Merge pull request #160 from CenterForMedicalGeneticsGhent/dev

Release PR v1.4.1

.github/workflows/ci.yml

@@ -65,3 +65,10 @@ jobs:
         if: always() # always run even if the previous step fails
         with:
           report_paths: "default.xml"
+
+      - name: Upload log file artifact
+        if: failure()
+        uses: actions/upload-artifact@v3
+        with:
+          name: nf-test-workdir
+          path: .nf-test/

.github/workflows/linting.yml

@@ -70,7 +70,7 @@ jobs:
 
       - name: Install dependencies
         run: |
-          python -m pip install --upgrade --force-reinstall git+https://github.com/nf-core/tools.git@dev
+          python -m pip install nf-core
 
       - name: Run nf-core lint
         env:

.gitignore

@@ -7,4 +7,4 @@ testing/
 testing*
 *.pyc
 null
-.nf-test
+.nf-test*

CHANGELOG.md

@@ -3,6 +3,24 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## v1.4.1 - Lively Leuven - [January 15 2024]
+
+### New Features
+
+1. Added the `--output_suffix` parameter to add a custom suffix to the basename of the output files.
+2. Implemented files for the alphamissense plugin of VEP.
+3. Added the `--only_pass` parameter to only output variants that have the `PASS` flag in the FILTER column. (This is only applied when `--filter` is also given)
+4. Added the `--keep_alt_contigs` parameter. This will tell the pipeline to not filter out the alternate contigs, which will now be done by default.
+5. Add dbsnp Ids to VCFs coming from vardict. This will be done automatically if a dbsnp VCF is given to the pipeline through the `--dbsnp` parameter.
+
+### Improvements
+
+1. Updated the seqplorer profile so that the output filenames are correct for easy import
+2. Changed the separator in `--vcfanno_resources` to `;`
+   instead of `,` to allow commas in glob patterns.
+3. Removed the reheader step from the vardict subworkflow and added a simple sed substitution to the vardictjava module
+4. `vcf2db` now uses a python 2 environment to increase it's stability
+
 ## v1.4.0 - Kingly Kortrijk - [December 6 2023]
 
 ### New Features

assets/dbsnp.toml

@@ -0,0 +1,15 @@
+[[annotation]]
+file="DBSNP_FILE"
+fields=["ID"]
+names=["rs_ids"]
+ops=["concat"]
+
+[[postannotation]]
+name="ID"
+fields=["rs_ids"]
+op="setid"
+type="String"
+
+[[postannotation]]
+fields=["rs_ids"]
+op="delete"

assets/multiqc_config.yml

@@ -1,5 +1,5 @@
 report_comment: >
-  This report has been generated by the <a href="https://github.com/CenterForMedicalGeneticsGhent/nf-cmgg-germline/1.4.0" target="_blank">CenterForMedicalGeneticsGhent/nf-cmgg-germline</a>
+  This report has been generated by the <a href="https://github.com/CenterForMedicalGeneticsGhent/nf-cmgg-germline/dev" target="_blank">CenterForMedicalGeneticsGhent/nf-cmgg-germline</a>
   analysis pipeline.
 report_section_order:
   "CenterForMedicalGeneticsGhent-nf-cmgg-germline-methods-description":

conf/hypercap.config

@@ -0,0 +1,13 @@
+/*
+========================================================================================
+    Nextflow config file for HyperCap runs
+========================================================================================
+*/
+
+params {
+    callers             = "vardict"
+    scatter_count       = 5
+    only_pass           = true
+
+    output_suffix       = "-vardict-decomposed-annotated"
+}

conf/modules.config

@@ -44,6 +44,8 @@ def individual_validation = { "${params.outdir}/${meta.sample}/validation/${getG
 
 def callers = params.callers.tokenize(",")
 
