Optional output from the VEP-moduel (#1775)

* Making the output from the VEP-moduel (ENSEMBLVEP) optionally vcf, json or tab. #1774

* Trying to fix tests

* Still trying to fix tests

* Fetching the vep-output-file-extension from the args.

* Update meta.yml

* WIP: Adding tests for vep-output json and tab

* updated the test.yml

Co-authored-by: nvnieuwk <101190534+nvnieuwk@users.noreply.github.com>
Co-authored-by: nvnieuwk <nicolas.vannieuwkerke@ugent.be>

modules/ensemblvep/main.nf

@@ -17,7 +17,9 @@ process ENSEMBLVEP {
     path  extra_files
 
     output:
-    tuple val(meta), path("*.ann.vcf"), emit: vcf
+    tuple val(meta), path("*.ann.vcf")  , optional:true, emit: vcf
+    tuple val(meta), path("*.ann.tab")  , optional:true, emit: tab
+    tuple val(meta), path("*.ann.json") , optional:true, emit: json
     path "*.summary.html"               , emit: report
     path "versions.yml"                 , emit: versions
 
@@ -26,16 +28,15 @@ process ENSEMBLVEP {
 
     script:
     def args = task.ext.args ?: ''
+    def file_extension = args.contains("--vcf") ? 'vcf' : args.contains("--json")? 'json' : args.contains("--tab")? 'tab' : 'vcf'
     def prefix = task.ext.prefix ?: "${meta.id}"
     def dir_cache = cache ? "\${PWD}/${cache}" : "/.vep"
     def reference = fasta ? "--fasta $fasta" : ""
 
     """
-    mkdir $prefix
-
     vep \\
         -i $vcf \\
-        -o ${prefix}.ann.vcf \\
+        -o ${prefix}.ann.${file_extension} \\
         $args \\
         $reference \\
         --assembly $genome \\
@@ -44,10 +45,8 @@ process ENSEMBLVEP {
         --cache_version $cache_version \\
         --dir_cache $dir_cache \\
         --fork $task.cpus \\
-        --vcf \\
+        --stats_file ${prefix}.summary.html \\
-        --stats_file ${prefix}.summary.html
 
-    rm -rf $prefix
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/ensemblvep/meta.yml

@@ -1,5 +1,5 @@
 name: ENSEMBLVEP
-description: Ensembl Variant Effect Predictor (VEP)
+description: Ensembl Variant Effect Predictor (VEP). The output-file-format is controlled through `task.ext.args`.
 keywords:
   - annotation
 tools:
@@ -49,8 +49,18 @@ output:
   - vcf:
       type: file
       description: |
-        annotated vcf
+        annotated vcf (optional)
       pattern: "*.ann.vcf"
+  - tab:
+      type: file
+      description: |
+        tab file with annotated variants (optional)
+      pattern: "*.ann.tab"
+  - json:
+      type: file
+      description: |
+        json file with annotated variants (optional)
+      pattern: "*.ann.json"
   - report:
       type: file
       description: VEP report file

tests/modules/ensemblvep/main.nf

@@ -4,6 +4,43 @@ nextflow.enable.dsl = 2
 
 include { ENSEMBLVEP } from '../../../modules/ensemblvep/main.nf'
 
+include { ENSEMBLVEP as ENSEMBLVEP_JSON } from '../../../modules/ensemblvep/main.nf'
+include { ENSEMBLVEP as ENSEMBLVEP_TAB } from '../../../modules/ensemblvep/main.nf'
+include { ENSEMBLVEP as ENSEMBLVEP_VCF } from '../../../modules/ensemblvep/main.nf'
+
+workflow test_ensemblvep_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", "104", [], fasta, [] )
+}
+
+workflow test_ensemblvep_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", "104", [], fasta, [] )
+}
+
+workflow test_ensemblvep_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", "104", [], fasta, [] )
+}
+
 workflow test_ensemblvep_fasta {
     input = [
         [ id:'test' ], // meta map

tests/modules/ensemblvep/nextflow.config

@@ -6,4 +6,18 @@ process {
         container = 'nfcore/vep:104.3.WBcel235'
     }
 
+    withName: ENSEMBLVEP_JSON {
+        container = 'nfcore/vep:104.3.WBcel235'
+        ext.args = '--json'
+    }
+
+    withName: ENSEMBLVEP_TAB {
+        container = 'nfcore/vep:104.3.WBcel235'
+        ext.args = '--tab'
+    }
+
+    withName: ENSEMBLVEP_VCF {
+        container = 'nfcore/vep:104.3.WBcel235'
+        ext.args = '--vcf'
+    }
 }

tests/modules/ensemblvep/test.yml

@@ -1,3 +1,27 @@
+- name: ensemblvep test_ensemblvep_fasta_json
+  command: nextflow run ./tests/modules/ensemblvep -entry test_ensemblvep_fasta_json -c ./tests/config/nextflow.config  -c ./tests/modules/ensemblvep/nextflow.config
+  tags:
+    - ensemblvep
+  files:
+    - path: output/ensemblvep/test.ann.json
+    - path: output/ensemblvep/test.summary.html
+
+- name: ensemblvep test_ensemblvep_fasta_tab
+  command: nextflow run ./tests/modules/ensemblvep -entry test_ensemblvep_fasta_tab -c ./tests/config/nextflow.config  -c ./tests/modules/ensemblvep/nextflow.config
+  tags:
+    - ensemblvep
+  files:
+    - path: output/ensemblvep/test.ann.tab
+    - path: output/ensemblvep/test.summary.html
+
+- name: ensemblvep test_ensemblvep_fasta_vcf
+  command: nextflow run ./tests/modules/ensemblvep -entry test_ensemblvep_fasta_vcf -c ./tests/config/nextflow.config  -c ./tests/modules/ensemblvep/nextflow.config
+  tags:
+    - ensemblvep
+  files:
+    - path: output/ensemblvep/test.ann.vcf
+    - path: output/ensemblvep/test.summary.html
+
 - name: ensemblvep test_ensemblvep_fasta
   command: nextflow run ./tests/modules/ensemblvep -entry test_ensemblvep_fasta -c ./tests/config/nextflow.config  -c ./tests/modules/ensemblvep/nextflow.config
   tags: