update ensemblvep and snpeff modules

modules/ensemblvep/Dockerfile

@@ -8,13 +8,14 @@ LABEL \
 COPY environment.yml /
 RUN conda env create -f /environment.yml && conda clean -a
 
-# Add conda installation dir to PATH (instead of doing 'conda activate')
-ENV PATH /opt/conda/envs/nf-core-vep-104.3/bin:$PATH
-
 # Setup default ARG variables
 ARG GENOME=GRCh38
 ARG SPECIES=homo_sapiens
-ARG VEP_VERSION=99
+ARG VEP_VERSION=104
+ARG VEP_TAG=104.3
+
+# Add conda installation dir to PATH (instead of doing 'conda activate')
+ENV PATH /opt/conda/envs/nf-core-vep-${VEP_TAG}/bin:$PATH
 
 # Download Genome
 RUN vep_install \
@@ -27,4 +28,4 @@ RUN vep_install \
     --NO_BIOPERL --NO_HTSLIB --NO_TEST --NO_UPDATE
 
 # Dump the details of the installed packages to a file for posterity
-RUN conda env export --name nf-core-vep-104.3 > nf-core-vep-104.3.yml
+RUN conda env export --name nf-core-vep-${VEP_TAG} > nf-core-vep-${VEP_TAG}.yml

modules/ensemblvep/build.sh

@@ -10,11 +10,12 @@ build_push() {
     VEP_TAG=$4
 
     docker build \
+        . \
         -t nfcore/vep:${VEP_TAG}.${GENOME} \
-        software/vep/. \
         --build-arg GENOME=${GENOME} \
         --build-arg SPECIES=${SPECIES} \
-        --build-arg VEP_VERSION=${VEP_VERSION}
+        --build-arg VEP_VERSION=${VEP_VERSION} \
+        --build-arg VEP_TAG=${VEP_TAG}
 
     docker push nfcore/vep:${VEP_TAG}.${GENOME}
 }

modules/ensemblvep/main.nf

@@ -13,6 +13,7 @@ process ENSEMBLVEP {
     val   species
     val   cache_version
     path  cache
+    path  extra_files
 
     output:
     tuple val(meta), path("*.ann.vcf"), emit: vcf

modules/ensemblvep/meta.yml

@@ -10,17 +10,6 @@ tools:
       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"]
-params:
-  - use_cache:
-      type: boolean
-      description: |
-        Enable the usage of containers with cache
-        Does not work with conda
-  - vep_tag:
-      type: value
-      description: |
-        Specify the tag for the container
-        https://hub.docker.com/r/nfcore/vep/tags
 input:
   - meta:
       type: map
@@ -47,6 +36,10 @@ input:
       type: file
       description: |
         path to VEP cache (optional)
+  - extra_files:
+      type: tuple
+      description: |
+        path to file(s) needed for plugins  (optional)
 output:
   - vcf:
       type: file

modules/snpeff/Dockerfile

@@ -8,15 +8,16 @@ LABEL \
 COPY environment.yml /
 RUN conda env create -f /environment.yml && conda clean -a
 
-# Add conda installation dir to PATH (instead of doing 'conda activate')
-ENV PATH /opt/conda/envs/nf-core-snpeff-5.0/bin:$PATH
-
 # Setup default ARG variables
 ARG GENOME=GRCh38
 ARG SNPEFF_CACHE_VERSION=99
+ARG SNPEFF_TAG=99
+
+# Add conda installation dir to PATH (instead of doing 'conda activate')
+ENV PATH /opt/conda/envs/nf-core-snpeff-${SNPEFF_TAG}/bin:$PATH
 