+def final_prefix = params.output_suffix ? { "${meta.id}${params.output_suffix}" } : { "${meta.id}.${getGenotypedCaller(meta.caller)}" }
+
 process {
 
     publishDir = [
@@ -76,7 +78,7 @@ process {
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ] // SAVE
-        ext.prefix = { "${meta.id}.${getGenotypedCaller(meta.caller)}" }
+        ext.prefix = final_prefix
     }
 
     /*
@@ -107,7 +109,8 @@ process {
 
     withName: "^.*:CRAM_PREPARE_SAMTOOLS_BEDTOOLS:FILTER_BEDS\$" {
         ext.prefix = { "${meta.id}.filter"}
-        ext.args = "-d 150"
+        ext.args = "-vE \"NO_COVERAGE${params.keep_alt_contigs ? "" : "|alt|random|decoy|Un"}\""
+        ext.args2 = "-d 150"
         publishDir  = [
             overwrite: true,
             enabled: true,
@@ -251,7 +254,7 @@ process {
                 }
 
                 withName: "^.*:GVCF_JOINT_GENOTYPE_GATK4:VCF_CONCAT_BCFTOOLS:BCFTOOLS_CONCAT\$" {
-                    ext.prefix = {"${meta.id}.${getGenotypedCaller(meta.caller)}"}
+                    ext.prefix = final_prefix
                     ext.args = "--allow-overlaps --output-type z"
                     publishDir = [
                         enabled: enableOutput("original"),
@@ -265,12 +268,12 @@ process {
                 if(params.filter){
                     withName: "^.*:CRAM_CALL_GENOTYPE_GATK4:VCF_FILTER_BCFTOOLS:FILTER_1\$" {
                         ext.prefix = { "${meta.id}_filtered_snps" }
-                        ext.args = {'--output-type z --soft-filter \'GATKCutoffSNP\' -e \'TYPE="snp" && (MQRankSum < -12.5 || ReadPosRankSum < -8.0 || QD < 2.0 || FS > 60.0 || (QD < 10.0 && AD[0:1] / (AD[0:1] + AD[0:0]) < 0.25 && ReadPosRankSum < 0.0) || MQ < 30.0)\' -m \'+\''}
+                        ext.args = {"--output-type z --soft-filter 'GATKCutoffSNP' -e 'TYPE=\"snp\" && (MQRankSum < -12.5 || ReadPosRankSum < -8.0 || QD < 2.0 || FS > 60.0 || MQ < 30.0)' -m '+'"}
                     }
 
                     withName: "^.*:CRAM_CALL_GENOTYPE_GATK4:VCF_FILTER_BCFTOOLS:FILTER_2\$" {
-                        ext.prefix = {"${meta.id}.${getGenotypedCaller(meta.caller)}"}
-                        ext.args = {'--output-type z --soft-filter \'GATKCutoffIndel\' -e \'TYPE="indel" && (ReadPosRankSum < -20.0 || QD < 2.0 || FS > 200.0 || SOR > 10.0 || (QD < 10.0 && AD[0:1] / (AD[0:1] + AD[0:0]) < 0.25 && ReadPosRankSum < 0.0))\' -m \'+\''}
+                        ext.prefix = final_prefix
+                        ext.args = {'--output-type z --soft-filter \'GATKCutoffIndel\' -e \'TYPE="indel" && (ReadPosRankSum < -20.0 || QD < 2.0 || FS > 200.0 || SOR > 10.0 )\' -m \'+\''}
                         publishDir = [
                             enabled: enableOutput("filter"),
                             overwrite: true,
@@ -310,23 +313,30 @@ process {
 
         withName: "^.*:CRAM_CALL_VARDICTJAVA:VCF_CONCAT_BCFTOOLS:BCFTOOLS_CONCAT\$" {
             ext.args   = '--allow-overlaps --output-type z'
+            ext.prefix = { "${meta.id}.${meta.caller}" }
+            publishDir  = [
+                overwrite: true,
+                enabled: enableOutput("original"),
+                mode: params.publish_dir_mode,
+                path: final_output,
+                saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+            ] // SAVE
         }
 
