Update in GATK4 variantfiltration: Added vcf_index to vcf tuple; output to vcf.gz format. (#1083)

* Added vcf_index to vcf tuple; output to vcf.gz format.

* Fix: extra new line in meta.yml.

* addressed review feedback

* fix: editorconfig error

* fix: gatk memory flag

* fix: editorconfig error

* fix: Indentation 

fix: Indentation

* Fix: lint editorconfig error

Removed one extra space

Co-authored-by: Robert A. Petit III <robbie.petit@gmail.com>

modules/gatk4/variantfiltration/main.nf

@@ -19,23 +19,29 @@ process GATK4_VARIANTFILTRATION {
     }
 
     input:
-    tuple val(meta), path(vcf)
+    tuple val(meta), path(vcf), path(vcf_tbi)
     path  fasta
     path  fai
     path  dict
 
     output:
-    tuple val(meta), path("*.vcf"), emit: vcf
+    tuple val(meta), path("*.vcf.gz"), emit: vcf
-    path "versions.yml"           , emit: versions
+    tuple val(meta), path("*.tbi")   , emit: tbi
-
+    path "versions.yml"		         , emit: versions
 
     script:
-    def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    def avail_mem = 3
+    if (!task.memory) {
+        log.info '[GATK HaplotypeCaller] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
+    } else {
+        avail_mem = task.memory.toGiga()
+    }
     """
-    gatk VariantFiltration \\
+    gatk --java-options "-Xmx${avail_mem}G" VariantFiltration \\
         -R $fasta \\
         -V $vcf \\
-        -O ${prefix}.vcf \\
+        -O ${prefix}.vcf.gz \\
         $options.args
 
     cat <<-END_VERSIONS > versions.yml

modules/gatk4/variantfiltration/meta.yml

@@ -21,8 +21,12 @@ input:
         e.g. [ id:'test']
   - vcf:
       type: list
-      description: Input VCF file
+      description: List of VCF(.gz) files
-      pattern: "*.{vcf}"
+      pattern: "*.{vcf,vcf.gz}"
+  - vcf_tbi:
+      type: list
+      description: List of VCF file indexes
+      pattern: "*.{idx,tbi}"
   - fasta:
       type: file
       description: Fasta file of reference genome
@@ -38,8 +42,12 @@ input:
 output:
   - vcf:
       type: file
-      description: filtered VCF file
+      description: Compressed VCF file
-      pattern: "*.filtered.{vcf}"
+      pattern: "*.vcf.gz"
+  - tbi:
+      type: file
+      description: Index of VCF file
+      pattern: "*.vcf.gz.tbi"
   - versions:
       type: file
       description: File containing software versions

tests/modules/gatk4/variantfiltration/main.nf

@@ -5,14 +5,32 @@ nextflow.enable.dsl = 2
 test_options = ['args': '--filter-name "test_filter" --filter-expression "MQ0 > 0"', 'suffix': '.filtered']
 include { GATK4_VARIANTFILTRATION } from '../../../../modules/gatk4/variantfiltration/main.nf' addParams( options: test_options )
 
-workflow test_gatk4_variantfiltration {
+// Basic parameters with uncompressed VCF input
+workflow test_gatk4_variantfiltration_vcf_input {
+
     input = [ [ id:'test' ], // meta map
-              [ file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true) ]
+              file(params.test_data['homo_sapiens']['illumina']['test_genome_vcf'], checkIfExists: true),
-            ]
+              file(params.test_data['homo_sapiens']['illumina']['test_genome_vcf_idx'], checkIfExists: true) ]
-    fasta = [ file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) ]
-    fai = [ file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true) ]
-    genome_dict = [ file(params.test_data['sarscov2']['genome']['genome_dict'], checkIfExists: true) ]
 
+    fasta        = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    fastaIndex   = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+    fastaDict    = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
 
-    GATK4_VARIANTFILTRATION ( input, fasta, fai, genome_dict )
+    GATK4_VARIANTFILTRATION ( input, fasta, fastaIndex, fastaDict )
 }
+
+// Basic parameters with compressed VCF input
+workflow test_gatk4_variantfiltration_gz_input {
+
+    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) ]
+
+    fasta        = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    fastaIndex   = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+    fastaDict    = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
+
+    GATK4_VARIANTFILTRATION ( input, fasta, fastaIndex, fastaDict )
+}
+
+

tests/modules/gatk4/variantfiltration/test.yml

@@ -1,9 +1,19 @@
-- name: gatk4 variantfiltration test_gatk4_variantfiltration
+- name: gatk4 variantfiltration test_gatk4_variantfiltration_vcf_input
-  command: nextflow run tests/modules/gatk4/variantfiltration -entry test_gatk4_variantfiltration -c tests/config/nextflow.config
+  command: nextflow run tests/modules/gatk4/variantfiltration -entry test_gatk4_variantfiltration_vcf_input -c tests/config/nextflow.config
   tags:
     - gatk4/variantfiltration
     - gatk4
   files:
-    - path: output/gatk4/test.filtered.vcf
+    - path: output/gatk4/test.filtered.vcf.gz
-      contains:
+      contains: ['BaseQRankSum=-1.318;DP=17;ExcessHet=3.0103;MLEAC=1,0,0;MLEAF=0.500,0.00,0.00;MQRankSum=0.000;RAW_MQandDP=61200,17;ReadPosRankSum=2.365']
-        - "AC=2;AN=2;DP=1;DP4=0,0,1,0;MQ=60;MQ0F=0;SGB=-0.379885"
+    - path: output/gatk4/test.filtered.vcf.gz.tbi
+
+- name: gatk4 variantfiltration test_gatk4_variantfiltration_gz_input
+  command: nextflow run tests/modules/gatk4/variantfiltration -entry test_gatk4_variantfiltration_gz_input -c tests/config/nextflow.config
+  tags:
+    - gatk4/variantfiltration
+    - gatk4
+  files:
+    - path: output/gatk4/test.filtered.vcf.gz
+      contains: ['BaseQRankSum=-1.318;DP=17;ExcessHet=3.0103;MLEAC=1,0,0;MLEAF=0.500,0.00,0.00;MQRankSum=0.000;RAW_MQandDP=61200,17;ReadPosRankSum=2.365']
+    - path: output/gatk4/test.filtered.vcf.gz.tbi