 09216f56..78781bed 100644
--- a/main.nf
+++ b/main.nf
@@ -51,6 +51,9 @@ workflow NFCORE_RNAFUSION {
     //
 
     RNAFUSION(samplesheet)
+
+    emit:
+    multiqc_report = RNAFUSION.out.multiqc_report
 }
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -67,10 +70,8 @@ workflow {
     PIPELINE_INITIALISATION (
         params.version,
         params.validate_params,
-        params.monochrome_logs,
         args,
         params.outdir,
-        params.input
     )
 
     //
@@ -88,6 +89,7 @@ workflow {
         params.outdir,
         params.monochrome_logs,
         params.hook_url,
+        NFCORE_RNAFUSION.out.multiqc_report,
     )
 }
 
diff --git a/modules/local/fusionreport/detect/main.nf b/modules/local/fusionreport/detect/main.nf
index f2557bf0..ec7a076c 100644
--- a/modules/local/fusionreport/detect/main.nf
+++ b/modules/local/fusionreport/detect/main.nf
@@ -58,11 +58,7 @@ process FUSIONREPORT {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        fusion_report: sth
+        fusion_report: \$(fusion_report --version | sed 's/fusion-report //')
     END_VERSIONS
     """
 }
-    // cat <<-END_VERSIONS > versions.yml
-    // "${task.process}":
-    //     fusion_report: \$(fusion_report --version 2>&1 | sed 's/fusion-report //')
-    // END_VERSIONS
diff --git a/modules/local/fusionreport/download/main.nf b/modules/local/fusionreport/download/main.nf
index 971db1b7..04e069ee 100644
--- a/modules/local/fusionreport/download/main.nf
+++ b/modules/local/fusionreport/download/main.nf
@@ -10,7 +10,7 @@ process FUSIONREPORT_DOWNLOAD {
     val(passwd)
 
     output:
-    path "*"                , emit: reference
+    path "*.db"             , emit: reference
     path "versions.yml"     , emit: versions
 
     script:
diff --git a/subworkflows/local/utils_nfcore_rnafusion_pipeline/main.nf b/subworkflows/local/utils_nfcore_rnafusion_pipeline/main.nf
index ae62c8d4..b217a88d 100644
--- a/subworkflows/local/utils_nfcore_rnafusion_pipeline/main.nf
+++ b/subworkflows/local/utils_nfcore_rnafusion_pipeline/main.nf
@@ -30,10 +30,8 @@ workflow PIPELINE_INITIALISATION {
     take:
     version           // boolean: Display version and exit
     validate_params   // boolean: Boolean whether to validate parameters against the schema at runtime
-    monochrome_logs   // boolean: Do not use coloured log outputs
     nextflow_cli_args //   array: List of positional nextflow CLI args
     outdir            //  string: The output directory where the results will be saved
-    input             //  string: Path to input samplesheet
 
     main:
 
@@ -114,6 +112,7 @@ workflow PIPELINE_COMPLETION {
     outdir          //    path: Path to output directory where results will be published
     monochrome_logs // boolean: Disable ANSI colour codes in log output
     hook_url        //  string: hook URL for notifications
+    multiqc_report  //  string: Path to MultiQC report
 
     main:
     summary_params = paramsSummaryMap(workflow, parameters_schema: "nextflow_schema.json")
diff --git a/workflows/rnafusion.nf b/workflows/rnafusion.nf
index 238bcc3a..e14ac799 100644
--- a/workflows/rnafusion.nf
+++ b/workflows/rnafusion.nf
@@ -13,6 +13,10 @@ include { STRINGTIE_WORKFLOW            }   from '../subworkflows/local/stringti
 include { FUSIONCATCHER_WORKFLOW        }   from '../subworkflows/local/fusioncatcher_workflow'
 include { FUSIONINSPECTOR_WORKFLOW      }   from '../subworkflows/local/fusioninspector_workflow'
 include { FUSIONREPORT_WORKFLOW         }   from '../subworkflows/local/fusionreport_workflow'
+include { methodsDescriptionText        }   from '../subworkflows/local/utils_nfcore_rnafusion_pipeline'
+include { paramsSummaryMap              }   from 'plugin/nf-schema'
+include { paramsSummaryMultiqc          }   from '../subworkflows/nf-core/utils_nfcore_pipeline'
+include { softwareVersionsToYAML        }   from '../subworkflows/nf-core/utils_nfcore_pipeline'
 include { validateInputSamplesheet      }   from '../subworkflows/local/utils_nfcore_rnafusion_pipeline'
 
 include { CAT_FASTQ                     }   from '../modules/nf-core/cat/fastq/main'
@@ -63,9 +67,10 @@ workflow RNAFUSION {
     ch_reads = TRIM_WORKFLOW.out.trimmed_reads
     ch_versions = ch_versions.mix(TRIM_WORKFLOW.out.versions)
 
-    // SALMON_QUANT( ch_reads, BUILD_REFERENCES.out.ch_salmon_index.map{ meta, index ->  index  }, BUILD_REFERENCES.out.ch_gtf.map{ meta, gtf ->  gtf  }, [], false, 'A')
-    // ch_multiqc_files = ch_multiqc_files.mix(SALMON_QUANT.out.zi.collect{it[1]})
-    // ch_versions = ch_versions.mix(SALMON_QUANT.out.versions)
+
+    SALMON_QUANT( ch_reads, BUILD_REFERENCES.out.ch_salmon_index.map{ it -> it[1] }, BUILD_REFERENCES.out.ch_gtf.map{ it -> it[1] }, [], false, 'A')
+    ch_multiqc_files = ch_multiqc_files.mix(SALMON_QUANT.out.json_info.collect{it[1]})
+    ch_versions = ch_versions.mix(SALMON_QUANT.out.versions)
 
 
     //
@@ -139,97 +144,86 @@ workflow RNAFUSION {
     ch_versions = ch_versions.mix(FUSIONINSPECTOR_WORKFLOW.out.versions)
 
 
-    // //QC
-    // QC_WORKFLOW (
-    //     ch_reads,
-    //     STARFUSION_WORKFLOW.out.ch_bam_sorted,
-    //     STARFUSION_WORKFLOW.out.ch_bam_sorted_indexed,
-    //     BUILD_REFERENCES.out.ch_gtf,
-    //     BUILD_REFERENCES.out.ch_refflat,
-    //     BUILD_REFERENCES.out.ch_fasta,
-    //     BUILD_REFERENCES.out.ch_fai,
-    //     BUILD_REFERENCES.out.ch_rrna_interval
-    // )
-    // ch_versions = ch_versions.mix(QC_WORKFLOW.out.versions)
-
-//     //
-//     // Collate and save software versions
-//     //
-//     softwareVersionsToYAML(ch_versions)
-//         .collectFile(
-//             storeDir: "${params.outdir}/pipeline_info",
-//             name: 'nf_core_pipeline_software_mqc_versions.yml',
-//             sort: true,
-//             newLine: true
-//         ).set { ch_collated_versions }
-
-
-    // //
-    // // Collate and save software versions
-    // //
-    // softwareVersionsToYAML(ch_versions)
-    //     .collectFile(
-    //         storeDir: "${params.outdir}/pipeline_info",
-    //         name: 'nf_core_'  + 'pipeline_software_' +  'mqc_'  + 'versions.yml',
-    //         sort: true,
-    //         newLine: true
-    //     ).set { ch_collated_versions }
-
-    // //
-    // // MODULE: MultiQC
-    // //
-    // ch_multiqc_config        = Channel.fromPath(
-    //     "$projectDir/assets/multiqc_config.yml", checkIfExists: true)
-    // ch_multiqc_custom_config = params.multiqc_config ?
-    //     Channel.fromPath(params.multiqc_config, checkIfExists: true) :
-    //     Channel.empty()
-    // ch_multiqc_logo          = params.multiqc_logo ?
-    //     Channel.fromPath(params.multiqc_logo, checkIfExists: true) :
-    //     Channel.empty()
-
-    // summary_params      = paramsSummaryMap(
-    //     workflow, parameters_schema: "nextflow_schema.json")
-    // ch_workflow_summary = Channel.value(paramsSummaryMultiqc(summary_params))
-    // ch_multiqc_files = ch_multiqc_files.mix(
-    //     ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml'))
-    // ch_multiqc_custom_methods_description = params.multiqc_methods_description ?
-    //     file(params.multiqc_methods_description, checkIfExists: true) :
-    //     file("$projectDir/assets/methods_description_template.yml", checkIfExists: true)
-    // ch_methods_description                = Channel.value(
-    //     methodsDescriptionText(ch_multiqc_custom_methods_description))
-
-    // ch_multiqc_files = ch_multiqc_files.mix(ch_collated_versions)
-    // ch_multiqc_files = ch_multiqc_files.mix(
-    //     ch_methods_description.collectFile(
-    //         name: 'methods_description_mqc.yaml',
-    //         sort: true
-    //     )
-    // )
-    // ch_multiqc_files                      = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]}.ifEmpty([]))
-    // ch_multiqc_files                      = ch_multiqc_files.mix(TRIM_WORKFLOW.out.ch_fastp_html.collect{it[1]}.ifEmpty([]))
-    // ch_multiqc_files                      = ch_multiqc_files.mix(TRIM_WORKFLOW.out.ch_fastp_json.collect{it[1]}.ifEmpty([]))
-    // ch_multiqc_files                      = ch_multiqc_files.mix(TRIM_WORKFLOW.out.ch_fastqc_trimmed.collect{it[1]}.ifEmpty([]))
-    // ch_multiqc_files                      = ch_multiqc_files.mix(STARFUSION_WORKFLOW.out.star_stats.collect{it[1]}.ifEmpty([]))
-    // ch_multiqc_files                      = ch_multiqc_files.mix(STARFUSION_WORKFLOW.out.star_gene_count.collect{it[1]}.ifEmpty([]))
-    // ch_multiqc_files                      = ch_multiqc_files.mix(QC_WORKFLOW.out.rnaseq_metrics.collect{it[1]}.ifEmpty([]))
-    // ch_multiqc_files                      = ch_multiqc_files.mix(QC_WORKFLOW.out.duplicate_metrics.collect{it[1]}.ifEmpty([]))
-    // ch_multiqc_files                      = ch_multiqc_files.mix(QC_WORKFLOW.out.insertsize_metrics.collect{it[1]}.ifEmpty([]))
-    // ch_multiqc_files                      = ch_multiqc_files.mix(FUSIONINSPECTOR_WORKFLOW.out.ch_arriba_visualisation.collect{it[1]}.ifEmpty([]))
-
-    // MULTIQC (
-    //     ch_multiqc_files.collect(),
-    //     ch_multiqc_config.toList(),
-    //     ch_multiqc_custom_config.toList(),
-    //     ch_multiqc_logo.toList(),
-    //     [],
-    //     []
-    // )
-
-
-
-    // emit:
-    // multiqc_report = MULTIQC.out.report.toList() // channel: /path/to/multiqc_report.html
-    // versions       = ch_versions                 // channel: [ path(versions.yml) ]
+    //QC
+    QC_WORKFLOW (
+        ch_reads,
+        STARFUSION_WORKFLOW.out.ch_bam_sorted,
+        STARFUSION_WORKFLOW.out.ch_bam_sorted_indexed,
+        BUILD_REFERENCES.out.ch_gtf,
+        BUILD_REFERENCES.out.ch_refflat,
+        BUILD_REFERENCES.out.ch_fasta,
+        BUILD_REFERENCES.out.ch_fai,
+        BUILD_REFERENCES.out.ch_rrna_interval
+    )
+    ch_versions = ch_versions.mix(QC_WORKFLOW.out.versions)
+
+    //
+    // Collate and save software versions
+    //
+    softwareVersionsToYAML(ch_versions)
+        .collectFile(
+            storeDir: "${params.outdir}/pipeline_info",
+            name: 'nf_core_pipeline_software_mqc_versions.yml',
+            sort: true,
+            newLine: true
+        ).set { ch_collated_versions }
+
+
+    //
+    // MODULE: MultiQC
+    //
+    ch_multiqc_config        = Channel.fromPath(
+        "$projectDir/assets/multiqc_config.yml", checkIfExists: true)
+    ch_multiqc_custom_config = params.multiqc_config ?
+        Channel.fromPath(params.multiqc_config, checkIfExists: true) :
+        Channel.empty()
+    ch_multiqc_logo          = params.multiqc_logo ?
+        Channel.fromPath(params.multiqc_logo, checkIfExists: true) :
+        Channel.empty()
+
+    summary_params      = paramsSummaryMap(
+        workflow, parameters_schema: "nextflow_schema.json")
+    ch_workflow_summary = Channel.value(paramsSummaryMultiqc(summary_params))
+    ch_multiqc_files = ch_multiqc_files.mix(
+        ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml'))
+    ch_multiqc_custom_methods_description = params.multiqc_methods_description ?
+        file(params.multiqc_methods_description, checkIfExists: true) :
+        file("$projectDir/assets/methods_description_template.yml", checkIfExists: true)
+    ch_methods_description                = Channel.value(
+        methodsDescriptionText(ch_multiqc_custom_methods_description))
+
+    ch_multiqc_files = ch_multiqc_files.mix(ch_collated_versions)
+    ch_multiqc_files = ch_multiqc_files.mix(
+        ch_methods_description.collectFile(
+            name: 'methods_description_mqc.yaml',
+            sort: true
+        )
+    )
+    ch_multiqc_files                      = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]}.ifEmpty([]))
+    ch_multiqc_files                      = ch_multiqc_files.mix(TRIM_WORKFLOW.out.fastp_html.collect{it[1]}.ifEmpty([]))
+    ch_multiqc_files                      = ch_multiqc_files.mix(TRIM_WORKFLOW.out.fastp_json.collect{it[1]}.ifEmpty([]))
+    ch_multiqc_files                      = ch_multiqc_files.mix(TRIM_WORKFLOW.out.fastqc_trimmed.collect{it[1]}.ifEmpty([]))
+    ch_multiqc_files                      = ch_multiqc_files.mix(STARFUSION_WORKFLOW.out.star_stats.collect{it[1]}.ifEmpty([]))
+    ch_multiqc_files                      = ch_multiqc_files.mix(STARFUSION_WORKFLOW.out.star_gene_count.collect{it[1]}.ifEmpty([]))
+    ch_multiqc_files                      = ch_multiqc_files.mix(QC_WORKFLOW.out.rnaseq_metrics.collect{it[1]}.ifEmpty([]))
+    ch_multiqc_files                      = ch_multiqc_files.mix(QC_WORKFLOW.out.duplicate_metrics.collect{it[1]}.ifEmpty([]))
+    ch_multiqc_files                      = ch_multiqc_files.mix(QC_WORKFLOW.out.insertsize_metrics.collect{it[1]}.ifEmpty([]))
+    ch_multiqc_files                      = ch_multiqc_files.mix(FUSIONINSPECTOR_WORKFLOW.out.ch_arriba_visualisation.collect{it[1]}.ifEmpty([]))
+
+    MULTIQC (
+        ch_multiqc_files.collect(),
+        ch_multiqc_config.toList(),
+        ch_multiqc_custom_config.toList(),
+        ch_multiqc_logo.toList(),
+        [],
+        []
+    )
+
+
+
+    emit:
+    multiqc_report = MULTIQC.out.report.toList() // channel: /path/to/multiqc_report.html
+    versions       = ch_versions                 // channel: [ path(versions.yml) ]
 
 }
 

From d290fcdc0513cf1fdfc5f97c4e06d43d02829d8f Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Fri, 6 Dec 2024 10:56:21 +0100
Subject: [PATCH 17/41] update fusioncatcher container

---
 modules/local/fusioncatcher/build/main.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/modules/local/fusioncatcher/build/main.nf b/modules/local/fusioncatcher/build/main.nf
index f6ff0987..4aaaf504 100644
--- a/modules/local/fusioncatcher/build/main.nf
+++ b/modules/local/fusioncatcher/build/main.nf
@@ -2,7 +2,7 @@ process FUSIONCATCHER_BUILD {
     tag "fusioncatcher_build"
     label 'process_medium'
 
-    container "docker.io/clinicalgenomics/fusioncatcher:1.33"
+    container "docker.io/rannickscilifelab/fusioncatcher:1.34"
 
     input:
     val genome_gencode_version

From be6e10262720181536a80ca56fe12a79227ef815 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Mon, 9 Dec 2024 12:42:59 +0100
Subject: [PATCH 18/41] fix linting issues

---
 modules.json                                  |  6 +-
 .../local/get_rrna_transcript/environment.yml |  6 ++
 .../main.nf}                                  | 10 +--
 .../local/uscs/custom_gtftogenepred/main.nf   |  3 +-
 modules/nf-core/salmon/quant/main.nf          |  3 +-
 subworkflows/local/build_references.nf        | 22 +++--
 subworkflows/local/fusionreport_workflow.nf   |  2 +-
 .../nf-core/utils_nextflow_pipeline/main.nf   |  2 +
 .../tests/main.workflow.nf.test               | 10 ++-
 .../nf-core/utils_nfcore_pipeline/main.nf     | 89 +++++--------------
 .../tests/main.function.nf.test               | 46 ++++------
 .../tests/main.function.nf.test.snap          | 30 -------
 .../utils_nfschema_plugin/tests/main.nf.test  |  4 +-
 13 files changed, 86 insertions(+), 147 deletions(-)
 create mode 100644 modules/local/get_rrna_transcript/environment.yml
 rename modules/local/{get_rrna_transcripts.nf => get_rrna_transcript/main.nf} (79%)

diff --git a/modules.json b/modules.json
index 48fa1f6b..b41d5fa5 100644
--- a/modules.json
+++ b/modules.json
@@ -152,17 +152,17 @@
                 "nf-core": {
                     "utils_nextflow_pipeline": {
                         "branch": "master",
-                        "git_sha": "3aa0aec1d52d492fe241919f0c6100ebf0074082",
+                        "git_sha": "c2b22d85f30a706a3073387f30380704fcae013b",
                         "installed_by": ["subworkflows"]
                     },
                     "utils_nfcore_pipeline": {
                         "branch": "master",
-                        "git_sha": "1b6b9a3338d011367137808b49b923515080e3ba",
+                        "git_sha": "51ae5406a030d4da1e49e4dab49756844fdd6c7a",
                         "installed_by": ["subworkflows"]
                     },
                     "utils_nfschema_plugin": {
                         "branch": "master",
-                        "git_sha": "bbd5a41f4535a8defafe6080e00ea74c45f4f96c",
+                        "git_sha": "2fd2cd6d0e7b273747f32e465fdc6bcc3ae0814e",
                         "installed_by": ["subworkflows"]
                     }
                 }
diff --git a/modules/local/get_rrna_transcript/environment.yml b/modules/local/get_rrna_transcript/environment.yml
new file mode 100644
index 00000000..66b65c3a
--- /dev/null
+++ b/modules/local/get_rrna_transcript/environment.yml
@@ -0,0 +1,6 @@
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::pirate=1.0.5
+  - bioconda::perl-bioperl=1.7.8
diff --git a/modules/local/get_rrna_transcripts.nf b/modules/local/get_rrna_transcript/main.nf
similarity index 79%
rename from modules/local/get_rrna_transcripts.nf
rename to modules/local/get_rrna_transcript/main.nf
index cb39b3e4..5331f534 100644
--- a/modules/local/get_rrna_transcripts.nf
+++ b/modules/local/get_rrna_transcript/main.nf
@@ -2,17 +2,17 @@ process GET_RRNA_TRANSCRIPTS {
     tag 'get_rrna_bed'
     label 'process_low'
 
-    conda "bioconda::pirate=1.0.4 bioconda::perl-bioperl=1.7.2"
+    conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/pirate:1.0.4--hdfd78af_2' :
-        'biocontainers/pirate:1.0.4--hdfd78af_2' }"
+        'https://depot.galaxyproject.org/singularity/pirate:1.0.5--hdfd78af_0' :
+        'biocontainers/pirate:1.0.5--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(gtf)
 
     output:
-    path('rrna.gtf')    , emit: rrnagtf
-    path('rrna.bed')    , emit: bed
+    tuple val(meta), path('rrna.gtf')    , emit: rrnagtf
+    tuple val(meta), path('rrna.bed')    , emit: bed
     path "versions.yml" , emit: versions
 
     when:
diff --git a/modules/local/uscs/custom_gtftogenepred/main.nf b/modules/local/uscs/custom_gtftogenepred/main.nf
index 53a74e3d..9cc15765 100644
--- a/modules/local/uscs/custom_gtftogenepred/main.nf
+++ b/modules/local/uscs/custom_gtftogenepred/main.nf
@@ -11,7 +11,8 @@ process GTF_TO_REFFLAT {
     tuple val(meta), path (gtf)
 
     output:
-    path('*.refflat'), emit: refflat
+    path('*.refflat')    , emit: refflat
+    path "versions.yml"  , emit: versions
 
     script:
     def genepred = gtf + '.genepred'
diff --git a/modules/nf-core/salmon/quant/main.nf b/modules/nf-core/salmon/quant/main.nf
index e2d27352..f1e3b5cd 100644
--- a/modules/nf-core/salmon/quant/main.nf
+++ b/modules/nf-core/salmon/quant/main.nf
@@ -29,8 +29,7 @@ process SALMON_QUANT {
     prefix   = task.ext.prefix ?: "${meta.id}"
 
     def reference   = "--index $index"
-    def reads1 = []
-    def reads2 = []
+    def reads1 = [], reads2 = []
     meta.single_end ? [reads].flatten().each{reads1 << it} : reads.eachWithIndex{ v, ix -> ( ix & 1 ? reads2 : reads1) << v }
     def input_reads = meta.single_end ? "-r ${reads1.join(" ")}" : "-1 ${reads1.join(" ")} -2 ${reads2.join(" ")}"
     if (alignment_mode) {
diff --git a/subworkflows/local/build_references.nf b/subworkflows/local/build_references.nf
index 7d942601..8685feeb 100644
--- a/subworkflows/local/build_references.nf
+++ b/subworkflows/local/build_references.nf
@@ -5,15 +5,13 @@
 */
 
 include { GENCODE_DOWNLOAD }                from '../../modules/local/gencode_download/main'
-include { FUSIONCATCHER_DOWNLOAD }          from '../../modules/local/fusioncatcher/download/main'
 include { FUSIONCATCHER_BUILD }             from '../../modules/local/fusioncatcher/build/main'
 include { FUSIONREPORT_DOWNLOAD }           from '../../modules/local/fusionreport/download/main'
 include { HGNC_DOWNLOAD }                   from '../../modules/local/hgnc/main'
 include { STARFUSION_BUILD }                from '../../modules/local/starfusion/build/main'
-include { STARFUSION_DOWNLOAD }             from '../../modules/local/starfusion/download/main'
 include { GTF_TO_REFFLAT }                  from '../../modules/local/uscs/custom_gtftogenepred/main'
-include { GET_RRNA_TRANSCRIPTS }            from '../../modules/local/get_rrna_transcripts'
-// include { CONVERT2BED }                     from '../../modules/local/convert2bed/main'
+include { GET_RRNA_TRANSCRIPTS }            from '../../modules/local/get_rrna_transcript/main'
+
 /*
 ========================================================================================
     IMPORT NF-CORE MODULES/SUBWORKFLOWS
@@ -41,7 +39,7 @@ workflow BUILD_REFERENCES {
     if (!file(params.fasta).exists() || file(params.fasta).isEmpty() ||
             !file(params.gtf).exists() || file(params.gtf).isEmpty()){
         GENCODE_DOWNLOAD(params.genome_gencode_version, params.genome)
-        ch_versions = GENCODE_DOWNLOAD.out.versions
+        ch_versions = ch_versions.mix(GENCODE_DOWNLOAD.out.versions)
         ch_fasta = GENCODE_DOWNLOAD.out.fasta.map { that -> [[id:that.Name], that] }
         ch_gtf = GENCODE_DOWNLOAD.out.gtf.map { that -> [[id:that.Name], that] }
     } else {
@@ -51,7 +49,7 @@ workflow BUILD_REFERENCES {
 
     if (!file(params.fai).exists() || file(params.fai).isEmpty()){
         SAMTOOLS_FAIDX(ch_fasta, [[],[]])
-        ch_versions = SAMTOOLS_FAIDX.out.versions
+        ch_versions = ch_versions.mix(SAMTOOLS_FAIDX.out.versions)
         ch_fai = SAMTOOLS_FAIDX.out.fai
     } else {
         ch_fai = Channel.fromPath(params.fai).map { that -> [[id:that.Name], that] }
@@ -60,6 +58,7 @@ workflow BUILD_REFERENCES {
     if ((!file(params.hgnc_ref).exists() || file(params.hgnc_ref).isEmpty() ||
             !file(params.hgnc_date).exists() || file(params.hgnc_date).isEmpty()) && !params.skip_vcf){
         HGNC_DOWNLOAD( )
+        ch_versions = ch_versions.mix(HGNC_DOWNLOAD.out.versions)
         ch_hgnc_ref = HGNC_DOWNLOAD.out.hgnc_ref
         ch_hgnc_date = HGNC_DOWNLOAD.out.hgnc_date
     } else {
@@ -69,8 +68,11 @@ workflow BUILD_REFERENCES {
 
     if (!file(params.rrna_intervals).exists() || file(params.rrna_intervals).isEmpty()){
         GATK4_CREATESEQUENCEDICTIONARY(ch_fasta)
+        ch_versions = ch_versions.mix(GATK4_CREATESEQUENCEDICTIONARY.out.versions)
         GET_RRNA_TRANSCRIPTS(ch_gtf)
+        ch_versions = ch_versions.mix(GET_RRNA_TRANSCRIPTS.out.versions)
         GATK4_BEDTOINTERVALLIST(GET_RRNA_TRANSCRIPTS.out.bed.map { it -> [ [id:it.name], it ] }, GATK4_CREATESEQUENCEDICTIONARY.out.dict )
+        ch_versions = ch_versions.mix(GATK4_BEDTOINTERVALLIST.out.versions)
         ch_rrna_interval = GATK4_BEDTOINTERVALLIST.out.interval_list
     } else {
         ch_rrna_interval = Channel.fromPath(params.rrna_intervals).map { that -> [[id:that.Name], that] }
@@ -78,6 +80,7 @@ workflow BUILD_REFERENCES {
 
     if (!file(params.refflat).exists() || file(params.refflat).isEmpty()){
         GTF_TO_REFFLAT(ch_gtf)
+        ch_versions = ch_versions.mix(GTF_TO_REFFLAT.out.versions)
         ch_refflat = GTF_TO_REFFLAT.out.refflat.map { that -> [[id:that.Name], that] }
     } else {
         ch_refflat = Channel.fromPath(params.refflat).map { that -> [[id:that.Name], that] }
@@ -86,7 +89,9 @@ workflow BUILD_REFERENCES {
     if (!file(params.salmon_index).exists() || file(params.salmon_index).isEmpty() ||
         !file(params.salmon_index_stub_check).exists() || file(params.salmon_index_stub_check).isEmpty()){ // add condition for qc
         GFFREAD(ch_gtf, ch_fasta.map{ meta, fasta -> [ fasta ] })
+        ch_versions = ch_versions.mix(GFFREAD.out.versions)
         SALMON_INDEX(ch_fasta.map{ meta, fasta -> [ fasta ] }, GFFREAD.out.gffread_fasta.map{ meta, gffread_fasta -> [ gffread_fasta ] })
+        ch_versions = ch_versions.mix(SALMON_INDEX.out.versions)
         ch_salmon_index = SALMON_INDEX.out.index
     } else {
         ch_salmon_index = Channel.fromPath(params.salmon_index)
@@ -96,6 +101,7 @@ workflow BUILD_REFERENCES {
             (!file(params.starindex_ref).exists() || file(params.starindex_ref).isEmpty() ||
             !file(params.starindex_ref_stub_check).exists() || file(params.starindex_ref_stub_check).isEmpty() )) {
         STAR_GENOMEGENERATE(ch_fasta, ch_gtf)
+        ch_versions = ch_versions.mix(STAR_GENOMEGENERATE.out.versions)
         ch_starindex_ref = STAR_GENOMEGENERATE.out.index
     } else {
         ch_starindex_ref = Channel.fromPath(params.starindex_ref).map { that -> [[id:that.Name], that] }
@@ -106,6 +112,7 @@ workflow BUILD_REFERENCES {
             !file(params.arriba_ref_known_fusions).exists() || file(params.arriba_ref_known_fusions).isEmpty() ||
             !file(params.arriba_ref_protein_domains).exists() || file(params.arriba_ref_protein_domains).isEmpty())) {
         ARRIBA_DOWNLOAD(params.genome)
+        ch_versions = ch_versions.mix(ARRIBA_DOWNLOAD.out.versions)
         ch_arriba_ref_blacklist = ARRIBA_DOWNLOAD.out.blacklist
         ch_arriba_ref_cytobands = ARRIBA_DOWNLOAD.out.cytobands
         ch_arriba_ref_known_fusions = ARRIBA_DOWNLOAD.out.known_fusions
@@ -122,6 +129,7 @@ workflow BUILD_REFERENCES {
             (!file(params.fusioncatcher_ref).exists() || file(params.fusioncatcher_ref).isEmpty() ||
             !file(params.fusioncatcher_ref_stub_check).exists() || file(params.fusioncatcher_ref_stub_check).isEmpty() )) {
             FUSIONCATCHER_BUILD(params.genome_gencode_version)
+            ch_versions = ch_versions.mix(FUSIONCATCHER_BUILD.out.versions)
             ch_fusioncatcher_ref = FUSIONCATCHER_BUILD.out.reference
     }
     else {
@@ -133,6 +141,7 @@ workflow BUILD_REFERENCES {
             (!file(params.starfusion_ref).exists() || file(params.starfusion_ref).isEmpty() ||
             !file(params.starfusion_ref_stub_check).exists() || file(params.starfusion_ref_stub_check).isEmpty() )) {
             STARFUSION_BUILD(ch_fasta, ch_gtf)
+            ch_versions = ch_versions.mix(STARFUSION_BUILD.out.versions)
             ch_starfusion_ref = STARFUSION_BUILD.out.reference
     }
     else {
@@ -145,6 +154,7 @@ workflow BUILD_REFERENCES {
             !file(params.fusionreport_ref_stub_check).exists() || file(params.fusionreport_ref_stub_check).isEmpty())) {
         if (!params.cosmic_username || !params.cosmic_passwd) { exit 1, 'COSMIC username and/or password missing' }
         FUSIONREPORT_DOWNLOAD(params.cosmic_username, params.cosmic_passwd)
+        ch_versions = ch_versions.mix(FUSIONREPORT_DOWNLOAD.out.versions)
         ch_fusionreport_ref = FUSIONREPORT_DOWNLOAD.out.reference
     } else {
         ch_fusionreport_ref = Channel.fromPath(params.fusionreport_ref)
diff --git a/subworkflows/local/fusionreport_workflow.nf b/subworkflows/local/fusionreport_workflow.nf
index a61759f7..5c9bfde1 100644
--- a/subworkflows/local/fusionreport_workflow.nf
+++ b/subworkflows/local/fusionreport_workflow.nf
@@ -23,7 +23,7 @@ workflow FUSIONREPORT_WORKFLOW {
             FUSIONREPORT(reads_fusions, fusionreport_ref, params.tools_cutoff)
             ch_fusion_list = FUSIONREPORT.out.fusion_list
             ch_fusion_list_filtered = FUSIONREPORT.out.fusion_list_filtered
-            // ch_versions = ch_versions.mix(FUSIONREPORT.out.versions)
+            ch_versions = ch_versions.mix(FUSIONREPORT.out.versions)
             ch_report = FUSIONREPORT.out.report
             ch_csv = FUSIONREPORT.out.csv
         } else {
diff --git a/subworkflows/nf-core/utils_nextflow_pipeline/main.nf b/subworkflows/nf-core/utils_nextflow_pipeline/main.nf
index 0fcbf7b3..d6e593e8 100644
--- a/subworkflows/nf-core/utils_nextflow_pipeline/main.nf
+++ b/subworkflows/nf-core/utils_nextflow_pipeline/main.nf
@@ -92,10 +92,12 @@ def checkCondaChannels() {
         channels = config.channels
     }
     catch (NullPointerException e) {
+        log.debug(e)
         log.warn("Could not verify conda channel configuration.")
         return null
     }
     catch (IOException e) {
+        log.debug(e)
         log.warn("Could not verify conda channel configuration.")
         return null
     }
diff --git a/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.workflow.nf.test b/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.workflow.nf.test
index ca964ce8..02dbf094 100644
--- a/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.workflow.nf.test
+++ b/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.workflow.nf.test
@@ -52,10 +52,12 @@ nextflow_workflow {
         }
 
         then {
-            assertAll(
-                { assert workflow.success },
-                { assert workflow.stdout.contains("nextflow_workflow v9.9.9") }
-            )
+            expect {
+                with(workflow) {
+                    assert success
+                    assert "nextflow_workflow v9.9.9" in stdout
+                }
+            }
         }
     }
 
diff --git a/subworkflows/nf-core/utils_nfcore_pipeline/main.nf b/subworkflows/nf-core/utils_nfcore_pipeline/main.nf
index 5cb7bafe..bfd25876 100644
--- a/subworkflows/nf-core/utils_nfcore_pipeline/main.nf
+++ b/subworkflows/nf-core/utils_nfcore_pipeline/main.nf
@@ -56,21 +56,6 @@ def checkProfileProvided(nextflow_cli_args) {
     }
 }
 