-        withName: "^.*:CRAM_CALL_VARDICTJAVA:BCFTOOLS_REHEADER\$" {
+        withName: "^.*:CRAM_CALL_VARDICTJAVA:TABIX_VCFANNO\$" {
+            ext.prefix = { "${meta.id}.${meta.caller}" }
             publishDir  = [
                 overwrite: true,
                 enabled: enableOutput("original"),
                 mode: params.publish_dir_mode,
                 path: final_output,
                 saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
             ] // SAVE
-            ext.prefix = { "${meta.id}.${meta.caller}" }
-            ext.args2  = '--output-type z'
         }
 
         if(params.filter) {
             withName: "^.*:CRAM_CALL_VARDICTJAVA:VCF_FILTER_BCFTOOLS:FILTER_1\$" {
-                ext.args = '-i \'QUAL >= 0\' --output-type z'
+                ext.args = "-i 'QUAL >= 0${params.only_pass ? " && FILTER=\"PASS\"" : ""}' --output-type z"
             }
 
             withName: "^.*:CRAM_CALL_VARDICTJAVA:VCF_FILTER_BCFTOOLS:FILTER_2\$" {
@@ -370,7 +380,7 @@ process {
                 enabled: enableOutput("normalize"),
                 mode: params.publish_dir_mode,
                 path: final_output,
-                saveAs: { filename -> filename.endsWith('.vcf.gz') ? "${meta.id}.${getGenotypedCaller(meta.caller)}.vcf.gz" : null }
+                saveAs: { filename -> filename.endsWith('.vcf.gz') ? filename.replaceAll(".normalized.vcf.gz\$", ".vcf.gz") : null }
             ] // SAVE
         }
 
@@ -380,7 +390,7 @@ process {
                 enabled: enableOutput("normalize"),
                 mode: params.publish_dir_mode,
                 path: final_output,
-                saveAs: { filename -> filename.endsWith('.vcf.gz.tbi') ? "${meta.id}.${getGenotypedCaller(meta.caller)}.vcf.gz.tbi" : null }
+                saveAs: { filename -> filename.endsWith('.vcf.gz.tbi') ? filename.replaceAll(".normalized.vcf.gz.tbi\$", ".vcF.gz.tbi") : null }
             ] // SAVE
         }
     }
@@ -395,7 +405,7 @@ process {
 
         withName: "^.*:VCF_EXTRACT_RELATE_SOMALIER:SOMALIER_RELATE\$" {
             ext.args = { ped ? "" : "--infer"}
-            ext.prefix = { "${meta.sample ?: meta.id}.${getGenotypedCaller(meta.caller)}" }
+            ext.prefix = final_prefix
             publishDir = [
                 overwrite: true,
                 enabled: true,
@@ -416,14 +426,14 @@ process {
             }
 
             withName: "^.*:VCF_PED_RTGTOOLS:BCFTOOLS_ANNOTATE\$" {
-                ext.prefix = { "${meta.sample ?: meta.id}.${getGenotypedCaller(meta.caller)}.pedheader" }
+                ext.prefix = final_prefix
                 ext.args = "--output-type z"
                 publishDir = [
                     enabled: enableOutput("add_ped"),
                     overwrite: true,
                     path: final_output,
                     mode: params.publish_dir_mode,
-                    saveAs: { filename -> filename.equals('versions.yml') ? null : filename.replace(".pedheader", "") }
+                    saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
                 ] // SAVE
             }
         }
@@ -458,6 +468,7 @@ process {
                     (params.vep_spliceregion)   ? '--plugin SpliceRegion' : '',
                     (params.vep_mastermind)     ? "--plugin Mastermind,${params.mastermind.split('/')[-1]}" : '',
                     (params.vep_maxentscan)     ? "--plugin MaxEntScan" : '',
+                    (params.vep_alphamissense)  ? "--plugin AlphaMissense,file=${params.alphamissense.split('/')[-1]}" : '',
                     (params.vep_eog)            ? "--custom ${params.eog.split('/')[-1]},EOG,vcf,overlap,0,AF" : '',
                     (params.vep_merged)         ? '--merged' : '',
                 ].join(' ').trim()}
@@ -476,7 +487,7 @@ process {
                     mode: params.publish_dir_mode,
                     saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
                 ] // SAVE
-                ext.prefix = { "${meta.id}.${getGenotypedCaller(meta.caller)}" }
+                ext.prefix = final_prefix
             }
 
