Bump ensembl-vep modules to 110.0 (nf-core#3658)

* bump ensembl-vep to 110.0 * update tests * put conda tests back * update config for ENSEMBLVEP_DOWNLOAD * update tests for related subworkflows * fix path to module * enable conda tests back * better tests * fix tests * nicer channels * fix channel queue to value * fix syntax
JPejovicApis · Oct 10, 2023 · 3a96faf · 3a96faf
1 parent 3685123
commit 3a96faf
Show file tree

Hide file tree

Showing 11 changed files with 182 additions and 112 deletions.
diff --git a/.github/workflows/pytest-workflow.yml b/.github/workflows/pytest-workflow.yml
@@ -76,8 +76,6 @@ jobs:
             tags: deepcell/mesmer
           - profile: "conda"
             tags: deepvariant
-          - profile: "conda"
-            tags: ensemblvep/vep
           - profile: "conda"
             tags: fastk/fastk
           - profile: "conda"
@@ -150,8 +148,6 @@ jobs:
             tags: subworkflows/bcl_demultiplex
           - profile: "conda"
             tags: subworkflows/vcf_annotate_ensemblvep_snpeff
-          - profile: "conda"
-            tags: subworkflows/vcf_annotate_ensemblvep
           - profile: "conda"
             tags: subworkflows/fasta_clean_fcs
           - profile: "conda"

diff --git a/modules/nf-core/ensemblvep/download/main.nf b/modules/nf-core/ensemblvep/download/main.nf
@@ -2,10 +2,10 @@ process ENSEMBLVEP_DOWNLOAD {
     tag "$meta.id"
     label 'process_medium'
 
-    conda "bioconda::ensembl-vep=109.3"
+    conda "bioconda::ensembl-vep=110.0"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/ensembl-vep:109.3--pl5321h2a3209d_1' :
-        'biocontainers/ensembl-vep:109.3--pl5321h2a3209d_1' }"
+        'https://depot.galaxyproject.org/singularity/ensembl-vep:110.0--pl5321h2a3209d_0' :
+        'biocontainers/ensembl-vep:110.0--pl5321h2a3209d_0' }"
 
     input:
     tuple val(meta), val(assembly), val(species), val(cache_version)

diff --git a/modules/nf-core/ensemblvep/vep/main.nf b/modules/nf-core/ensemblvep/vep/main.nf
@@ -2,10 +2,10 @@ process ENSEMBLVEP_VEP {
     tag "$meta.id"
     label 'process_medium'
 
-    conda "bioconda::ensembl-vep=109.3"
+    conda "bioconda::ensembl-vep=110.0"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/ensembl-vep:109.3--pl5321h2a3209d_1' :
-        'biocontainers/ensembl-vep:109.3--pl5321h2a3209d_1' }"
+        'https://depot.galaxyproject.org/singularity/ensembl-vep:110.0--pl5321h2a3209d_0' :
+        'biocontainers/ensembl-vep:110.0--pl5321h2a3209d_0' }"
 
     input:
     tuple val(meta), path(vcf), path(custom_extra_files)

diff --git a/tests/modules/nf-core/ensemblvep/download/main.nf b/tests/modules/nf-core/ensemblvep/download/main.nf
@@ -2,10 +2,13 @@
 
 nextflow.enable.dsl = 2
 
-include { ENSEMBLVEP_DOWNLOAD } from '../../../../../modules/nf-core/ensemblvep/download/main.nf'
+include { ENSEMBLVEP_DOWNLOAD } from '../../../../../modules/nf-core/ensemblvep/download/main'
 
-workflow test_ensemblvep_download {
-    input = [[id:"test"], "WBcel235", "caenorhabditis_elegans", "108"]
+vep_cache_version = "110"
+vep_genome = "WBcel235"
+vep_species = "caenorhabditis_elegans"
+vep_cache_input = Channel.of([[id:"${vep_cache_version}_${vep_genome}"], vep_genome, vep_species, vep_cache_version])
 