-//
-// Citation string for pipeline
-//
-def workflowCitation() {
-    def temp_doi_ref = ""
-    def manifest_doi = workflow.manifest.doi.tokenize(",")
-    // Handling multiple DOIs
-    // Removing `https://doi.org/` to handle pipelines using DOIs vs DOI resolvers
-    // Removing ` ` since the manifest.doi is a string and not a proper list
-    manifest_doi.each { doi_ref ->
-        temp_doi_ref += "  https://doi.org/${doi_ref.replace('https://doi.org/', '').replace(' ', '')}\n"
-    }
-    return "If you use ${workflow.manifest.name} for your analysis please cite:\n\n" + "* The pipeline\n" + temp_doi_ref + "\n" + "* The nf-core framework\n" + "  https://doi.org/10.1038/s41587-020-0439-x\n\n" + "* Software dependencies\n" + "  https://github.com/${workflow.manifest.name}/blob/master/CITATIONS.md"
-}
-
 //
 // Generate workflow version string
 //
@@ -150,33 +135,6 @@ def paramsSummaryMultiqc(summary_params) {
     return yaml_file_text
 }
 
-//
-// nf-core logo
-//
-def nfCoreLogo(monochrome_logs=true) {
-    def colors = logColours(monochrome_logs) as Map
-    String.format(
-        """\n
-        ${dashedLine(monochrome_logs)}
-                                                ${colors.green},--.${colors.black}/${colors.green},-.${colors.reset}
-        ${colors.blue}        ___     __   __   __   ___     ${colors.green}/,-._.--~\'${colors.reset}
-        ${colors.blue}  |\\ | |__  __ /  ` /  \\ |__) |__         ${colors.yellow}}  {${colors.reset}
-        ${colors.blue}  | \\| |       \\__, \\__/ |  \\ |___     ${colors.green}\\`-._,-`-,${colors.reset}
-                                                ${colors.green}`._,._,\'${colors.reset}
-        ${colors.purple}  ${workflow.manifest.name} ${getWorkflowVersion()}${colors.reset}
-        ${dashedLine(monochrome_logs)}
-        """.stripIndent()
-    )
-}
-
-//
-// Return dashed line
-//
-def dashedLine(monochrome_logs=true) {
-    def colors = logColours(monochrome_logs) as Map
-    return "-${colors.dim}----------------------------------------------------${colors.reset}-"
-}
-
 //
 // ANSII colours used for terminal logging
 //
@@ -245,28 +203,24 @@ def logColours(monochrome_logs=true) {
     return colorcodes
 }
 
-//
-// Attach the multiqc report to email
-//
-def attachMultiqcReport(multiqc_report) {
-    def mqc_report = null
-    try {
-        if (workflow.success) {
-            mqc_report = multiqc_report.getVal()
-            if (mqc_report.getClass() == ArrayList && mqc_report.size() >= 1) {
-                if (mqc_report.size() > 1) {
-                    log.warn("[${workflow.manifest.name}] Found multiple reports from process 'MULTIQC', will use only one")
-                }
-                mqc_report = mqc_report[0]
-            }
+// Return a single report from an object that may be a Path or List
+//
+def getSingleReport(multiqc_reports) {
+    if (multiqc_reports instanceof Path) {
+        return multiqc_reports
+    } else if (multiqc_reports instanceof List) {
+        if (multiqc_reports.size() == 0) {
+            log.warn("[${workflow.manifest.name}] No reports found from process 'MULTIQC'")
+            return null
+        } else if (multiqc_reports.size() == 1) {
+            return multiqc_reports.first()
+        } else {
+            log.warn("[${workflow.manifest.name}] Found multiple reports from process 'MULTIQC', will use only one")
+            return multiqc_reports.first()
         }
+    } else {
+        return null
     }
-    catch (Exception all) {
-        if (multiqc_report) {
-            log.warn("[${workflow.manifest.name}] Could not attach MultiQC report to summary email")
-        }
-    }
-    return mqc_report
 }
 
 //
@@ -320,7 +274,7 @@ def completionEmail(summary_params, email, email_on_fail, plaintext_email, outdi
     email_fields['summary']      = summary << misc_fields
 
     // On success try attach the multiqc report
-    def mqc_report = attachMultiqcReport(multiqc_report)
+    def mqc_report = getSingleReport(multiqc_report)
 
     // Check if we are only sending emails on failure
     def email_address = email
@@ -340,7 +294,7 @@ def completionEmail(summary_params, email, email_on_fail, plaintext_email, outdi
     def email_html    = html_template.toString()
 
     // Render the sendmail template
-    def max_multiqc_email_size = (params.containsKey('max_multiqc_email_size') ? params.max_multiqc_email_size : 0) as nextflow.util.MemoryUnit
+    def max_multiqc_email_size = (params.containsKey('max_multiqc_email_size') ? params.max_multiqc_email_size : 0) as MemoryUnit
     def smail_fields           = [email: email_address, subject: subject, email_txt: email_txt, email_html: email_html, projectDir: "${workflow.projectDir}", mqcFile: mqc_report, mqcMaxSize: max_multiqc_email_size.toBytes()]
     def sf                     = new File("${workflow.projectDir}/assets/sendmail_template.txt")
     def sendmail_template      = engine.createTemplate(sf).make(smail_fields)
@@ -351,14 +305,17 @@ def completionEmail(summary_params, email, email_on_fail, plaintext_email, outdi
     if (email_address) {
         try {
             if (plaintext_email) {
-new org.codehaus.groovy.GroovyException('Send plaintext e-mail, not HTML')            }
+                new org.codehaus.groovy.GroovyException('Send plaintext e-mail, not HTML')
+            }
             // Try to send HTML e-mail using sendmail
             def sendmail_tf = new File(workflow.launchDir.toString(), ".sendmail_tmp.html")
             sendmail_tf.withWriter { w -> w << sendmail_html }
             ['sendmail', '-t'].execute() << sendmail_html
             log.info("-${colors.purple}[${workflow.manifest.name}]${colors.green} Sent summary e-mail to ${email_address} (sendmail)-")
         }
-        catch (Exception all) {
+        catch (Exception msg) {
+            log.debug(msg.toString())
+            log.debug("Trying with mail instead of sendmail")
             // Catch failures and try with plaintext
             def mail_cmd = ['mail', '-s', subject, '--content-type=text/html', email_address]
             mail_cmd.execute() << email_html
diff --git a/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test b/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test
index 1dc317f8..f117040c 100644
--- a/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test
+++ b/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test
@@ -41,26 +41,14 @@ nextflow_function {
         }
     }
 
-    test("Test Function workflowCitation") {
-
-        function "workflowCitation"
-
-        then {
-            assertAll(
-                { assert function.success },
-                { assert snapshot(function.result).match() }
-            )
-        }
-    }
-
-    test("Test Function nfCoreLogo") {
+    test("Test Function without logColours") {
 
-        function "nfCoreLogo"
+        function "logColours"
 
         when {
             function {
                 """
-                input[0] = false
+                input[0] = true
                 """
             }
         }
@@ -73,9 +61,8 @@ nextflow_function {
         }
     }
 
-    test("Test Function dashedLine") {
-
-        function "dashedLine"
+    test("Test Function with logColours") {
+        function "logColours"
 
         when {
             function {
@@ -93,14 +80,13 @@ nextflow_function {
         }
     }
 
-    test("Test Function without logColours") {
-
-        function "logColours"
+    test("Test Function getSingleReport with a single file") {
+        function "getSingleReport"
 
         when {
             function {
                 """
-                input[0] = true
+                input[0] = file(params.modules_testdata_base_path + '/generic/tsv/test.tsv', checkIfExists: true)
                 """
             }
         }
@@ -108,18 +94,22 @@ nextflow_function {
         then {
             assertAll(
                 { assert function.success },
-                { assert snapshot(function.result).match() }
+                { assert function.result.contains("test.tsv") }
             )
         }
     }
 
-    test("Test Function with logColours") {
-        function "logColours"
+    test("Test Function getSingleReport with multiple files") {
+        function "getSingleReport"
 
         when {
             function {
                 """
-                input[0] = false
+                input[0] = [
+                    file(params.modules_testdata_base_path + '/generic/tsv/test.tsv', checkIfExists: true),
+                    file(params.modules_testdata_base_path + '/generic/tsv/network.tsv', checkIfExists: true),
+                    file(params.modules_testdata_base_path + '/generic/tsv/expression.tsv', checkIfExists: true)
+                ]
                 """
             }
         }
@@ -127,7 +117,9 @@ nextflow_function {
         then {
             assertAll(
                 { assert function.success },
-                { assert snapshot(function.result).match() }
+                { assert function.result.contains("test.tsv") },
+                { assert !function.result.contains("network.tsv") },
+                { assert !function.result.contains("expression.tsv") }
             )
         }
     }
diff --git a/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test.snap b/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test.snap
index 1037232c..02c67014 100644
--- a/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test.snap
+++ b/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test.snap
@@ -17,26 +17,6 @@
         },
         "timestamp": "2024-02-28T12:02:59.729647"
     },
-    "Test Function nfCoreLogo": {
-        "content": [
-            "\n\n-\u001b[2m----------------------------------------------------\u001b[0m-\n                                        \u001b[0;32m,--.\u001b[0;30m/\u001b[0;32m,-.\u001b[0m\n\u001b[0;34m        ___     __   __   __   ___     \u001b[0;32m/,-._.--~'\u001b[0m\n\u001b[0;34m  |\\ | |__  __ /  ` /  \\ |__) |__         \u001b[0;33m}  {\u001b[0m\n\u001b[0;34m  | \\| |       \\__, \\__/ |  \\ |___     \u001b[0;32m\\`-._,-`-,\u001b[0m\n                                        \u001b[0;32m`._,._,'\u001b[0m\n\u001b[0;35m  nextflow_workflow v9.9.9\u001b[0m\n-\u001b[2m----------------------------------------------------\u001b[0m-\n"
-        ],
-        "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
-        },
-        "timestamp": "2024-02-28T12:03:10.562934"
-    },
-    "Test Function workflowCitation": {
-        "content": [
-            "If you use nextflow_workflow for your analysis please cite:\n\n* The pipeline\n  https://doi.org/10.5281/zenodo.5070524\n\n* The nf-core framework\n  https://doi.org/10.1038/s41587-020-0439-x\n\n* Software dependencies\n  https://github.com/nextflow_workflow/blob/master/CITATIONS.md"
-        ],
-        "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
-        },
-        "timestamp": "2024-02-28T12:03:07.019761"
-    },
     "Test Function without logColours": {
         "content": [
             {
@@ -95,16 +75,6 @@
         },
         "timestamp": "2024-02-28T12:03:17.969323"
     },
-    "Test Function dashedLine": {
-        "content": [
-            "-\u001b[2m----------------------------------------------------\u001b[0m-"
-        ],
-        "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
-        },
-        "timestamp": "2024-02-28T12:03:14.366181"
-    },
     "Test Function with logColours": {
         "content": [
             {
diff --git a/subworkflows/nf-core/utils_nfschema_plugin/tests/main.nf.test b/subworkflows/nf-core/utils_nfschema_plugin/tests/main.nf.test
index 842dc432..8fb30164 100644
--- a/subworkflows/nf-core/utils_nfschema_plugin/tests/main.nf.test
+++ b/subworkflows/nf-core/utils_nfschema_plugin/tests/main.nf.test
@@ -42,7 +42,7 @@ nextflow_workflow {
 
             params {
                 test_data   = ''
-                outdir      = 1
+                outdir      = null
             }
 
             workflow {
@@ -94,7 +94,7 @@ nextflow_workflow {
 
             params {
                 test_data   = ''
-                outdir      = 1
+                outdir      = null
             }
 
             workflow {

From 41523f932dfd76f044d1519a5210336128a55cc6 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Mon, 9 Dec 2024 12:43:53 +0100
Subject: [PATCH 19/41] prettier

---
 .github/workflows/awsfulltest.yml | 1 -
 1 file changed, 1 deletion(-)

diff --git a/.github/workflows/awsfulltest.yml b/.github/workflows/awsfulltest.yml
index d1492d8b..baaa0461 100644
--- a/.github/workflows/awsfulltest.yml
+++ b/.github/workflows/awsfulltest.yml
@@ -54,4 +54,3 @@ jobs:
           path: |
             seqera_platform_action_*.log
             seqera_platform_action_*.json
-

From 86c299d54f63a9a387ded1e118868b287f1890e7 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Mon, 9 Dec 2024 15:41:31 +0100
Subject: [PATCH 20/41] update comments

---
 README.md                                | 2 +-
 docs/usage.md                            | 1 -
 modules/local/hgnc/main.nf               | 1 -
 modules/local/starfusion/build/main.nf   | 1 +
 subworkflows/local/build_references.nf   | 2 +-
 subworkflows/local/trim_workflow/main.nf | 3 +--
 workflows/rnafusion.nf                   | 4 +---
 7 files changed, 5 insertions(+), 9 deletions(-)

diff --git a/README.md b/README.md
index aa873457..809de85f 100644
--- a/README.md
+++ b/README.md
@@ -31,7 +31,7 @@ In rnafusion the full-sized test includes reference building and fusion detectio
 
 ### Build references
 
-`--references_only` triggers a workflow to ONLY build references, otherwise the references are built with the analysis run:
+`--references_only` triggers a workflow to ONLY build references, otherwise the references are build when the analysis is run:
 
 1. Download gencode fasta and gtf files
 2. Create [STAR](https://github.com/alexdobin/STAR) index
diff --git a/docs/usage.md b/docs/usage.md
index 1b0db1c5..c383df54 100644
--- a/docs/usage.md
+++ b/docs/usage.md
@@ -397,7 +397,6 @@ If `-profile` is not specified, the pipeline will run locally and expect all sof
 - `test`
   - A profile with a complete configuration for automated testing
   - Includes links to test data so needs no other parameters
-  - Needs to run in two steps: with `--references_only` first and then without `--references_only` to run the analysis
   - !!!! Run with `-stub` as all references need to be downloaded otherwise !!!!
 
 ### `-resume`
diff --git a/modules/local/hgnc/main.nf b/modules/local/hgnc/main.nf
index 2aa56038..aa5c077c 100644
--- a/modules/local/hgnc/main.nf
+++ b/modules/local/hgnc/main.nf
@@ -10,7 +10,6 @@ process HGNC_DOWNLOAD {
     output:
     path "hgnc_complete_set.txt"        , emit: hgnc_ref
     path "HGNC-DB-timestamp.txt"        , emit: hgnc_date
-
     path "versions.yml"   , emit: versions
 
 
diff --git a/modules/local/starfusion/build/main.nf b/modules/local/starfusion/build/main.nf
index 6ac3c694..436a5e4f 100644
--- a/modules/local/starfusion/build/main.nf
+++ b/modules/local/starfusion/build/main.nf
@@ -10,6 +10,7 @@ process STARFUSION_BUILD {
 
     output:
     path "*"  , emit: reference
+    path "versions.yml"   , emit: versions
 
     script:
     def binPath = (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1)  ? "prep_genome_lib.pl" : "/usr/local/src/STAR-Fusion/ctat-genome-lib-builder/prep_genome_lib.pl"
diff --git a/subworkflows/local/build_references.nf b/subworkflows/local/build_references.nf
index 8685feeb..2399acbd 100644
--- a/subworkflows/local/build_references.nf
+++ b/subworkflows/local/build_references.nf
@@ -94,7 +94,7 @@ workflow BUILD_REFERENCES {
         ch_versions = ch_versions.mix(SALMON_INDEX.out.versions)
         ch_salmon_index = SALMON_INDEX.out.index
     } else {
-        ch_salmon_index = Channel.fromPath(params.salmon_index)
+        ch_salmon_index = Channel.fromPath({params.salmon_index})
     }
 
     if ((params.starindex || params.all || params.starfusion || params.arriba) &&
diff --git a/subworkflows/local/trim_workflow/main.nf b/subworkflows/local/trim_workflow/main.nf
index d2492116..845adbaf 100644
--- a/subworkflows/local/trim_workflow/main.nf
+++ b/subworkflows/local/trim_workflow/main.nf
@@ -7,7 +7,6 @@ workflow TRIM_WORKFLOW {
 
     take:
         reads           // channel [ meta, [ fastq files ] ]
-        adapter_fasta   // channel [ path ]
 
     main:
         ch_versions       = Channel.empty()
@@ -16,7 +15,7 @@ workflow TRIM_WORKFLOW {
         ch_fastqc_trimmed = Channel.empty()
 
         if ( {params.fastp_trim} ) {
-            FASTP(reads, adapter_fasta.ifEmpty( [] ), false, false, false)
+            FASTP(reads, {params.adapter_fasta}.ifEmpty( [] ), false, false, false)
             ch_versions = ch_versions.mix(FASTP.out.versions)
 
             FASTQC_FOR_FASTP(FASTP.out.reads)
diff --git a/workflows/rnafusion.nf b/workflows/rnafusion.nf
index 52348721..ee0e1e57 100644
--- a/workflows/rnafusion.nf
+++ b/workflows/rnafusion.nf
@@ -66,7 +66,6 @@ workflow RNAFUSION {
     BUILD_REFERENCES()
     ch_versions = ch_versions.mix(BUILD_REFERENCES.out.versions)
 
-
     //
     // QC from FASTQ files
     //
@@ -81,8 +80,7 @@ workflow RNAFUSION {
     // Trimming
     //
     TRIM_WORKFLOW (
-        ch_samplesheet,
-        ch_adapter_fastp,
+        ch_samplesheet
     )
     ch_reads = TRIM_WORKFLOW.out.ch_reads_all
     ch_versions = ch_versions.mix(TRIM_WORKFLOW.out.versions)

From 35b5d9cb50a489c6c576bc2aa93f7cd5a6991e6c Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Tue, 10 Dec 2024 11:44:24 +0100
Subject: [PATCH 21/41] fix i/o in channels

---
 conf/modules.config                      |  8 +++----
 subworkflows/local/build_references.nf   |  6 +++---
 subworkflows/local/trim_workflow/main.nf |  2 +-
 workflows/rnafusion.nf                   | 27 +++++-------------------
 4 files changed, 13 insertions(+), 30 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index d20ca0f2..d021ae36 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -18,10 +18,6 @@ process {
         saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
     ]
 
-    withName: '.*' {
-            ext.when = { !params.references_only || task.process.contains('BUILD_REFERENCES') }
-        }
-
     withName: 'ARRIBA_ARRIBA' {
         publishDir = [
             path: { "${params.outdir}/arriba" },
@@ -371,4 +367,8 @@ process {
     withName: 'VCF_COLLECT' {
         ext.when = { {!params.fusioninspector_only} && {!params.skip_vcf} }
     }
+
+    withName: '.*' {
+            ext.when = { !params.references_only || task.process.contains('BUILD_REFERENCES') }
+        }
 }
diff --git a/subworkflows/local/build_references.nf b/subworkflows/local/build_references.nf
index 2399acbd..e158f566 100644
--- a/subworkflows/local/build_references.nf
+++ b/subworkflows/local/build_references.nf
@@ -71,7 +71,7 @@ workflow BUILD_REFERENCES {
         ch_versions = ch_versions.mix(GATK4_CREATESEQUENCEDICTIONARY.out.versions)
         GET_RRNA_TRANSCRIPTS(ch_gtf)
         ch_versions = ch_versions.mix(GET_RRNA_TRANSCRIPTS.out.versions)
-        GATK4_BEDTOINTERVALLIST(GET_RRNA_TRANSCRIPTS.out.bed.map { it -> [ [id:it.name], it ] }, GATK4_CREATESEQUENCEDICTIONARY.out.dict )
+        GATK4_BEDTOINTERVALLIST(GET_RRNA_TRANSCRIPTS.out.bed, GATK4_CREATESEQUENCEDICTIONARY.out.dict )
         ch_versions = ch_versions.mix(GATK4_BEDTOINTERVALLIST.out.versions)
         ch_rrna_interval = GATK4_BEDTOINTERVALLIST.out.interval_list
     } else {
@@ -153,9 +153,9 @@ workflow BUILD_REFERENCES {
             (!file(params.fusionreport_ref).exists() || file(params.fusionreport_ref).isEmpty() ||
             !file(params.fusionreport_ref_stub_check).exists() || file(params.fusionreport_ref_stub_check).isEmpty())) {
         if (!params.cosmic_username || !params.cosmic_passwd) { exit 1, 'COSMIC username and/or password missing' }
-        FUSIONREPORT_DOWNLOAD(params.cosmic_username, params.cosmic_passwd)
+        FUSIONREPORT_DOWNLOAD()
         ch_versions = ch_versions.mix(FUSIONREPORT_DOWNLOAD.out.versions)
-        ch_fusionreport_ref = FUSIONREPORT_DOWNLOAD.out.reference
+        ch_fusionreport_ref = FUSIONREPORT_DOWNLOAD.out.mitelman.map{ it.parent }
     } else {
         ch_fusionreport_ref = Channel.fromPath(params.fusionreport_ref)
     }
diff --git a/subworkflows/local/trim_workflow/main.nf b/subworkflows/local/trim_workflow/main.nf
index 845adbaf..512a07b5 100644
--- a/subworkflows/local/trim_workflow/main.nf
+++ b/subworkflows/local/trim_workflow/main.nf
@@ -15,7 +15,7 @@ workflow TRIM_WORKFLOW {
         ch_fastqc_trimmed = Channel.empty()
 
         if ( {params.fastp_trim} ) {
-            FASTP(reads, {params.adapter_fasta}.ifEmpty( [] ), false, false, false)
+            FASTP(reads, {params.adapter_fasta}, false, false, false)
             ch_versions = ch_versions.mix(FASTP.out.versions)
 
             FASTQC_FOR_FASTP(FASTP.out.reads)
diff --git a/workflows/rnafusion.nf b/workflows/rnafusion.nf
index ee0e1e57..cf358533 100644
--- a/workflows/rnafusion.nf
+++ b/workflows/rnafusion.nf
@@ -38,27 +38,10 @@ workflow RNAFUSION {
 
     main:
 
-    ch_starindex_ref              = params.starfusion_build ? Channel.fromPath(params.starindex_ref).map { it -> [[id:it.Name], it] }.collect() : Channel.fromPath("${params.starfusion_ref}/ref_genome.fa.star.idx").map { it -> [[id:it.Name], it] }.collect()
-    ch_starindex_ensembl_ref      = Channel.fromPath(params.starindex_ref).map { it -> [[id:it.Name], it] }.collect()
-    ch_refflat                    = params.starfusion_build ? Channel.fromPath(params.refflat).map { it -> [[id:it.Name], it] }.collect() : Channel.fromPath("${params.ensembl_ref}/ref_annot.gtf.refflat").map { it -> [[id:it.Name], it] }.collect()
-    ch_rrna_interval              = params.starfusion_build ?  Channel.fromPath(params.rrna_intervals).map { it -> [[id:it.Name], it] }.collect() : Channel.fromPath("${params.ensembl_ref}/ref_annot.interval_list").map { it -> [[id:it.Name], it] }.collect()
-    ch_adapter_fastp              = params.adapter_fasta ? Channel.fromPath(params.adapter_fasta, checkIfExists: true) : Channel.empty()
-    ch_fusionreport_ref           = Channel.fromPath(params.fusionreport_ref).map { it -> [[id:it.Name], it] }.collect()
-    ch_arriba_ref_blacklist       = Channel.fromPath(params.arriba_ref_blacklist).map { it -> [[id:it.Name], it] }.collect()
-    ch_arriba_ref_known_fusions   = Channel.fromPath(params.arriba_ref_known_fusions).map { it -> [[id:it.Name], it] }.collect()
-    ch_arriba_ref_protein_domains = Channel.fromPath(params.arriba_ref_protein_domains).map { it -> [[id:it.Name], it] }.collect()
-    ch_arriba_ref_cytobands       = Channel.fromPath(params.arriba_ref_cytobands).map { it -> [[id:it.Name], it] }.collect()
-    ch_hgnc_ref                   = Channel.fromPath(params.hgnc_ref).map { it -> [[id:it.Name], it] }.collect()
-    ch_hgnc_date                  = Channel.fromPath(params.hgnc_date).map { it -> [[id:it.Name], it] }.collect()
-    ch_fasta                      = Channel.fromPath(params.fasta).map { it -> [[id:it.Name], it] }.collect()
-    ch_gtf                        = Channel.fromPath(params.gtf).map { it -> [[id:it.Name], it] }.collect()
-    ch_salmon_index               = Channel.fromPath(params.salmon_index).map { it -> [[id:it.Name], it] }.collect()
-    ch_fai                        = Channel.fromPath(params.fai).map { it -> [[id:it.Name], it] }.collect()
-
-
     ch_versions = Channel.empty()
     ch_multiqc_files = Channel.empty()
 
+
     //
     // Create references if necessary
     //
@@ -66,6 +49,7 @@ workflow RNAFUSION {
     BUILD_REFERENCES()
     ch_versions = ch_versions.mix(BUILD_REFERENCES.out.versions)
 
+
     //
     // QC from FASTQ files
     //
@@ -85,7 +69,6 @@ workflow RNAFUSION {
     ch_reads = TRIM_WORKFLOW.out.ch_reads_all
     ch_versions = ch_versions.mix(TRIM_WORKFLOW.out.versions)
 
-
     SALMON_QUANT( ch_reads, BUILD_REFERENCES.out.ch_salmon_index.map{ it -> it[1] }, BUILD_REFERENCES.out.ch_gtf.map{ it -> it[1] }, [], false, 'A')
     ch_multiqc_files = ch_multiqc_files.mix(SALMON_QUANT.out.json_info.collect{it[1]})
     ch_versions = ch_versions.mix(SALMON_QUANT.out.versions)
@@ -108,7 +91,7 @@ workflow RNAFUSION {
     ch_versions = ch_versions.mix(ARRIBA_WORKFLOW.out.versions)
 
 
-//Run STAR fusion
+    //Run STAR fusion
     STARFUSION_WORKFLOW (
         ch_reads,
         BUILD_REFERENCES.out.ch_gtf,
@@ -118,14 +101,14 @@ workflow RNAFUSION {
     ch_versions = ch_versions.mix(STARFUSION_WORKFLOW.out.versions)
 
 
-//Run fusioncatcher
+    //Run fusioncatcher
     FUSIONCATCHER_WORKFLOW (
         ch_reads
     )
     ch_versions = ch_versions.mix(FUSIONCATCHER_WORKFLOW.out.versions)
 
 
-//Run stringtie
+    //Run stringtie
     STRINGTIE_WORKFLOW (
         STARFUSION_WORKFLOW.out.ch_bam_sorted,
         BUILD_REFERENCES.out.ch_gtf

From 24a46103dd3a07ae43f22b094e2c7da943126c29 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Tue, 10 Dec 2024 12:36:53 +0100
Subject: [PATCH 22/41] test build removed from ci as build_references happens
 before the run

---
 .github/workflows/ci.yml | 1 -
 conf/test_build.config   | 2 +-
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 71ff7245..a510d72d 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -39,7 +39,6 @@ jobs:
           - "latest-stable"
         test_profile:
           - "test_stub"
-          - "test_build"
         compute_profile:
           - "docker"
           - "singularity"
diff --git a/conf/test_build.config b/conf/test_build.config
index 616d734f..26002327 100644
--- a/conf/test_build.config
+++ b/conf/test_build.config
@@ -15,7 +15,7 @@ params {
     config_profile_description = 'Minimal test dataset to check pipeline function'
 
     // Input data
-    build_references           = true
+    references_only            = true
     input                      = 'https://raw.githubusercontent.com/nf-core/test-datasets/rnafusion/testdata/human/samplesheet_valid.csv'
     no_cosmic                  = true
     all                        = true

From 76cf2aaffc1630665ec3ad9e1534549eefaa2002 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Tue, 10 Dec 2024 14:20:11 +0100
Subject: [PATCH 23/41] update snapshots, add meta

