New ensemblvep/download module (nf-core#2847)

* ensemblvep -> ensemblvep/vep + add ensemblvep/download

* update tags

* lint

* fix subworkflow tag

* update exclude matrix

* proper stub

.github/workflows/pytest-workflow.yml

@@ -54,7 +54,7 @@ jobs:
           - profile: "conda"
             tags: deepvariant
           - profile: "conda"
-            tags: ensemblvep
+            tags: ensemblvep/vep
           - profile: "conda"
             tags: fastk/fastk
           - profile: "conda"
@@ -81,6 +81,8 @@ jobs:
             tags: merquryfk/merquryfk
           - profile: "conda"
             tags: merquryfk/ploidyplot
+          - profile: "conda"
+            tags: subworkflows/vcf_annotate_ensemblvep
     env:
       NXF_ANSI_LOG: false
     steps:

modules/nf-core/ensemblvep/download/main.nf

@@ -0,0 +1,45 @@
+process ENSEMBLVEP_DOWNLOAD {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda "bioconda::ensembl-vep=108.2"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/ensembl-vep:108.2--pl5321h4a94de4_0' :
+        'quay.io/biocontainers/ensembl-vep:108.2--pl5321h4a94de4_0' }"
+
+    input:
+    tuple val(meta), val(assembly), val(species), val(cache_version)
+
+    output:
+    tuple val(meta), path("vep_cache"), emit: cache
+    path "versions.yml"               , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    """
+    vep_install \\
+        --CACHEDIR vep_cache \\
+        --SPECIES $species \\
+        --ASSEMBLY $assembly \\
+        --CACHE_VERSION $cache_version \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        ensemblvep: \$( echo \$(vep --help 2>&1) | sed 's/^.*Versions:.*ensembl-vep : //;s/ .*\$//')
+    END_VERSIONS
+    """
+
+    stub:
+    """
+    mkdir vep_cache
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        ensemblvep: \$( echo \$(vep --help 2>&1) | sed 's/^.*Versions:.*ensembl-vep : //;s/ .*\$//')
+    END_VERSIONS
+    """
+}

modules/nf-core/ensemblvep/download/meta.yml

@@ -0,0 +1,41 @@
+name: ENSEMBLVEP_DOWNLOAD
+description: Ensembl Variant Effect Predictor (VEP). The cache downloading options are controlled through `task.ext.args`.
+keywords:
+  - annotation
+tools:
+  - ensemblvep:
+      description: |
+        VEP determines the effect of your variants (SNPs, insertions, deletions, CNVs
+        or structural variants) on genes, transcripts, and protein sequence, as well as regulatory regions.
+      homepage: https://www.ensembl.org/info/docs/tools/vep/index.html
+      documentation: https://www.ensembl.org/info/docs/tools/vep/script/index.html
+      licence: ["Apache-2.0"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - assembly:
+      type: value
+      description: |
+        Genome assembly
+  - species:
+      type: value
+      description: |
+        Specie
+  - cache_version:
+      type: value
+      description: |
+        cache version
+output:
+  - cache:
+      type: file
+      description: cache
+      pattern: "*"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@maxulysse"

modules/nf-core/ensemblvep/main.nf → modules/nf-core/ensemblvep/vep/main.nf

@@ -1,4 +1,4 @@
-process ENSEMBLVEP {
+process ENSEMBLVEP_VEP {
     tag "$meta.id"
     label 'process_medium'
 

modules/nf-core/ensemblvep/meta.yml → modules/nf-core/ensemblvep/vep/meta.yml

@@ -1,4 +1,4 @@
-name: ENSEMBLVEP
+name: ENSEMBLVEP_VEP
 description: Ensembl Variant Effect Predictor (VEP). The output-file-format is controlled through `task.ext.args`.
 keywords:
   - annotation

subworkflows/nf-core/vcf_annotate_ensemblvep/main.nf

@@ -2,8 +2,8 @@
 // Run VEP to annotate VCF files
 //
 
-include { ENSEMBLVEP  } from '../../../modules/nf-core/ensemblvep/main'
-include { TABIX_TABIX } from '../../../modules/nf-core/tabix/tabix/main'
+include { ENSEMBLVEP_VEP } from '../../../modules/nf-core/ensemblvep/vep/main'
+include { TABIX_TABIX    } from '../../../modules/nf-core/tabix/tabix/main'
 
 workflow VCF_ANNOTATE_ENSEMBLVEP {
     take:
@@ -18,19 +18,19 @@ workflow VCF_ANNOTATE_ENSEMBLVEP {
     main:
     ch_versions = Channel.empty()
 
-    ENSEMBLVEP(vcf, vep_genome, vep_species, vep_cache_version, vep_cache, fasta, vep_extra_files)
-    TABIX_TABIX(ENSEMBLVEP.out.vcf)
+    ENSEMBLVEP_VEP(vcf, vep_genome, vep_species, vep_cache_version, vep_cache, fasta, vep_extra_files)
+    TABIX_TABIX(ENSEMBLVEP_VEP.out.vcf)
 