-    ENSEMBLVEP_DOWNLOAD(input)
+workflow test_ensemblvep_download {
+    ENSEMBLVEP_DOWNLOAD(vep_cache_input)
 }
diff --git a/tests/modules/nf-core/ensemblvep/download/test.yml b/tests/modules/nf-core/ensemblvep/download/test.yml
@@ -4,4 +4,4 @@
     - ensemblvep
     - ensemblvep/download
   files:
-    - path: output/ensemblvep/vep_cache/caenorhabditis_elegans/108_WBcel235/
+    - path: output/ensemblvep/vep_cache/caenorhabditis_elegans/110_WBcel235/
diff --git a/tests/modules/nf-core/ensemblvep/vep/main.nf b/tests/modules/nf-core/ensemblvep/vep/main.nf
@@ -2,126 +2,164 @@
 
 nextflow.enable.dsl = 2
 
-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'
-include { ENSEMBLVEP_VEP as ENSEMBLVEP_VEP_CUSTOM    } from '../../../../../modules/nf-core/ensemblvep/vep/main.nf'
+include { ENSEMBLVEP_VEP as ENSEMBLVEP_VEP_DEFAULT   } from '../../../../../modules/nf-core/ensemblvep/vep/main'
+include { ENSEMBLVEP_VEP as ENSEMBLVEP_VEP_JSON      } from '../../../../../modules/nf-core/ensemblvep/vep/main'
+include { ENSEMBLVEP_VEP as ENSEMBLVEP_VEP_TAB       } from '../../../../../modules/nf-core/ensemblvep/vep/main'
+include { ENSEMBLVEP_VEP as ENSEMBLVEP_VEP_VCF       } from '../../../../../modules/nf-core/ensemblvep/vep/main'
+include { ENSEMBLVEP_VEP as ENSEMBLVEP_VEP_VCF_BGZIP } from '../../../../../modules/nf-core/ensemblvep/vep/main'
+include { ENSEMBLVEP_VEP as ENSEMBLVEP_VEP_VCF_GZIP  } from '../../../../../modules/nf-core/ensemblvep/vep/main'
+include { ENSEMBLVEP_VEP as ENSEMBLVEP_VEP_CUSTOM    } from '../../../../../modules/nf-core/ensemblvep/vep/main'
+include { ENSEMBLVEP_DOWNLOAD                        } from '../../../../../modules/nf-core/ensemblvep/download/main'
+
+vep_cache_version = "110"
+vep_genome = "WBcel235"
+vep_species = "caenorhabditis_elegans"
+vep_cache_input = Channel.of([[id:"${vep_cache_version}_${vep_genome}"], vep_genome, vep_species, vep_cache_version])
 
 workflow test_ensemblvep_vep_fasta_json {
-    input = [
+    input = Channel.of([
         [ id:'test' ], // meta map
         file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true),
         []
-    ]
+    ])
 
-    fasta = [
-        [ id: 'fasta' ],
+    fasta = Channel.value([
+        [id:"fasta"],
         file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
-    ]
+    ])
 
-    ENSEMBLVEP_VEP_JSON ( input, "WBcel235", "caenorhabditis_elegans", "108", [], fasta, [] )
+    ENSEMBLVEP_DOWNLOAD(vep_cache_input)
+
+    vep_cache = ENSEMBLVEP_DOWNLOAD.out.cache.map{ meta, cache -> [cache] }
+
+    ENSEMBLVEP_VEP_JSON ( input, vep_genome, vep_species, vep_cache_version, vep_cache, fasta, [] )
 }
 
 workflow test_ensemblvep_vep_fasta_tab {
-    input = [
+    input = Channel.of([
         [ id:'test' ], // meta map
         file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true),
         []
-    ]
+    ])
+
+    ENSEMBLVEP_DOWNLOAD(vep_cache_input)
+
+    vep_cache = ENSEMBLVEP_DOWNLOAD.out.cache.map{ meta, cache -> [cache] }
 
-    fasta = [
-        [ id: 'fasta' ],
+    fasta = Channel.value([
+        [id:"fasta"],
         file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
-    ]
+    ])
 