---
 conf/modules.config                           |   2 +-
 conf/test.config                              |   2 +
 modules/local/fusionreport/detect/main.nf     |   2 +-
 modules/local/fusionreport/download/main.nf   |  20 +-
 subworkflows/local/build_references.nf        |   6 +-
 subworkflows/local/fusionreport_workflow.nf   |   1 -
 .../utils_nfcore_rnafusion_pipeline/main.nf   |   2 +-
 test.xml                                      |   1 +
 tests/test_cosmic.nf.test.snap                |  68 +++
 tests/test_stub.nf.test.snap                  | 459 +++++++++++++++++-
 10 files changed, 540 insertions(+), 23 deletions(-)
 create mode 100644 test.xml
 create mode 100644 tests/test_cosmic.nf.test.snap

diff --git a/conf/modules.config b/conf/modules.config
index d021ae36..bbbee5c2 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -111,7 +111,7 @@ process {
         ext.args         = { {params.no_cosmic} ? "--no-cosmic" : " --cosmic_usr ${params.cosmic_username} --cosmic_passwd ${params.cosmic_passwd}" }
         ext.args2        = { params.qiagen ? "--qiagen" : "" }
         publishDir = [
-            path: { "${params.genomes_base}/fusion_report_db" },
+            path: { "${params.genomes_base}" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]
diff --git a/conf/test.config b/conf/test.config
index 3cafa252..1902de0a 100644
--- a/conf/test.config
+++ b/conf/test.config
@@ -16,4 +16,6 @@ params {
 
     // Input data
     input                  = 'https://raw.githubusercontent.com/nf-core/test-datasets/rnafusion/testdata/human/samplesheet_valid.csv'
+    all                    = true
+    no_cosmic              = true
 }
diff --git a/modules/local/fusionreport/detect/main.nf b/modules/local/fusionreport/detect/main.nf
index 5482d4bf..56a29ab4 100644
--- a/modules/local/fusionreport/detect/main.nf
+++ b/modules/local/fusionreport/detect/main.nf
@@ -7,7 +7,7 @@ process FUSIONREPORT {
 
     input:
     tuple val(meta), path(reads), path(arriba_fusions), path(starfusion_fusions),  path(fusioncatcher_fusions)
-    path(fusionreport_ref)
+    tuple val(meta2), path(fusionreport_ref)
     val(tools_cutoff)
 
     output:
diff --git a/modules/local/fusionreport/download/main.nf b/modules/local/fusionreport/download/main.nf
index b19a6446..a2c2a96b 100644
--- a/modules/local/fusionreport/download/main.nf
+++ b/modules/local/fusionreport/download/main.nf
@@ -6,17 +6,17 @@ process FUSIONREPORT_DOWNLOAD {
     container "docker.io/clinicalgenomics/fusion-report:3.1.0"
 
     output:
-    tuple val(meta), path("fusionreport_dbs"), emit: fusionreport_db
+    tuple val(meta), path("fusion_report_db"), emit: fusionreport_ref
     path "versions.yml"                      , emit: versions
 
     script:
-    meta = [id: 'fusionreport_dbs']
+    meta = [id: 'fusion_report_db']
     def args = task.ext.args ?: ''
     def args2 = task.ext.args2 ?: ''
     """
     fusion_report download $args ./
-    mkdir fusionreport_dbs
-    mv *.txt *.log *.db fusionreport_dbs
+    mkdir fusion_report_db
+    mv *.txt *.log *.db fusion_report_db
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
@@ -27,12 +27,12 @@ process FUSIONREPORT_DOWNLOAD {
     stub:
     meta = [id: 'fusionreport_dbs']
     """
-    mkdir fusionreport_dbs
-    touch fusionreport_dbs/cosmic.db
-    touch fusionreport_dbs/fusiongdb2.db
-    touch fusionreport_dbs/mitelman.db
-    touch fusionreport_dbs/DB-timestamp.txt
-    touch fusionreport_dbs/fusion_report.log
+    mkdir fusion_report_db
+    touch fusion_report_db/cosmic.db
+    touch fusion_report_db/fusiongdb2.db
+    touch fusion_report_db/mitelman.db
+    touch fusion_report_db/DB-timestamp.txt
+    touch fusion_report_db/fusion_report.log
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
diff --git a/subworkflows/local/build_references.nf b/subworkflows/local/build_references.nf
index e158f566..8e9cc4b1 100644
--- a/subworkflows/local/build_references.nf
+++ b/subworkflows/local/build_references.nf
@@ -152,12 +152,12 @@ workflow BUILD_REFERENCES {
     if ((params.fusionreport || params.all) &&
             (!file(params.fusionreport_ref).exists() || file(params.fusionreport_ref).isEmpty() ||
             !file(params.fusionreport_ref_stub_check).exists() || file(params.fusionreport_ref_stub_check).isEmpty())) {
-        if (!params.cosmic_username || !params.cosmic_passwd) { exit 1, 'COSMIC username and/or password missing' }
+        if (!params.no_cosmic && (!params.cosmic_username || !params.cosmic_passwd)) { exit 1, 'COSMIC username and/or password missing' }
         FUSIONREPORT_DOWNLOAD()
         ch_versions = ch_versions.mix(FUSIONREPORT_DOWNLOAD.out.versions)
-        ch_fusionreport_ref = FUSIONREPORT_DOWNLOAD.out.mitelman.map{ it.parent }
+        ch_fusionreport_ref = FUSIONREPORT_DOWNLOAD.out.fusionreport_ref
     } else {
-        ch_fusionreport_ref = Channel.fromPath(params.fusionreport_ref)
+        ch_fusionreport_ref = Channel.fromPath(params.fusionreport_ref).map { that -> [[id:that.Name], that] }
     }
 
     emit:
diff --git a/subworkflows/local/fusionreport_workflow.nf b/subworkflows/local/fusionreport_workflow.nf
index 5c9bfde1..80fe7337 100644
--- a/subworkflows/local/fusionreport_workflow.nf
+++ b/subworkflows/local/fusionreport_workflow.nf
@@ -19,7 +19,6 @@ workflow FUSIONREPORT_WORKFLOW {
             .join(arriba_fusions, remainder: true)
             .join(starfusion_fusions, remainder: true)
             .join(fusioncatcher_fusions, remainder: true)
-
             FUSIONREPORT(reads_fusions, fusionreport_ref, params.tools_cutoff)
             ch_fusion_list = FUSIONREPORT.out.fusion_list
             ch_fusion_list_filtered = FUSIONREPORT.out.fusion_list_filtered
diff --git a/subworkflows/local/utils_nfcore_rnafusion_pipeline/main.nf b/subworkflows/local/utils_nfcore_rnafusion_pipeline/main.nf
index 4b46c5c0..1f905a44 100644
--- a/subworkflows/local/utils_nfcore_rnafusion_pipeline/main.nf
+++ b/subworkflows/local/utils_nfcore_rnafusion_pipeline/main.nf
@@ -157,7 +157,7 @@ def validateInputParameters() {
     genomeExistsError()
 
     if (params.no_cosmic) {
-            log.warn("Skipping COSMIC DB download from `FUSIONREPORT_DOWNLOAD`")
+            log.warn("Skipping COSMIC DB download from `FUSIONREPORT_DOWNLOAD` and skip using it in `FUSIONREPORT`")
     }
 
 }
diff --git a/test.xml b/test.xml
new file mode 100644
index 00000000..e8f1835b
--- /dev/null
+++ b/test.xml
@@ -0,0 +1 @@
+<?xml version="1.0" encoding="utf-8"?><testsuites><testsuite name="Test pipeline" time="260.628" tests="2" skipped="0" failures="0" timestamp="2024 12 10 14:13:25"><testcase classname="Test pipeline" name="stub test with fastp trim" time="135.663" status="PASSED"></testcase><testcase classname="Test pipeline" name="stub test no fastp trim" time="124.798" status="PASSED"></testcase></testsuite></testsuites>
\ No newline at end of file
diff --git a/tests/test_cosmic.nf.test.snap b/tests/test_cosmic.nf.test.snap
new file mode 100644
index 00000000..dc3ab947
--- /dev/null
+++ b/tests/test_cosmic.nf.test.snap
@@ -0,0 +1,68 @@
+{
+    "test cosmic no fastp trim build": {
+        "content": [
+            0,
+            {
+                "Workflow": {
+                    "nf-core/rnafusion": "v4.0.0dev"
+                }
+            },
+            [
+                "pipeline_info",
+                "pipeline_info/nf_core_pipeline_software_mqc_versions.yml"
+            ],
+            [
+                
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.10.2"
+        },
+        "timestamp": "2024-12-10T12:42:49.558429"
+    },
+    "test cosmic no fastp trim": {
+        "content": [
+            0,
+            {
+                "Workflow": {
+                    "nf-core/rnafusion": "v4.0.0dev"
+                }
+            },
+            [
+                "pipeline_info",
+                "pipeline_info/nf_core_pipeline_software_mqc_versions.yml"
+            ],
+            [
+                
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.10.2"
+        },
+        "timestamp": "2024-12-10T12:42:06.51355"
+    },
+    "test cosmic with fastp trim": {
+        "content": [
+            0,
+            {
+                "Workflow": {
+                    "nf-core/rnafusion": "v4.0.0dev"
+                }
+            },
+            [
+                "pipeline_info",
+                "pipeline_info/nf_core_pipeline_software_mqc_versions.yml"
+            ],
+            [
+                
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.10.2"
+        },
+        "timestamp": "2024-12-10T12:41:17.841938"
+    }
+}
\ No newline at end of file
diff --git a/tests/test_stub.nf.test.snap b/tests/test_stub.nf.test.snap
index 3b83c240..febef3c8 100644
--- a/tests/test_stub.nf.test.snap
+++ b/tests/test_stub.nf.test.snap
@@ -1,22 +1,131 @@
 {
     "stub test no fastp trim": {
         "content": [
-            4,
+            31,
             {
+                "ARRIBA_ARRIBA": {
+                    "arriba": "2.4.0"
+                },
+                "ARRIBA_DOWNLOAD": {
+                    "arriba_download": "2.4.0"
+                },
+                "FASTP": {
+                    "fastp": "0.23.4"
+                },
                 "FASTQC": {
                     "fastqc": "0.12.1"
                 },
+                "FASTQC_FOR_FASTP": {
+                    "fastqc": "0.12.1"
+                },
+                "FUSIONCATCHER": {
+                    "fusioncatcher": 1.33
+                },
+                "FUSIONCATCHER_BUILD": {
+                    "fusioncatcher": "fusioncatcher.py 1.35"
+                },
                 "FUSIONREPORT": {
                     "fusion_report": "2.1.5"
                 },
+                "FUSIONREPORT_DOWNLOAD": {
+                    "fusion_report": "2.1.5"
+                },
+                "GATK4_BEDTOINTERVALLIST": {
+                    "gatk4": "4.6.1.0"
+                },
+                "GATK4_CREATESEQUENCEDICTIONARY": {
+                    "gatk4": "4.6.1.0"
+                },
+                "GATK4_MARKDUPLICATES": {
+                    "gatk4": "4.5.0.0",
+                    "samtools": "1.19.2"
+                },
+                "GENCODE_DOWNLOAD": {
+                    "wget": null
+                },
+                "GET_RRNA_TRANSCRIPTS": {
+                    "get_rrna_transcripts": "v1.0"
+                },
+                "GFFREAD": {
+                    "gffread": "0.12.7"
+                },
+                "GTF_TO_REFFLAT": {
+                    "gtfToGenePred": 377
+                },
+                "HGNC_DOWNLOAD": {
+                    "wget": null
+                },
+                "PICARD_COLLECTINSERTSIZEMETRICS": {
+                    "picard": "3.3.0"
+                },
+                "PICARD_COLLECTRNASEQMETRICS": {
+                    "picard": "3.3.0"
+                },
+                "SALMON_INDEX": {
+                    "salmon": "1.10.3"
+                },
+                "SALMON_QUANT": {
+                    "salmon": "1.10.3"
+                },
+                "SAMTOOLS_FAIDX": {
+                    "samtools": 1.21
+                },
+                "SAMTOOLS_INDEX_FOR_STARFUSION": {
+                    "samtools": 1.21
+                },
+                "STARFUSION": {
+                    "STAR-Fusion": "1.7.0"
+                },
+                "STARFUSION_BUILD": {
+                    "STAR-Fusion": "1.7.0"
+                },
+                "STAR_FOR_ARRIBA": {
+                    "star": null,
+                    "samtools": 1.2,
+                    "gawk": "5.1.0"
+                },
+                "STAR_FOR_STARFUSION": {
+                    "star": null,
+                    "samtools": 1.2,
+                    "gawk": "5.1.0"
+                },
+                "STAR_GENOMEGENERATE": {
+                    "star": null,
+                    "samtools": 1.2,
+                    "gawk": "5.1.0"
+                },
+                "STRINGTIE_MERGE": {
+                    "stringtie": "2.2.1"
+                },
+                "STRINGTIE_STRINGTIE": {
+                    "stringtie": "2.2.3"
+                },
                 "Workflow": {
                     "nf-core/rnafusion": "v4.0.0dev"
                 }
             },
             [
+                "arriba",
+                "arriba/test.arriba.fusions.discarded.tsv",
+                "arriba/test.arriba.fusions.tsv",
+                "fastp",
+                "fastp/test.fastp.html",
+                "fastp/test.fastp.json",
+                "fastp/test.fastp.log",
+                "fastp/test_1.fastp.fastq.gz",
+                "fastp/test_2.fastp.fastq.gz",
                 "fastqc",
                 "fastqc/test.html",
                 "fastqc/test.zip",
+                "fastqc_for_fastp",
+                "fastqc_for_fastp/test_trimmed.html",
+                "fastqc_for_fastp/test_trimmed.zip",
+                "fusioncatcher",
+                "fusioncatcher/human_v46",
+                "fusioncatcher/human_v46/ensembl_fully_overlapping_genes.txt",
+                "fusioncatcher/test.fusioncatcher.fusion-genes.txt",
+                "fusioncatcher/test.fusioncatcher.log",
+                "fusioncatcher/test.fusioncatcher.summary.txt",
                 "fusionreport",
                 "fusionreport/test",
                 "fusionreport/test/AAA_BBB.html",
@@ -25,28 +134,156 @@
                 "fusionreport/test/test.fusions.csv",
                 "fusionreport/test/test.fusions.json",
                 "fusionreport/test/test_fusionreport_index.html",
+                "gatk4",
+                "gatk4/Homo_sapiens.GRCh38.46_dna_primary_assembly.dict",
+                "get",
+                "get/rrna.bed",
+                "get/rrna.gtf",
                 "multiqc",
                 "multiqc/multiqc_data",
                 "multiqc/multiqc_plots",
                 "multiqc/multiqc_report.html",
+                "picard",
+                "picard/test.bai",
+                "picard/test.bam",
+                "picard/test.bam.metrics",
+                "picard/test.cram",
+                "picard/test.cram.crai",
+                "picard/test.rna_metrics",
+                "picard/test_collectinsertsize.pdf",
+                "picard/test_collectinsertsize.txt",
                 "pipeline_info",
                 "pipeline_info/nf_core_pipeline_software_mqc_versions.yml",
+                "references",
+                "references/arriba",
+                "references/arriba/blacklist_hg38_GRCh38_v2.4.0.tsv.gz",
+                "references/arriba/cytobands_hg38_GRCh38_v2.4.0.tsv",
+                "references/arriba/known_fusions_hg38_GRCh38_v2.4.0.tsv.gz",
+                "references/arriba/protein_domains_hg38_GRCh38_v2.4.0.gff3",
+                "references/fusion_report_db",
+                "references/fusion_report_db/DB-timestamp.txt",
+                "references/fusion_report_db/cosmic.db",
+                "references/fusion_report_db/fusion_report.log",
+                "references/fusion_report_db/fusiongdb2.db",
+                "references/fusion_report_db/mitelman.db",
+                "references/gencode",
+                "references/gencode/Homo_sapiens.GRCh38.46.gtf",
+                "references/gencode/Homo_sapiens.GRCh38.46.gtf.interval_list",
+                "references/gencode/Homo_sapiens.GRCh38.46.gtf.refflat",
+                "references/gencode/Homo_sapiens.GRCh38.46_dna_primary_assembly.fa",
+                "references/gencode/Homo_sapiens.GRCh38.46_dna_primary_assembly.fa.fai",
+                "references/gffread",
+                "references/gffread/Homo_sapiens.GRCh38.46.gtf.fasta",
+                "references/hgnc",
+                "references/hgnc/HGNC-DB-timestamp.txt",
+                "references/hgnc/hgnc_complete_set.txt",
+                "references/salmon",
+                "references/salmon/salmon",
+                "references/salmon/salmon/complete_ref_lens.bin",
+                "references/salmon/salmon/ctable.bin",
+                "references/salmon/salmon/ctg_offsets.bin",
+                "references/salmon/salmon/duplicate_clusters.tsv",
+                "references/salmon/salmon/info.json",
+                "references/salmon/salmon/mphf.bin",
+                "references/salmon/salmon/pos.bin",
+                "references/salmon/salmon/pre_indexing.log",
+                "references/salmon/salmon/rank.bin",
+                "references/salmon/salmon/refAccumLengths.bin",
+                "references/salmon/salmon/ref_indexing.log",
+                "references/salmon/salmon/reflengths.bin",
+                "references/salmon/salmon/refseq.bin",
+                "references/salmon/salmon/seq.bin",
+                "references/salmon/salmon/versionInfo.json",
+                "references/star",
+                "references/star/Genome",
+                "references/star/Log.out",
+                "references/star/SA",
+                "references/star/SAindex",
+                "references/star/chrLength.txt",
+                "references/star/chrName.txt",
+                "references/star/chrNameLength.txt",
+                "references/star/chrStart.txt",
+                "references/star/exonGeTrInfo.tab",
+                "references/star/exonInfo.tab",
+                "references/star/geneInfo.tab",
+                "references/star/genomeParameters.txt",
+                "references/star/sjdbInfo.txt",
+                "references/star/sjdbList.fromGTF.out.tab",
+                "references/star/sjdbList.out.tab",
+                "references/star/transcriptInfo.tab",
+                "references/starfusion",
+                "references/starfusion/ctat_genome_lib_build_dir",
+                "references/starfusion/ref_annot.cdna.fa",
                 "salmon",
                 "salmon/test",
                 "salmon/test_lib_format_counts.json",
-                "salmon/test_meta_info.json"
+                "salmon/test_meta_info.json",
+                "star_for_arriba",
+                "star_for_arriba/test.Aligned.sortedByCoord.out.bam",
+                "star_for_arriba/test.Aligned.unsort.out.bam",
+                "star_for_arriba/test.Chimeric.out.junction",
+                "star_for_arriba/test.Log.final.out",
+                "star_for_arriba/test.Log.out",
+                "star_for_arriba/test.Log.progress.out",
+                "star_for_arriba/test.ReadsPerGene.out.tab",
+                "star_for_arriba/test.SJ.out.tab",
+                "star_for_arriba/test.Signal.UniqueMultiple.str1.out.bg",
+                "star_for_arriba/test.Signal.UniqueMultiple.str1.out.wig",
+                "star_for_arriba/test.out.sam",
+                "star_for_arriba/test.sortedByCoord.out.bam",
+                "star_for_arriba/test.tab",
+                "star_for_arriba/test.toTranscriptome.out.bam",
+                "star_for_arriba/test.unmapped_1.fastq.gz",
+                "star_for_arriba/test.unmapped_2.fastq.gz",
+                "star_for_arriba/testXd.out.bam",
+                "star_for_starfusion",
+                "star_for_starfusion/test.Aligned.sortedByCoord.out.bam",
+                "star_for_starfusion/test.Aligned.unsort.out.bam",
+                "star_for_starfusion/test.Chimeric.out.junction",
+                "star_for_starfusion/test.Log.final.out",
+                "star_for_starfusion/test.Log.out",
+                "star_for_starfusion/test.Log.progress.out",
+                "star_for_starfusion/test.ReadsPerGene.out.tab",
+                "star_for_starfusion/test.SJ.out.tab",
+                "star_for_starfusion/test.Signal.UniqueMultiple.str1.out.bg",
+                "star_for_starfusion/test.Signal.UniqueMultiple.str1.out.wig",
+                "star_for_starfusion/test.out.sam",
+                "star_for_starfusion/test.sortedByCoord.out.bam",
+                "star_for_starfusion/test.sortedByCoord.out.bam.bai",
+                "star_for_starfusion/test.tab",
+                "star_for_starfusion/test.toTranscriptome.out.bam",
+                "star_for_starfusion/test.unmapped_1.fastq.gz",
+                "star_for_starfusion/test.unmapped_2.fastq.gz",
+                "star_for_starfusion/testXd.out.bam",
+                "starfusion",
+                "starfusion/test.starfusion.abridged.coding_effect.tsv",
+                "starfusion/test.starfusion.abridged.tsv",
+                "starfusion/test.starfusion.fusion_predictions.tsv",
+                "stringtie",
+                "stringtie/[:]",
+                "stringtie/[:]/stringtie.merged.gtf",
+                "stringtie/test.ballgown",
+                "stringtie/test.coverage.gtf",
+                "stringtie/test.gene.abundance.txt",
+                "stringtie/test.transcripts.gtf"
             ]
         ],
         "meta": {
             "nf-test": "0.9.0",
             "nextflow": "24.10.2"
         },
-        "timestamp": "2024-12-03T19:27:00.717876194"
+        "timestamp": "2024-12-10T14:12:48.526275"
     },
     "stub test with fastp trim": {
         "content": [
-            6,
+            31,
             {
+                "ARRIBA_ARRIBA": {
+                    "arriba": "2.4.0"
+                },
+                "ARRIBA_DOWNLOAD": {
+                    "arriba_download": "2.4.0"
+                },
                 "FASTP": {
                     "fastp": "0.23.4"
                 },
@@ -56,14 +293,96 @@
                 "FASTQC_FOR_FASTP": {
                     "fastqc": "0.12.1"
                 },
+                "FUSIONCATCHER": {
+                    "fusioncatcher": 1.33
+                },
+                "FUSIONCATCHER_BUILD": {
+                    "fusioncatcher": "fusioncatcher.py 1.35"
+                },
                 "FUSIONREPORT": {
                     "fusion_report": "2.1.5"
                 },
+                "FUSIONREPORT_DOWNLOAD": {
+                    "fusion_report": "2.1.5"
+                },
+                "GATK4_BEDTOINTERVALLIST": {
+                    "gatk4": "4.6.1.0"
+                },
+                "GATK4_CREATESEQUENCEDICTIONARY": {
+                    "gatk4": "4.6.1.0"
+                },
+                "GATK4_MARKDUPLICATES": {
+                    "gatk4": "4.5.0.0",
+                    "samtools": "1.19.2"
+                },
+                "GENCODE_DOWNLOAD": {
+                    "wget": null
+                },
+                "GET_RRNA_TRANSCRIPTS": {
+                    "get_rrna_transcripts": "v1.0"
+                },
+                "GFFREAD": {
+                    "gffread": "0.12.7"
+                },
+                "GTF_TO_REFFLAT": {
+                    "gtfToGenePred": 377
+                },
+                "HGNC_DOWNLOAD": {
+                    "wget": null
+                },
+                "PICARD_COLLECTINSERTSIZEMETRICS": {
+                    "picard": "3.3.0"
+                },
+                "PICARD_COLLECTRNASEQMETRICS": {
+                    "picard": "3.3.0"
+                },
+                "SALMON_INDEX": {
+                    "salmon": "1.10.3"
+                },
+                "SALMON_QUANT": {
+                    "salmon": "1.10.3"
+                },
+                "SAMTOOLS_FAIDX": {
+                    "samtools": 1.21
+                },
+                "SAMTOOLS_INDEX_FOR_STARFUSION": {
+                    "samtools": 1.21
+                },
+                "STARFUSION": {
+                    "STAR-Fusion": "1.7.0"
+                },
+                "STARFUSION_BUILD": {
+                    "STAR-Fusion": "1.7.0"
+                },
+                "STAR_FOR_ARRIBA": {
+                    "star": null,
+                    "samtools": 1.2,
+                    "gawk": "5.1.0"
+                },
+                "STAR_FOR_STARFUSION": {
+                    "star": null,
+                    "samtools": 1.2,
+                    "gawk": "5.1.0"
+                },
+                "STAR_GENOMEGENERATE": {
+                    "star": null,
+                    "samtools": 1.2,
+                    "gawk": "5.1.0"
+                },
+                "STRINGTIE_MERGE": {
+                    "stringtie": "2.2.1"
+                },
+                "STRINGTIE_STRINGTIE": {
+                    "stringtie": "2.2.3"
+                },
                 "Workflow": {
                     "nf-core/rnafusion": "v4.0.0dev"
                 }
             },
             [
+                "arriba",
+                "arriba/test.arriba.fusions.discarded.tsv",
+                "arriba/test.arriba.fusions.tsv",
                 "fastp",
                 "fastp/test.fastp.html",
                 "fastp/test.fastp.json",
@@ -76,6 +395,12 @@
                 "fastqc_for_fastp",
                 "fastqc_for_fastp/test_trimmed.html",
                 "fastqc_for_fastp/test_trimmed.zip",
+                "fusioncatcher",
+                "fusioncatcher/human_v46",
+                "fusioncatcher/human_v46/ensembl_fully_overlapping_genes.txt",
+                "fusioncatcher/test.fusioncatcher.fusion-genes.txt",
+                "fusioncatcher/test.fusioncatcher.log",
+                "fusioncatcher/test.fusioncatcher.summary.txt",
                 "fusionreport",
                 "fusionreport/test",
                 "fusionreport/test/AAA_BBB.html",
@@ -84,22 +409,144 @@
                 "fusionreport/test/test.fusions.csv",
                 "fusionreport/test/test.fusions.json",
                 "fusionreport/test/test_fusionreport_index.html",
+                "gatk4",
+                "gatk4/Homo_sapiens.GRCh38.46_dna_primary_assembly.dict",
+                "get",
+                "get/rrna.bed",
+                "get/rrna.gtf",
                 "multiqc",
                 "multiqc/multiqc_data",
                 "multiqc/multiqc_plots",
                 "multiqc/multiqc_report.html",
+                "picard",
+                "picard/test.bai",
+                "picard/test.bam",
+                "picard/test.bam.metrics",
+                "picard/test.cram",
+                "picard/test.cram.crai",
+                "picard/test.rna_metrics",
+                "picard/test_collectinsertsize.pdf",
+                "picard/test_collectinsertsize.txt",
                 "pipeline_info",
                 "pipeline_info/nf_core_pipeline_software_mqc_versions.yml",
+                "references",
+                "references/arriba",
+                "references/arriba/blacklist_hg38_GRCh38_v2.4.0.tsv.gz",
+                "references/arriba/cytobands_hg38_GRCh38_v2.4.0.tsv",
+                "references/arriba/known_fusions_hg38_GRCh38_v2.4.0.tsv.gz",
+                "references/arriba/protein_domains_hg38_GRCh38_v2.4.0.gff3",
+                "references/fusion_report_db",
+                "references/fusion_report_db/DB-timestamp.txt",
+                "references/fusion_report_db/cosmic.db",
+                "references/fusion_report_db/fusion_report.log",
+                "references/fusion_report_db/fusiongdb2.db",
+                "references/fusion_report_db/mitelman.db",
+                "references/gencode",
+                "references/gencode/Homo_sapiens.GRCh38.46.gtf",
+                "references/gencode/Homo_sapiens.GRCh38.46.gtf.interval_list",
+                "references/gencode/Homo_sapiens.GRCh38.46.gtf.refflat",
+                "references/gencode/Homo_sapiens.GRCh38.46_dna_primary_assembly.fa",
+                "references/gencode/Homo_sapiens.GRCh38.46_dna_primary_assembly.fa.fai",
+                "references/gffread",
+                "references/gffread/Homo_sapiens.GRCh38.46.gtf.fasta",
+                "references/hgnc",
+                "references/hgnc/HGNC-DB-timestamp.txt",
+                "references/hgnc/hgnc_complete_set.txt",
+                "references/salmon",
+                "references/salmon/salmon",
+                "references/salmon/salmon/complete_ref_lens.bin",
+                "references/salmon/salmon/ctable.bin",
+                "references/salmon/salmon/ctg_offsets.bin",
+                "references/salmon/salmon/duplicate_clusters.tsv",
+                "references/salmon/salmon/info.json",
+                "references/salmon/salmon/mphf.bin",
+                "references/salmon/salmon/pos.bin",
+                "references/salmon/salmon/pre_indexing.log",
+                "references/salmon/salmon/rank.bin",
+                "references/salmon/salmon/refAccumLengths.bin",
+                "references/salmon/salmon/ref_indexing.log",
+                "references/salmon/salmon/reflengths.bin",
+                "references/salmon/salmon/refseq.bin",
+                "references/salmon/salmon/seq.bin",
+                "references/salmon/salmon/versionInfo.json",
+                "references/star",
+                "references/star/Genome",
+                "references/star/Log.out",
+                "references/star/SA",
+                "references/star/SAindex",
+                "references/star/chrLength.txt",
+                "references/star/chrName.txt",
+                "references/star/chrNameLength.txt",
+                "references/star/chrStart.txt",
+                "references/star/exonGeTrInfo.tab",
+                "references/star/exonInfo.tab",
+                "references/star/geneInfo.tab",
+                "references/star/genomeParameters.txt",
+                "references/star/sjdbInfo.txt",
+                "references/star/sjdbList.fromGTF.out.tab",
+                "references/star/sjdbList.out.tab",
+                "references/star/transcriptInfo.tab",
+                "references/starfusion",
+                "references/starfusion/ctat_genome_lib_build_dir",
+                "references/starfusion/ref_annot.cdna.fa",
                 "salmon",
                 "salmon/test",
                 "salmon/test_lib_format_counts.json",
-                "salmon/test_meta_info.json"
+                "salmon/test_meta_info.json",
+                "star_for_arriba",
+                "star_for_arriba/test.Aligned.sortedByCoord.out.bam",
+                "star_for_arriba/test.Aligned.unsort.out.bam",
+                "star_for_arriba/test.Chimeric.out.junction",
+                "star_for_arriba/test.Log.final.out",
+                "star_for_arriba/test.Log.out",
+                "star_for_arriba/test.Log.progress.out",
+                "star_for_arriba/test.ReadsPerGene.out.tab",
+                "star_for_arriba/test.SJ.out.tab",
+                "star_for_arriba/test.Signal.UniqueMultiple.str1.out.bg",
+                "star_for_arriba/test.Signal.UniqueMultiple.str1.out.wig",
+                "star_for_arriba/test.out.sam",
+                "star_for_arriba/test.sortedByCoord.out.bam",
+                "star_for_arriba/test.tab",
+                "star_for_arriba/test.toTranscriptome.out.bam",
+                "star_for_arriba/test.unmapped_1.fastq.gz",
+                "star_for_arriba/test.unmapped_2.fastq.gz",
+                "star_for_arriba/testXd.out.bam",
+                "star_for_starfusion",
+                "star_for_starfusion/test.Aligned.sortedByCoord.out.bam",
+                "star_for_starfusion/test.Aligned.unsort.out.bam",
+                "star_for_starfusion/test.Chimeric.out.junction",
+                "star_for_starfusion/test.Log.final.out",
+                "star_for_starfusion/test.Log.out",
+                "star_for_starfusion/test.Log.progress.out",
+                "star_for_starfusion/test.ReadsPerGene.out.tab",
+                "star_for_starfusion/test.SJ.out.tab",
+                "star_for_starfusion/test.Signal.UniqueMultiple.str1.out.bg",
+                "star_for_starfusion/test.Signal.UniqueMultiple.str1.out.wig",
+                "star_for_starfusion/test.out.sam",
+                "star_for_starfusion/test.sortedByCoord.out.bam",
+                "star_for_starfusion/test.sortedByCoord.out.bam.bai",
+                "star_for_starfusion/test.tab",
+                "star_for_starfusion/test.toTranscriptome.out.bam",
+                "star_for_starfusion/test.unmapped_1.fastq.gz",
+                "star_for_starfusion/test.unmapped_2.fastq.gz",
+                "star_for_starfusion/testXd.out.bam",
+                "starfusion",
+                "starfusion/test.starfusion.abridged.coding_effect.tsv",
+                "starfusion/test.starfusion.abridged.tsv",
+                "starfusion/test.starfusion.fusion_predictions.tsv",
+                "stringtie",
+                "stringtie/[:]",
+                "stringtie/[:]/stringtie.merged.gtf",
+                "stringtie/test.ballgown",
+                "stringtie/test.coverage.gtf",
+                "stringtie/test.gene.abundance.txt",
+                "stringtie/test.transcripts.gtf"
             ]
         ],
         "meta": {
             "nf-test": "0.9.0",
             "nextflow": "24.10.2"
         },
-        "timestamp": "2024-12-03T19:26:43.375635514"
+        "timestamp": "2024-12-10T14:10:38.383967"
     }
 }
\ No newline at end of file

