update for bcftools merge (#1908)

* update for bcftools merge

* Update modules/bcftools/merge/main.nf

Co-authored-by: Maxime U. Garcia <maxime.garcia@scilifelab.se>

* Update modules/bcftools/merge/main.nf

Co-authored-by: Maxime U. Garcia <maxime.garcia@scilifelab.se>

* updated test.yml

* added the bed file to the main input tuple

* merged all output into one output channel

* added a test for bcf.gz output

* Update modules/bcftools/merge/main.nf

Co-authored-by: Matthias De Smet <11850640+matthdsm@users.noreply.github.com>

* updated the tests

Co-authored-by: Maxime U. Garcia <maxime.garcia@scilifelab.se>
Co-authored-by: Matthias De Smet <11850640+matthdsm@users.noreply.github.com>

modules/bcftools/convert/meta.yml

@@ -53,10 +53,22 @@ output:
       type: file
       description: File containing software versions
       pattern: "versions.yml"
+  - vcf_gz:
+      type: file
+      description: VCF merged output file (bgzipped) => when `--output-type z` is used
+      pattern: "*.vcf.gz"
   - vcf:
       type: file
-      description: The converted VCF file
-      pattern: "*.{bam,cram,sam}"
+      description: VCF merged output file => when `--output-type v` is used
+      pattern: "*.vcf"
+  - bcf_gz:
+      type: file
+      description: BCF merged output file (bgzipped) => when `--output-type b` is used
+      pattern: "*.bcf.gz"
+  - bcf:
+      type: file
+      description: BCF merged output file => when `--output-type u` is used
+      pattern: "*.bcf"
 
 authors:
   - "@nvnieuwk"

modules/bcftools/merge/main.nf

@@ -9,22 +9,35 @@ process BCFTOOLS_MERGE {
 
     input:
     tuple val(meta), path(vcfs), path(tbis)
+    path bed
+    path fasta
+    path fasta_fai
 
     output:
-    tuple val(meta), path("*.gz"), emit: vcf
-    path  "versions.yml"         , emit: versions
+    tuple val(meta), path("*.{bcf,vcf}{,.gz}"), emit: merged_variants
+    path "versions.yml"                       , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
 
     script:
     def args = task.ext.args   ?: ''
-    prefix   = task.ext.prefix ?: "${meta.id}"
+    def prefix   = task.ext.prefix ?: "${meta.id}"
+
+    def regions = bed ? "--regions-file $bed" : ""
+    def extension = args.contains("--output-type b") || args.contains("-Ob") ? "bcf.gz" :
+                    args.contains("--output-type u") || args.contains("-Ou") ? "bcf" :
+                    args.contains("--output-type v") || args.contains("-Ov") ? "vcf" :
+                    "vcf.gz"
+
     """
-    bcftools merge -Oz \\
-        --output ${prefix}.vcf.gz \\
+    bcftools merge \\
+        $regions \\
+        --threads $task.cpus \\
+        --output ${prefix}.${extension} \\
         $args \\
         *.vcf.gz
+
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
         bcftools: \$(bcftools --version 2>&1 | head -n1 | sed 's/^.*bcftools //; s/ .*\$//')

modules/bcftools/merge/meta.yml

@@ -28,16 +28,40 @@ input:
       description: |
         List containing the tbi index files corresponding to the vcfs input files
         e.g. [ 'file1.vcf.tbi', 'file2.vcf.tbi' ]
+  - bed:
+      type: file
+      description: "(Optional) The bed regions to merge on"
+      pattern: "*.bed"
+  - fasta:
+      type: file
+      description: "(Optional) The fasta reference file (only necessary for the `--gvcf FILE` parameter)"
+      pattern: "*.{fasta,fa}"
+  - fasta:
+      type: file
+      description: "(Optional) The fasta reference file index (only necessary for the `--gvcf FILE` parameter)"
+      pattern: "*.fai"
 output:
   - meta:
       type: map
       description: |
         Groovy Map containing sample information
         e.g. [ id:'test', single_end:false ]
+  - vcf_gz:
+      type: file
+      description: VCF merged output file (bgzipped) => when `--output-type z` is used
+      pattern: "*.vcf.gz"
   - vcf:
       type: file
-      description: VCF merged output file
-      pattern: "*.{vcf.gz}"
+      description: VCF merged output file => when `--output-type v` is used
+      pattern: "*.vcf"
+  - bcf_gz:
+      type: file
+      description: BCF merged output file (bgzipped) => when `--output-type b` is used
+      pattern: "*.bcf.gz"
+  - bcf:
+      type: file
+      description: BCF merged output file => when `--output-type u` is used
+      pattern: "*.bcf"
   - versions:
       type: file
       description: File containing software versions
@@ -45,3 +69,4 @@ output:
 authors:
   - "@joseespinosa"
   - "@drpatelh"
+  - "@nvnieuwk"

tests/modules/bcftools/merge/main.nf

@@ -3,7 +3,9 @@
 nextflow.enable.dsl = 2
 
 //keep --no-verson argument, otherwise md5 will change on each execution
-include { BCFTOOLS_MERGE } from '../../../../modules/bcftools/merge/main.nf'
+include { BCFTOOLS_MERGE                        } from '../../../../modules/bcftools/merge/main.nf'
+include { BCFTOOLS_MERGE as BCFTOOLS_MERGE_GVCF } from '../../../../modules/bcftools/merge/main.nf'
+include { BCFTOOLS_MERGE as BCFTOOLS_MERGE_BCF  } from '../../../../modules/bcftools/merge/main.nf'
 
 workflow test_bcftools_merge {
     input = [ [ id:'test' ], // meta map
@@ -13,5 +15,54 @@ workflow test_bcftools_merge {
                 file(params.test_data['sarscov2']['illumina']['test3_vcf_gz_tbi'], checkIfExists: true) ]
             ]
 