-    ENSEMBLVEP_VEP_TAB ( input, "WBcel235", "caenorhabditis_elegans", "108", [], fasta, [] )
+    ENSEMBLVEP_VEP_TAB ( input, vep_genome, vep_species, vep_cache_version, vep_cache, fasta, [] )
 }
 
 workflow test_ensemblvep_vep_fasta_vcf {
-    input = [
+    input = Channel.of([
         [ id:'test' ], // meta map
         file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true),
         []
-    ]
+    ])
 
-    fasta = [
-        [ id: 'fasta' ],
+    fasta = Channel.value([
+        [id:"fasta"],
         file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
-    ]
+    ])
 
-    ENSEMBLVEP_VEP_VCF ( input, "WBcel235", "caenorhabditis_elegans", "108", [], fasta, [] )
+    ENSEMBLVEP_DOWNLOAD(vep_cache_input)
+
+    vep_cache = ENSEMBLVEP_DOWNLOAD.out.cache.map{ meta, cache -> [cache] }
+
+    ENSEMBLVEP_VEP_VCF ( input, vep_genome, vep_species, vep_cache_version, vep_cache, fasta, [] )
 }
 
 workflow test_ensemblvep_vep_fasta_vcf_bgzip {
-    input = [
+    input = Channel.of([
         [ id:'test' ], // meta map
         file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true),
         []
-    ]
+    ])
 
-    fasta = [
-        [ id: 'fasta' ],
+    fasta = Channel.value([
+        [id:"fasta"],
         file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
-    ]
+    ])
+
+    ENSEMBLVEP_DOWNLOAD(vep_cache_input)
+
+    vep_cache = ENSEMBLVEP_DOWNLOAD.out.cache.map{ meta, cache -> [cache] }
 
-    ENSEMBLVEP_VEP_VCF_BGZIP ( input, "WBcel235", "caenorhabditis_elegans", "108", [], fasta, [] )
+    ENSEMBLVEP_VEP_VCF_BGZIP ( input, vep_genome, vep_species, vep_cache_version, vep_cache, fasta, [] )
 }
 
 workflow test_ensemblvep_vep_fasta_vcf_gzip {
-    input = [
+    input = Channel.of([
         [ id:'test' ], // meta map
         file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true),
         []
-    ]
+    ])
 
-    fasta = [
-        [ id: 'fasta' ],
+    fasta = Channel.value([
+        [id:"fasta"],
         file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
-    ]
+    ])
 
-    ENSEMBLVEP_VEP_VCF_GZIP ( input, "WBcel235", "caenorhabditis_elegans", "108", [], fasta, [] )
+    ENSEMBLVEP_DOWNLOAD(vep_cache_input)
+
+    vep_cache = ENSEMBLVEP_DOWNLOAD.out.cache.map{ meta, cache -> [cache] }
+
+    ENSEMBLVEP_VEP_VCF_GZIP ( input, vep_genome, vep_species, vep_cache_version, vep_cache, fasta, [] )
 }
 
 workflow test_ensemblvep_vep_fasta {
-    input = [
+    input = Channel.of([
         [ id:'test' ], // meta map
         file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true),
         []
-    ]
+    ])
 
-    fasta = [
-        [ id: 'fasta' ],
+    fasta = Channel.value([
+        [id:"fasta"],
         file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
-    ]
+    ])
+
+    ENSEMBLVEP_DOWNLOAD(vep_cache_input)
+
+    vep_cache = ENSEMBLVEP_DOWNLOAD.out.cache.map{ meta, cache -> [cache] }
 
-    ENSEMBLVEP_VEP_DEFAULT ( input, "WBcel235", "caenorhabditis_elegans", "108", [], fasta, [] )
+    ENSEMBLVEP_VEP_DEFAULT ( input, vep_genome, vep_species, vep_cache_version, vep_cache, fasta, [] )
 }
 
 workflow test_ensemblvep_vep_no_fasta {
-    input = [
+    input = Channel.of([
         [ id:'test' ], // meta map
         file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true),
         []
-    ]
+    ])
 