 # Download Genome
 RUN snpEff download -v ${GENOME}.${SNPEFF_CACHE_VERSION}
 
 # Dump the details of the installed packages to a file for posterity
-RUN conda env export --name nf-core-snpeff-5.0 > nf-core-snpeff-5.0.yml
+RUN conda env export --name nf-core-snpeff-${SNPEFF_TAG} > nf-core-snpeff-${SNPEFF_TAG}.yml

modules/snpeff/build.sh

@@ -9,10 +9,11 @@ build_push() {
     SNPEFF_TAG=$3
 
     docker build \
+        . \
         -t nfcore/snpeff:${SNPEFF_TAG}.${GENOME} \
-        software/snpeff/. \
         --build-arg GENOME=${GENOME} \
-        --build-arg SNPEFF_CACHE_VERSION=${SNPEFF_CACHE_VERSION}
+        --build-arg SNPEFF_CACHE_VERSION=${SNPEFF_CACHE_VERSION} \
+        --build-arg SNPEFF_TAG=${SNPEFF_TAG}
 
     docker push nfcore/snpeff:${SNPEFF_TAG}.${GENOME}
 }

modules/snpeff/meta.yml

@@ -10,18 +10,6 @@ tools:
       homepage: https://pcingola.github.io/SnpEff/
       documentation: https://pcingola.github.io/SnpEff/se_introduction/
       licence: ["MIT"]
-params:
-  - use_cache:
-      type: boolean
-      description: |
-        boolean to enable the usage of containers with cache
-        Enable the usage of containers with cache
-        Does not work with conda
-  - snpeff_tag:
-      type: value
-      description: |
-        Specify the tag for the container
-        https://hub.docker.com/r/nfcore/snpeff/tags
 input:
   - meta:
       type: map

subworkflows/nf-core/annotation/ensemblvep/main.nf

@@ -0,0 +1,31 @@
+//
+// Run VEP to annotate VCF files
+//
+
+include { ENSEMBLVEP       } from '../../../../modules/ensemblvep/main'
+include { TABIX_BGZIPTABIX } from '../../../../modules/tabix/bgziptabix/main'
+
+workflow ANNOTATION_ENSEMBLVEP {
+    take:
+    vcf               // channel: [ val(meta), vcf ]
+    vep_genome        //   value: genome to use
+    vep_species       //   value: species to use
+    vep_cache_version //   value: cache version to use
+    vep_cache         //    path: /path/to/vep/cache (optionnal)
+    vep_extra_files   // channel: [ file1, file2...] (optionnal)
+
+    main:
+    ch_versions = Channel.empty()
+
+    ENSEMBLVEP(vcf, vep_genome, vep_species, vep_cache_version, vep_cache, vep_extra_files)
+    TABIX_BGZIPTABIX(ENSEMBLVEP.out.vcf)
+
+    // Gather versions of all tools used
+    ch_versions = ch_versions.mix(ENSEMBLVEP.out.versions.first())
+    ch_versions = ch_versions.mix(TABIX_BGZIPTABIX.out.versions.first())
+
+    emit:
+    vcf_tbi  = TABIX_BGZIPTABIX.out.gz_tbi // channel: [ val(meta), vcf.gz, vcf.gz.tbi ]
+    reports  = ENSEMBLVEP.out.report       //    path: *.html
+    versions = ch_versions                 //    path: versions.yml
+}

subworkflows/nf-core/annotation/ensemblvep/meta.yml

@@ -0,0 +1,49 @@
+name: annotation_ensemblvep
+description: |
+  Perform annotation with ensemblvep and bgzip + tabix index the resulting VCF file
+keywords:
+  - ensemblvep
+modules:
+  - ensemblvep
+  - tabix/bgziptabix
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - vcf:
+      type: file
+      description: |
+        vcf to annotate
+  - genome:
+      type: value
+      description: |
+        which genome to annotate with
+  - species:
+      type: value
+      description: |
+        which species to annotate with
+  - cache_version:
+      type: value
+      description: |
+        which version of the cache to annotate with
+  - cache:
+      type: file
+      description: |
+        path to VEP cache (optional)
+  - extra_files:
+      type: tuple
+      description: |
+        path to file(s) needed for plugins  (optional)
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - vcf_tbi:
+      type: file
+      description: Compressed vcf file + tabix index
+      pattern: "[ *{.vcf.gz,vcf.gz.tbi} ]"
+authors:
+  - "@maxulysse"