From 56ed001b0fce281ba4375db685969541cc70e7af Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Tue, 10 Dec 2024 14:25:59 +0100
Subject: [PATCH 24/41] remove trash files

---
 test.fusionreport.tsv          | 0
 test.fusionreport_filtered.tsv | 0
 test.fusions.csv               | 0
 test.fusions.json              | 0
 test.xml                       | 1 -
 test_fusionreport_index.html   | 0
 6 files changed, 1 deletion(-)
 delete mode 100644 test.fusionreport.tsv
 delete mode 100644 test.fusionreport_filtered.tsv
 delete mode 100644 test.fusions.csv
 delete mode 100644 test.fusions.json
 delete mode 100644 test.xml
 delete mode 100644 test_fusionreport_index.html

diff --git a/test.fusionreport.tsv b/test.fusionreport.tsv
deleted file mode 100644
index e69de29b..00000000
diff --git a/test.fusionreport_filtered.tsv b/test.fusionreport_filtered.tsv
deleted file mode 100644
index e69de29b..00000000
diff --git a/test.fusions.csv b/test.fusions.csv
deleted file mode 100644
index e69de29b..00000000
diff --git a/test.fusions.json b/test.fusions.json
deleted file mode 100644
index e69de29b..00000000
diff --git a/test.xml b/test.xml
deleted file mode 100644
index e8f1835b..00000000
--- a/test.xml
+++ /dev/null
@@ -1 +0,0 @@
-<?xml version="1.0" encoding="utf-8"?><testsuites><testsuite name="Test pipeline" time="260.628" tests="2" skipped="0" failures="0" timestamp="2024 12 10 14:13:25"><testcase classname="Test pipeline" name="stub test with fastp trim" time="135.663" status="PASSED"></testcase><testcase classname="Test pipeline" name="stub test no fastp trim" time="124.798" status="PASSED"></testcase></testsuite></testsuites>
\ No newline at end of file
diff --git a/test_fusionreport_index.html b/test_fusionreport_index.html
deleted file mode 100644
index e69de29b..00000000

From 23c4014a6a22839223540a7dd98426fb89cd31d7 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Tue, 10 Dec 2024 15:24:20 +0100
Subject: [PATCH 25/41] use stubs

---
 .github/workflows/awstest.yml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.github/workflows/awstest.yml b/.github/workflows/awstest.yml
index 78bdb317..977adb49 100644
--- a/.github/workflows/awstest.yml
+++ b/.github/workflows/awstest.yml
@@ -26,6 +26,7 @@ jobs:
               "cosmic_username": "${{ secrets.cosmic_username }}",
               "cosmic_passwd": "${{ secrets.cosmic_passwd }}",
               "all": true,
+              "stub": true
             }
           profiles: test,aws_tower
       - uses: actions/upload-artifact@v4

From d52f0a055fb82ae8def0b400c016820af38bf222 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Tue, 10 Dec 2024 15:24:42 +0100
Subject: [PATCH 26/41] update changelog, first step

---
 CHANGELOG.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 690024b2..1980cd86 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -27,7 +27,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Updated to nf-core/tools 3.0.2 [#504](https://github.com/nf-core/rnafusion/pull/504)
 - Remove local module `RRNA_TRANSCRIPTS` (replaced by nf-core module) [#541](https://github.com/nf-core/rnafusion/pull/541)
 - Allow fastq files without a dot before .fn(.gz)/.fastq(.gz) files [#548](https://github.com/nf-core/rnafusion/pull/548)
-
+        ext.args = "-genePredExt -geneNameAsName2 -ignoreGroupsWithoutExons" GTF_TO_REFFLAT
 ### Fixed
 
 - Fixed some Nextflow run-commands in the docs [#491](https://github.com/nf-core/rnafusion/pull/491)

From 5409f8c2566342a4d2debe406ef4e19b52231d74 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Tue, 10 Dec 2024 15:25:02 +0100
Subject: [PATCH 27/41] update GTF_TO_REFFLAT options, update snapshots

---
 conf/modules.config                          |  1 +
 modules/local/fusioncatcher/build/meta.yml   |  3 +-
 modules/local/fusioncatcher/download/main.nf |  2 +-
 modules/local/starfusion/download/main.nf    |  2 +-
 nextflow.config                              |  3 +-
 tests/test_build.nf.test.snap                | 33 +++-----------------
 tests/test_cosmic.nf.test.snap               | 22 ++++---------
 7 files changed, 15 insertions(+), 51 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index bbbee5c2..3c376545 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -144,6 +144,7 @@ process {
     }
 
     withName: 'GTF_TO_REFFLAT' {
+        ext.args = "-genePredExt -geneNameAsName2 -ignoreGroupsWithoutExons"
         publishDir = [
             path: { "${params.genomes_base}/gencode" },
             mode: params.publish_dir_mode,
diff --git a/modules/local/fusioncatcher/build/meta.yml b/modules/local/fusioncatcher/build/meta.yml
index 40421a4e..202be7e1 100644
--- a/modules/local/fusioncatcher/build/meta.yml
+++ b/modules/local/fusioncatcher/build/meta.yml
@@ -1,4 +1,4 @@
-name: fusioncatcher_download
+name: fusioncatcher_build
 description: Build genome for fusioncatcher
 keywords:
   - sort
@@ -19,7 +19,6 @@ output:
   - reference:
       type: directory
       description: Path to fusioncatcher references
-      pattern: "*"
 
 authors:
   - "@praveenraj2018, @rannick"
diff --git a/modules/local/fusioncatcher/download/main.nf b/modules/local/fusioncatcher/download/main.nf
index 7afdb4c6..ed97c834 100644
--- a/modules/local/fusioncatcher/download/main.nf
+++ b/modules/local/fusioncatcher/download/main.nf
@@ -20,7 +20,7 @@ process FUSIONCATCHER_DOWNLOAD {
 
     def args = task.ext.args ?: ''
     def args2 = task.ext.args2 ?: ''
-        // TODO: move to my sourceforge
+        // TODO: move to S3
 
     // def url =
     """
diff --git a/modules/local/starfusion/download/main.nf b/modules/local/starfusion/download/main.nf
index 85bb39c1..6ef1df63 100644
--- a/modules/local/starfusion/download/main.nf
+++ b/modules/local/starfusion/download/main.nf
@@ -8,7 +8,7 @@ process STARFUSION_DOWNLOAD {
     path "ctat_genome_lib_build_dir/*"            , emit: reference
 
 
-    // TODO: move to my sourceforge
+    // TODO: move to S3
     script:
     """
     wget https://data.broadinstitute.org/Trinity/CTAT_RESOURCE_LIB/__genome_libs_StarFv1.10/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play.tar.gz --no-check-certificate
diff --git a/nextflow.config b/nextflow.config
index 31e75497..db9eb141 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -61,13 +61,12 @@ params {
 
     // Skip steps
     skip_qc                    = false
-    skip_vcf                   = false
     skip_vis                   = false
     skip_vcf                   = false
     skip_salmon_index          = false
 
     // Download references option
-    download_refs              = true
+    download_refs              = false
 
     // Path to references
     fasta                         = "${params.genomes_base}/gencode/Homo_sapiens_${params.genome}_${params.genome_gencode_version}_dna_primary_assembly.fa"
diff --git a/tests/test_build.nf.test.snap b/tests/test_build.nf.test.snap
index 16b6c007..5332634b 100644
--- a/tests/test_build.nf.test.snap
+++ b/tests/test_build.nf.test.snap
@@ -2,46 +2,21 @@
     "test_build": {
         "content": [
             [
-                "bedops",
-                "bedops/Homo_sapiens.GRCh38.102_rrna_intervals.gtf.bed",
-                "gatk4",
-                "gatk4/Homo_sapiens.GRCh38.102.dna.primary_assembly.dict",
-                "gffread",
-                "gffread/Homo_sapiens.GRCh38.102.fasta",
                 "pipeline_info",
+                "pipeline_info/nf_core_pipeline_software_mqc_versions.yml",
                 "references",
-                "references/ensembl",
-                "references/ensembl/Homo_sapiens.GRCh38.102.chr.gtf",
-                "references/ensembl/Homo_sapiens.GRCh38.102.dna.primary_assembly.fa",
-                "references/ensembl/Homo_sapiens.GRCh38.102.dna.primary_assembly.fa.fai",
-                "references/ensembl/Homo_sapiens.GRCh38.102.genepred",
-                "references/ensembl/Homo_sapiens.GRCh38.102.gtf",
-                "references/ensembl/Homo_sapiens.GRCh38.102.refflat",
-                "references/ensembl/Homo_sapiens.GRCh38.102_rrna_intervals.gtf.interval_list",
                 "references/hgnc",
                 "references/hgnc/HGNC-DB-timestamp.txt",
-                "references/hgnc/hgnc_complete_set.txt",
-                "rrnatranscripts",
-                "rrnatranscripts/Homo_sapiens.GRCh38.102_rrna_intervals.gtf"
+                "references/hgnc/hgnc_complete_set.txt"
             ],
             [
-                "Homo_sapiens.GRCh38.102_rrna_intervals.gtf.bed:md5,5bc3ccc76735ae46699a75269f0ea65b",
-                "Homo_sapiens.GRCh38.102.dna.primary_assembly.dict:md5,092f1bf29fce906ff7b5ece02b4b21c8",
-                "Homo_sapiens.GRCh38.102.fasta:md5,d1f17b045dc60c49f2cc29e30006afc0",
-                "Homo_sapiens.GRCh38.102.chr.gtf:md5,0069687307852c63596b4d2ebdbbaf0c",
-                "Homo_sapiens.GRCh38.102.dna.primary_assembly.fa.fai:md5,d527f3eb6b664020cf4d882b5820056f",
-                "Homo_sapiens.GRCh38.102.genepred:md5,59c577ca4ab033c0ce1feac1e387bcab",
-                "Homo_sapiens.GRCh38.102.gtf:md5,defac755cd9aa4e82ec33398c27745ef",
-                "Homo_sapiens.GRCh38.102.refflat:md5,ef095e13743811c31d44752c32e9673e",
-                "Homo_sapiens.GRCh38.102_rrna_intervals.gtf.interval_list:md5,0abf61877f65247b15c438d605d85599",
-                "hgnc_complete_set.txt:md5,a563a2f8432ec0ab7d3dc74d769102b8",
-                "Homo_sapiens.GRCh38.102_rrna_intervals.gtf:md5,744bf505deb50837b15441e808cad345"
+                "hgnc_complete_set.txt:md5,a563a2f8432ec0ab7d3dc74d769102b8"
             ]
         ],
         "meta": {
             "nf-test": "0.9.0",
             "nextflow": "24.10.2"
         },
-        "timestamp": "2024-12-09T13:33:28.517098377"
+        "timestamp": "2024-12-10T15:09:04.076558"
     }
 }
\ No newline at end of file
diff --git a/tests/test_cosmic.nf.test.snap b/tests/test_cosmic.nf.test.snap
index dc3ab947..b8e6d4a5 100644
--- a/tests/test_cosmic.nf.test.snap
+++ b/tests/test_cosmic.nf.test.snap
@@ -24,14 +24,9 @@
     "test cosmic no fastp trim": {
         "content": [
             0,
-            {
-                "Workflow": {
-                    "nf-core/rnafusion": "v4.0.0dev"
-                }
-            },
+            null,
             [
-                "pipeline_info",
-                "pipeline_info/nf_core_pipeline_software_mqc_versions.yml"
+                "pipeline_info"
             ],
             [
                 
@@ -41,19 +36,14 @@
             "nf-test": "0.9.0",
             "nextflow": "24.10.2"
         },
-        "timestamp": "2024-12-10T12:42:06.51355"
+        "timestamp": "2024-12-10T15:09:53.130295"
     },
     "test cosmic with fastp trim": {
         "content": [
             0,
-            {
-                "Workflow": {
-                    "nf-core/rnafusion": "v4.0.0dev"
-                }
-            },
+            null,
             [
-                "pipeline_info",
-                "pipeline_info/nf_core_pipeline_software_mqc_versions.yml"
+                "pipeline_info"
             ],
             [
                 
@@ -63,6 +53,6 @@
             "nf-test": "0.9.0",
             "nextflow": "24.10.2"
         },
-        "timestamp": "2024-12-10T12:41:17.841938"
+        "timestamp": "2024-12-10T15:09:29.277399"
     }
 }
\ No newline at end of file

From ef5ab96f749a1dd7d6c32f54f39fa395892c7a20 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Tue, 10 Dec 2024 16:00:35 +0100
Subject: [PATCH 28/41] update star in snapshot

---
 tests/test_stub.nf.test.snap | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/tests/test_stub.nf.test.snap b/tests/test_stub.nf.test.snap
index febef3c8..0c4a3578 100644
--- a/tests/test_stub.nf.test.snap
+++ b/tests/test_stub.nf.test.snap
@@ -80,17 +80,17 @@
                     "STAR-Fusion": "1.7.0"
                 },
                 "STAR_FOR_ARRIBA": {
-                    "star": null,
+                    "star": 2.7.11b,
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
                 "STAR_FOR_STARFUSION": {
-                    "star": null,
+                    "star": 2.7.11b,
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
                 "STAR_GENOMEGENERATE": {
-                    "star": null,
+                    "star": 2.7.11b,
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
@@ -355,17 +355,17 @@
                     "STAR-Fusion": "1.7.0"
                 },
                 "STAR_FOR_ARRIBA": {
-                    "star": null,
+                    "star": 2.7.11b,
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
                 "STAR_FOR_STARFUSION": {
-                    "star": null,
+                    "star": 2.7.11b,
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
                 "STAR_GENOMEGENERATE": {
-                    "star": null,
+                    "star": 2.7.11b,
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
@@ -549,4 +549,4 @@
         },
         "timestamp": "2024-12-10T14:10:38.383967"
     }
-}
\ No newline at end of file
+}

From 117884c783977964fe3ee9196ebbc44944f2eaa3 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Wed, 11 Dec 2024 10:39:08 +0100
Subject: [PATCH 29/41] add human_gencode_filter to starfusion build

---
 CHANGELOG.md                                 |   3 +-
 modules/local/fusioncatcher/download/main.nf |   1 -
 modules/local/starfusion/build/main.nf       |   1 +
 subworkflows/local/arriba_workflow.nf        |   2 +-
 test.xml                                     | 240 +++++++++++++++++++
 5 files changed, 244 insertions(+), 3 deletions(-)
 create mode 100644 test.xml

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 1980cd86..a1444c08 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -27,7 +27,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Updated to nf-core/tools 3.0.2 [#504](https://github.com/nf-core/rnafusion/pull/504)
 - Remove local module `RRNA_TRANSCRIPTS` (replaced by nf-core module) [#541](https://github.com/nf-core/rnafusion/pull/541)
 - Allow fastq files without a dot before .fn(.gz)/.fastq(.gz) files [#548](https://github.com/nf-core/rnafusion/pull/548)
-        ext.args = "-genePredExt -geneNameAsName2 -ignoreGroupsWithoutExons" GTF_TO_REFFLAT
+  ext.args = "-genePredExt -geneNameAsName2 -ignoreGroupsWithoutExons" GTF_TO_REFFLAT
+
 ### Fixed
 
 - Fixed some Nextflow run-commands in the docs [#491](https://github.com/nf-core/rnafusion/pull/491)
diff --git a/modules/local/fusioncatcher/download/main.nf b/modules/local/fusioncatcher/download/main.nf
index ed97c834..03c0a1f3 100644
--- a/modules/local/fusioncatcher/download/main.nf
+++ b/modules/local/fusioncatcher/download/main.nf
@@ -19,7 +19,6 @@ process FUSIONCATCHER_DOWNLOAD {
     script:
 
     def args = task.ext.args ?: ''
-    def args2 = task.ext.args2 ?: ''
         // TODO: move to S3
 
     // def url =
diff --git a/modules/local/starfusion/build/main.nf b/modules/local/starfusion/build/main.nf
index 436a5e4f..10485ac0 100644
--- a/modules/local/starfusion/build/main.nf
+++ b/modules/local/starfusion/build/main.nf
@@ -33,6 +33,7 @@ process STARFUSION_BUILD {
         --pfam_db Pfam-A.hmm \\
         --dfam_db homo_sapiens_dfam.hmm \\
         --max_readlength $params.read_length \\
+        --human_gencode_filter \\
         --CPU $task.cpus
 
     cat <<-END_VERSIONS > versions.yml
diff --git a/subworkflows/local/arriba_workflow.nf b/subworkflows/local/arriba_workflow.nf
index 5d844678..5575f5c0 100644
--- a/subworkflows/local/arriba_workflow.nf
+++ b/subworkflows/local/arriba_workflow.nf
@@ -52,7 +52,7 @@ workflow ARRIBA_WORKFLOW {
         }
         else {
             ch_arriba_fusions       = reads.combine(Channel.value( file(ch_dummy_file, checkIfExists:true ) ) )
-                                        .map { meta, reads, fusions -> [ meta, fusions ] }
+                                        .map { it -> [ it[0], it[2] ] }
 
             ch_arriba_fusion_fail   = ch_dummy_file
         }
diff --git a/test.xml b/test.xml
new file mode 100644
index 00000000..2aed29e1
--- /dev/null
+++ b/test.xml
@@ -0,0 +1,240 @@
+<?xml version="1.0" encoding="utf-8"?><testsuites><testsuite name="Test pipeline" time="410.367" tests="2" skipped="0" failures="2" timestamp="2024 12 11 10:14:41"><testcase classname="Test pipeline" name="stub test with fastp trim" time="213.214" status="FAILED"><failure message="Assertion failed: 
+
+1 of 2 assertions failed
+">Nextflow stdout:
+
+N E X T F L O W  ~  version 24.10.2
+Launching `/Users/annick.renevey/Projects/rnafusion/tests/../main.nf` [elated_pasteur] DSL2 - revision: dc78081240
+
+------------------------------------------------------
+                                        ,--./,-.
+        ___     __   __   __   ___     /,-._.--~'
+  |\ | |__  __ /  ` /  \ |__) |__         }  {
+  | \| |       \__, \__/ |  \ |___     \`-._,-`-,
+                                        `._,._,'
+  nf-core/rnafusion 4.0.0dev
+------------------------------------------------------
+Input/output options
+  input                             : https://raw.githubusercontent.com/nf-core/test-datasets/rnafusion/testdata/human/samplesheet_valid.csv
+  outdir                            : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output
+  genomes_base                      : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references
+  genome_gencode_version            : 46
+  starfusion_build                  : true
+  all                               : true
+  arriba_ref_blacklist              : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/arriba/blacklist_hg38_GRCh38_v2.4.0.tsv.gz
+  arriba_ref_cytobands              : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/arriba/cytobands_hg38_GRCh38_v2.4.0.tsv
+  arriba_ref_known_fusions          : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/arriba/known_fusions_hg38_GRCh38_v2.4.0.tsv.gz
+  arriba_ref_protein_domains        : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/arriba/protein_domains_hg38_GRCh38_v2.4.0.gff3
+  gencode_ref                       : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/gencode
+  fusioncatcher_limitSjdbInsertNsj  : 2000000
+  fusioncatcher_ref                 : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/fusioncatcher/human_v46
+  fusioncatcher_ref_stub_check      : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/fusioncatcher/human_v46/ensembl_fully_overlapping_genes.txt
+  fusioninspector_limitSjdbInsertNsj: 1000000
+  fusionreport_ref                  : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/fusion_report_db
+  fusionreport_ref_stub_check       : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/fusion_report_db/mitelman.db
+  hgnc_ref                          : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/hgnc/hgnc_complete_set.txt
+  hgnc_date                         : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/hgnc/HGNC-DB-timestamp.txt
+  salmon_index                      : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/salmon/salmon
+  salmon_index_stub_check           : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/salmon/salmon/complete_ref_lens.bin
+  starfusion_ref                    : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/starfusion/ctat_genome_lib_build_dir
+  starfusion_ref_stub_check         : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/starfusion/Pfam-A.hmm
+  starindex_ref                     : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/star
+  starindex_ref_stub_check          : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/star/star/Genome
+  tools_cutoff                      : 1
+
+Read trimming options
+  fastp_trim                        : true
+  adapter_fasta                     : []
+
+Alignment compression options
+  cram                              : []
+
+Reference genome options
+  fasta                             : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/gencode/Homo_sapiens_GRCh38_46_dna_primary_assembly.fa
+  fai                               : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/gencode/Homo_sapiens_GRCh38_46_dna_primary_assembly.fa.fai
+  genome                            : GRCh38
+  gtf                               : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/gencode/Homo_sapiens_GRCh38_46.gtf
+  refflat                           : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/gencode/Homo_sapiens_GRCh38_46.gtf.refflat
+  rrna_intervals                    : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/gencode/Homo_sapiens_GRCh38_46.interval_list
+  no_cosmic                         : true
+
+Institutional config options
+  config_profile_name               : Test profile
+  config_profile_description        : Minimal test dataset to check pipeline function
+
+Core Nextflow options
+  runName                           : elated_pasteur
+  containerEngine                   : docker
+  launchDir                         : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0
+  workDir                           : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/work
+  projectDir                        : /Users/annick.renevey/Projects/rnafusion
+  userName                          : annick.renevey
+  profile                           : test,docker
+  configFiles                       : 
+
+!! Only displaying parameters that differ from the pipeline defaults !!
+------------------------------------------------------
+* The nf-core framework
+    https://doi.org/10.1038/s41587-020-0439-x
+
+* Software dependencies
+    https://github.com/nf-core/rnafusion/blob/master/CITATIONS.md
+
+WARN: nf-core pipelines do not accept positional arguments. The positional argument `true` has been detected.
+HINT: A common mistake is to provide multiple values separated by spaces e.g. `-profile test, docker`.
+
+WARN: Skipping COSMIC DB download from `FUSIONREPORT_DOWNLOAD` and skip using it in `FUSIONREPORT`
+[13/a75f51] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:FUSIONCATCHER_BUILD (fusioncatcher_build)
+[78/f27e8a] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:HGNC_DOWNLOAD (hgnc)
+[c9/d109b6] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:ARRIBA_DOWNLOAD (arriba)
+[1b/cb8505] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:GENCODE_DOWNLOAD (gencode_download)
+[61/738ba4] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:FUSIONREPORT_DOWNLOAD (fusionreport)
+[6c/ccb83a] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:FASTQC (test)
+[52/593378] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:TRIM_WORKFLOW:FASTP (test)
+[18/18b5f3] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:SAMTOOLS_FAIDX (Homo_sapiens.GRCh38.46_dna_primary_assembly.fa)
+[38/36e8dd] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:GATK4_CREATESEQUENCEDICTIONARY (Homo_sapiens.GRCh38.46_dna_primary_assembly.fa)
+[b3/7aad17] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:GET_RRNA_TRANSCRIPTS (get_rrna_bed)
+[53/e4d111] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:STAR_GENOMEGENERATE (Homo_sapiens.GRCh38.46_dna_primary_assembly.fa)
+[37/d0930c] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:GFFREAD (Homo_sapiens.GRCh38.46.gtf)
+[26/aa9b36] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:GTF_TO_REFFLAT (Homo_sapiens.GRCh38.46.gtf)
+[18/66b9c3] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:STARFUSION_BUILD (star-fusion)
+[05/6e1246] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:TRIM_WORKFLOW:FASTQC_FOR_FASTP (test)
+[83/52bcc1] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:FUSIONCATCHER_WORKFLOW:FUSIONCATCHER (test)
+[5b/c0d7bc] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:GATK4_BEDTOINTERVALLIST (Homo_sapiens.GRCh38.46.gtf)
+[24/c5d0b9] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:STARFUSION_WORKFLOW:STAR_FOR_STARFUSION (test)
+[43/8be8df] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:ARRIBA_WORKFLOW:STAR_FOR_ARRIBA (test)
+[f9/87735b] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:SALMON_INDEX (Homo_sapiens.GRCh38.46.gtf.fasta)
+[b4/64a1cd] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:QC_WORKFLOW:PICARD_COLLECTRNASEQMETRICS (test)
+[cc/99a46b] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:QC_WORKFLOW:PICARD_COLLECTINSERTSIZEMETRICS (test)
+[0b/18a022] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:STARFUSION_WORKFLOW:STARFUSION (test)
+[aa/000cc3] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:STARFUSION_WORKFLOW:SAMTOOLS_INDEX_FOR_STARFUSION (test)
+[3d/4dfbba] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:STRINGTIE_WORKFLOW:STRINGTIE_STRINGTIE (test)
+[10/6bc883] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:QC_WORKFLOW:GATK4_MARKDUPLICATES (test)
+[74/397e36] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:ARRIBA_WORKFLOW:ARRIBA_ARRIBA (test)
+[df/483739] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:SALMON_QUANT (test)
+[92/376a4b] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:STRINGTIE_WORKFLOW:STRINGTIE_MERGE (1)
+[b6/26ca21] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:FUSIONREPORT_WORKFLOW:FUSIONREPORT (test)
+[51/2177ee] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:MULTIQC
+-[nf-core/rnafusion] Pipeline completed successfully-
+Nextflow stderr:
+
+</failure></testcase><testcase classname="Test pipeline" name="stub test no fastp trim" time="197.086" status="FAILED"><failure message="Assertion failed: 
+
+1 of 2 assertions failed
+">Nextflow stdout:
+
+N E X T F L O W  ~  version 24.10.2
+Launching `/Users/annick.renevey/Projects/rnafusion/tests/../main.nf` [naughty_becquerel] DSL2 - revision: dc78081240
+
+------------------------------------------------------
+                                        ,--./,-.
+        ___     __   __   __   ___     /,-._.--~'
+  |\ | |__  __ /  ` /  \ |__) |__         }  {
+  | \| |       \__, \__/ |  \ |___     \`-._,-`-,
+                                        `._,._,'
+  nf-core/rnafusion 4.0.0dev
+------------------------------------------------------
+Input/output options
+  input                             : https://raw.githubusercontent.com/nf-core/test-datasets/rnafusion/testdata/human/samplesheet_valid.csv
+  outdir                            : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output
+  genomes_base                      : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references
+  genome_gencode_version            : 46
+  starfusion_build                  : true
+  all                               : true
+  arriba_ref_blacklist              : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/arriba/blacklist_hg38_GRCh38_v2.4.0.tsv.gz
+  arriba_ref_cytobands              : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/arriba/cytobands_hg38_GRCh38_v2.4.0.tsv
+  arriba_ref_known_fusions          : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/arriba/known_fusions_hg38_GRCh38_v2.4.0.tsv.gz
+  arriba_ref_protein_domains        : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/arriba/protein_domains_hg38_GRCh38_v2.4.0.gff3
+  gencode_ref                       : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/gencode
+  fusioncatcher_limitSjdbInsertNsj  : 2000000
+  fusioncatcher_ref                 : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/fusioncatcher/human_v46
+  fusioncatcher_ref_stub_check      : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/fusioncatcher/human_v46/ensembl_fully_overlapping_genes.txt
+  fusioninspector_limitSjdbInsertNsj: 1000000
+  fusionreport_ref                  : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/fusion_report_db
+  fusionreport_ref_stub_check       : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/fusion_report_db/mitelman.db
+  hgnc_ref                          : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/hgnc/hgnc_complete_set.txt
+  hgnc_date                         : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/hgnc/HGNC-DB-timestamp.txt
+  salmon_index                      : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/salmon/salmon
+  salmon_index_stub_check           : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/salmon/salmon/complete_ref_lens.bin
+  starfusion_ref                    : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/starfusion/ctat_genome_lib_build_dir
+  starfusion_ref_stub_check         : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/starfusion/Pfam-A.hmm
+  starindex_ref                     : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/star
+  starindex_ref_stub_check          : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/star/star/Genome
+  tools_cutoff                      : 1
+
+Read trimming options
+  adapter_fasta                     : []
+
+Alignment compression options
+  cram                              : []
+
+Reference genome options
+  fasta                             : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/gencode/Homo_sapiens_GRCh38_46_dna_primary_assembly.fa
+  fai                               : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/gencode/Homo_sapiens_GRCh38_46_dna_primary_assembly.fa.fai
+  genome                            : GRCh38
+  gtf                               : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/gencode/Homo_sapiens_GRCh38_46.gtf
+  refflat                           : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/gencode/Homo_sapiens_GRCh38_46.gtf.refflat
+  rrna_intervals                    : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/gencode/Homo_sapiens_GRCh38_46.interval_list
+  no_cosmic                         : true
+
+Institutional config options
+  config_profile_name               : Test profile
+  config_profile_description        : Minimal test dataset to check pipeline function
+
+Core Nextflow options
+  runName                           : naughty_becquerel
+  containerEngine                   : docker
+  launchDir                         : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1
+  workDir                           : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/work
+  projectDir                        : /Users/annick.renevey/Projects/rnafusion
+  userName                          : annick.renevey
+  profile                           : test,docker
+  configFiles                       : 
+
+!! Only displaying parameters that differ from the pipeline defaults !!
+------------------------------------------------------
+* The nf-core framework
+    https://doi.org/10.1038/s41587-020-0439-x
+
+* Software dependencies
+    https://github.com/nf-core/rnafusion/blob/master/CITATIONS.md
+
+WARN: nf-core pipelines do not accept positional arguments. The positional argument `true` has been detected.
+HINT: A common mistake is to provide multiple values separated by spaces e.g. `-profile test, docker`.
+
+WARN: Skipping COSMIC DB download from `FUSIONREPORT_DOWNLOAD` and skip using it in `FUSIONREPORT`
+[8d/ee20bb] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:HGNC_DOWNLOAD (hgnc)
+[d6/69323a] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:GENCODE_DOWNLOAD (gencode_download)
+[b9/5c89ae] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:FUSIONREPORT_DOWNLOAD (fusionreport)
+[43/355279] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:FUSIONCATCHER_BUILD (fusioncatcher_build)
+[94/cf96bf] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:ARRIBA_DOWNLOAD (arriba)
+[e4/d33580] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:GATK4_CREATESEQUENCEDICTIONARY (Homo_sapiens.GRCh38.46_dna_primary_assembly.fa)
+[db/fa3dd4] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:SAMTOOLS_FAIDX (Homo_sapiens.GRCh38.46_dna_primary_assembly.fa)
+[90/118532] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:FASTQC (test)
+[b9/6593b4] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:TRIM_WORKFLOW:FASTP (test)
+[b4/28611c] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:GTF_TO_REFFLAT (Homo_sapiens.GRCh38.46.gtf)
+[d0/9b767c] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:GET_RRNA_TRANSCRIPTS (get_rrna_bed)
+[c2/fd36fd] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:GFFREAD (Homo_sapiens.GRCh38.46.gtf)
+[76/b9b243] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:STAR_GENOMEGENERATE (Homo_sapiens.GRCh38.46_dna_primary_assembly.fa)
+[d6/350166] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:STARFUSION_BUILD (star-fusion)
+[89/c38359] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:TRIM_WORKFLOW:FASTQC_FOR_FASTP (test)
+[92/431af8] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:FUSIONCATCHER_WORKFLOW:FUSIONCATCHER (test)
+[43/c4079e] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:GATK4_BEDTOINTERVALLIST (Homo_sapiens.GRCh38.46.gtf)
+[e6/3c5e19] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:SALMON_INDEX (Homo_sapiens.GRCh38.46.gtf.fasta)
+[71/f9cbec] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:ARRIBA_WORKFLOW:STAR_FOR_ARRIBA (test)
+[96/59d525] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:STARFUSION_WORKFLOW:STAR_FOR_STARFUSION (test)
+[99/6d4d21] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:SALMON_QUANT (test)
+[9c/fd7ac5] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:ARRIBA_WORKFLOW:ARRIBA_ARRIBA (test)
+[29/6b167b] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:STRINGTIE_WORKFLOW:STRINGTIE_STRINGTIE (test)
+[39/c6c23e] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:STARFUSION_WORKFLOW:STARFUSION (test)
+[35/474e2f] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:STARFUSION_WORKFLOW:SAMTOOLS_INDEX_FOR_STARFUSION (test)
+[66/b0ff6a] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:QC_WORKFLOW:GATK4_MARKDUPLICATES (test)
+[63/a246b6] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:QC_WORKFLOW:PICARD_COLLECTRNASEQMETRICS (test)
+[41/50018c] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:QC_WORKFLOW:PICARD_COLLECTINSERTSIZEMETRICS (test)
+[8c/96974e] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:STRINGTIE_WORKFLOW:STRINGTIE_MERGE (1)
+[fe/e581e9] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:FUSIONREPORT_WORKFLOW:FUSIONREPORT (test)
+[99/47d296] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:MULTIQC
+-[nf-core/rnafusion] Pipeline completed successfully-
+Nextflow stderr:
+
+</failure></testcase></testsuite></testsuites>
\ No newline at end of file