-    ENSEMBLVEP_VEP_DEFAULT ( input, "WBcel235", "caenorhabditis_elegans", "108", [], [[], []], [] )
+    ENSEMBLVEP_DOWNLOAD(vep_cache_input)
+
+    vep_cache = ENSEMBLVEP_DOWNLOAD.out.cache.map{ meta, cache -> [cache] }
+
+    ENSEMBLVEP_VEP_DEFAULT ( input, vep_genome, vep_species, vep_cache_version, vep_cache, [[], []], [] )
 }
 
 workflow test_ensemblvep_vep_fasta_custom {
-    input = [
+    input = Channel.of([
         [ id:'test' ], // meta map
         file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true),
             [ file(params.test_data['sarscov2']['illumina']['test2_vcf'], checkIfExists: true),
             file(params.test_data['sarscov2']['illumina']['test3_vcf'], checkIfExists: true)]
-    ]
+    ])
 
-    fasta = [
-        [ id: 'fasta' ],
+    fasta = Channel.value([
+        [id:"fasta"],
         file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
-    ]
+    ])
+
+    ENSEMBLVEP_DOWNLOAD(vep_cache_input)
+
+    vep_cache = ENSEMBLVEP_DOWNLOAD.out.cache.map{ meta, cache -> [cache] }
 
-    ENSEMBLVEP_VEP_VCF_BGZIP ( input, "WBcel235", "caenorhabditis_elegans", "108", [], fasta, [] )
+    ENSEMBLVEP_VEP_VCF_BGZIP ( input, vep_genome, vep_species, vep_cache_version, vep_cache, fasta, [] )
 }
diff --git a/tests/modules/nf-core/ensemblvep/vep/nextflow.config b/tests/modules/nf-core/ensemblvep/vep/nextflow.config
@@ -2,37 +2,31 @@ process {
 
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
 
-    withName: ENSEMBLVEP_VEP_DEFAULT {
-        container = 'docker.io/nfcore/vep:108.2.WBcel235'
+    withName: ENSEMBLVEP_DOWNLOAD {
+        ext.args = '--AUTO c --CONVERT --NO_BIOPERL --NO_HTSLIB --NO_TEST --NO_UPDATE'
     }
 
     withName: ENSEMBLVEP_VEP_JSON {
-        container = 'docker.io/nfcore/vep:108.2.WBcel235'
         ext.args = '--json'
     }
 
     withName: ENSEMBLVEP_VEP_TAB {
-        container = 'docker.io/nfcore/vep:108.2.WBcel235'
         ext.args = '--tab'
     }
 
     withName: ENSEMBLVEP_VEP_VCF {
-        container = 'docker.io/nfcore/vep:108.2.WBcel235'
         ext.args = '--vcf'
     }
 
     withName: ENSEMBLVEP_VEP_VCF_BGZIP {
-        container = 'docker.io/nfcore/vep:108.2.WBcel235'
         ext.args = '--vcf --compress_output bgzip'
     }
 
     withName: ENSEMBLVEP_VEP_VCF_GZIP {
-        container = 'docker.io/nfcore/vep:108.2.WBcel235'
         ext.args = '--vcf --compress_output gzip'
     }
 
     withName: ENSEMBLVEP_VEP_CUSTOM {
-        container = 'docker.io/nfcore/vep:108.2.WBcel235'
         ext.args = '--custom test2.vcf,,vcf,exact,0,TOPMED --custom test3.vcf,,vcf,exact,0,TOPMED'
     }
 }
diff --git a/tests/subworkflows/nf-core/vcf_annotate_ensemblvep/main.nf b/tests/subworkflows/nf-core/vcf_annotate_ensemblvep/main.nf
@@ -2,16 +2,26 @@
 
