BugFix: add missing tbi output channel to genotypeGVCFs (#1153)

* initial commit to setup branch

* workflow finished

* Update nextflow.config

* tumour to tumor, getpileup passed as nomral and tumor

* paired_somatic renamed to tumor_normal_somatic

* Apply suggestions from code review

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

* Update subworkflows/nf-core/gatk_tumor_normal_somatic_variant_calling/main.nf

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

* updated index names in meta.yml

* changed index file names in main script and test

* Apply suggestions from code review

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

* Apply suggestions from code review

* fixed bug from changes

* Apply suggestions from code review

* modified yml to allow new subworkflow testing

* Update test.yml

* Update test.yml

* added output channel for tbi files, tweaked method of adding blank inputs for gendb tests

* Update main.nf

* Update main.nf

Co-authored-by: GCJMackenzie <gavin.mackenzie@nibsc.org>
Co-authored-by: Maxime U. Garcia <maxime.garcia@scilifelab.se>

modules/gatk4/genotypegvcfs/main.nf

@@ -2,10 +2,10 @@ process GATK4_GENOTYPEGVCFS {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.0.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.3.0" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.0.0--0' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.3.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.0.0--0' }"
+        'quay.io/biocontainers/gatk4:4.2.3.0--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(gvcf), path(gvcf_index)
@@ -18,6 +18,7 @@ process GATK4_GENOTYPEGVCFS {
 
     output:
     tuple val(meta), path("*.vcf.gz"), emit: vcf
+    tuple val(meta), path("*.tbi")   , emit: tbi
     path  "versions.yml"             , emit: versions
 
     script:

modules/gatk4/genotypegvcfs/meta.yml

@@ -60,6 +60,10 @@ output:
       type: file
       description: Genotyped VCF file
       pattern: "*.vcf.gz"
+  - tbi:
+      type: file
+      description: Tbi index for VCF file
+      pattern: "*.vcf.gz"
   - versions:
       type: file
       description: File containing software versions

tests/config/test_data.config

@@ -193,9 +193,9 @@ params {
                 test2_baserecalibrator_table                   = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test2.baserecalibrator.table"
                 test_pileups_table                             = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test.pileups.table"
                 test2_pileups_table                            = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test2.pileups.table"
-                test_genomicsdb_tar_gz                         = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_genomicsdb.tar.gz"
 
                 test_genomicsdb_tar_gz                         = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_genomicsdb.tar.gz"
+                test_pon_genomicsdb_tar_gz                     = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_pon_genomicsdb.tar.gz"
 
                 test_test2_paired_mutect2_calls_vcf_gz         = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.vcf.gz"
                 test_test2_paired_mutect2_calls_vcf_gz_tbi     = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.vcf.gz.tbi"

tests/modules/gatk4/genotypegvcfs/main.nf

@@ -7,7 +7,7 @@ include { UNTAR               } from '../../../../modules/untar/main.nf'
 
 // Basic parameters with uncompressed VCF input
 workflow test_gatk4_genotypegvcfs_vcf_input {
-    
+
     input = [ [ id:'test' ], // meta map
               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) ]
@@ -21,7 +21,7 @@ workflow test_gatk4_genotypegvcfs_vcf_input {
 
 // Basic parameters with compressed VCF input
 workflow test_gatk4_genotypegvcfs_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) ]
@@ -35,7 +35,7 @@ workflow test_gatk4_genotypegvcfs_gz_input {
 
 // Basic parameters + optional dbSNP
 workflow test_gatk4_genotypegvcfs_gz_input_dbsnp {
-    
+
     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) ]
@@ -52,7 +52,7 @@ workflow test_gatk4_genotypegvcfs_gz_input_dbsnp {
 
 // Basic parameters + optional intervals
 workflow test_gatk4_genotypegvcfs_gz_input_intervals {
-    
+
     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) ]
@@ -68,7 +68,7 @@ workflow test_gatk4_genotypegvcfs_gz_input_intervals {
 
 // Basic parameters + optional dbSNP + optional intervals
 workflow test_gatk4_genotypegvcfs_gz_input_dbsnp_intervals {
-    
+
     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) ]
@@ -95,20 +95,16 @@ workflow test_gatk4_genotypegvcfs_gendb_input {
     test_genomicsdb = file(params.test_data['homo_sapiens']['illumina']['test_genomicsdb_tar_gz'], checkIfExists: true)
 
     UNTAR ( test_genomicsdb )
-
+    gendb = UNTAR.out.untar.collect()
-    Channel.of(file("mock_gvcf_index.txt")).set{mock_gvcf_index}
+    gendb.add([])
-    Channel
+    input = Channel.of([ id:'test' ]).combine(gendb)
-        .of([ id:'test' ])
-        .combine(UNTAR.out.untar)
-        .combine(mock_gvcf_index)
-        .set{ input }
 