-    ch_vcf_tbi = ENSEMBLVEP.out.vcf.join(TABIX_TABIX.out.tbi)
+    ch_vcf_tbi = ENSEMBLVEP_VEP.out.vcf.join(TABIX_TABIX.out.tbi)
 
     // Gather versions of all tools used
-    ch_versions = ch_versions.mix(ENSEMBLVEP.out.versions)
+    ch_versions = ch_versions.mix(ENSEMBLVEP_VEP.out.versions)
     ch_versions = ch_versions.mix(TABIX_TABIX.out.versions)
 
     emit:
     vcf_tbi  = ch_vcf_tbi                  // channel: [ val(meta), vcf.gz, vcf.gz.tbi ]
-    json     = ENSEMBLVEP.out.json         // channel: [ val(meta), json ]
-    tab      = ENSEMBLVEP.out.tab          // channel: [ val(meta), tab ]
-    reports  = ENSEMBLVEP.out.report       //    path: *.html
-    versions = ch_versions                 //    path: versions.yml
+    json     = ENSEMBLVEP_VEP.out.json     // channel: [ val(meta), json ]
+    tab      = ENSEMBLVEP_VEP.out.tab      // channel: [ val(meta), tab ]
+    reports  = ENSEMBLVEP_VEP.out.report   // channel: [ *.html ]
+    versions = ch_versions                 // channel: [ versions.yml ]
 }

tests/config/pytest_modules.yml

@@ -931,9 +931,13 @@ endorspy:
   - modules/nf-core/endorspy/**
   - tests/modules/nf-core/endorspy/**
 
-ensemblvep:
-  - modules/nf-core/ensemblvep/**
-  - tests/modules/nf-core/ensemblvep/**
+ensemblvep/download:
+  - modules/nf-core/ensemblvep/download/**
+  - tests/modules/nf-core/ensemblvep/download/**
+
+ensemblvep/vep:
+  - modules/nf-core/ensemblvep/vep/**
+  - tests/modules/nf-core/ensemblvep/vep/**
 
 entrezdirect/esearch:
   - modules/nf-core/entrezdirect/esearch/**
@@ -3063,9 +3067,9 @@ subworkflows/homer/groseq:
   - subworkflows/nf-core/homer/groseq/**
   - tests/subworkflows/nf-core/homer/groseq/**
 
-subworkflows/vcf_annotate_ensembl_vep:
-  - subworkflows/nf-core/vcf_annotate_ensembl_vep/**
-  - tests/subworkflows/nf-core/vcf_annotate_ensembl_vep/**
+subworkflows/vcf_annotate_ensemblvep:
+  - subworkflows/nf-core/vcf_annotate_ensemblvep/**
+  - tests/subworkflows/nf-core/vcf_annotate_ensemblvep/**
 
 subworkflows/vcf_annotate_snpeff:
   - subworkflows/nf-core/vcf_annotate_snpeff/**

tests/modules/nf-core/ensemblvep/download/main.nf

@@ -0,0 +1,11 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { ENSEMBLVEP_DOWNLOAD } from '../../../../../modules/nf-core/ensemblvep/download/main.nf'
+
+workflow test_ensemblvep_download {
+    input = [[id:"test"], "WBcel235", "caenorhabditis_elegans", "108"]
+
+    ENSEMBLVEP_DOWNLOAD(input)
+}

tests/modules/nf-core/ensemblvep/download/nextflow.config

@@ -0,0 +1,9 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName: ENSEMBLVEP_DOWNLOAD {
+        ext.args = '--AUTO c --CONVERT --NO_BIOPERL --NO_HTSLIB --NO_TEST --NO_UPDATE'
+    }
+
+}

tests/modules/nf-core/ensemblvep/download/test.yml

@@ -0,0 +1,7 @@
+- name: ensemblvep test_ensemblvep_download
+  command: nextflow run ./tests/modules/nf-core/ensemblvep/download -entry test_ensemblvep_download -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/ensemblvep/download/nextflow.config
+  tags:
+    - ensemblvep
+    - ensemblvep/download
+  files:
+    - path: output/ensemblvep/vep_cache/caenorhabditis_elegans/108_WBcel235/

tests/modules/nf-core/ensemblvep/main.nf → tests/modules/nf-core/ensemblvep/vep/main.nf