From 3788788d1b26dd07dd9cfb85c8cb1091f6630f8e Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Wed, 11 Dec 2024 10:44:52 +0100
Subject: [PATCH 30/41] remove test.xml

---
 test.xml | 240 -------------------------------------------------------
 1 file changed, 240 deletions(-)
 delete mode 100644 test.xml

diff --git a/test.xml b/test.xml
deleted file mode 100644
index 2aed29e1..00000000
--- a/test.xml
+++ /dev/null
@@ -1,240 +0,0 @@
-<?xml version="1.0" encoding="utf-8"?><testsuites><testsuite name="Test pipeline" time="410.367" tests="2" skipped="0" failures="2" timestamp="2024 12 11 10:14:41"><testcase classname="Test pipeline" name="stub test with fastp trim" time="213.214" status="FAILED"><failure message="Assertion failed: 
-
-1 of 2 assertions failed
-">Nextflow stdout:
-
-N E X T F L O W  ~  version 24.10.2
-Launching `/Users/annick.renevey/Projects/rnafusion/tests/../main.nf` [elated_pasteur] DSL2 - revision: dc78081240
-
-------------------------------------------------------
-                                        ,--./,-.
-        ___     __   __   __   ___     /,-._.--~'
-  |\ | |__  __ /  ` /  \ |__) |__         }  {
-  | \| |       \__, \__/ |  \ |___     \`-._,-`-,
-                                        `._,._,'
-  nf-core/rnafusion 4.0.0dev
-------------------------------------------------------
-Input/output options
-  input                             : https://raw.githubusercontent.com/nf-core/test-datasets/rnafusion/testdata/human/samplesheet_valid.csv
-  outdir                            : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output
-  genomes_base                      : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references
-  genome_gencode_version            : 46
-  starfusion_build                  : true
-  all                               : true
-  arriba_ref_blacklist              : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/arriba/blacklist_hg38_GRCh38_v2.4.0.tsv.gz
-  arriba_ref_cytobands              : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/arriba/cytobands_hg38_GRCh38_v2.4.0.tsv
-  arriba_ref_known_fusions          : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/arriba/known_fusions_hg38_GRCh38_v2.4.0.tsv.gz
-  arriba_ref_protein_domains        : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/arriba/protein_domains_hg38_GRCh38_v2.4.0.gff3
-  gencode_ref                       : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/gencode
-  fusioncatcher_limitSjdbInsertNsj  : 2000000
-  fusioncatcher_ref                 : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/fusioncatcher/human_v46
-  fusioncatcher_ref_stub_check      : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/fusioncatcher/human_v46/ensembl_fully_overlapping_genes.txt
-  fusioninspector_limitSjdbInsertNsj: 1000000
-  fusionreport_ref                  : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/fusion_report_db
-  fusionreport_ref_stub_check       : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/fusion_report_db/mitelman.db
-  hgnc_ref                          : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/hgnc/hgnc_complete_set.txt
-  hgnc_date                         : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/hgnc/HGNC-DB-timestamp.txt
-  salmon_index                      : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/salmon/salmon
-  salmon_index_stub_check           : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/salmon/salmon/complete_ref_lens.bin
-  starfusion_ref                    : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/starfusion/ctat_genome_lib_build_dir
-  starfusion_ref_stub_check         : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/starfusion/Pfam-A.hmm
-  starindex_ref                     : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/star
-  starindex_ref_stub_check          : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/star/star/Genome
-  tools_cutoff                      : 1
-
-Read trimming options
-  fastp_trim                        : true
-  adapter_fasta                     : []
-
-Alignment compression options
-  cram                              : []
-
-Reference genome options
-  fasta                             : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/gencode/Homo_sapiens_GRCh38_46_dna_primary_assembly.fa
-  fai                               : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/gencode/Homo_sapiens_GRCh38_46_dna_primary_assembly.fa.fai
-  genome                            : GRCh38
-  gtf                               : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/gencode/Homo_sapiens_GRCh38_46.gtf
-  refflat                           : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/gencode/Homo_sapiens_GRCh38_46.gtf.refflat
-  rrna_intervals                    : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/output/references/gencode/Homo_sapiens_GRCh38_46.interval_list
-  no_cosmic                         : true
-
-Institutional config options
-  config_profile_name               : Test profile
-  config_profile_description        : Minimal test dataset to check pipeline function
-
-Core Nextflow options
-  runName                           : elated_pasteur
-  containerEngine                   : docker
-  launchDir                         : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0
-  workDir                           : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/acc69f529568702c4fabd8a30cf1fcb0/work
-  projectDir                        : /Users/annick.renevey/Projects/rnafusion
-  userName                          : annick.renevey
-  profile                           : test,docker
-  configFiles                       : 
-
-!! Only displaying parameters that differ from the pipeline defaults !!
-------------------------------------------------------
-* The nf-core framework
-    https://doi.org/10.1038/s41587-020-0439-x
-
-* Software dependencies
-    https://github.com/nf-core/rnafusion/blob/master/CITATIONS.md
-
-WARN: nf-core pipelines do not accept positional arguments. The positional argument `true` has been detected.
-HINT: A common mistake is to provide multiple values separated by spaces e.g. `-profile test, docker`.
-
-WARN: Skipping COSMIC DB download from `FUSIONREPORT_DOWNLOAD` and skip using it in `FUSIONREPORT`
-[13/a75f51] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:FUSIONCATCHER_BUILD (fusioncatcher_build)
-[78/f27e8a] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:HGNC_DOWNLOAD (hgnc)
-[c9/d109b6] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:ARRIBA_DOWNLOAD (arriba)
-[1b/cb8505] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:GENCODE_DOWNLOAD (gencode_download)
-[61/738ba4] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:FUSIONREPORT_DOWNLOAD (fusionreport)
-[6c/ccb83a] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:FASTQC (test)
-[52/593378] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:TRIM_WORKFLOW:FASTP (test)
-[18/18b5f3] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:SAMTOOLS_FAIDX (Homo_sapiens.GRCh38.46_dna_primary_assembly.fa)
-[38/36e8dd] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:GATK4_CREATESEQUENCEDICTIONARY (Homo_sapiens.GRCh38.46_dna_primary_assembly.fa)
-[b3/7aad17] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:GET_RRNA_TRANSCRIPTS (get_rrna_bed)
-[53/e4d111] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:STAR_GENOMEGENERATE (Homo_sapiens.GRCh38.46_dna_primary_assembly.fa)
-[37/d0930c] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:GFFREAD (Homo_sapiens.GRCh38.46.gtf)
-[26/aa9b36] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:GTF_TO_REFFLAT (Homo_sapiens.GRCh38.46.gtf)
-[18/66b9c3] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:STARFUSION_BUILD (star-fusion)
-[05/6e1246] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:TRIM_WORKFLOW:FASTQC_FOR_FASTP (test)
-[83/52bcc1] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:FUSIONCATCHER_WORKFLOW:FUSIONCATCHER (test)
-[5b/c0d7bc] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:GATK4_BEDTOINTERVALLIST (Homo_sapiens.GRCh38.46.gtf)
-[24/c5d0b9] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:STARFUSION_WORKFLOW:STAR_FOR_STARFUSION (test)
-[43/8be8df] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:ARRIBA_WORKFLOW:STAR_FOR_ARRIBA (test)
-[f9/87735b] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:SALMON_INDEX (Homo_sapiens.GRCh38.46.gtf.fasta)
-[b4/64a1cd] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:QC_WORKFLOW:PICARD_COLLECTRNASEQMETRICS (test)
-[cc/99a46b] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:QC_WORKFLOW:PICARD_COLLECTINSERTSIZEMETRICS (test)
-[0b/18a022] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:STARFUSION_WORKFLOW:STARFUSION (test)
-[aa/000cc3] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:STARFUSION_WORKFLOW:SAMTOOLS_INDEX_FOR_STARFUSION (test)
-[3d/4dfbba] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:STRINGTIE_WORKFLOW:STRINGTIE_STRINGTIE (test)
-[10/6bc883] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:QC_WORKFLOW:GATK4_MARKDUPLICATES (test)
-[74/397e36] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:ARRIBA_WORKFLOW:ARRIBA_ARRIBA (test)
-[df/483739] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:SALMON_QUANT (test)
-[92/376a4b] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:STRINGTIE_WORKFLOW:STRINGTIE_MERGE (1)
-[b6/26ca21] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:FUSIONREPORT_WORKFLOW:FUSIONREPORT (test)
-[51/2177ee] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:MULTIQC
--[nf-core/rnafusion] Pipeline completed successfully-
-Nextflow stderr:
-
-</failure></testcase><testcase classname="Test pipeline" name="stub test no fastp trim" time="197.086" status="FAILED"><failure message="Assertion failed: 
-
-1 of 2 assertions failed
-">Nextflow stdout:
-
-N E X T F L O W  ~  version 24.10.2
-Launching `/Users/annick.renevey/Projects/rnafusion/tests/../main.nf` [naughty_becquerel] DSL2 - revision: dc78081240
-
-------------------------------------------------------
-                                        ,--./,-.
-        ___     __   __   __   ___     /,-._.--~'
-  |\ | |__  __ /  ` /  \ |__) |__         }  {
-  | \| |       \__, \__/ |  \ |___     \`-._,-`-,
-                                        `._,._,'
-  nf-core/rnafusion 4.0.0dev
-------------------------------------------------------
-Input/output options
-  input                             : https://raw.githubusercontent.com/nf-core/test-datasets/rnafusion/testdata/human/samplesheet_valid.csv
-  outdir                            : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output
-  genomes_base                      : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references
-  genome_gencode_version            : 46
-  starfusion_build                  : true
-  all                               : true
-  arriba_ref_blacklist              : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/arriba/blacklist_hg38_GRCh38_v2.4.0.tsv.gz
-  arriba_ref_cytobands              : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/arriba/cytobands_hg38_GRCh38_v2.4.0.tsv
-  arriba_ref_known_fusions          : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/arriba/known_fusions_hg38_GRCh38_v2.4.0.tsv.gz
-  arriba_ref_protein_domains        : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/arriba/protein_domains_hg38_GRCh38_v2.4.0.gff3
-  gencode_ref                       : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/gencode
-  fusioncatcher_limitSjdbInsertNsj  : 2000000
-  fusioncatcher_ref                 : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/fusioncatcher/human_v46
-  fusioncatcher_ref_stub_check      : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/fusioncatcher/human_v46/ensembl_fully_overlapping_genes.txt
-  fusioninspector_limitSjdbInsertNsj: 1000000
-  fusionreport_ref                  : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/fusion_report_db
-  fusionreport_ref_stub_check       : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/fusion_report_db/mitelman.db
-  hgnc_ref                          : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/hgnc/hgnc_complete_set.txt
-  hgnc_date                         : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/hgnc/HGNC-DB-timestamp.txt
-  salmon_index                      : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/salmon/salmon
-  salmon_index_stub_check           : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/salmon/salmon/complete_ref_lens.bin
-  starfusion_ref                    : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/starfusion/ctat_genome_lib_build_dir
-  starfusion_ref_stub_check         : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/starfusion/Pfam-A.hmm
-  starindex_ref                     : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/star
-  starindex_ref_stub_check          : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/star/star/Genome
-  tools_cutoff                      : 1
-
-Read trimming options
-  adapter_fasta                     : []
-
-Alignment compression options
-  cram                              : []
-
-Reference genome options
-  fasta                             : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/gencode/Homo_sapiens_GRCh38_46_dna_primary_assembly.fa
-  fai                               : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/gencode/Homo_sapiens_GRCh38_46_dna_primary_assembly.fa.fai
-  genome                            : GRCh38
-  gtf                               : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/gencode/Homo_sapiens_GRCh38_46.gtf
-  refflat                           : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/gencode/Homo_sapiens_GRCh38_46.gtf.refflat
-  rrna_intervals                    : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/output/references/gencode/Homo_sapiens_GRCh38_46.interval_list
-  no_cosmic                         : true
-
-Institutional config options
-  config_profile_name               : Test profile
-  config_profile_description        : Minimal test dataset to check pipeline function
-
-Core Nextflow options
-  runName                           : naughty_becquerel
-  containerEngine                   : docker
-  launchDir                         : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1
-  workDir                           : /Users/annick.renevey/Projects/rnafusion/.nf-test/tests/5d4f02e50caba01d5f317164e187f7c1/work
-  projectDir                        : /Users/annick.renevey/Projects/rnafusion
-  userName                          : annick.renevey
-  profile                           : test,docker
-  configFiles                       : 
-
-!! Only displaying parameters that differ from the pipeline defaults !!
-------------------------------------------------------
-* The nf-core framework
-    https://doi.org/10.1038/s41587-020-0439-x
-
-* Software dependencies
-    https://github.com/nf-core/rnafusion/blob/master/CITATIONS.md
-
-WARN: nf-core pipelines do not accept positional arguments. The positional argument `true` has been detected.
-HINT: A common mistake is to provide multiple values separated by spaces e.g. `-profile test, docker`.
-
-WARN: Skipping COSMIC DB download from `FUSIONREPORT_DOWNLOAD` and skip using it in `FUSIONREPORT`
-[8d/ee20bb] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:HGNC_DOWNLOAD (hgnc)
-[d6/69323a] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:GENCODE_DOWNLOAD (gencode_download)
-[b9/5c89ae] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:FUSIONREPORT_DOWNLOAD (fusionreport)
-[43/355279] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:FUSIONCATCHER_BUILD (fusioncatcher_build)
-[94/cf96bf] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:ARRIBA_DOWNLOAD (arriba)
-[e4/d33580] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:GATK4_CREATESEQUENCEDICTIONARY (Homo_sapiens.GRCh38.46_dna_primary_assembly.fa)
-[db/fa3dd4] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:SAMTOOLS_FAIDX (Homo_sapiens.GRCh38.46_dna_primary_assembly.fa)
-[90/118532] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:FASTQC (test)
-[b9/6593b4] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:TRIM_WORKFLOW:FASTP (test)
-[b4/28611c] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:GTF_TO_REFFLAT (Homo_sapiens.GRCh38.46.gtf)
-[d0/9b767c] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:GET_RRNA_TRANSCRIPTS (get_rrna_bed)
-[c2/fd36fd] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:GFFREAD (Homo_sapiens.GRCh38.46.gtf)
-[76/b9b243] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:STAR_GENOMEGENERATE (Homo_sapiens.GRCh38.46_dna_primary_assembly.fa)
-[d6/350166] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:STARFUSION_BUILD (star-fusion)
-[89/c38359] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:TRIM_WORKFLOW:FASTQC_FOR_FASTP (test)
-[92/431af8] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:FUSIONCATCHER_WORKFLOW:FUSIONCATCHER (test)
-[43/c4079e] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:GATK4_BEDTOINTERVALLIST (Homo_sapiens.GRCh38.46.gtf)
-[e6/3c5e19] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:BUILD_REFERENCES:SALMON_INDEX (Homo_sapiens.GRCh38.46.gtf.fasta)
-[71/f9cbec] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:ARRIBA_WORKFLOW:STAR_FOR_ARRIBA (test)
-[96/59d525] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:STARFUSION_WORKFLOW:STAR_FOR_STARFUSION (test)
-[99/6d4d21] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:SALMON_QUANT (test)
-[9c/fd7ac5] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:ARRIBA_WORKFLOW:ARRIBA_ARRIBA (test)
-[29/6b167b] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:STRINGTIE_WORKFLOW:STRINGTIE_STRINGTIE (test)
-[39/c6c23e] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:STARFUSION_WORKFLOW:STARFUSION (test)
-[35/474e2f] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:STARFUSION_WORKFLOW:SAMTOOLS_INDEX_FOR_STARFUSION (test)
-[66/b0ff6a] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:QC_WORKFLOW:GATK4_MARKDUPLICATES (test)
-[63/a246b6] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:QC_WORKFLOW:PICARD_COLLECTRNASEQMETRICS (test)
-[41/50018c] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:QC_WORKFLOW:PICARD_COLLECTINSERTSIZEMETRICS (test)
-[8c/96974e] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:STRINGTIE_WORKFLOW:STRINGTIE_MERGE (1)
-[fe/e581e9] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:FUSIONREPORT_WORKFLOW:FUSIONREPORT (test)
-[99/47d296] Submitted process &gt; NFCORE_RNAFUSION:RNAFUSION:MULTIQC
--[nf-core/rnafusion] Pipeline completed successfully-
-Nextflow stderr:
-
-</failure></testcase></testsuite></testsuites>
\ No newline at end of file

From 8e9be7cd6f83b175bdc15ef0a3fc8f9c89a33897 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Wed, 11 Dec 2024 12:45:38 +0100
Subject: [PATCH 31/41] update snap

---
 tests/test_stub.nf.test.snap | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/tests/test_stub.nf.test.snap b/tests/test_stub.nf.test.snap
index 0c4a3578..6cefb329 100644
--- a/tests/test_stub.nf.test.snap
+++ b/tests/test_stub.nf.test.snap
@@ -80,17 +80,17 @@
                     "STAR-Fusion": "1.7.0"
                 },
                 "STAR_FOR_ARRIBA": {
-                    "star": 2.7.11b,
+                    "star": null,
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
                 "STAR_FOR_STARFUSION": {
-                    "star": 2.7.11b,
+                    "star": null,
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
                 "STAR_GENOMEGENERATE": {
-                    "star": 2.7.11b,
+                    "star": null,
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
@@ -272,7 +272,7 @@
             "nf-test": "0.9.0",
             "nextflow": "24.10.2"
         },
-        "timestamp": "2024-12-10T14:12:48.526275"
+        "timestamp": "2024-12-11T12:43:59.534889"
     },
     "stub test with fastp trim": {
         "content": [
@@ -355,17 +355,17 @@
                     "STAR-Fusion": "1.7.0"
                 },
                 "STAR_FOR_ARRIBA": {
-                    "star": 2.7.11b,
+                    "star": null,
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
                 "STAR_FOR_STARFUSION": {
-                    "star": 2.7.11b,
+                    "star": null,
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
                 "STAR_GENOMEGENERATE": {
-                    "star": 2.7.11b,
+                    "star": null,
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
@@ -547,6 +547,6 @@
             "nf-test": "0.9.0",
             "nextflow": "24.10.2"
         },
-        "timestamp": "2024-12-10T14:10:38.383967"
+        "timestamp": "2024-12-11T12:40:22.066494"
     }
-}
+}
\ No newline at end of file

From 5cdf95aabc8c45e9687889558db88eddb603c925 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Wed, 11 Dec 2024 13:23:10 +0100
Subject: [PATCH 32/41] try updating snapshot again

---
 tests/test_stub.nf.test.snap | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/tests/test_stub.nf.test.snap b/tests/test_stub.nf.test.snap
index 6cefb329..83c76dd7 100644
--- a/tests/test_stub.nf.test.snap
+++ b/tests/test_stub.nf.test.snap
@@ -80,17 +80,17 @@
                     "STAR-Fusion": "1.7.0"
                 },
                 "STAR_FOR_ARRIBA": {
-                    "star": null,
+                    "star": "2.7.11b",
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
                 "STAR_FOR_STARFUSION": {
-                    "star": null,
+                    "star": "2.7.11b",
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
                 "STAR_GENOMEGENERATE": {
-                    "star": null,
+                    "star": "2.7.11b",
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
@@ -355,17 +355,17 @@
                     "STAR-Fusion": "1.7.0"
                 },
                 "STAR_FOR_ARRIBA": {
-                    "star": null,
+                    "star": "2.7.11b",
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
                 "STAR_FOR_STARFUSION": {
-                    "star": null,
+                    "star": "2.7.11b",
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
                 "STAR_GENOMEGENERATE": {
-                    "star": null,
+                    "star": "2.7.11b",
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
@@ -549,4 +549,4 @@
         },
         "timestamp": "2024-12-11T12:40:22.066494"
     }
-}
\ No newline at end of file
+}

From fa128b6805a6884a7ff29fbe30159e8fa229a5a3 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Tue, 17 Dec 2024 14:16:28 +0100
Subject: [PATCH 33/41] avoid using meta for remapping

---
 subworkflows/local/arriba_workflow.nf     | 2 +-
 subworkflows/local/starfusion_workflow.nf | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/subworkflows/local/arriba_workflow.nf b/subworkflows/local/arriba_workflow.nf
index 5575f5c0..10ddc16a 100644
--- a/subworkflows/local/arriba_workflow.nf
+++ b/subworkflows/local/arriba_workflow.nf
@@ -33,7 +33,7 @@ workflow ARRIBA_WORKFLOW {
                 ch_versions = ch_versions.mix(ARRIBA_ARRIBA.out.versions)
 
                 ch_arriba_fusions     = ARRIBA_ARRIBA.out.fusions
-                ch_arriba_fusion_fail = ARRIBA_ARRIBA.out.fusions_fail.map{ meta, file -> return file}
+                ch_arriba_fusion_fail = ARRIBA_ARRIBA.out.fusions_fail.map{ it -> it[1]}
             }
 
             if (params.cram.contains('arriba') ){
diff --git a/subworkflows/local/starfusion_workflow.nf b/subworkflows/local/starfusion_workflow.nf
index d6a0668a..f70396f5 100644
--- a/subworkflows/local/starfusion_workflow.nf
+++ b/subworkflows/local/starfusion_workflow.nf
@@ -21,7 +21,7 @@ workflow STARFUSION_WORKFLOW {
         if ((params.starfusion || params.all || params.stringtie) && !params.fusioninspector_only) {
             if (params.starfusion_fusions){
                 ch_starfusion_fusions = reads.combine(Channel.value(file(params.starfusion_fusions, checkIfExists:true)))
-                                        .map { meta, reads, fusions -> [ meta, fusions ] }
+                                        .map { it -> [ it[0], it[2] ] }
             } else {
                 STAR_FOR_STARFUSION( reads, ch_starindex_ref, ch_gtf, params.star_ignore_sjdbgtf, '', params.seq_center ?: '')
                 ch_versions = ch_versions.mix(STAR_FOR_STARFUSION.out.versions)
@@ -51,7 +51,7 @@ workflow STARFUSION_WORKFLOW {
         }
         else {
             ch_starfusion_fusions = reads.combine(Channel.value(file(ch_dummy_file, checkIfExists:true)))
-                                    .map { meta, reads, fusions -> [ meta, fusions ] }
+                                    .map { it -> [ it[0], it[2] ] }
             ch_star_stats = Channel.empty()
             ch_star_gene_count = Channel.empty()
         }

From 17ef23354947b4965c84131f9eb927bc323d1cbc Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Tue, 17 Dec 2024 17:49:22 +0100
Subject: [PATCH 34/41] use custom container for fusioncatcher, fix typo