     GATK4_GENOTYPEGVCFS ( input, fasta, fastaIndex, fastaDict, [], [], [] )
 }
 
 // Basic parameters with GenomicsDB + optional dbSNP
 workflow test_gatk4_genotypegvcfs_gendb_input_dbsnp {
-    
+
     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)
@@ -119,20 +115,16 @@ workflow test_gatk4_genotypegvcfs_gendb_input_dbsnp {
     test_genomicsdb = file(params.test_data['homo_sapiens']['illumina']['test_genomicsdb_tar_gz'], checkIfExists: true)
 
     UNTAR ( test_genomicsdb )
-
+    gendb = UNTAR.out.untar.collect()
-    Channel.of(file("mock_gvcf_index.txt")).set{mock_gvcf_index}
+    gendb.add([])
-    Channel
+    input = Channel.of([ id:'test' ]).combine(gendb)
-        .of([ id:'test' ])
-        .combine(UNTAR.out.untar)
-        .combine(mock_gvcf_index)
-        .set{ input }
 
     GATK4_GENOTYPEGVCFS ( input, fasta, fastaIndex, fastaDict, dbsnp, dbsnpIndex, [] )
 }
 
 // Basic parameters with GenomicsDB + optional intervals
 workflow test_gatk4_genotypegvcfs_gendb_input_intervals {
-    
+
     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)
@@ -142,20 +134,16 @@ workflow test_gatk4_genotypegvcfs_gendb_input_intervals {
     test_genomicsdb = file(params.test_data['homo_sapiens']['illumina']['test_genomicsdb_tar_gz'], checkIfExists: true)
 
     UNTAR ( test_genomicsdb )
-
+    gendb = UNTAR.out.untar.collect()
-    Channel.of(file("mock_gvcf_index.txt")).set{mock_gvcf_index}
+    gendb.add([])
-    Channel
+    input = Channel.of([ id:'test' ]).combine(gendb)
-        .of([ id:'test' ])
-        .combine(UNTAR.out.untar)
-        .combine(mock_gvcf_index)
-        .set{ input }
 
     GATK4_GENOTYPEGVCFS ( input, fasta, fastaIndex, fastaDict, [], [], intervalsBed )
 }
 
 // Basic parameters with GenomicsDB + optional dbSNP + optional intervals
 workflow test_gatk4_genotypegvcfs_gendb_input_dbsnp_intervals {
-    
+
     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)
@@ -168,13 +156,9 @@ workflow test_gatk4_genotypegvcfs_gendb_input_dbsnp_intervals {
     test_genomicsdb = file(params.test_data['homo_sapiens']['illumina']['test_genomicsdb_tar_gz'], checkIfExists: true)
 
     UNTAR ( test_genomicsdb )
-
+    gendb = UNTAR.out.untar.collect()
-    Channel.of(file("mock_gvcf_index.txt")).set{mock_gvcf_index}
+    gendb.add([])
-    Channel
+    input = Channel.of([ id:'test' ]).combine(gendb)
-        .of([ id:'test' ])
-        .combine(UNTAR.out.untar)
-        .combine(mock_gvcf_index)
-        .set{ input }
 
     GATK4_GENOTYPEGVCFS ( input, fasta, fastaIndex, fastaDict, dbsnp, dbsnpIndex, intervalsBed )
 }

tests/modules/gatk4/genotypegvcfs/test.yml

@@ -6,6 +6,7 @@
   files:
     - path: output/gatk4/test.genotyped.vcf.gz
       contains: ['AC=1;AF=0.500;AN=2;BaseQRankSum=0.00;DP=211;ExcessHet=3.0103;FS=0.000;MLEAC=1;MLEAF=0.500;MQ=60.00;MQRankSum=0.00;QD=0.95;ReadPosRankSum=1.09;SOR=0.680']
+    - path: output/gatk4/test.genotyped.vcf.gz.tbi
 
 - name: gatk4 genotypegvcfs test_gatk4_genotypegvcfs_gz_input
   command: nextflow run ./tests/modules/gatk4/genotypegvcfs -entry test_gatk4_genotypegvcfs_gz_input -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/genotypegvcfs/nextflow.config
@@ -15,6 +16,7 @@
   files:
     - path: output/gatk4/test.genotyped.vcf.gz
       contains: ['AC=1;AF=0.500;AN=2;BaseQRankSum=0.00;DP=211;ExcessHet=3.0103;FS=0.000;MLEAC=1;MLEAF=0.500;MQ=60.00;MQRankSum=0.00;QD=0.95;ReadPosRankSum=1.09;SOR=0.680']
+    - path: output/gatk4/test.genotyped.vcf.gz.tbi
 
 - name: gatk4 genotypegvcfs test_gatk4_genotypegvcfs_gz_input_dbsnp
   command: nextflow run ./tests/modules/gatk4/genotypegvcfs -entry test_gatk4_genotypegvcfs_gz_input_dbsnp -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/genotypegvcfs/nextflow.config
@@ -24,6 +26,7 @@
   files:
     - path: output/gatk4/test.genotyped.vcf.gz
       contains: ['AC=1;AF=0.500;AN=2;BaseQRankSum=0.00;DB;DP=211;ExcessHet=3.0103;FS=0.000;MLEAC=1;MLEAF=0.500;MQ=60.00;MQRankSum=0.00;QD=0.95;ReadPosRankSum=1.09;SOR=0.680']
+    - path: output/gatk4/test.genotyped.vcf.gz.tbi
 