-    BCFTOOLS_MERGE ( input )
+    bed = []
+    fasta = []
+    fasta_fai = []
+
+    BCFTOOLS_MERGE ( input, bed, fasta, fasta_fai )
+}
+
+workflow test_bcftools_merge_bed {
+    input = [ [ id:'test' ], // meta map
+              [ file(params.test_data['sarscov2']['illumina']['test2_vcf_gz'], checkIfExists: true),
+                file(params.test_data['sarscov2']['illumina']['test3_vcf_gz'], checkIfExists: true) ],
+              [ file(params.test_data['sarscov2']['illumina']['test2_vcf_gz_tbi'], checkIfExists: true),
+                file(params.test_data['sarscov2']['illumina']['test3_vcf_gz_tbi'], checkIfExists: true) ]
+            ]
+
+    bed = file(params.test_data['sarscov2']['genome']['test_bed'], checkIfExists: true)
+    fasta = []
+    fasta_fai = []
+
+    BCFTOOLS_MERGE ( input, bed, fasta, fasta_fai )
+}
+
+workflow test_bcftools_merge_gvcf {
+    input = [ [ id:'test' ], // meta map
+              [ file(params.test_data['homo_sapiens']['illumina']['test_genome_vcf_gz'], checkIfExists: true),
+                file(params.test_data['homo_sapiens']['illumina']['test_genome_vcf_gz_tbi'], checkIfExists: true) ],
+              [ file(params.test_data['homo_sapiens']['illumina']['test2_genome_vcf_gz'], checkIfExists: true),
+                file(params.test_data['homo_sapiens']['illumina']['test2_genome_vcf_gz_tbi'], checkIfExists: true) ]
+            ]
+
+    bed = []
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    fasta_fai = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+
+    BCFTOOLS_MERGE_GVCF ( input, bed, fasta, fasta_fai )
+}
+
+workflow test_bcftools_merge_bcf {
+    input = [ [ id:'test' ], // meta map
+              [ file(params.test_data['sarscov2']['illumina']['test2_vcf_gz'], checkIfExists: true),
+                file(params.test_data['sarscov2']['illumina']['test3_vcf_gz'], checkIfExists: true) ],
+              [ file(params.test_data['sarscov2']['illumina']['test2_vcf_gz_tbi'], checkIfExists: true),
+                file(params.test_data['sarscov2']['illumina']['test3_vcf_gz_tbi'], checkIfExists: true) ]
+            ]
+
+    bed = []
+    fasta = []
+    fasta_fai = []
+
+    BCFTOOLS_MERGE_BCF ( input, bed, fasta, fasta_fai )
 }

tests/modules/bcftools/merge/nextflow.config

@@ -3,7 +3,15 @@ process {
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
 
     withName: BCFTOOLS_MERGE {
-        ext.args = '--force-samples --no-version'
+        ext.args = '--force-samples --no-version --output-type z'
+    }
+
+    withName: BCFTOOLS_MERGE_GVCF {
+        ext.args = {"--force-samples --no-version -m none --output-type z --gvcf $fasta"}
+    }
+
+    withName: BCFTOOLS_MERGE_BCF {
+        ext.args = "--force-samples --no-version --output-type b"
     }
 
 }

tests/modules/bcftools/merge/test.yml

@@ -1,8 +1,35 @@
 - name: bcftools merge test_bcftools_merge
-  command: nextflow run ./tests/modules/bcftools/merge -entry test_bcftools_merge -c ./tests/config/nextflow.config -c ./tests/modules/bcftools/merge/nextflow.config
+  command: nextflow run ./tests/modules/bcftools/merge -entry test_bcftools_merge -c ./tests/config/nextflow.config  -c ./tests/modules/bcftools/merge/nextflow.config
   tags:
     - bcftools/merge
     - bcftools
   files:
     - path: output/bcftools/test.vcf.gz
       md5sum: 744b28bef1469aabdcfd354293ef725d
+
+- name: bcftools merge test_bcftools_merge_bed
+  command: nextflow run ./tests/modules/bcftools/merge -entry test_bcftools_merge_bed -c ./tests/config/nextflow.config  -c ./tests/modules/bcftools/merge/nextflow.config
+  tags:
+    - bcftools/merge
+    - bcftools
+  files:
+    - path: output/bcftools/test.vcf.gz
+      md5sum: 9597e71ae1706f76f00707687be43240
+
+- name: bcftools merge test_bcftools_merge_gvcf
+  command: nextflow run ./tests/modules/bcftools/merge -entry test_bcftools_merge_gvcf -c ./tests/config/nextflow.config  -c ./tests/modules/bcftools/merge/nextflow.config
+  tags:
+    - bcftools/merge
+    - bcftools
+  files:
+    - path: output/bcftools/test.vcf.gz
+      md5sum: 8aef4d860228cb651e0cb920376f5118
+
+- name: bcftools merge test_bcftools_merge_bcf
+  command: nextflow run ./tests/modules/bcftools/merge -entry test_bcftools_merge_bcf -c ./tests/config/nextflow.config  -c ./tests/modules/bcftools/merge/nextflow.config
+  tags:
+    - bcftools/merge
+    - bcftools
+  files:
+    - path: output/bcftools/test.bcf.gz
+      md5sum: 3ca1ab0d9a6ede049c6eeadf88177eb9