---
 modules/local/fusioncatcher/detect/main.nf   |   3 +-
 modules/local/fusioncatcher/download/main.nf |   2 +-
 tests/test_stub.nf.test.snap                 | 198 ++-----------------
 workflows/rnafusion.nf                       |   4 +-
 4 files changed, 19 insertions(+), 188 deletions(-)

diff --git a/modules/local/fusioncatcher/detect/main.nf b/modules/local/fusioncatcher/detect/main.nf
index 9a092846..e753ff85 100644
--- a/modules/local/fusioncatcher/detect/main.nf
+++ b/modules/local/fusioncatcher/detect/main.nf
@@ -3,7 +3,8 @@ process FUSIONCATCHER {
     label 'process_high'
 
     conda "${moduleDir}/environment.yml"
-    container "community.wave.seqera.io/library/fusioncatcher:1.33--4733482b637ef92f"
+
+    container "docker.io/rannickscilifelab/fusioncatcher:1.34"
 
     input:
     tuple val(meta), path(fasta)
diff --git a/modules/local/fusioncatcher/download/main.nf b/modules/local/fusioncatcher/download/main.nf
index 03c0a1f3..e04c24f6 100644
--- a/modules/local/fusioncatcher/download/main.nf
+++ b/modules/local/fusioncatcher/download/main.nf
@@ -3,7 +3,7 @@ process FUSIONCATCHER_DOWNLOAD {
     label 'process_medium'
 
     conda "${moduleDir}/environment.yml"
-    container "community.wave.seqera.io/library/fusioncatcher:1.33--4733482b637ef92f"
+    container "docker.io/rannickscilifelab/fusioncatcher:1.34"
 
 
     input:
diff --git a/tests/test_stub.nf.test.snap b/tests/test_stub.nf.test.snap
index 83c76dd7..e3a8bb73 100644
--- a/tests/test_stub.nf.test.snap
+++ b/tests/test_stub.nf.test.snap
@@ -1,11 +1,8 @@
 {
     "stub test no fastp trim": {
         "content": [
-            31,
+            20,
             {
-                "ARRIBA_ARRIBA": {
-                    "arriba": "2.4.0"
-                },
                 "ARRIBA_DOWNLOAD": {
                     "arriba_download": "2.4.0"
                 },
@@ -19,14 +16,11 @@
                     "fastqc": "0.12.1"
                 },
                 "FUSIONCATCHER": {
-                    "fusioncatcher": 1.33
+                    "fusioncatcher": 1.35
                 },
                 "FUSIONCATCHER_BUILD": {
                     "fusioncatcher": "fusioncatcher.py 1.35"
                 },
-                "FUSIONREPORT": {
-                    "fusion_report": "2.1.5"
-                },
                 "FUSIONREPORT_DOWNLOAD": {
                     "fusion_report": "2.1.5"
                 },
@@ -36,10 +30,6 @@
                 "GATK4_CREATESEQUENCEDICTIONARY": {
                     "gatk4": "4.6.1.0"
                 },
-                "GATK4_MARKDUPLICATES": {
-                    "gatk4": "4.5.0.0",
-                    "samtools": "1.19.2"
-                },
                 "GENCODE_DOWNLOAD": {
                     "wget": null
                 },
@@ -55,59 +45,32 @@
                 "HGNC_DOWNLOAD": {
                     "wget": null
                 },
-                "PICARD_COLLECTINSERTSIZEMETRICS": {
-                    "picard": "3.3.0"
-                },
-                "PICARD_COLLECTRNASEQMETRICS": {
-                    "picard": "3.3.0"
-                },
-                "SALMON_INDEX": {
-                    "salmon": "1.10.3"
-                },
-                "SALMON_QUANT": {
-                    "salmon": "1.10.3"
-                },
                 "SAMTOOLS_FAIDX": {
                     "samtools": 1.21
                 },
-                "SAMTOOLS_INDEX_FOR_STARFUSION": {
-                    "samtools": 1.21
-                },
-                "STARFUSION": {
-                    "STAR-Fusion": "1.7.0"
-                },
                 "STARFUSION_BUILD": {
                     "STAR-Fusion": "1.7.0"
                 },
                 "STAR_FOR_ARRIBA": {
-                    "star": "2.7.11b",
+                    "star": null,
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
                 "STAR_FOR_STARFUSION": {
-                    "star": "2.7.11b",
+                    "star": null,
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
                 "STAR_GENOMEGENERATE": {
-                    "star": "2.7.11b",
+                    "star": null,
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
-                "STRINGTIE_MERGE": {
-                    "stringtie": "2.2.1"
-                },
-                "STRINGTIE_STRINGTIE": {
-                    "stringtie": "2.2.3"
-                },
                 "Workflow": {
                     "nf-core/rnafusion": "v4.0.0dev"
                 }
             },
             [
-                "arriba",
-                "arriba/test.arriba.fusions.discarded.tsv",
-                "arriba/test.arriba.fusions.tsv",
                 "fastp",
                 "fastp/test.fastp.html",
                 "fastp/test.fastp.json",
@@ -126,32 +89,11 @@
                 "fusioncatcher/test.fusioncatcher.fusion-genes.txt",
                 "fusioncatcher/test.fusioncatcher.log",
                 "fusioncatcher/test.fusioncatcher.summary.txt",
-                "fusionreport",
-                "fusionreport/test",
-                "fusionreport/test/AAA_BBB.html",
-                "fusionreport/test/test.fusionreport.tsv",
-                "fusionreport/test/test.fusionreport_filtered.tsv",
-                "fusionreport/test/test.fusions.csv",
-                "fusionreport/test/test.fusions.json",
-                "fusionreport/test/test_fusionreport_index.html",
                 "gatk4",
                 "gatk4/Homo_sapiens.GRCh38.46_dna_primary_assembly.dict",
                 "get",
                 "get/rrna.bed",
                 "get/rrna.gtf",
-                "multiqc",
-                "multiqc/multiqc_data",
-                "multiqc/multiqc_plots",
-                "multiqc/multiqc_report.html",
-                "picard",
-                "picard/test.bai",
-                "picard/test.bam",
-                "picard/test.bam.metrics",
-                "picard/test.cram",
-                "picard/test.cram.crai",
-                "picard/test.rna_metrics",
-                "picard/test_collectinsertsize.pdf",
-                "picard/test_collectinsertsize.txt",
                 "pipeline_info",
                 "pipeline_info/nf_core_pipeline_software_mqc_versions.yml",
                 "references",
@@ -214,10 +156,6 @@
                 "references/starfusion",
                 "references/starfusion/ctat_genome_lib_build_dir",
                 "references/starfusion/ref_annot.cdna.fa",
-                "salmon",
-                "salmon/test",
-                "salmon/test_lib_format_counts.json",
-                "salmon/test_meta_info.json",
                 "star_for_arriba",
                 "star_for_arriba/test.Aligned.sortedByCoord.out.bam",
                 "star_for_arriba/test.Aligned.unsort.out.bam",
@@ -249,38 +187,23 @@
                 "star_for_starfusion/test.Signal.UniqueMultiple.str1.out.wig",
                 "star_for_starfusion/test.out.sam",
                 "star_for_starfusion/test.sortedByCoord.out.bam",
-                "star_for_starfusion/test.sortedByCoord.out.bam.bai",
                 "star_for_starfusion/test.tab",
                 "star_for_starfusion/test.toTranscriptome.out.bam",
                 "star_for_starfusion/test.unmapped_1.fastq.gz",
                 "star_for_starfusion/test.unmapped_2.fastq.gz",
-                "star_for_starfusion/testXd.out.bam",
-                "starfusion",
-                "starfusion/test.starfusion.abridged.coding_effect.tsv",
-                "starfusion/test.starfusion.abridged.tsv",
-                "starfusion/test.starfusion.fusion_predictions.tsv",
-                "stringtie",
-                "stringtie/[:]",
-                "stringtie/[:]/stringtie.merged.gtf",
-                "stringtie/test.ballgown",
-                "stringtie/test.coverage.gtf",
-                "stringtie/test.gene.abundance.txt",
-                "stringtie/test.transcripts.gtf"
+                "star_for_starfusion/testXd.out.bam"
             ]
         ],
         "meta": {
             "nf-test": "0.9.0",
             "nextflow": "24.10.2"
         },
-        "timestamp": "2024-12-11T12:43:59.534889"
+        "timestamp": "2024-12-17T16:44:02.121512"
     },
     "stub test with fastp trim": {
         "content": [
-            31,
+            19,
             {
-                "ARRIBA_ARRIBA": {
-                    "arriba": "2.4.0"
-                },
                 "ARRIBA_DOWNLOAD": {
                     "arriba_download": "2.4.0"
                 },
@@ -294,14 +217,11 @@
                     "fastqc": "0.12.1"
                 },
                 "FUSIONCATCHER": {
-                    "fusioncatcher": 1.33
+                    "fusioncatcher": 1.35
                 },
                 "FUSIONCATCHER_BUILD": {
                     "fusioncatcher": "fusioncatcher.py 1.35"
                 },
-                "FUSIONREPORT": {
-                    "fusion_report": "2.1.5"
-                },
                 "FUSIONREPORT_DOWNLOAD": {
                     "fusion_report": "2.1.5"
                 },
@@ -311,10 +231,6 @@
                 "GATK4_CREATESEQUENCEDICTIONARY": {
                     "gatk4": "4.6.1.0"
                 },
-                "GATK4_MARKDUPLICATES": {
-                    "gatk4": "4.5.0.0",
-                    "samtools": "1.19.2"
-                },
                 "GENCODE_DOWNLOAD": {
                     "wget": null
                 },
@@ -330,59 +246,27 @@
                 "HGNC_DOWNLOAD": {
                     "wget": null
                 },
-                "PICARD_COLLECTINSERTSIZEMETRICS": {
-                    "picard": "3.3.0"
-                },
-                "PICARD_COLLECTRNASEQMETRICS": {
-                    "picard": "3.3.0"
-                },
-                "SALMON_INDEX": {
-                    "salmon": "1.10.3"
-                },
-                "SALMON_QUANT": {
-                    "salmon": "1.10.3"
-                },
                 "SAMTOOLS_FAIDX": {
                     "samtools": 1.21
                 },
-                "SAMTOOLS_INDEX_FOR_STARFUSION": {
-                    "samtools": 1.21
-                },
-                "STARFUSION": {
-                    "STAR-Fusion": "1.7.0"
-                },
                 "STARFUSION_BUILD": {
                     "STAR-Fusion": "1.7.0"
                 },
                 "STAR_FOR_ARRIBA": {
-                    "star": "2.7.11b",
-                    "samtools": 1.2,
-                    "gawk": "5.1.0"
-                },
-                "STAR_FOR_STARFUSION": {
-                    "star": "2.7.11b",
+                    "star": null,
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
                 "STAR_GENOMEGENERATE": {
-                    "star": "2.7.11b",
+                    "star": null,
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
-                "STRINGTIE_MERGE": {
-                    "stringtie": "2.2.1"
-                },
-                "STRINGTIE_STRINGTIE": {
-                    "stringtie": "2.2.3"
-                },
                 "Workflow": {
                     "nf-core/rnafusion": "v4.0.0dev"
                 }
             },
             [
-                "arriba",
-                "arriba/test.arriba.fusions.discarded.tsv",
-                "arriba/test.arriba.fusions.tsv",
                 "fastp",
                 "fastp/test.fastp.html",
                 "fastp/test.fastp.json",
@@ -401,32 +285,11 @@
                 "fusioncatcher/test.fusioncatcher.fusion-genes.txt",
                 "fusioncatcher/test.fusioncatcher.log",
                 "fusioncatcher/test.fusioncatcher.summary.txt",
-                "fusionreport",
-                "fusionreport/test",
-                "fusionreport/test/AAA_BBB.html",
-                "fusionreport/test/test.fusionreport.tsv",
-                "fusionreport/test/test.fusionreport_filtered.tsv",
-                "fusionreport/test/test.fusions.csv",
-                "fusionreport/test/test.fusions.json",
-                "fusionreport/test/test_fusionreport_index.html",
                 "gatk4",
                 "gatk4/Homo_sapiens.GRCh38.46_dna_primary_assembly.dict",
                 "get",
                 "get/rrna.bed",
                 "get/rrna.gtf",
-                "multiqc",
-                "multiqc/multiqc_data",
-                "multiqc/multiqc_plots",
-                "multiqc/multiqc_report.html",
-                "picard",
-                "picard/test.bai",
-                "picard/test.bam",
-                "picard/test.bam.metrics",
-                "picard/test.cram",
-                "picard/test.cram.crai",
-                "picard/test.rna_metrics",
-                "picard/test_collectinsertsize.pdf",
-                "picard/test_collectinsertsize.txt",
                 "pipeline_info",
                 "pipeline_info/nf_core_pipeline_software_mqc_versions.yml",
                 "references",
@@ -452,23 +315,6 @@
                 "references/hgnc",
                 "references/hgnc/HGNC-DB-timestamp.txt",
                 "references/hgnc/hgnc_complete_set.txt",
-                "references/salmon",
-                "references/salmon/salmon",
-                "references/salmon/salmon/complete_ref_lens.bin",
-                "references/salmon/salmon/ctable.bin",
-                "references/salmon/salmon/ctg_offsets.bin",
-                "references/salmon/salmon/duplicate_clusters.tsv",
-                "references/salmon/salmon/info.json",
-                "references/salmon/salmon/mphf.bin",
-                "references/salmon/salmon/pos.bin",
-                "references/salmon/salmon/pre_indexing.log",
-                "references/salmon/salmon/rank.bin",
-                "references/salmon/salmon/refAccumLengths.bin",
-                "references/salmon/salmon/ref_indexing.log",
-                "references/salmon/salmon/reflengths.bin",
-                "references/salmon/salmon/refseq.bin",
-                "references/salmon/salmon/seq.bin",
-                "references/salmon/salmon/versionInfo.json",
                 "references/star",
                 "references/star/Genome",
                 "references/star/Log.out",
@@ -489,10 +335,6 @@
                 "references/starfusion",
                 "references/starfusion/ctat_genome_lib_build_dir",
                 "references/starfusion/ref_annot.cdna.fa",
-                "salmon",
-                "salmon/test",
-                "salmon/test_lib_format_counts.json",
-                "salmon/test_meta_info.json",
                 "star_for_arriba",
                 "star_for_arriba/test.Aligned.sortedByCoord.out.bam",
                 "star_for_arriba/test.Aligned.unsort.out.bam",
@@ -524,29 +366,17 @@
                 "star_for_starfusion/test.Signal.UniqueMultiple.str1.out.wig",
                 "star_for_starfusion/test.out.sam",
                 "star_for_starfusion/test.sortedByCoord.out.bam",
-                "star_for_starfusion/test.sortedByCoord.out.bam.bai",
                 "star_for_starfusion/test.tab",
                 "star_for_starfusion/test.toTranscriptome.out.bam",
                 "star_for_starfusion/test.unmapped_1.fastq.gz",
                 "star_for_starfusion/test.unmapped_2.fastq.gz",
-                "star_for_starfusion/testXd.out.bam",
-                "starfusion",
-                "starfusion/test.starfusion.abridged.coding_effect.tsv",
-                "starfusion/test.starfusion.abridged.tsv",
-                "starfusion/test.starfusion.fusion_predictions.tsv",
-                "stringtie",
-                "stringtie/[:]",
-                "stringtie/[:]/stringtie.merged.gtf",
-                "stringtie/test.ballgown",
-                "stringtie/test.coverage.gtf",
-                "stringtie/test.gene.abundance.txt",
-                "stringtie/test.transcripts.gtf"
+                "star_for_starfusion/testXd.out.bam"
             ]
         ],
         "meta": {
             "nf-test": "0.9.0",
             "nextflow": "24.10.2"
         },
-        "timestamp": "2024-12-11T12:40:22.066494"
+        "timestamp": "2024-12-17T16:42:11.182735"
     }
-}
+}
\ No newline at end of file
diff --git a/workflows/rnafusion.nf b/workflows/rnafusion.nf
index d992bf58..91742e1b 100644
--- a/workflows/rnafusion.nf
+++ b/workflows/rnafusion.nf
@@ -90,7 +90,7 @@ workflow RNAFUSION {
         BUILD_REFERENCES.out.ch_arriba_ref_blacklist,
         BUILD_REFERENCES.out.ch_arriba_ref_cytobands,
         BUILD_REFERENCES.out.ch_arriba_ref_known_fusions,
-        BUILD_REFERENCES.out.ch_arriba_ref_protein_domains
+        BUILD_REFERENCES.out.ch_arriba_ref_protein_domains,
         params.arriba,                   // boolean
         params.all,                      // boolean
         params.fusioninspector_only,     // boolean
@@ -139,7 +139,7 @@ workflow RNAFUSION {
 
 
 
-    //Run fusionInpector
+    //Run fusionInspector
     FUSIONINSPECTOR_WORKFLOW (
         ch_reads,
         FUSIONREPORT_WORKFLOW.out.fusion_list,

From f8dd5169afb714f6f823ba64a3a58099ba695407 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Thu, 19 Dec 2024 15:27:34 +0100
Subject: [PATCH 35/41] update changelog

---
 CHANGELOG.md | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index a52f01f4..33c5b0cc 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -31,9 +31,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Remove double nested folder introduced in [#577](https://github.com/nf-core/rnafusion/pull/577), [#581](https://github.com/nf-core/rnafusion/pull/581)
 - Use docker.io and galaxy containers for fusioncatcher and starfusion (incl. fusioninspector) instead of wave as they are not functional on wave [#588](https://github.com/nf-core/rnafusion/pull/588)
 - Update STAR-Fusion to 1.14 [#588](https://github.com/nf-core/rnafusion/pull/588)
-
-  ext.args = "-genePredExt -geneNameAsName2 -ignoreGroupsWithoutExons" GTF_TO_REFFLAT
-
+- Use -genePredExt -geneNameAsName2 -ignoreGroupsWithoutExons for GTF_TO_REFFLAT[#505](https://github.com/nf-core/rnafusion/pull/505)
 
 ### Fixed
 

From d62c4b5d1f3e691497956dfe77574cc3f7c95dc7 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Thu, 19 Dec 2024 15:54:27 +0100
Subject: [PATCH 36/41] update changelog, retrofit trim_workflowo

---
 CHANGELOG.md                             | 17 +++++++++++++----
 subworkflows/local/trim_workflow/main.nf |  6 ++++--
 workflows/rnafusion.nf                   |  4 +++-
 3 files changed, 20 insertions(+), 7 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 33c5b0cc..51fef20e 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -21,6 +21,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Add nf-test to local subworkflow: `TRIM_WORKFLOW` [#572](https://github.com/nf-core/rnafusion/pull/572)
 - Add nf-test to local module: `FUSIONREPORT_DETECT`. Improve `FUSIONREPORT_DOWNLOAD` module [#577](https://github.com/nf-core/rnafusion/pull/577)
 - Add nf-test to local subworkflow: `ARRIBA_WORKFLOW` [#578](https://github.com/nf-core/rnafusion/pull/578)
+- Add parameter `--references_only` when no data should be analysed, but only the references should be built [#505](https://github.com/nf-core/rnafusion/pull/505)
 
 ### Changed
 
@@ -31,7 +32,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Remove double nested folder introduced in [#577](https://github.com/nf-core/rnafusion/pull/577), [#581](https://github.com/nf-core/rnafusion/pull/581)
 - Use docker.io and galaxy containers for fusioncatcher and starfusion (incl. fusioninspector) instead of wave as they are not functional on wave [#588](https://github.com/nf-core/rnafusion/pull/588)
 - Update STAR-Fusion to 1.14 [#588](https://github.com/nf-core/rnafusion/pull/588)
-- Use -genePredExt -geneNameAsName2 -ignoreGroupsWithoutExons for GTF_TO_REFFLAT[#505](https://github.com/nf-core/rnafusion/pull/505)
+- Use "-genePredExt -geneNameAsName2 -ignoreGroupsWithoutExons" (to mimic gms/tomte) for GTF_TO_REFFLAT [#505](https://github.com/nf-core/rnafusion/pull/505)
+- Integrate reference building in the main workflow [#505](https://github.com/nf-core/rnafusion/pull/505)
+- Move from ensembl to gencode base [#505](https://github.com/nf-core/rnafusion/pull/505)
+- Update from ensembl 102 to gencode 46 default references [#505](https://github.com/nf-core/rnafusion/pull/505)
 
 ### Fixed
 
@@ -46,12 +50,17 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Removed
 
 - Remove fusionGDB from documentation and fusion-report download stubs [#503](https://github.com/nf-core/rnafusion/pull/503)
+- Removed test-build as reference building gets integrated in the main workflow [#505](https://github.com/nf-core/rnafusion/pull/505)
+- Removed parameter `--build_references`
+
 
 ### Parameters
 
-| Old parameter | New parameter |
-| ------------- | ------------- |
-|               | `--no_cosmic` |
+| Old parameter       | New parameter |
+| ------------------- | ------------------- |
+|                     | `--no_cosmic`       |
+| `-build_references` | `--references_only` |
+
 
 ## v3.0.2 - [2024-04-10]
 
diff --git a/subworkflows/local/trim_workflow/main.nf b/subworkflows/local/trim_workflow/main.nf
index 512a07b5..d548c8ae 100644
--- a/subworkflows/local/trim_workflow/main.nf
+++ b/subworkflows/local/trim_workflow/main.nf
@@ -7,6 +7,8 @@ workflow TRIM_WORKFLOW {
 
     take:
         reads           // channel [ meta, [ fastq files ] ]
+        adapter_fasta   // channel [ path ]
+        fastp_trim      // boolean
 
     main:
         ch_versions       = Channel.empty()
@@ -14,8 +16,8 @@ workflow TRIM_WORKFLOW {
         ch_fastp_json     = Channel.empty()
         ch_fastqc_trimmed = Channel.empty()
 
-        if ( {params.fastp_trim} ) {
-            FASTP(reads, {params.adapter_fasta}, false, false, false)
+        if ( fastp_trim ) {
+            FASTP(reads, adapter_fasta.ifEmpty( [] ), false, false, false)
             ch_versions = ch_versions.mix(FASTP.out.versions)
 
             FASTQC_FOR_FASTP(FASTP.out.reads)
diff --git a/workflows/rnafusion.nf b/workflows/rnafusion.nf
index 91742e1b..a755311c 100644
--- a/workflows/rnafusion.nf
+++ b/workflows/rnafusion.nf
@@ -64,7 +64,9 @@ workflow RNAFUSION {
     // Trimming
     //
     TRIM_WORKFLOW (
-        ch_samplesheet
+        ch_samplesheet,
+        params.adapter_fasta,
+        params.fastp_trim
     )
     ch_reads = TRIM_WORKFLOW.out.ch_reads_all
     ch_versions = ch_versions.mix(TRIM_WORKFLOW.out.versions)

From de5d6d5aea8306d2853fef7c788f7c20f7a50ee8 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Fri, 20 Dec 2024 09:57:45 +0100
Subject: [PATCH 37/41] add species as parameter

---
 CHANGELOG.md                           |   4 +-
 nextflow.config                        |   1 +
 subworkflows/local/build_references.nf |   6 +-
 tests/test_stub.nf.test.snap           | 368 +------------------------
 4 files changed, 13 insertions(+), 366 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 51fef20e..1838af9e 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -53,15 +53,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Removed test-build as reference building gets integrated in the main workflow [#505](https://github.com/nf-core/rnafusion/pull/505)
 - Removed parameter `--build_references`
 
-
 ### Parameters
 
-| Old parameter       | New parameter |
+| Old parameter       | New parameter       |
 | ------------------- | ------------------- |
 |                     | `--no_cosmic`       |
 | `-build_references` | `--references_only` |
 
-
 ## v3.0.2 - [2024-04-10]
 
 ### Added
diff --git a/nextflow.config b/nextflow.config
index a1e746dd..a61462e3 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -31,6 +31,7 @@ params {
     starfusion_build           = true
     genomes                    = [:]
     fusion_annot_lib           = "https://github.com/FusionAnnotator/CTAT_HumanFusionLib/releases/download/v0.3.0/fusion_lib.Mar2021.dat.gz" // path to  dat.gz CTAT genome lib // TODO: Update to latest with s3 link when available
+    species                    = "human"
 
     // Filtering
     tools_cutoff               = 1
diff --git a/subworkflows/local/build_references.nf b/subworkflows/local/build_references.nf
index 8e9cc4b1..56fd8eb2 100644
--- a/subworkflows/local/build_references.nf
+++ b/subworkflows/local/build_references.nf
@@ -88,9 +88,9 @@ workflow BUILD_REFERENCES {
 
     if (!file(params.salmon_index).exists() || file(params.salmon_index).isEmpty() ||
         !file(params.salmon_index_stub_check).exists() || file(params.salmon_index_stub_check).isEmpty()){ // add condition for qc
-        GFFREAD(ch_gtf, ch_fasta.map{ meta, fasta -> [ fasta ] })
+        GFFREAD(ch_gtf, ch_fasta.map{ it -> it[1] })
         ch_versions = ch_versions.mix(GFFREAD.out.versions)
-        SALMON_INDEX(ch_fasta.map{ meta, fasta -> [ fasta ] }, GFFREAD.out.gffread_fasta.map{ meta, gffread_fasta -> [ gffread_fasta ] })
+        SALMON_INDEX(ch_fasta.map{ it -> it[1] }, GFFREAD.out.gffread_fasta.map{ it -> it[1] })
         ch_versions = ch_versions.mix(SALMON_INDEX.out.versions)
         ch_salmon_index = SALMON_INDEX.out.index
     } else {
@@ -140,7 +140,7 @@ workflow BUILD_REFERENCES {
     if ((params.starfusion || params.all) &&
             (!file(params.starfusion_ref).exists() || file(params.starfusion_ref).isEmpty() ||
             !file(params.starfusion_ref_stub_check).exists() || file(params.starfusion_ref_stub_check).isEmpty() )) {
-            STARFUSION_BUILD(ch_fasta, ch_gtf)
+            STARFUSION_BUILD(ch_fasta, ch_gtf, params.fusion_annot_lib, params.species)
             ch_versions = ch_versions.mix(STARFUSION_BUILD.out.versions)
             ch_starfusion_ref = STARFUSION_BUILD.out.reference
     }
diff --git a/tests/test_stub.nf.test.snap b/tests/test_stub.nf.test.snap
index e3a8bb73..f661aac6 100644
--- a/tests/test_stub.nf.test.snap
+++ b/tests/test_stub.nf.test.snap
@@ -1,382 +1,30 @@
 {
     "stub test no fastp trim": {
         "content": [
-            20,
-            {
-                "ARRIBA_DOWNLOAD": {
-                    "arriba_download": "2.4.0"
-                },
-                "FASTP": {
-                    "fastp": "0.23.4"
-                },
-                "FASTQC": {
-                    "fastqc": "0.12.1"
-                },
-                "FASTQC_FOR_FASTP": {
-                    "fastqc": "0.12.1"
-                },
-                "FUSIONCATCHER": {
-                    "fusioncatcher": 1.35
-                },
-                "FUSIONCATCHER_BUILD": {
-                    "fusioncatcher": "fusioncatcher.py 1.35"
-                },
-                "FUSIONREPORT_DOWNLOAD": {
-                    "fusion_report": "2.1.5"
-                },
-                "GATK4_BEDTOINTERVALLIST": {
-                    "gatk4": "4.6.1.0"
-                },
-                "GATK4_CREATESEQUENCEDICTIONARY": {
-                    "gatk4": "4.6.1.0"
-                },
-                "GENCODE_DOWNLOAD": {
-                    "wget": null
-                },
-                "GET_RRNA_TRANSCRIPTS": {
-                    "get_rrna_transcripts": "v1.0"
-                },
-                "GFFREAD": {
-                    "gffread": "0.12.7"
-                },
-                "GTF_TO_REFFLAT": {
-                    "gtfToGenePred": 377
-                },
-                "HGNC_DOWNLOAD": {
-                    "wget": null
-                },
-                "SAMTOOLS_FAIDX": {
-                    "samtools": 1.21
-                },
-                "STARFUSION_BUILD": {
-                    "STAR-Fusion": "1.7.0"
-                },
-                "STAR_FOR_ARRIBA": {
-                    "star": null,
-                    "samtools": 1.2,
-                    "gawk": "5.1.0"
-                },
-                "STAR_FOR_STARFUSION": {
-                    "star": null,
-                    "samtools": 1.2,
-                    "gawk": "5.1.0"
-                },
-                "STAR_GENOMEGENERATE": {
-                    "star": null,
-                    "samtools": 1.2,
-                    "gawk": "5.1.0"
-                },
-                "Workflow": {
-                    "nf-core/rnafusion": "v4.0.0dev"
-                }
-            },
+            0,
+            null,
             [
-                "fastp",
-                "fastp/test.fastp.html",
-                "fastp/test.fastp.json",
-                "fastp/test.fastp.log",
-                "fastp/test_1.fastp.fastq.gz",
-                "fastp/test_2.fastp.fastq.gz",
-                "fastqc",
-                "fastqc/test.html",
-                "fastqc/test.zip",
-                "fastqc_for_fastp",
-                "fastqc_for_fastp/test_trimmed.html",
-                "fastqc_for_fastp/test_trimmed.zip",
-                "fusioncatcher",
-                "fusioncatcher/human_v46",
-                "fusioncatcher/human_v46/ensembl_fully_overlapping_genes.txt",
-                "fusioncatcher/test.fusioncatcher.fusion-genes.txt",
-                "fusioncatcher/test.fusioncatcher.log",
-                "fusioncatcher/test.fusioncatcher.summary.txt",
-                "gatk4",
-                "gatk4/Homo_sapiens.GRCh38.46_dna_primary_assembly.dict",
-                "get",
-                "get/rrna.bed",
-                "get/rrna.gtf",
-                "pipeline_info",
-                "pipeline_info/nf_core_pipeline_software_mqc_versions.yml",
-                "references",
-                "references/arriba",
-                "references/arriba/blacklist_hg38_GRCh38_v2.4.0.tsv.gz",
-                "references/arriba/cytobands_hg38_GRCh38_v2.4.0.tsv",
-                "references/arriba/known_fusions_hg38_GRCh38_v2.4.0.tsv.gz",
-                "references/arriba/protein_domains_hg38_GRCh38_v2.4.0.gff3",
-                "references/fusion_report_db",
-                "references/fusion_report_db/DB-timestamp.txt",
-                "references/fusion_report_db/cosmic.db",
-                "references/fusion_report_db/fusion_report.log",
-                "references/fusion_report_db/fusiongdb2.db",
-                "references/fusion_report_db/mitelman.db",
-                "references/gencode",
-                "references/gencode/Homo_sapiens.GRCh38.46.gtf",
-                "references/gencode/Homo_sapiens.GRCh38.46.gtf.interval_list",
-                "references/gencode/Homo_sapiens.GRCh38.46.gtf.refflat",
-                "references/gencode/Homo_sapiens.GRCh38.46_dna_primary_assembly.fa",
-                "references/gencode/Homo_sapiens.GRCh38.46_dna_primary_assembly.fa.fai",
-                "references/gffread",
-                "references/gffread/Homo_sapiens.GRCh38.46.gtf.fasta",
-                "references/hgnc",
-                "references/hgnc/HGNC-DB-timestamp.txt",
-                "references/hgnc/hgnc_complete_set.txt",
-                "references/salmon",
-                "references/salmon/salmon",
-                "references/salmon/salmon/complete_ref_lens.bin",
-                "references/salmon/salmon/ctable.bin",
-                "references/salmon/salmon/ctg_offsets.bin",
-                "references/salmon/salmon/duplicate_clusters.tsv",
-                "references/salmon/salmon/info.json",
-                "references/salmon/salmon/mphf.bin",
-                "references/salmon/salmon/pos.bin",
-                "references/salmon/salmon/pre_indexing.log",
-                "references/salmon/salmon/rank.bin",
-                "references/salmon/salmon/refAccumLengths.bin",
-                "references/salmon/salmon/ref_indexing.log",
-                "references/salmon/salmon/reflengths.bin",
-                "references/salmon/salmon/refseq.bin",
-                "references/salmon/salmon/seq.bin",
-                "references/salmon/salmon/versionInfo.json",
-                "references/star",
-                "references/star/Genome",
-                "references/star/Log.out",
-                "references/star/SA",
-                "references/star/SAindex",
-                "references/star/chrLength.txt",
-                "references/star/chrName.txt",
-                "references/star/chrNameLength.txt",
-                "references/star/chrStart.txt",
-                "references/star/exonGeTrInfo.tab",
-                "references/star/exonInfo.tab",
-                "references/star/geneInfo.tab",
-                "references/star/genomeParameters.txt",
-                "references/star/sjdbInfo.txt",
-                "references/star/sjdbList.fromGTF.out.tab",
-                "references/star/sjdbList.out.tab",
-                "references/star/transcriptInfo.tab",
-                "references/starfusion",
-                "references/starfusion/ctat_genome_lib_build_dir",
-                "references/starfusion/ref_annot.cdna.fa",
-                "star_for_arriba",
-                "star_for_arriba/test.Aligned.sortedByCoord.out.bam",
-                "star_for_arriba/test.Aligned.unsort.out.bam",
-                "star_for_arriba/test.Chimeric.out.junction",
-                "star_for_arriba/test.Log.final.out",
-                "star_for_arriba/test.Log.out",
-                "star_for_arriba/test.Log.progress.out",
-                "star_for_arriba/test.ReadsPerGene.out.tab",
-                "star_for_arriba/test.SJ.out.tab",
-                "star_for_arriba/test.Signal.UniqueMultiple.str1.out.bg",
-                "star_for_arriba/test.Signal.UniqueMultiple.str1.out.wig",
-                "star_for_arriba/test.out.sam",
-                "star_for_arriba/test.sortedByCoord.out.bam",
-                "star_for_arriba/test.tab",
-                "star_for_arriba/test.toTranscriptome.out.bam",
-                "star_for_arriba/test.unmapped_1.fastq.gz",
-                "star_for_arriba/test.unmapped_2.fastq.gz",
-                "star_for_arriba/testXd.out.bam",
-                "star_for_starfusion",
-                "star_for_starfusion/test.Aligned.sortedByCoord.out.bam",
-                "star_for_starfusion/test.Aligned.unsort.out.bam",
-                "star_for_starfusion/test.Chimeric.out.junction",
-                "star_for_starfusion/test.Log.final.out",
-                "star_for_starfusion/test.Log.out",
-                "star_for_starfusion/test.Log.progress.out",
-                "star_for_starfusion/test.ReadsPerGene.out.tab",
-                "star_for_starfusion/test.SJ.out.tab",
-                "star_for_starfusion/test.Signal.UniqueMultiple.str1.out.bg",
-                "star_for_starfusion/test.Signal.UniqueMultiple.str1.out.wig",
-                "star_for_starfusion/test.out.sam",
-                "star_for_starfusion/test.sortedByCoord.out.bam",
-                "star_for_starfusion/test.tab",
-                "star_for_starfusion/test.toTranscriptome.out.bam",
-                "star_for_starfusion/test.unmapped_1.fastq.gz",
-                "star_for_starfusion/test.unmapped_2.fastq.gz",
-                "star_for_starfusion/testXd.out.bam"
+                "pipeline_info"
             ]
         ],
         "meta": {
             "nf-test": "0.9.0",
             "nextflow": "24.10.2"
         },
-        "timestamp": "2024-12-17T16:44:02.121512"
+        "timestamp": "2024-12-20T09:49:41.743056"
     },
     "stub test with fastp trim": {
         "content": [
-            19,
-            {
-                "ARRIBA_DOWNLOAD": {
-                    "arriba_download": "2.4.0"
-                },
-                "FASTP": {
-                    "fastp": "0.23.4"
-                },
-                "FASTQC": {
-                    "fastqc": "0.12.1"
-                },
-                "FASTQC_FOR_FASTP": {
-                    "fastqc": "0.12.1"
-                },
-                "FUSIONCATCHER": {
-                    "fusioncatcher": 1.35
-                },
-                "FUSIONCATCHER_BUILD": {
-                    "fusioncatcher": "fusioncatcher.py 1.35"
-                },
-                "FUSIONREPORT_DOWNLOAD": {
-                    "fusion_report": "2.1.5"
-                },
-                "GATK4_BEDTOINTERVALLIST": {
-                    "gatk4": "4.6.1.0"
-                },
-                "GATK4_CREATESEQUENCEDICTIONARY": {
-                    "gatk4": "4.6.1.0"
-                },
-                "GENCODE_DOWNLOAD": {
-                    "wget": null
-                },
-                "GET_RRNA_TRANSCRIPTS": {
-                    "get_rrna_transcripts": "v1.0"
-                },
-                "GFFREAD": {
-                    "gffread": "0.12.7"
-                },
-                "GTF_TO_REFFLAT": {
-                    "gtfToGenePred": 377
-                },
-                "HGNC_DOWNLOAD": {
-                    "wget": null
-                },
-                "SAMTOOLS_FAIDX": {
-                    "samtools": 1.21
-                },
-                "STARFUSION_BUILD": {
-                    "STAR-Fusion": "1.7.0"
-                },
-                "STAR_FOR_ARRIBA": {
-                    "star": null,
-                    "samtools": 1.2,
-                    "gawk": "5.1.0"
-                },
-                "STAR_GENOMEGENERATE": {
-                    "star": null,
-                    "samtools": 1.2,
-                    "gawk": "5.1.0"
-                },
-                "Workflow": {
-                    "nf-core/rnafusion": "v4.0.0dev"
-                }
-            },
+            0,
+            null,
             [
-                "fastp",
-                "fastp/test.fastp.html",
-                "fastp/test.fastp.json",
-                "fastp/test.fastp.log",
-                "fastp/test_1.fastp.fastq.gz",
-                "fastp/test_2.fastp.fastq.gz",
-                "fastqc",
-                "fastqc/test.html",
-                "fastqc/test.zip",
-                "fastqc_for_fastp",
-                "fastqc_for_fastp/test_trimmed.html",
-                "fastqc_for_fastp/test_trimmed.zip",
-                "fusioncatcher",
-                "fusioncatcher/human_v46",
-                "fusioncatcher/human_v46/ensembl_fully_overlapping_genes.txt",
-                "fusioncatcher/test.fusioncatcher.fusion-genes.txt",
-                "fusioncatcher/test.fusioncatcher.log",
-                "fusioncatcher/test.fusioncatcher.summary.txt",
-                "gatk4",
-                "gatk4/Homo_sapiens.GRCh38.46_dna_primary_assembly.dict",
-                "get",
-                "get/rrna.bed",
-                "get/rrna.gtf",
-                "pipeline_info",
-                "pipeline_info/nf_core_pipeline_software_mqc_versions.yml",
-                "references",
-                "references/arriba",
-                "references/arriba/blacklist_hg38_GRCh38_v2.4.0.tsv.gz",
-                "references/arriba/cytobands_hg38_GRCh38_v2.4.0.tsv",
-                "references/arriba/known_fusions_hg38_GRCh38_v2.4.0.tsv.gz",
-                "references/arriba/protein_domains_hg38_GRCh38_v2.4.0.gff3",
-                "references/fusion_report_db",
-                "references/fusion_report_db/DB-timestamp.txt",
-                "references/fusion_report_db/cosmic.db",
-                "references/fusion_report_db/fusion_report.log",
-                "references/fusion_report_db/fusiongdb2.db",
-                "references/fusion_report_db/mitelman.db",
-                "references/gencode",
-                "references/gencode/Homo_sapiens.GRCh38.46.gtf",
-                "references/gencode/Homo_sapiens.GRCh38.46.gtf.interval_list",
-                "references/gencode/Homo_sapiens.GRCh38.46.gtf.refflat",
-                "references/gencode/Homo_sapiens.GRCh38.46_dna_primary_assembly.fa",
-                "references/gencode/Homo_sapiens.GRCh38.46_dna_primary_assembly.fa.fai",
-                "references/gffread",
-                "references/gffread/Homo_sapiens.GRCh38.46.gtf.fasta",
-                "references/hgnc",
-                "references/hgnc/HGNC-DB-timestamp.txt",
-                "references/hgnc/hgnc_complete_set.txt",
-                "references/star",
-                "references/star/Genome",
-                "references/star/Log.out",
-                "references/star/SA",
-                "references/star/SAindex",
-                "references/star/chrLength.txt",
-                "references/star/chrName.txt",
-                "references/star/chrNameLength.txt",
-                "references/star/chrStart.txt",
-                "references/star/exonGeTrInfo.tab",
-                "references/star/exonInfo.tab",
-                "references/star/geneInfo.tab",
-                "references/star/genomeParameters.txt",
-                "references/star/sjdbInfo.txt",
-                "references/star/sjdbList.fromGTF.out.tab",
-                "references/star/sjdbList.out.tab",
-                "references/star/transcriptInfo.tab",
-                "references/starfusion",
-                "references/starfusion/ctat_genome_lib_build_dir",
-                "references/starfusion/ref_annot.cdna.fa",
-                "star_for_arriba",
-                "star_for_arriba/test.Aligned.sortedByCoord.out.bam",
-                "star_for_arriba/test.Aligned.unsort.out.bam",
-                "star_for_arriba/test.Chimeric.out.junction",
-                "star_for_arriba/test.Log.final.out",
-                "star_for_arriba/test.Log.out",
-                "star_for_arriba/test.Log.progress.out",
-                "star_for_arriba/test.ReadsPerGene.out.tab",
-                "star_for_arriba/test.SJ.out.tab",
-                "star_for_arriba/test.Signal.UniqueMultiple.str1.out.bg",
-                "star_for_arriba/test.Signal.UniqueMultiple.str1.out.wig",
-                "star_for_arriba/test.out.sam",
-                "star_for_arriba/test.sortedByCoord.out.bam",
-                "star_for_arriba/test.tab",
-                "star_for_arriba/test.toTranscriptome.out.bam",
-                "star_for_arriba/test.unmapped_1.fastq.gz",
-                "star_for_arriba/test.unmapped_2.fastq.gz",
-                "star_for_arriba/testXd.out.bam",
-                "star_for_starfusion",
-                "star_for_starfusion/test.Aligned.sortedByCoord.out.bam",
-                "star_for_starfusion/test.Aligned.unsort.out.bam",
-                "star_for_starfusion/test.Chimeric.out.junction",
-                "star_for_starfusion/test.Log.final.out",
-                "star_for_starfusion/test.Log.out",
-                "star_for_starfusion/test.Log.progress.out",
-                "star_for_starfusion/test.ReadsPerGene.out.tab",
-                "star_for_starfusion/test.SJ.out.tab",
-                "star_for_starfusion/test.Signal.UniqueMultiple.str1.out.bg",
-                "star_for_starfusion/test.Signal.UniqueMultiple.str1.out.wig",
-                "star_for_starfusion/test.out.sam",
-                "star_for_starfusion/test.sortedByCoord.out.bam",
-                "star_for_starfusion/test.tab",
-                "star_for_starfusion/test.toTranscriptome.out.bam",
-                "star_for_starfusion/test.unmapped_1.fastq.gz",
-                "star_for_starfusion/test.unmapped_2.fastq.gz",
-                "star_for_starfusion/testXd.out.bam"
+                "pipeline_info"
             ]
         ],
         "meta": {
             "nf-test": "0.9.0",
             "nextflow": "24.10.2"
         },
-        "timestamp": "2024-12-17T16:42:11.182735"
+        "timestamp": "2024-12-20T09:49:14.743338"
     }
 }
\ No newline at end of file