             if (params.vcfanno){
@@ -488,7 +499,7 @@ process {
                         mode: params.publish_dir_mode,
                         saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
                     ] // SAVE
-                    ext.prefix = { "${meta.id}.${getGenotypedCaller(meta.caller)}" }
+                    ext.prefix = final_prefix
                 }
             }
 
@@ -536,8 +547,9 @@ process {
         */
 
         if(params.gemini){
-            withName: VCF2DB{
-                ext.prefix = { "${meta.sample ?: meta.id}.${getGenotypedCaller(meta.caller)}" }
+            withName: "^.*:VCF2DB\$" {
+                ext.args = "--a-ok gnomAD_AC --a-ok gnomAD_Hom"
+                ext.prefix = final_prefix
                 publishDir = [
                     overwrite: true,
                     path: final_output,
@@ -547,13 +559,13 @@ process {
             }
         }
 
-        withName: TABIX_FINAL {
+        withName: "^.*:TABIX_FINAL\$" {
             publishDir = [
                 enabled: true,
                 overwrite: true,
                 path: final_output,
                 mode: params.publish_dir_mode,
-                saveAs: { filename -> filename.equals('versions.yml') ? null : "${meta.id}.${getGenotypedCaller(meta.caller)}.vcf.gz.tbi" }
+                saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
             ] // SAVE
         }
     }
@@ -568,17 +580,6 @@ process {
         cache = false
     }
 
-    withName: MULTIQC {
-        publishDir = [
-            overwrite: true,
-            path: { "${params.outdir}/multiqc_reports" },
-            mode: params.publish_dir_mode,
-            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
-        ] // SAVE => Fix the location problem
-        errorStrategy = {task.exitStatus == 143 ? 'retry' : 'ignore'}
-        ext.args      = { params.multiqc_config ? "--config $multiqc_custom_config" : "" }
-    }
-
     withName: 'MULTIQC' {
         ext.args   = params.multiqc_title ? "--title \"$params.multiqc_title\"" : ''
         publishDir = [

conf/seqplorer.config

@@ -5,19 +5,18 @@
 */
 
 params {
-    filter          = true
-    decompose       = true
-    normalize       = true
+    filter              = true
+    normalize           = true
+    gemini              = true
 
+    vcfanno             = true
     annotate            = true
-    vep_dbnsfp          = true
+    vep_merged          = true
     vep_spliceai        = true
     vep_mastermind      = true
     vep_eog             = true
     vep_maxentscan      = true
     vep_spliceregion    = true
 
-
-    gemini          = true
-
+    output_suffix       = "-gatk4-haplotype-joint-decomposed-annotated"
 }

conf/test.config

@@ -50,6 +50,6 @@ params {
     // VCFanno
     vcfanno           = true
     vcfanno_config    = "${projectDir}/assets/vcfanno.toml"
-    vcfanno_resources = "https://github.com/brentp/vcfanno/raw/master/example/exac.vcf.gz,https://github.com/brentp/vcfanno/raw/master/example/exac.vcf.gz.tbi"
+    vcfanno_resources = "https://github.com/brentp/vcfanno/raw/master/example/exac.vcf.gz;https://github.com/brentp/vcfanno/raw/master/example/exac.vcf.gz.tbi"
 
 }