subworkflows/nf-core/annotation/snpeff/main.nf

@@ -0,0 +1,28 @@
+//
+// Run SNPEFF to annotate VCF files
+//
+
+include { SNPEFF           } from '../../../../modules/snpeff/main'
+include { TABIX_BGZIPTABIX } from '../../../../modules/tabix/bgziptabix/main'
+
+workflow ANNOTATION_SNPEFF {
+    take:
+    vcf          // channel: [ val(meta), vcf ]
+    snpeff_db    //   value: db version to use
+    snpeff_cache //    path: /path/to/snpeff/cache (optionnal)
+
+    main:
+    ch_versions = Channel.empty()
+
+    SNPEFF(vcf, snpeff_db, snpeff_cache)
+    TABIX_BGZIPTABIX(SNPEFF.out.vcf)
+
+    // Gather versions of all tools used
+    ch_versions = ch_versions.mix(SNPEFF.out.versions.first())
+    ch_versions = ch_versions.mix(TABIX_BGZIPTABIX.out.versions.first())
+
+    emit:
+    vcf_tbi  = TABIX_BGZIPTABIX.out.gz_tbi // channel: [ val(meta), vcf.gz, vcf.gz.tbi ]
+    reports  = SNPEFF.out.report           //    path: *.html
+    versions = ch_versions                 //    path: versions.yml
+}

subworkflows/nf-core/annotation/snpeff/meta.yml

@@ -11,11 +11,19 @@ input:
       type: map
       description: |
         Groovy Map containing sample information
-        e.g. [ id:'test' ]
-  - input:
-      type: vcf
-      description: list containing one vcf file
-      pattern: "[ *.{vcf,vcf.gz} ]"
+        e.g. [ id:'test', single_end:false ]
+  - vcf:
+      type: file
+      description: |
+        vcf to annotate
+  - db:
+      type: value
+      description: |
+        which db to annotate with
+  - cache:
+      type: file
+      description: |
+        path to snpEff cache (optional)
 output:
   - versions:
       type: file

subworkflows/nf-core/annotation_ensemblvep/main.nf

@@ -1,26 +0,0 @@
-//
-// Run VEP to annotate VCF files
-//
-
-include { ENSEMBLVEP                                } from '../../../modules/ensemblvep/main'
-include { TABIX_BGZIPTABIX as ANNOTATION_BGZIPTABIX } from '../../../modules/tabix/bgziptabix/main'
-
-workflow ANNOTATION_ENSEMBLVEP {
-    take:
-    vcf               // channel: [ val(meta), vcf ]
-    vep_genome        //   value: which genome
-    vep_species       //   value: which species
-    vep_cache_version //   value: which cache version
-    vep_cache         //    path: path_to_vep_cache (optionnal)
-
-    main:
-    ENSEMBLVEP(vcf, vep_genome, vep_species, vep_cache_version, vep_cache)
-    ANNOTATION_BGZIPTABIX(ENSEMBLVEP.out.vcf)
-
-    ch_versions = ENSEMBLVEP.out.versions.first().mix(ANNOTATION_BGZIPTABIX.out.versions.first())
-
-    emit:
-    vcf_tbi  = ANNOTATION_BGZIPTABIX.out.gz_tbi // channel: [ val(meta), vcf.gz, vcf.gz.tbi ]
-    reports  = ENSEMBLVEP.out.report            //    path: *.html
-    versions = ch_versions                      //    path: versions.yml
-}

subworkflows/nf-core/annotation_ensemblvep/meta.yml

@@ -1,29 +0,0 @@
-name: annotation_ensemblvep
-description: |
-  Perform annotation with ensemblvep and bgzip + tabix index the resulting VCF file
-keywords:
-  - ensemblvep
-modules:
-  - ensemblvep
-  - tabix/bgziptabix
-input:
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. [ id:'test' ]
-  - input:
-      type: vcf
-      description: list containing one vcf file
-      pattern: "[ *.{vcf,vcf.gz} ]"
-output:
-  - versions:
-      type: file
-      description: File containing software versions
-      pattern: "versions.yml"
-  - vcf_tbi:
-      type: file
-      description: Compressed vcf file + tabix index
-      pattern: "[ *{.vcf.gz,vcf.gz.tbi} ]"
-authors:
-  - "@maxulysse"