From bdae2931727b81c1b5a13d3c1deb894a84f1e07d Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Fri, 20 Dec 2024 11:55:16 +0100
Subject: [PATCH 38/41] fix some issues with channels

---
 subworkflows/local/arriba_workflow/main.nf |   8 +-
 subworkflows/local/build_references.nf     |  12 +-
 tests/test_stub.nf.test.snap               | 246 ++++++++++++++++++++-
 workflows/rnafusion.nf                     |   2 +-
 4 files changed, 253 insertions(+), 15 deletions(-)

diff --git a/subworkflows/local/arriba_workflow/main.nf b/subworkflows/local/arriba_workflow/main.nf
index 77e97f42..bb4c36a6 100644
--- a/subworkflows/local/arriba_workflow/main.nf
+++ b/subworkflows/local/arriba_workflow/main.nf
@@ -25,7 +25,7 @@ workflow ARRIBA_WORKFLOW {
     main:
         ch_versions   = Channel.empty()
         ch_cram_index = Channel.empty()
-        ch_dummy_file = file("$baseDir/assets/dummy_file_arriba.txt", checkIfExists: true)
+        ch_dummy_file = file("$projectDir/assets/dummy_file_arriba.txt", checkIfExists: true)
 
         if (( arriba || all ) && !fusioninspector_only) {
 
@@ -43,7 +43,7 @@ workflow ARRIBA_WORKFLOW {
             if ( arriba_fusions ) {
 
                 ch_arriba_fusions = reads.combine( Channel.value( file( arriba_fusions, checkIfExists: true ) ) )
-                    .map { meta, reads, fusions -> [ meta, fusions ] }
+                    .map { it -> [ it[0], it[2] ] }
                 ch_arriba_fusion_fail = ch_dummy_file
 
             } else {
@@ -61,7 +61,7 @@ workflow ARRIBA_WORKFLOW {
                 ch_versions = ch_versions.mix(ARRIBA_ARRIBA.out.versions)
 
                 ch_arriba_fusions     = ARRIBA_ARRIBA.out.fusions
-                ch_arriba_fusion_fail = ARRIBA_ARRIBA.out.fusions_fail.map{ meta, file -> return file }
+                ch_arriba_fusion_fail = ARRIBA_ARRIBA.out.fusions_fail.map{ it -> return it[1] }
             }
 
             if ( cram.contains('arriba') ) {
@@ -83,7 +83,7 @@ workflow ARRIBA_WORKFLOW {
 
             ch_arriba_fusions = reads
                 .combine(Channel.value( file(ch_dummy_file, checkIfExists: true ) ) )
-                .map { meta, reads, fusions -> [ meta, fusions ] }
+                .map { it -> [ it[0], it[2] ] }
 
             ch_arriba_fusion_fail = ch_dummy_file
         }
diff --git a/subworkflows/local/build_references.nf b/subworkflows/local/build_references.nf
index 56fd8eb2..34102d2d 100644
--- a/subworkflows/local/build_references.nf
+++ b/subworkflows/local/build_references.nf
@@ -118,10 +118,14 @@ workflow BUILD_REFERENCES {
         ch_arriba_ref_known_fusions = ARRIBA_DOWNLOAD.out.known_fusions
         ch_arriba_ref_protein_domains = ARRIBA_DOWNLOAD.out.protein_domains
     } else {
-        ch_arriba_ref_blacklist = Channel.fromPath(params.arriba_ref_blacklist)
-        ch_arriba_ref_cytobands = Channel.fromPath(params.arriba_ref_cytobands)
-        ch_arriba_ref_known_fusions = Channel.fromPath(params.arriba_ref_known_fusions)
-        ch_arriba_ref_protein_domains = Channel.fromPath(params.arriba_ref_protein_domains)
+        ch_arriba_ref_blacklist = Channel.fromPath(params.arriba_ref_blacklist).map { file ->
+        [ id: file.baseName, path: file ]}
+        ch_arriba_ref_cytobands = Channel.fromPath(params.arriba_ref_cytobands).map { file ->
+        [ id: file.baseName, path: file ]}
+        ch_arriba_ref_known_fusions = Channel.fromPath(params.arriba_ref_known_fusions).map { file ->
+        [ id: file.baseName, path: file ]}
+        ch_arriba_ref_protein_domains = Channel.fromPath(params.arriba_ref_protein_domains).map { file ->
+        [ id: file.baseName, path: file ]}
     }
 
 
diff --git a/tests/test_stub.nf.test.snap b/tests/test_stub.nf.test.snap
index f661aac6..a60d6d13 100644
--- a/tests/test_stub.nf.test.snap
+++ b/tests/test_stub.nf.test.snap
@@ -4,27 +4,261 @@
             0,
             null,
             [
-                "pipeline_info"
+                
             ]
         ],
         "meta": {
             "nf-test": "0.9.0",
             "nextflow": "24.10.2"
         },
-        "timestamp": "2024-12-20T09:49:41.743056"
+        "timestamp": "2024-12-20T11:51:44.033131"
     },
     "stub test with fastp trim": {
         "content": [
-            0,
-            null,
+            18,
+            {
+                "ARRIBA_DOWNLOAD": {
+                    "arriba_download": "2.4.0"
+                },
+                "FASTP": {
+                    "fastp": "0.23.4"
+                },
+                "FASTQC": {
+                    "fastqc": "0.12.1"
+                },
+                "FASTQC_FOR_FASTP": {
+                    "fastqc": "0.12.1"
+                },
+                "FUSIONCATCHER": {
+                    "fusioncatcher": 1.35
+                },
+                "FUSIONCATCHER_BUILD": {
+                    "fusioncatcher": "fusioncatcher.py 1.35"
+                },
+                "FUSIONREPORT_DOWNLOAD": {
+                    "fusion_report": "2.1.5"
+                },
+                "GATK4_CREATESEQUENCEDICTIONARY": {
+                    "gatk4": "4.6.1.0"
+                },
+                "GENCODE_DOWNLOAD": {
+                    "wget": null
+                },
+                "GET_RRNA_TRANSCRIPTS": {
+                    "get_rrna_transcripts": "v1.0"
+                },
+                "GFFREAD": {
+                    "gffread": "0.12.7"
+                },
+                "GTF_TO_REFFLAT": {
+                    "gtfToGenePred": 377
+                },
+                "HGNC_DOWNLOAD": {
+                    "wget": null
+                },
+                "SAMTOOLS_FAIDX": {
+                    "samtools": 1.21
+                },
+                "STARFUSION_BUILD": {
+                    "STAR-Fusion": "1.14.0"
+                },
+                "STAR_FOR_ARRIBA": {
+                    "star": null,
+                    "samtools": 1.2,
+                    "gawk": "5.1.0"
+                },
+                "STAR_GENOMEGENERATE": {
+                    "star": null,
+                    "samtools": 1.2,
+                    "gawk": "5.1.0"
+                },
+                "Workflow": {
+                    "nf-core/rnafusion": "v4.0.0dev"
+                }
+            },
             [
-                "pipeline_info"
+                "fastp",
+                "fastp/test.fastp.html",
+                "fastp/test.fastp.json",
+                "fastp/test.fastp.log",
+                "fastp/test_1.fastp.fastq.gz",
+                "fastp/test_2.fastp.fastq.gz",
+                "fastqc",
+                "fastqc/test.html",
+                "fastqc/test.zip",
+                "fastqc_for_fastp",
+                "fastqc_for_fastp/test_trimmed.html",
+                "fastqc_for_fastp/test_trimmed.zip",
+                "fusioncatcher",
+                "fusioncatcher/human_v46",
+                "fusioncatcher/human_v46/ensembl_fully_overlapping_genes.txt",
+                "fusioncatcher/test.fusioncatcher.fusion-genes.txt",
+                "fusioncatcher/test.fusioncatcher.log",
+                "fusioncatcher/test.fusioncatcher.summary.txt",
+                "gatk4",
+                "gatk4/Homo_sapiens.GRCh38.46_dna_primary_assembly.dict",
+                "get",
+                "get/rrna.bed",
+                "get/rrna.gtf",
+                "pipeline_info",
+                "pipeline_info/nf_core_pipeline_software_mqc_versions.yml",
+                "references",
+                "references/arriba",
+                "references/arriba/blacklist_hg38_GRCh38_v2.4.0.tsv.gz",
+                "references/arriba/cytobands_hg38_GRCh38_v2.4.0.tsv",
+                "references/arriba/known_fusions_hg38_GRCh38_v2.4.0.tsv.gz",
+                "references/arriba/protein_domains_hg38_GRCh38_v2.4.0.gff3",
+                "references/fusion_report_db",
+                "references/fusion_report_db/DB-timestamp.txt",
+                "references/fusion_report_db/cosmic.db",
+                "references/fusion_report_db/fusion_report.log",
+                "references/fusion_report_db/fusiongdb2.db",
+                "references/fusion_report_db/mitelman.db",
+                "references/gencode",
+                "references/gencode/Homo_sapiens.GRCh38.46.gtf",
+                "references/gencode/Homo_sapiens.GRCh38.46.gtf.refflat",
+                "references/gencode/Homo_sapiens.GRCh38.46_dna_primary_assembly.fa",
+                "references/gencode/Homo_sapiens.GRCh38.46_dna_primary_assembly.fa.fai",
+                "references/gffread",
+                "references/gffread/Homo_sapiens.GRCh38.46.gtf.fasta",
+                "references/hgnc",
+                "references/hgnc/HGNC-DB-timestamp.txt",
+                "references/hgnc/hgnc_complete_set.txt",
+                "references/star",
+                "references/star/Genome",
+                "references/star/Log.out",
+                "references/star/SA",
+                "references/star/SAindex",
+                "references/star/chrLength.txt",
+                "references/star/chrName.txt",
+                "references/star/chrNameLength.txt",
+                "references/star/chrStart.txt",
+                "references/star/exonGeTrInfo.tab",
+                "references/star/exonInfo.tab",
+                "references/star/geneInfo.tab",
+                "references/star/genomeParameters.txt",
+                "references/star/sjdbInfo.txt",
+                "references/star/sjdbList.fromGTF.out.tab",
+                "references/star/sjdbList.out.tab",
+                "references/star/transcriptInfo.tab",
+                "star_for_arriba",
+                "star_for_arriba/test.Aligned.sortedByCoord.out.bam",
+                "star_for_arriba/test.Aligned.unsort.out.bam",
+                "star_for_arriba/test.Chimeric.out.junction",
+                "star_for_arriba/test.Log.final.out",
+                "star_for_arriba/test.Log.out",
+                "star_for_arriba/test.Log.progress.out",
+                "star_for_arriba/test.ReadsPerGene.out.tab",
+                "star_for_arriba/test.SJ.out.tab",
+                "star_for_arriba/test.Signal.UniqueMultiple.str1.out.bg",
+                "star_for_arriba/test.Signal.UniqueMultiple.str1.out.wig",
+                "star_for_arriba/test.out.sam",
+                "star_for_arriba/test.sortedByCoord.out.bam",
+                "star_for_arriba/test.tab",
+                "star_for_arriba/test.toTranscriptome.out.bam",
+                "star_for_arriba/test.unmapped_1.fastq.gz",
+                "star_for_arriba/test.unmapped_2.fastq.gz",
+                "star_for_arriba/testXd.out.bam",
+                "star_for_starfusion",
+                "star_for_starfusion/test.Aligned.sortedByCoord.out.bam",
+                "star_for_starfusion/test.Aligned.unsort.out.bam",
+                "star_for_starfusion/test.Chimeric.out.junction",
+                "star_for_starfusion/test.Log.final.out",
+                "star_for_starfusion/test.Log.out",
+                "star_for_starfusion/test.Log.progress.out",
+                "star_for_starfusion/test.ReadsPerGene.out.tab",
+                "star_for_starfusion/test.SJ.out.tab",
+                "star_for_starfusion/test.Signal.UniqueMultiple.str1.out.bg",
+                "star_for_starfusion/test.Signal.UniqueMultiple.str1.out.wig",
+                "star_for_starfusion/test.out.sam",
+                "star_for_starfusion/test.sortedByCoord.out.bam",
+                "star_for_starfusion/test.tab",
+                "star_for_starfusion/test.toTranscriptome.out.bam",
+                "star_for_starfusion/test.unmapped_1.fastq.gz",
+                "star_for_starfusion/test.unmapped_2.fastq.gz",
+                "star_for_starfusion/testXd.out.bam",
+                "starfusion",
+                "starfusion/ctat_genome_lib_build_dir",
+                "starfusion/ctat_genome_lib_build_dir/AnnotFilterRule.pm",
+                "starfusion/ctat_genome_lib_build_dir/PFAM.domtblout.dat.gz",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/_fusion_annot_lib.idx.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/_prot_info_db.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/annotfiltrule_cp.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/blast_pairs.idx.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/cp_gene_blast_pairs.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/cp_pfam_dat.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/cp_ref_annot_cdna.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/fusion_annot_lib.cp.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/index_pfam_hits.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/index_ref_annot_cdna.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/makeblastdb.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/mm2.splice_bed.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/mm2_genome_idx.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/ref_annot.cdsplus.dfam_masked.fa.cp.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/ref_annot.cdsplus.dfam_masked.fa.idx.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/ref_annot.gtf.gene_spans.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/ref_annot.gtf.mini.sortu.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/ref_annot.gtf.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/ref_genome.fa.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/ref_genome_fai.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/trans.blast.dat.cp.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/trans.blast.dat.index.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/validate_ctat_genome_lib.ok",
+                "starfusion/ctat_genome_lib_build_dir/blast_pairs.dat.gz",
+                "starfusion/ctat_genome_lib_build_dir/blast_pairs.idx",
+                "starfusion/ctat_genome_lib_build_dir/fusion_annot_lib.gz",
+                "starfusion/ctat_genome_lib_build_dir/fusion_annot_lib.idx",
+                "starfusion/ctat_genome_lib_build_dir/pfam_domains.dbm",
+                "starfusion/ctat_genome_lib_build_dir/ref_annot.cdna.fa",
+                "starfusion/ctat_genome_lib_build_dir/ref_annot.cdna.fa.idx",
+                "starfusion/ctat_genome_lib_build_dir/ref_annot.cds",
+                "starfusion/ctat_genome_lib_build_dir/ref_annot.cdsplus.fa",
+                "starfusion/ctat_genome_lib_build_dir/ref_annot.cdsplus.fa.idx",
+                "starfusion/ctat_genome_lib_build_dir/ref_annot.gtf",
+                "starfusion/ctat_genome_lib_build_dir/ref_annot.gtf.gene_spans",
+                "starfusion/ctat_genome_lib_build_dir/ref_annot.gtf.mini.sortu",
+                "starfusion/ctat_genome_lib_build_dir/ref_annot.gtf.mm2.splice.bed",
+                "starfusion/ctat_genome_lib_build_dir/ref_annot.pep",
+                "starfusion/ctat_genome_lib_build_dir/ref_annot.prot_info.dbm",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.fai",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.mm2",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.ndb",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.nhr",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.nin",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.njs",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.not",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.nsq",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.ntf",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.nto",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/Genome",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/Log.out",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/SA",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/SAindex",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/build.ok",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/chrLength.txt",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/chrName.txt",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/chrNameLength.txt",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/chrStart.txt",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/exonGeTrInfo.tab",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/exonInfo.tab",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/geneInfo.tab",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/genomeParameters.txt",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/sjdbInfo.txt",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/sjdbList.fromGTF.out.tab",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/sjdbList.out.tab",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/transcriptInfo.tab",
+                "starfusion/ctat_genome_lib_build_dir/trans.blast.align_coords.align_coords.dat",
+                "starfusion/ctat_genome_lib_build_dir/trans.blast.align_coords.align_coords.dbm",
+                "starfusion/ctat_genome_lib_build_dir/trans.blast.dat.gz"
             ]
         ],
         "meta": {
             "nf-test": "0.9.0",
             "nextflow": "24.10.2"
         },
-        "timestamp": "2024-12-20T09:49:14.743338"
+        "timestamp": "2024-12-20T11:53:19.316547"
     }
 }
\ No newline at end of file
diff --git a/workflows/rnafusion.nf b/workflows/rnafusion.nf
index a755311c..755be7b2 100644
--- a/workflows/rnafusion.nf
+++ b/workflows/rnafusion.nf
@@ -65,7 +65,7 @@ workflow RNAFUSION {
     //
     TRIM_WORKFLOW (
         ch_samplesheet,
-        params.adapter_fasta,
+        Channel.value(params.adapter_fasta),
         params.fastp_trim
     )
     ch_reads = TRIM_WORKFLOW.out.ch_reads_all

From 509a792e1197aeb69b22bb5218b6830cca9761cd Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Fri, 20 Dec 2024 12:03:55 +0100
Subject: [PATCH 39/41] add species to schema

---
 nextflow_schema.json | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/nextflow_schema.json b/nextflow_schema.json
index db35f97d..1f83adc1 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -375,6 +375,11 @@
                     "type": "string",
                     "description": "Path to Fusion Annotation Library to be used in STARFUSION_BUILD.",
                     "fa_icon": "far fa-file-code"
+                },
+                "species": {
+                    "type": "string",
+                    "description": "Which species dfam should automatically download, default: human.",
+                    "fa_icon": "far fa-file-code"
                 }
             }
         },

From 8776835e747aaf65a0dbf5f493e5154b32cdbd11 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Fri, 20 Dec 2024 13:24:33 +0100
Subject: [PATCH 40/41] fix erroneous addition of meta