 nextflow.enable.dsl = 2
 
-include { VCF_ANNOTATE_ENSEMBLVEP as VCF_ANNOTATE_ENSEMBLVEP_DEFAULT } from '../../../../subworkflows/nf-core/vcf_annotate_ensemblvep/main.nf'
-include { VCF_ANNOTATE_ENSEMBLVEP as VCF_ANNOTATE_ENSEMBLVEP_CUSTOM  } from '../../../../subworkflows/nf-core/vcf_annotate_ensemblvep/main.nf'
+include { ENSEMBLVEP_DOWNLOAD                                        } from '../../../../modules/nf-core/ensemblvep/download/main'
+include { VCF_ANNOTATE_ENSEMBLVEP as VCF_ANNOTATE_ENSEMBLVEP_CUSTOM  } from '../../../../subworkflows/nf-core/vcf_annotate_ensemblvep/main'
+include { VCF_ANNOTATE_ENSEMBLVEP as VCF_ANNOTATE_ENSEMBLVEP_DEFAULT } from '../../../../subworkflows/nf-core/vcf_annotate_ensemblvep/main'
+
+vep_cache_version = "110"
+vep_genome = "WBcel235"
+vep_species = "caenorhabditis_elegans"
+vep_cache_input = Channel.of([[id:"${vep_cache_version}_${vep_genome}"], vep_genome, vep_species, vep_cache_version])
 
 workflow vcf_annotate_ensemblvep {
     input = Channel.of([
         [ id:'test' ], // meta map
         file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true), []
     ])
 
-    VCF_ANNOTATE_ENSEMBLVEP_DEFAULT ( input, [[],[]], "WBcel235", "caenorhabditis_elegans", "108", [], [] )
+    ENSEMBLVEP_DOWNLOAD(vep_cache_input)
+
+    vep_cache = ENSEMBLVEP_DOWNLOAD.out.cache.map{ meta, cache -> [cache] }
+
+    VCF_ANNOTATE_ENSEMBLVEP_DEFAULT ( input, [[],[]], vep_genome, vep_species, vep_cache_version, vep_cache, [] )
 }
 
 workflow vcf_annotate_ensemblvep_custom {
@@ -24,5 +34,9 @@ workflow vcf_annotate_ensemblvep_custom {
         ]
     ])
 
-    VCF_ANNOTATE_ENSEMBLVEP_CUSTOM ( input, [[],[]], "WBcel235", "caenorhabditis_elegans", "108", [], [] )
+    ENSEMBLVEP_DOWNLOAD(vep_cache_input)
+
+    vep_cache = ENSEMBLVEP_DOWNLOAD.out.cache.map{ meta, cache -> [cache] }
+
+    VCF_ANNOTATE_ENSEMBLVEP_CUSTOM ( input, [[],[]], vep_genome, vep_species, vep_cache_version, vep_cache, [] )
 }
diff --git a/tests/subworkflows/nf-core/vcf_annotate_ensemblvep/nextflow.config b/tests/subworkflows/nf-core/vcf_annotate_ensemblvep/nextflow.config
@@ -2,16 +2,16 @@ process {
 
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
 
-    withName: ENSEMBLVEP_VEP {
-        container = 'docker.io/nfcore/vep:108.2.WBcel235'
-    }
-
-    withName: vcf_annotate_ensemblvep_custom:VCF_ANNOTATE_ENSEMBLVEP_CUSTOM:ENSEMBLVEP_VEP {
-        ext.args   = '--custom test2.vcf,,vcf,exact,0,TOPMED --custom test3.vcf,,vcf,exact,0,TOPMED'
+    withName: ENSEMBLVEP_DOWNLOAD {
+        ext.args = '--AUTO c --CONVERT --NO_BIOPERL --NO_HTSLIB --NO_TEST --NO_UPDATE'
     }
 
     withName: TABIX_TABIX {
         ext.prefix = { "${meta.id}_vep.ann" }
     }
 
+    withName: vcf_annotate_ensemblvep_custom:VCF_ANNOTATE_ENSEMBLVEP_CUSTOM:ENSEMBLVEP_VEP {
+        ext.args   = '--custom test2.vcf,,vcf,exact,0,TOPMED --custom test3.vcf,,vcf,exact,0,TOPMED'
+    }
+
 }