subworkflows/nf-core/annotation_snpeff/main.nf

@@ -1,23 +0,0 @@
-//
-// Run SNPEFF to annotate VCF files
-//
-
-include { SNPEFF                                    } from '../../../modules/snpeff/main'
-include { TABIX_BGZIPTABIX as ANNOTATION_BGZIPTABIX } from '../../../modules/tabix/bgziptabix/main'
-
-workflow ANNOTATION_SNPEFF {
-    take:
-    vcf            // channel: [ val(meta), vcf ]
-    snpeff_db      //   value: version of db to use
-    snpeff_cache   //    path: path_to_snpeff_cache (optionnal)
-
-    main:
-    SNPEFF(vcf, snpeff_db, snpeff_cache)
-    ANNOTATION_BGZIPTABIX(SNPEFF.out.vcf)
-    ch_versions = SNPEFF.out.versions.first().mix(ANNOTATION_BGZIPTABIX.out.versions.first())
-
-    emit:
-    vcf_tbi  = ANNOTATION_BGZIPTABIX.out.gz_tbi // channel: [ val(meta), vcf.gz, vcf.gz.tbi ]
-    reports  = SNPEFF.out.report                //    path: *.html
-    versions = ch_versions                      //    path: versions.yml
-}

tests/modules/ensemblvep/main.nf

@@ -10,5 +10,5 @@ workflow test_ensemblvep {
         file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true)
     ]
 
-    ENSEMBLVEP ( input, "WBcel235", "caenorhabditis_elegans", "104", [] )
+    ENSEMBLVEP ( input, "WBcel235", "caenorhabditis_elegans", "104", [], [] )
 }

tests/subworkflows/nf-core/annotation/ensemblvep/main.nf

@@ -2,7 +2,7 @@
 
 nextflow.enable.dsl = 2
 
-include { ANNOTATION_ENSEMBLVEP } from '../../../../subworkflows/nf-core/annotation_ensemblvep/main'
+include { ANNOTATION_ENSEMBLVEP } from '../../../../../subworkflows/nf-core/annotation/ensemblvep/main'
 
 workflow annotation_ensemblvep {
     input = [
@@ -10,5 +10,5 @@ workflow annotation_ensemblvep {
         file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true)
     ]
 
-    ANNOTATION_ENSEMBLVEP ( input, "WBcel235", "caenorhabditis_elegans", "104", [] )
+    ANNOTATION_ENSEMBLVEP ( input, "WBcel235", "caenorhabditis_elegans", "104", [], [] )
 }

tests/subworkflows/nf-core/annotation/ensemblvep/nextflow.config

@@ -7,7 +7,7 @@ process {
         publishDir = [ enabled: false ]
     }
 
-    withName: ANNOTATION_BGZIPTABIX {
+    withName: TABIX_BGZIPTABIX {
         ext.prefix = { "${meta.id}_VEP.ann.vcf" }
     }
 

tests/subworkflows/nf-core/annotation/snpeff/main.nf

@@ -2,7 +2,7 @@
 
 nextflow.enable.dsl = 2
 
-include { ANNOTATION_SNPEFF } from '../../../../subworkflows/nf-core/annotation_snpeff/main'
+include { ANNOTATION_SNPEFF } from '../../../../../subworkflows/nf-core/annotation_snpeff/main'
 
 workflow annotation_snpeff {
     input = [

tests/subworkflows/nf-core/annotation/snpeff/nextflow.config

@@ -7,7 +7,7 @@ process {
         publishDir = [ enabled: false ]
     }
 
-    withName: ANNOTATION_BGZIPTABIX {
+    withName: TABIX_BGZIPTABIX {
         ext.prefix = { "${meta.id}_snpEff.ann.vcf" }
     }