@@ -2,85 +2,84 @@
 
 nextflow.enable.dsl = 2
 
-include { ENSEMBLVEP } from '../../../../modules/nf-core/ensemblvep/main.nf'
-
-include { ENSEMBLVEP as ENSEMBLVEP_JSON } from '../../../../modules/nf-core/ensemblvep/main.nf'
-include { ENSEMBLVEP as ENSEMBLVEP_TAB } from '../../../../modules/nf-core/ensemblvep/main.nf'
-include { ENSEMBLVEP as ENSEMBLVEP_VCF } from '../../../../modules/nf-core/ensemblvep/main.nf'
-include { ENSEMBLVEP as ENSEMBLVEP_VCF_BGZIP } from '../../../../modules/nf-core/ensemblvep/main.nf'
-include { ENSEMBLVEP as ENSEMBLVEP_VCF_GZIP  } from '../../../../modules/nf-core/ensemblvep/main.nf'
-
-workflow test_ensemblvep_fasta_json {
+include { ENSEMBLVEP_VEP as ENSEMBLVEP_VEP_DEFAULT   } from '../../../../../modules/nf-core/ensemblvep/vep/main.nf'
+include { ENSEMBLVEP_VEP as ENSEMBLVEP_VEP_JSON      } from '../../../../../modules/nf-core/ensemblvep/vep/main.nf'
+include { ENSEMBLVEP_VEP as ENSEMBLVEP_VEP_TAB       } from '../../../../../modules/nf-core/ensemblvep/vep/main.nf'
+include { ENSEMBLVEP_VEP as ENSEMBLVEP_VEP_VCF       } from '../../../../../modules/nf-core/ensemblvep/vep/main.nf'
+include { ENSEMBLVEP_VEP as ENSEMBLVEP_VEP_VCF_BGZIP } from '../../../../../modules/nf-core/ensemblvep/vep/main.nf'
+include { ENSEMBLVEP_VEP as ENSEMBLVEP_VEP_VCF_GZIP  } from '../../../../../modules/nf-core/ensemblvep/vep/main.nf'
+
+workflow test_ensemblvep_vep_fasta_json {
     input = [
         [ id:'test' ], // meta map
         file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true)
     ]
 
     fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
 
-    ENSEMBLVEP_JSON ( input, "WBcel235", "caenorhabditis_elegans", "108", [], fasta, [] )
+    ENSEMBLVEP_VEP_JSON ( input, "WBcel235", "caenorhabditis_elegans", "108", [], fasta, [] )
 }
 
-workflow test_ensemblvep_fasta_tab {
+workflow test_ensemblvep_vep_fasta_tab {
     input = [
         [ id:'test' ], // meta map
         file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true)
     ]
 
     fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
 
-    ENSEMBLVEP_TAB ( input, "WBcel235", "caenorhabditis_elegans", "108", [], fasta, [] )
+    ENSEMBLVEP_VEP_TAB ( input, "WBcel235", "caenorhabditis_elegans", "108", [], fasta, [] )
 }
 
-workflow test_ensemblvep_fasta_vcf {
+workflow test_ensemblvep_vep_fasta_vcf {
     input = [
         [ id:'test' ], // meta map
         file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true)
     ]
 
     fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
 
-    ENSEMBLVEP_VCF ( input, "WBcel235", "caenorhabditis_elegans", "108", [], fasta, [] )
+    ENSEMBLVEP_VEP_VCF ( input, "WBcel235", "caenorhabditis_elegans", "108", [], fasta, [] )
 }
 
-workflow test_ensemblvep_fasta_vcf_bgzip {
+workflow test_ensemblvep_vep_fasta_vcf_bgzip {
     input = [
         [ id:'test' ], // meta map
         file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true)
     ]
 
     fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
 
-    ENSEMBLVEP_VCF_BGZIP ( input, "WBcel235", "caenorhabditis_elegans", "108", [], fasta, [] )
+    ENSEMBLVEP_VEP_VCF_BGZIP ( input, "WBcel235", "caenorhabditis_elegans", "108", [], fasta, [] )
 }
 
-workflow test_ensemblvep_fasta_vcf_gzip {
+workflow test_ensemblvep_vep_fasta_vcf_gzip {
     input = [
         [ id:'test' ], // meta map
         file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true)
     ]
 
     fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
 
-    ENSEMBLVEP_VCF_GZIP ( input, "WBcel235", "caenorhabditis_elegans", "108", [], fasta, [] )
+    ENSEMBLVEP_VEP_VCF_GZIP ( input, "WBcel235", "caenorhabditis_elegans", "108", [], fasta, [] )
 }
 
-workflow test_ensemblvep_fasta {
+workflow test_ensemblvep_vep_fasta {
     input = [
         [ id:'test' ], // meta map
         file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true)
     ]
 
     fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
 
-    ENSEMBLVEP ( input, "WBcel235", "caenorhabditis_elegans", "108", [], fasta, [] )
+    ENSEMBLVEP_VEP_DEFAULT ( input, "WBcel235", "caenorhabditis_elegans", "108", [], fasta, [] )
 }
 
-workflow test_ensemblvep_no_fasta {
+workflow test_ensemblvep_vep_no_fasta {
     input = [
         [ id:'test' ], // meta map
         file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true)
     ]
 
-    ENSEMBLVEP ( input, "WBcel235", "caenorhabditis_elegans", "108", [], [], [] )
+    ENSEMBLVEP_VEP_DEFAULT ( input, "WBcel235", "caenorhabditis_elegans", "108", [], [], [] )
 }