---
 subworkflows/local/arriba_workflow/main.nf |   8 +-
 subworkflows/local/build_references.nf     |  12 +-
 tests/test_stub.nf.test.snap               | 431 ++++++++++++++++++++-
 3 files changed, 432 insertions(+), 19 deletions(-)

diff --git a/subworkflows/local/arriba_workflow/main.nf b/subworkflows/local/arriba_workflow/main.nf
index bb4c36a6..5fa2ed2b 100644
--- a/subworkflows/local/arriba_workflow/main.nf
+++ b/subworkflows/local/arriba_workflow/main.nf
@@ -52,10 +52,10 @@ workflow ARRIBA_WORKFLOW {
                     STAR_FOR_ARRIBA.out.bam,
                     ch_fasta,
                     ch_gtf,
-                    ch_arriba_ref_blacklist.map{ it[1] },
-                    ch_arriba_ref_known_fusions.map{ it[1] },
-                    ch_arriba_ref_cytobands.map{ it[1] },
-                    ch_arriba_ref_protein_domains.map{ it[1] }
+                    ch_arriba_ref_blacklist,
+                    ch_arriba_ref_known_fusions,
+                    ch_arriba_ref_cytobands,
+                    ch_arriba_ref_protein_domains
                 )
 
                 ch_versions = ch_versions.mix(ARRIBA_ARRIBA.out.versions)
diff --git a/subworkflows/local/build_references.nf b/subworkflows/local/build_references.nf
index 34102d2d..56fd8eb2 100644
--- a/subworkflows/local/build_references.nf
+++ b/subworkflows/local/build_references.nf
@@ -118,14 +118,10 @@ workflow BUILD_REFERENCES {
         ch_arriba_ref_known_fusions = ARRIBA_DOWNLOAD.out.known_fusions
         ch_arriba_ref_protein_domains = ARRIBA_DOWNLOAD.out.protein_domains
     } else {
-        ch_arriba_ref_blacklist = Channel.fromPath(params.arriba_ref_blacklist).map { file ->
-        [ id: file.baseName, path: file ]}
-        ch_arriba_ref_cytobands = Channel.fromPath(params.arriba_ref_cytobands).map { file ->
-        [ id: file.baseName, path: file ]}
-        ch_arriba_ref_known_fusions = Channel.fromPath(params.arriba_ref_known_fusions).map { file ->
-        [ id: file.baseName, path: file ]}
-        ch_arriba_ref_protein_domains = Channel.fromPath(params.arriba_ref_protein_domains).map { file ->
-        [ id: file.baseName, path: file ]}
+        ch_arriba_ref_blacklist = Channel.fromPath(params.arriba_ref_blacklist)
+        ch_arriba_ref_cytobands = Channel.fromPath(params.arriba_ref_cytobands)
+        ch_arriba_ref_known_fusions = Channel.fromPath(params.arriba_ref_known_fusions)
+        ch_arriba_ref_protein_domains = Channel.fromPath(params.arriba_ref_protein_domains)
     }
 
 
diff --git a/tests/test_stub.nf.test.snap b/tests/test_stub.nf.test.snap
index a60d6d13..e1892a6a 100644
--- a/tests/test_stub.nf.test.snap
+++ b/tests/test_stub.nf.test.snap
@@ -1,22 +1,343 @@
 {
     "stub test no fastp trim": {
         "content": [
-            0,
-            null,
+            29,
+            {
+                "ARRIBA_ARRIBA": {
+                    "arriba": "2.4.0"
+                },
+                "ARRIBA_DOWNLOAD": {
+                    "arriba_download": "2.4.0"
+                },
+                "FASTQC": {
+                    "fastqc": "0.12.1"
+                },
+                "FUSIONCATCHER": {
+                    "fusioncatcher": 1.35
+                },
+                "FUSIONCATCHER_BUILD": {
+                    "fusioncatcher": "fusioncatcher.py 1.35"
+                },
+                "FUSIONREPORT": {
+                    "fusion_report": "2.1.5"
+                },
+                "FUSIONREPORT_DOWNLOAD": {
+                    "fusion_report": "2.1.5"
+                },
+                "GATK4_BEDTOINTERVALLIST": {
+                    "gatk4": "4.6.1.0"
+                },
+                "GATK4_CREATESEQUENCEDICTIONARY": {
+                    "gatk4": "4.6.1.0"
+                },
+                "GATK4_MARKDUPLICATES": {
+                    "gatk4": "4.5.0.0",
+                    "samtools": "1.19.2"
+                },
+                "GENCODE_DOWNLOAD": {
+                    "wget": null
+                },
+                "GET_RRNA_TRANSCRIPTS": {
+                    "get_rrna_transcripts": "v1.0"
+                },
+                "GFFREAD": {
+                    "gffread": "0.12.7"
+                },
+                "GTF_TO_REFFLAT": {
+                    "gtfToGenePred": 377
+                },
+                "HGNC_DOWNLOAD": {
+                    "wget": null
+                },
+                "PICARD_COLLECTINSERTSIZEMETRICS": {
+                    "picard": "3.3.0"
+                },
+                "PICARD_COLLECTRNASEQMETRICS": {
+                    "picard": "3.3.0"
+                },
+                "SALMON_INDEX": {
+                    "salmon": "1.10.3"
+                },
+                "SALMON_QUANT": {
+                    "salmon": "1.10.3"
+                },
+                "SAMTOOLS_FAIDX": {
+                    "samtools": 1.21
+                },
+                "SAMTOOLS_INDEX_FOR_STARFUSION": {
+                    "samtools": 1.21
+                },
+                "STARFUSION": {
+                    "STAR-Fusion": "1.14.0"
+                },
+                "STARFUSION_BUILD": {
+                    "STAR-Fusion": "1.14.0"
+                },
+                "STAR_FOR_ARRIBA": {
+                    "star": null,
+                    "samtools": 1.2,
+                    "gawk": "5.1.0"
+                },
+                "STAR_FOR_STARFUSION": {
+                    "star": null,
+                    "samtools": 1.2,
+                    "gawk": "5.1.0"
+                },
+                "STAR_GENOMEGENERATE": {
+                    "star": null,
+                    "samtools": 1.2,
+                    "gawk": "5.1.0"
+                },
+                "STRINGTIE_MERGE": {
+                    "stringtie": "2.2.1"
+                },
+                "STRINGTIE_STRINGTIE": {
+                    "stringtie": "2.2.3"
+                },
+                "Workflow": {
+                    "nf-core/rnafusion": "v4.0.0dev"
+                }
+            },
             [
-                
+                "arriba",
+                "arriba/test.arriba.fusions.discarded.tsv",
+                "arriba/test.arriba.fusions.tsv",
+                "fastqc",
+                "fastqc/test.html",
+                "fastqc/test.zip",
+                "fusioncatcher",
+                "fusioncatcher/human_v46",
+                "fusioncatcher/human_v46/ensembl_fully_overlapping_genes.txt",
+                "fusioncatcher/test.fusioncatcher.fusion-genes.txt",
+                "fusioncatcher/test.fusioncatcher.log",
+                "fusioncatcher/test.fusioncatcher.summary.txt",
+                "fusionreport",
+                "fusionreport/test",
+                "fusionreport/test/AAA_BBB.html",
+                "fusionreport/test/test.fusionreport.tsv",
+                "fusionreport/test/test.fusionreport_filtered.tsv",
+                "fusionreport/test/test.fusions.csv",
+                "fusionreport/test/test.fusions.json",
+                "fusionreport/test/test_fusionreport_index.html",
+                "gatk4",
+                "gatk4/Homo_sapiens.GRCh38.46_dna_primary_assembly.dict",
+                "get",
+                "get/rrna.bed",
+                "get/rrna.gtf",
+                "multiqc",
+                "multiqc/multiqc_data",
+                "multiqc/multiqc_plots",
+                "multiqc/multiqc_report.html",
+                "picard",
+                "picard/test.bai",
+                "picard/test.bam",
+                "picard/test.bam.metrics",
+                "picard/test.cram",
+                "picard/test.cram.crai",
+                "picard/test.rna_metrics",
+                "picard/test_collectinsertsize.pdf",
+                "picard/test_collectinsertsize.txt",
+                "pipeline_info",
+                "pipeline_info/nf_core_pipeline_software_mqc_versions.yml",
+                "references",
+                "references/arriba",
+                "references/arriba/blacklist_hg38_GRCh38_v2.4.0.tsv.gz",
+                "references/arriba/cytobands_hg38_GRCh38_v2.4.0.tsv",
+                "references/arriba/known_fusions_hg38_GRCh38_v2.4.0.tsv.gz",
+                "references/arriba/protein_domains_hg38_GRCh38_v2.4.0.gff3",
+                "references/fusion_report_db",
+                "references/fusion_report_db/DB-timestamp.txt",
+                "references/fusion_report_db/cosmic.db",
+                "references/fusion_report_db/fusion_report.log",
+                "references/fusion_report_db/fusiongdb2.db",
+                "references/fusion_report_db/mitelman.db",
+                "references/gencode",
+                "references/gencode/Homo_sapiens.GRCh38.46.gtf",
+                "references/gencode/Homo_sapiens.GRCh38.46.gtf.interval_list",
+                "references/gencode/Homo_sapiens.GRCh38.46.gtf.refflat",
+                "references/gencode/Homo_sapiens.GRCh38.46_dna_primary_assembly.fa",
+                "references/gencode/Homo_sapiens.GRCh38.46_dna_primary_assembly.fa.fai",
+                "references/gffread",
+                "references/gffread/Homo_sapiens.GRCh38.46.gtf.fasta",
+                "references/hgnc",
+                "references/hgnc/HGNC-DB-timestamp.txt",
+                "references/hgnc/hgnc_complete_set.txt",
+                "references/salmon",
+                "references/salmon/salmon",
+                "references/salmon/salmon/complete_ref_lens.bin",
+                "references/salmon/salmon/ctable.bin",
+                "references/salmon/salmon/ctg_offsets.bin",
+                "references/salmon/salmon/duplicate_clusters.tsv",
+                "references/salmon/salmon/info.json",
+                "references/salmon/salmon/mphf.bin",
+                "references/salmon/salmon/pos.bin",
+                "references/salmon/salmon/pre_indexing.log",
+                "references/salmon/salmon/rank.bin",
+                "references/salmon/salmon/refAccumLengths.bin",
+                "references/salmon/salmon/ref_indexing.log",
+                "references/salmon/salmon/reflengths.bin",
+                "references/salmon/salmon/refseq.bin",
+                "references/salmon/salmon/seq.bin",
+                "references/salmon/salmon/versionInfo.json",
+                "references/star",
+                "references/star/Genome",
+                "references/star/Log.out",
+                "references/star/SA",
+                "references/star/SAindex",
+                "references/star/chrLength.txt",
+                "references/star/chrName.txt",
+                "references/star/chrNameLength.txt",
+                "references/star/chrStart.txt",
+                "references/star/exonGeTrInfo.tab",
+                "references/star/exonInfo.tab",
+                "references/star/geneInfo.tab",
+                "references/star/genomeParameters.txt",
+                "references/star/sjdbInfo.txt",
+                "references/star/sjdbList.fromGTF.out.tab",
+                "references/star/sjdbList.out.tab",
+                "references/star/transcriptInfo.tab",
+                "salmon",
+                "salmon/test",
+                "salmon/test_lib_format_counts.json",
+                "salmon/test_meta_info.json",
+                "star_for_arriba",
+                "star_for_arriba/test.Aligned.sortedByCoord.out.bam",
+                "star_for_arriba/test.Aligned.unsort.out.bam",
+                "star_for_arriba/test.Chimeric.out.junction",
+                "star_for_arriba/test.Log.final.out",
+                "star_for_arriba/test.Log.out",
+                "star_for_arriba/test.Log.progress.out",
+                "star_for_arriba/test.ReadsPerGene.out.tab",
+                "star_for_arriba/test.SJ.out.tab",
+                "star_for_arriba/test.Signal.UniqueMultiple.str1.out.bg",
+                "star_for_arriba/test.Signal.UniqueMultiple.str1.out.wig",
+                "star_for_arriba/test.out.sam",
+                "star_for_arriba/test.sortedByCoord.out.bam",
+                "star_for_arriba/test.tab",
+                "star_for_arriba/test.toTranscriptome.out.bam",
+                "star_for_arriba/test.unmapped_1.fastq.gz",
+                "star_for_arriba/test.unmapped_2.fastq.gz",
+                "star_for_arriba/testXd.out.bam",
+                "star_for_starfusion",
+                "star_for_starfusion/test.Aligned.sortedByCoord.out.bam",
+                "star_for_starfusion/test.Aligned.unsort.out.bam",
+                "star_for_starfusion/test.Chimeric.out.junction",
+                "star_for_starfusion/test.Log.final.out",
+                "star_for_starfusion/test.Log.out",
+                "star_for_starfusion/test.Log.progress.out",
+                "star_for_starfusion/test.ReadsPerGene.out.tab",
+                "star_for_starfusion/test.SJ.out.tab",
+                "star_for_starfusion/test.Signal.UniqueMultiple.str1.out.bg",
+                "star_for_starfusion/test.Signal.UniqueMultiple.str1.out.wig",
+                "star_for_starfusion/test.out.sam",
+                "star_for_starfusion/test.sortedByCoord.out.bam",
+                "star_for_starfusion/test.sortedByCoord.out.bam.bai",
+                "star_for_starfusion/test.tab",
+                "star_for_starfusion/test.toTranscriptome.out.bam",
+                "star_for_starfusion/test.unmapped_1.fastq.gz",
+                "star_for_starfusion/test.unmapped_2.fastq.gz",
+                "star_for_starfusion/testXd.out.bam",
+                "starfusion",
+                "starfusion/ctat_genome_lib_build_dir",
+                "starfusion/ctat_genome_lib_build_dir/AnnotFilterRule.pm",
+                "starfusion/ctat_genome_lib_build_dir/PFAM.domtblout.dat.gz",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/_fusion_annot_lib.idx.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/_prot_info_db.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/annotfiltrule_cp.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/blast_pairs.idx.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/cp_gene_blast_pairs.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/cp_pfam_dat.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/cp_ref_annot_cdna.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/fusion_annot_lib.cp.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/index_pfam_hits.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/index_ref_annot_cdna.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/makeblastdb.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/mm2.splice_bed.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/mm2_genome_idx.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/ref_annot.cdsplus.dfam_masked.fa.cp.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/ref_annot.cdsplus.dfam_masked.fa.idx.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/ref_annot.gtf.gene_spans.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/ref_annot.gtf.mini.sortu.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/ref_annot.gtf.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/ref_genome.fa.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/ref_genome_fai.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/trans.blast.dat.cp.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/trans.blast.dat.index.ok",
+                "starfusion/ctat_genome_lib_build_dir/__chkpts/validate_ctat_genome_lib.ok",
+                "starfusion/ctat_genome_lib_build_dir/blast_pairs.dat.gz",
+                "starfusion/ctat_genome_lib_build_dir/blast_pairs.idx",
+                "starfusion/ctat_genome_lib_build_dir/fusion_annot_lib.gz",
+                "starfusion/ctat_genome_lib_build_dir/fusion_annot_lib.idx",
+                "starfusion/ctat_genome_lib_build_dir/pfam_domains.dbm",
+                "starfusion/ctat_genome_lib_build_dir/ref_annot.cdna.fa",
+                "starfusion/ctat_genome_lib_build_dir/ref_annot.cdna.fa.idx",
+                "starfusion/ctat_genome_lib_build_dir/ref_annot.cds",
+                "starfusion/ctat_genome_lib_build_dir/ref_annot.cdsplus.fa",
+                "starfusion/ctat_genome_lib_build_dir/ref_annot.cdsplus.fa.idx",
+                "starfusion/ctat_genome_lib_build_dir/ref_annot.gtf",
+                "starfusion/ctat_genome_lib_build_dir/ref_annot.gtf.gene_spans",
+                "starfusion/ctat_genome_lib_build_dir/ref_annot.gtf.mini.sortu",
+                "starfusion/ctat_genome_lib_build_dir/ref_annot.gtf.mm2.splice.bed",
+                "starfusion/ctat_genome_lib_build_dir/ref_annot.pep",
+                "starfusion/ctat_genome_lib_build_dir/ref_annot.prot_info.dbm",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.fai",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.mm2",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.ndb",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.nhr",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.nin",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.njs",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.not",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.nsq",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.ntf",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.nto",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/Genome",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/Log.out",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/SA",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/SAindex",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/build.ok",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/chrLength.txt",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/chrName.txt",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/chrNameLength.txt",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/chrStart.txt",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/exonGeTrInfo.tab",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/exonInfo.tab",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/geneInfo.tab",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/genomeParameters.txt",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/sjdbInfo.txt",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/sjdbList.fromGTF.out.tab",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/sjdbList.out.tab",
+                "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/transcriptInfo.tab",
+                "starfusion/ctat_genome_lib_build_dir/trans.blast.align_coords.align_coords.dat",
+                "starfusion/ctat_genome_lib_build_dir/trans.blast.align_coords.align_coords.dbm",
+                "starfusion/ctat_genome_lib_build_dir/trans.blast.dat.gz",
+                "starfusion/test.starfusion.abridged.coding_effect.tsv",
+                "starfusion/test.starfusion.abridged.tsv",
+                "starfusion/test.starfusion.fusion_predictions.tsv",
+                "stringtie",
+                "stringtie/[:]",
+                "stringtie/[:]/stringtie.merged.gtf",
+                "stringtie/test.ballgown",
+                "stringtie/test.coverage.gtf",
+                "stringtie/test.gene.abundance.txt",
+                "stringtie/test.transcripts.gtf"
             ]
         ],
         "meta": {
             "nf-test": "0.9.0",
             "nextflow": "24.10.2"
         },
-        "timestamp": "2024-12-20T11:51:44.033131"
+        "timestamp": "2024-12-20T13:17:20.018293"
     },
     "stub test with fastp trim": {
         "content": [
-            18,
+            31,
             {
+                "ARRIBA_ARRIBA": {
+                    "arriba": "2.4.0"
+                },
                 "ARRIBA_DOWNLOAD": {
                     "arriba_download": "2.4.0"
                 },
@@ -35,12 +356,22 @@
                 "FUSIONCATCHER_BUILD": {
                     "fusioncatcher": "fusioncatcher.py 1.35"
                 },
+                "FUSIONREPORT": {
+                    "fusion_report": "2.1.5"
+                },
                 "FUSIONREPORT_DOWNLOAD": {
                     "fusion_report": "2.1.5"
                 },
+                "GATK4_BEDTOINTERVALLIST": {
+                    "gatk4": "4.6.1.0"
+                },
                 "GATK4_CREATESEQUENCEDICTIONARY": {
                     "gatk4": "4.6.1.0"
                 },
+                "GATK4_MARKDUPLICATES": {
+                    "gatk4": "4.5.0.0",
+                    "samtools": "1.19.2"
+                },
                 "GENCODE_DOWNLOAD": {
                     "wget": null
                 },
@@ -56,9 +387,27 @@
                 "HGNC_DOWNLOAD": {
                     "wget": null
                 },
+                "PICARD_COLLECTINSERTSIZEMETRICS": {
+                    "picard": "3.3.0"
+                },
+                "PICARD_COLLECTRNASEQMETRICS": {
+                    "picard": "3.3.0"
+                },
+                "SALMON_INDEX": {
+                    "salmon": "1.10.3"
+                },
+                "SALMON_QUANT": {
+                    "salmon": "1.10.3"
+                },
                 "SAMTOOLS_FAIDX": {
                     "samtools": 1.21
                 },
+                "SAMTOOLS_INDEX_FOR_STARFUSION": {
+                    "samtools": 1.21
+                },
+                "STARFUSION": {
+                    "STAR-Fusion": "1.14.0"
+                },
                 "STARFUSION_BUILD": {
                     "STAR-Fusion": "1.14.0"
                 },
@@ -67,16 +416,30 @@
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
+                "STAR_FOR_STARFUSION": {
+                    "star": null,
+                    "samtools": 1.2,
+                    "gawk": "5.1.0"
+                },
                 "STAR_GENOMEGENERATE": {
                     "star": null,
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
+                "STRINGTIE_MERGE": {
+                    "stringtie": "2.2.1"
+                },
+                "STRINGTIE_STRINGTIE": {
+                    "stringtie": "2.2.3"
+                },
                 "Workflow": {
                     "nf-core/rnafusion": "v4.0.0dev"
                 }
             },
             [
+                "arriba",
+                "arriba/test.arriba.fusions.discarded.tsv",
+                "arriba/test.arriba.fusions.tsv",
                 "fastp",
                 "fastp/test.fastp.html",
                 "fastp/test.fastp.json",
@@ -95,11 +458,32 @@
                 "fusioncatcher/test.fusioncatcher.fusion-genes.txt",
                 "fusioncatcher/test.fusioncatcher.log",
                 "fusioncatcher/test.fusioncatcher.summary.txt",
+                "fusionreport",
+                "fusionreport/test",
+                "fusionreport/test/AAA_BBB.html",
+                "fusionreport/test/test.fusionreport.tsv",
+                "fusionreport/test/test.fusionreport_filtered.tsv",
+                "fusionreport/test/test.fusions.csv",
+                "fusionreport/test/test.fusions.json",
+                "fusionreport/test/test_fusionreport_index.html",
                 "gatk4",
                 "gatk4/Homo_sapiens.GRCh38.46_dna_primary_assembly.dict",
                 "get",
                 "get/rrna.bed",
                 "get/rrna.gtf",
+                "multiqc",
+                "multiqc/multiqc_data",
+                "multiqc/multiqc_plots",
+                "multiqc/multiqc_report.html",
+                "picard",
+                "picard/test.bai",
+                "picard/test.bam",
+                "picard/test.bam.metrics",
+                "picard/test.cram",
+                "picard/test.cram.crai",
+                "picard/test.rna_metrics",
+                "picard/test_collectinsertsize.pdf",
+                "picard/test_collectinsertsize.txt",
                 "pipeline_info",
                 "pipeline_info/nf_core_pipeline_software_mqc_versions.yml",
                 "references",
@@ -116,6 +500,7 @@
                 "references/fusion_report_db/mitelman.db",
                 "references/gencode",
                 "references/gencode/Homo_sapiens.GRCh38.46.gtf",
+                "references/gencode/Homo_sapiens.GRCh38.46.gtf.interval_list",
                 "references/gencode/Homo_sapiens.GRCh38.46.gtf.refflat",
                 "references/gencode/Homo_sapiens.GRCh38.46_dna_primary_assembly.fa",
                 "references/gencode/Homo_sapiens.GRCh38.46_dna_primary_assembly.fa.fai",
@@ -124,6 +509,23 @@
                 "references/hgnc",
                 "references/hgnc/HGNC-DB-timestamp.txt",
                 "references/hgnc/hgnc_complete_set.txt",
+                "references/salmon",
+                "references/salmon/salmon",
+                "references/salmon/salmon/complete_ref_lens.bin",
+                "references/salmon/salmon/ctable.bin",
+                "references/salmon/salmon/ctg_offsets.bin",
+                "references/salmon/salmon/duplicate_clusters.tsv",
+                "references/salmon/salmon/info.json",
+                "references/salmon/salmon/mphf.bin",
+                "references/salmon/salmon/pos.bin",
+                "references/salmon/salmon/pre_indexing.log",
+                "references/salmon/salmon/rank.bin",
+                "references/salmon/salmon/refAccumLengths.bin",
+                "references/salmon/salmon/ref_indexing.log",
+                "references/salmon/salmon/reflengths.bin",
+                "references/salmon/salmon/refseq.bin",
+                "references/salmon/salmon/seq.bin",
+                "references/salmon/salmon/versionInfo.json",
                 "references/star",
                 "references/star/Genome",
                 "references/star/Log.out",
@@ -141,6 +543,10 @@
                 "references/star/sjdbList.fromGTF.out.tab",
                 "references/star/sjdbList.out.tab",
                 "references/star/transcriptInfo.tab",
+                "salmon",
+                "salmon/test",
+                "salmon/test_lib_format_counts.json",
+                "salmon/test_meta_info.json",
                 "star_for_arriba",
                 "star_for_arriba/test.Aligned.sortedByCoord.out.bam",
                 "star_for_arriba/test.Aligned.unsort.out.bam",
@@ -172,6 +578,7 @@
                 "star_for_starfusion/test.Signal.UniqueMultiple.str1.out.wig",
                 "star_for_starfusion/test.out.sam",
                 "star_for_starfusion/test.sortedByCoord.out.bam",
+                "star_for_starfusion/test.sortedByCoord.out.bam.bai",
                 "star_for_starfusion/test.tab",
                 "star_for_starfusion/test.toTranscriptome.out.bam",
                 "star_for_starfusion/test.unmapped_1.fastq.gz",
@@ -252,13 +659,23 @@
                 "starfusion/ctat_genome_lib_build_dir/ref_genome.fa.star.idx/transcriptInfo.tab",
                 "starfusion/ctat_genome_lib_build_dir/trans.blast.align_coords.align_coords.dat",
                 "starfusion/ctat_genome_lib_build_dir/trans.blast.align_coords.align_coords.dbm",
-                "starfusion/ctat_genome_lib_build_dir/trans.blast.dat.gz"
+                "starfusion/ctat_genome_lib_build_dir/trans.blast.dat.gz",
+                "starfusion/test.starfusion.abridged.coding_effect.tsv",
+                "starfusion/test.starfusion.abridged.tsv",
+                "starfusion/test.starfusion.fusion_predictions.tsv",
+                "stringtie",
+                "stringtie/[:]",
+                "stringtie/[:]/stringtie.merged.gtf",
+                "stringtie/test.ballgown",
+                "stringtie/test.coverage.gtf",
+                "stringtie/test.gene.abundance.txt",
+                "stringtie/test.transcripts.gtf"
             ]
         ],
         "meta": {
             "nf-test": "0.9.0",
             "nextflow": "24.10.2"
         },
-        "timestamp": "2024-12-20T11:53:19.316547"
+        "timestamp": "2024-12-20T13:15:06.974011"
     }
 }
\ No newline at end of file

From ab65540133a556fda772f776a3bc4391a1f12329 Mon Sep 17 00:00:00 2001
From: Annick Renevey <47788523+rannick@users.noreply.github.com>
Date: Fri, 20 Dec 2024 14:02:55 +0100
Subject: [PATCH 41/41] fixes

---
 tests/test_stub.nf.test.snap | 78 +++++++++++++++++++++++++++++++-----
 workflows/rnafusion.nf       |  6 +--
 2 files changed, 70 insertions(+), 14 deletions(-)

diff --git a/tests/test_stub.nf.test.snap b/tests/test_stub.nf.test.snap
index e1892a6a..0ac620e7 100644
--- a/tests/test_stub.nf.test.snap
+++ b/tests/test_stub.nf.test.snap
@@ -1,7 +1,7 @@
 {
     "stub test no fastp trim": {
         "content": [
-            29,
+            31,
             {
                 "ARRIBA_ARRIBA": {
                     "arriba": "2.4.0"
@@ -9,6 +9,9 @@
                 "ARRIBA_DOWNLOAD": {
                     "arriba_download": "2.4.0"
                 },
+                "CTATSPLICING_STARTOCANCERINTRONS": {
+                    "ctat-splicing": "0.0.2"
+                },
                 "FASTQC": {
                     "fastqc": "0.12.1"
                 },
@@ -74,17 +77,17 @@
                     "STAR-Fusion": "1.14.0"
                 },
                 "STAR_FOR_ARRIBA": {
-                    "star": null,
+                    "star": "2.7.11b",
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
                 "STAR_FOR_STARFUSION": {
-                    "star": null,
+                    "star": "2.7.11b",
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
                 "STAR_GENOMEGENERATE": {
-                    "star": null,
+                    "star": "2.7.11b",
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
@@ -102,6 +105,31 @@
                 "arriba",
                 "arriba/test.arriba.fusions.discarded.tsv",
                 "arriba/test.arriba.fusions.tsv",
+                "ctatsplicing",
+                "ctatsplicing/arriba",
+                "ctatsplicing/arriba/test.cancer.introns",
+                "ctatsplicing/arriba/test.cancer.introns.prelim",
+                "ctatsplicing/arriba/test.cancer_intron_reads.sorted.bam",
+                "ctatsplicing/arriba/test.cancer_intron_reads.sorted.bam.bai",
+                "ctatsplicing/arriba/test.chckpts",
+                "ctatsplicing/arriba/test.ctat-splicing.igv.html",
+                "ctatsplicing/arriba/test.gene_reads.sorted.sifted.bam",
+                "ctatsplicing/arriba/test.gene_reads.sorted.sifted.bam.bai",
+                "ctatsplicing/arriba/test.igv.tracks",
+                "ctatsplicing/arriba/test.introns",
+                "ctatsplicing/arriba/test.introns.for_IGV.bed",
+                "ctatsplicing/starfusion",
+                "ctatsplicing/starfusion/test.cancer.introns",
+                "ctatsplicing/starfusion/test.cancer.introns.prelim",
+                "ctatsplicing/starfusion/test.cancer_intron_reads.sorted.bam",
+                "ctatsplicing/starfusion/test.cancer_intron_reads.sorted.bam.bai",
+                "ctatsplicing/starfusion/test.chckpts",
+                "ctatsplicing/starfusion/test.ctat-splicing.igv.html",
+                "ctatsplicing/starfusion/test.gene_reads.sorted.sifted.bam",
+                "ctatsplicing/starfusion/test.gene_reads.sorted.sifted.bam.bai",
+                "ctatsplicing/starfusion/test.igv.tracks",
+                "ctatsplicing/starfusion/test.introns",
+                "ctatsplicing/starfusion/test.introns.for_IGV.bed",
                 "fastqc",
                 "fastqc/test.html",
                 "fastqc/test.zip",
@@ -329,11 +357,11 @@
             "nf-test": "0.9.0",
             "nextflow": "24.10.2"
         },
-        "timestamp": "2024-12-20T13:17:20.018293"
+        "timestamp": "2024-12-20T14:00:19.311265"
     },
     "stub test with fastp trim": {
         "content": [
-            31,
+            33,
             {
                 "ARRIBA_ARRIBA": {
                     "arriba": "2.4.0"
@@ -341,6 +369,9 @@
                 "ARRIBA_DOWNLOAD": {
                     "arriba_download": "2.4.0"
                 },
+                "CTATSPLICING_STARTOCANCERINTRONS": {
+                    "ctat-splicing": "0.0.2"
+                },
                 "FASTP": {
                     "fastp": "0.23.4"
                 },
@@ -412,17 +443,17 @@
                     "STAR-Fusion": "1.14.0"
                 },
                 "STAR_FOR_ARRIBA": {
-                    "star": null,
+                    "star": "2.7.11b",
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
                 "STAR_FOR_STARFUSION": {
-                    "star": null,
+                    "star": "2.7.11b",
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
                 "STAR_GENOMEGENERATE": {
-                    "star": null,
+                    "star": "2.7.11b",
                     "samtools": 1.2,
                     "gawk": "5.1.0"
                 },
@@ -440,6 +471,31 @@
                 "arriba",
                 "arriba/test.arriba.fusions.discarded.tsv",
                 "arriba/test.arriba.fusions.tsv",
+                "ctatsplicing",
+                "ctatsplicing/arriba",
+                "ctatsplicing/arriba/test.cancer.introns",
+                "ctatsplicing/arriba/test.cancer.introns.prelim",
+                "ctatsplicing/arriba/test.cancer_intron_reads.sorted.bam",
+                "ctatsplicing/arriba/test.cancer_intron_reads.sorted.bam.bai",
+                "ctatsplicing/arriba/test.chckpts",
+                "ctatsplicing/arriba/test.ctat-splicing.igv.html",
+                "ctatsplicing/arriba/test.gene_reads.sorted.sifted.bam",
+                "ctatsplicing/arriba/test.gene_reads.sorted.sifted.bam.bai",
+                "ctatsplicing/arriba/test.igv.tracks",
+                "ctatsplicing/arriba/test.introns",
+                "ctatsplicing/arriba/test.introns.for_IGV.bed",
+                "ctatsplicing/starfusion",
+                "ctatsplicing/starfusion/test.cancer.introns",
+                "ctatsplicing/starfusion/test.cancer.introns.prelim",
+                "ctatsplicing/starfusion/test.cancer_intron_reads.sorted.bam",
+                "ctatsplicing/starfusion/test.cancer_intron_reads.sorted.bam.bai",
+                "ctatsplicing/starfusion/test.chckpts",
+                "ctatsplicing/starfusion/test.ctat-splicing.igv.html",
+                "ctatsplicing/starfusion/test.gene_reads.sorted.sifted.bam",
+                "ctatsplicing/starfusion/test.gene_reads.sorted.sifted.bam.bai",
+                "ctatsplicing/starfusion/test.igv.tracks",
+                "ctatsplicing/starfusion/test.introns",
+                "ctatsplicing/starfusion/test.introns.for_IGV.bed",
                 "fastp",
                 "fastp/test.fastp.html",
                 "fastp/test.fastp.json",
@@ -676,6 +732,6 @@
             "nf-test": "0.9.0",
             "nextflow": "24.10.2"
         },
-        "timestamp": "2024-12-20T13:15:06.974011"
+        "timestamp": "2024-12-20T13:57:10.179877"
     }
-}
\ No newline at end of file
+}
diff --git a/workflows/rnafusion.nf b/workflows/rnafusion.nf
index 3c98cf6b..857827aa 100644
--- a/workflows/rnafusion.nf
+++ b/workflows/rnafusion.nf
@@ -92,7 +92,7 @@ workflow RNAFUSION {
         BUILD_REFERENCES.out.ch_arriba_ref_cytobands,
         BUILD_REFERENCES.out.ch_arriba_ref_known_fusions,
         BUILD_REFERENCES.out.ch_arriba_ref_protein_domains,
-        ch_starfusion_ref,
+        BUILD_REFERENCES.out.ch_starfusion_ref,
         params.arriba,                   // boolean
         params.all,                      // boolean
         params.fusioninspector_only,     // boolean
@@ -110,8 +110,8 @@ workflow RNAFUSION {
         ch_reads,
         BUILD_REFERENCES.out.ch_gtf,
         BUILD_REFERENCES.out.ch_starindex_ref,
-        BUILD_REFERENCES.out.ch_fasta
-        ch_starfusion_ref
+        BUILD_REFERENCES.out.ch_fasta,
+        BUILD_REFERENCES.out.ch_starfusion_ref
     )
     ch_versions = ch_versions.mix(STARFUSION_WORKFLOW.out.versions)