 - name: gatk4 genotypegvcfs test_gatk4_genotypegvcfs_gz_input_intervals
   command: nextflow run ./tests/modules/gatk4/genotypegvcfs -entry test_gatk4_genotypegvcfs_gz_input_intervals -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/genotypegvcfs/nextflow.config
@@ -33,6 +36,7 @@
   files:
     - path: output/gatk4/test.genotyped.vcf.gz
       contains: ['AC=1;AF=0.500;AN=2;BaseQRankSum=0.00;DP=211;ExcessHet=3.0103;FS=0.000;MLEAC=1;MLEAF=0.500;MQ=60.00;MQRankSum=0.00;QD=0.95;ReadPosRankSum=1.09;SOR=0.680']
+    - path: output/gatk4/test.genotyped.vcf.gz.tbi
 
 - name: gatk4 genotypegvcfs test_gatk4_genotypegvcfs_gz_input_dbsnp_intervals
   command: nextflow run ./tests/modules/gatk4/genotypegvcfs -entry test_gatk4_genotypegvcfs_gz_input_dbsnp_intervals -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/genotypegvcfs/nextflow.config
@@ -42,6 +46,7 @@
   files:
     - path: output/gatk4/test.genotyped.vcf.gz
       contains: ['AC=1;AF=0.500;AN=2;BaseQRankSum=0.00;DB;DP=211;ExcessHet=3.0103;FS=0.000;MLEAC=1;MLEAF=0.500;MQ=60.00;MQRankSum=0.00;QD=0.95;ReadPosRankSum=1.09;SOR=0.680']
+    - path: output/gatk4/test.genotyped.vcf.gz.tbi
 
 - name: gatk4 genotypegvcfs test_gatk4_genotypegvcfs_gendb_input
   command: nextflow run ./tests/modules/gatk4/genotypegvcfs -entry test_gatk4_genotypegvcfs_gendb_input -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/genotypegvcfs/nextflow.config
@@ -51,6 +56,7 @@
   files:
     - path: output/gatk4/test.genotyped.vcf.gz
       contains: ['AC=1;AF=0.500;AN=2;BaseQRankSum=0.00;DP=211;ExcessHet=3.0103;FS=0.000;MLEAC=1;MLEAF=0.500;MQ=60.00;MQRankSum=0.00;QD=0.95;ReadPosRankSum=1.09;SOR=0.680']
+    - path: output/gatk4/test.genotyped.vcf.gz.tbi
 
 - name: gatk4 genotypegvcfs test_gatk4_genotypegvcfs_gendb_input_dbsnp
   command: nextflow run ./tests/modules/gatk4/genotypegvcfs -entry test_gatk4_genotypegvcfs_gendb_input_dbsnp -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/genotypegvcfs/nextflow.config
@@ -60,6 +66,7 @@
   files:
     - path: output/gatk4/test.genotyped.vcf.gz
       contains: ['AC=1;AF=0.500;AN=2;BaseQRankSum=0.00;DB;DP=211;ExcessHet=3.0103;FS=0.000;MLEAC=1;MLEAF=0.500;MQ=60.00;MQRankSum=0.00;QD=0.95;ReadPosRankSum=1.09;SOR=0.680']
+    - path: output/gatk4/test.genotyped.vcf.gz.tbi
 
 - name: gatk4 genotypegvcfs test_gatk4_genotypegvcfs_gendb_input_intervals
   command: nextflow run ./tests/modules/gatk4/genotypegvcfs -entry test_gatk4_genotypegvcfs_gendb_input_intervals -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/genotypegvcfs/nextflow.config
@@ -69,6 +76,7 @@
   files:
     - path: output/gatk4/test.genotyped.vcf.gz
       contains: ['AC=1;AF=0.500;AN=2;BaseQRankSum=0.00;DP=211;ExcessHet=3.0103;FS=0.000;MLEAC=1;MLEAF=0.500;MQ=60.00;MQRankSum=0.00;QD=0.95;ReadPosRankSum=1.09;SOR=0.680']
+    - path: output/gatk4/test.genotyped.vcf.gz.tbi
 
 - name: gatk4 genotypegvcfs test_gatk4_genotypegvcfs_gendb_input_dbsnp_intervals
   command: nextflow run ./tests/modules/gatk4/genotypegvcfs -entry test_gatk4_genotypegvcfs_gendb_input_dbsnp_intervals -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/genotypegvcfs/nextflow.config
@@ -78,3 +86,4 @@
   files:
     - path: output/gatk4/test.genotyped.vcf.gz
       contains: ['AC=1;AF=0.500;AN=2;BaseQRankSum=0.00;DB;DP=211;ExcessHet=3.0103;FS=0.000;MLEAC=1;MLEAF=0.500;MQ=60.00;MQRankSum=0.00;QD=0.95;ReadPosRankSum=1.09;SOR=0.680']
+    - path: output/gatk4/test.genotyped.vcf.gz.tbi