Improve syntax/logic coherence in all gatk4 plugins (#1459)

* feat: code polishing

* Apply suggestions from code review

Co-authored-by: FriederikeHanssen <Friederike.hanssen@qbic.uni-tuebingen.de>

* code polishing

* more code polishing

* code polishing

* tests for applybqsrspark

* fix typo

* no need to check md5sum for versions.yml

* fix: use correct syntax

* code polishing again

* add tests for markduplicatesspark

* simplify mergevcfs tests

* add tests for baserecalibratorspark

* fix: path to entry

* code polishing

* fix linting

* simplify module

* update meta.yml

* fix pair mode

* fix: MITO mode

* more tests

* fix command

* bad copy paste

* fix typos

* fix tests

* fix test

* update meta.yml

* correct versions.yml in all test.yml

* code polishing

* code polishing

* more code polishing

* fix args

* add tmpdir for all

Co-authored-by: FriederikeHanssen <Friederike.hanssen@qbic.uni-tuebingen.de>

modules/gatk4/applybqsr/main.nf

@@ -14,7 +14,7 @@ process GATK4_APPLYBQSR {
     path  dict
 
     output:
-    tuple val(meta), path("*.bam"),  emit: bam, optional: true
+    tuple val(meta), path("*.bam") , emit: bam,  optional: true
     tuple val(meta), path("*.cram"), emit: cram, optional: true
     path "versions.yml"            , emit: versions
 
@@ -24,8 +24,7 @@ process GATK4_APPLYBQSR {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def interval = intervals ? "-L ${intervals}" : ""
+    def interval_command = intervals ? "--intervals $intervals" : ""
-    def file_type = input.getExtension()
 
     def avail_mem = 3
     if (!task.memory) {
@@ -35,12 +34,12 @@ process GATK4_APPLYBQSR {
     }
     """
     gatk --java-options "-Xmx${avail_mem}g" ApplyBQSR \\
-        -R $fasta \\
+        --input $input \\
-        -I $input \\
+        --output ${prefix}.${input.getExtension()} \\
+        --reference $fasta \\
         --bqsr-recal-file $bqsr_table \\
-        $interval \\
+        $interval_command \\
         --tmp-dir . \\
-        -O ${prefix}.${file_type} \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

modules/gatk4/applybqsr/meta.yml

@@ -61,6 +61,10 @@ output:
       type: file
       description: Recalibrated BAM file
       pattern: "*.{bam}"
+  - cram:
+      type: file
+      description: Recalibrated CRAM file
+      pattern: "*.{cram}"
 
 authors:
   - "@yocra3"

modules/gatk4/applybqsrspark/main.nf

@@ -0,0 +1,51 @@
+process GATK4_APPLYBQSR_SPARK {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.3.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.3.0--hdfd78af_0' :
+        'quay.io/biocontainers/gatk4:4.2.3.0--hdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(input), path(input_index), path(bqsr_table), path(intervals)
+    path  fasta
+    path  fai
+    path  dict
+
+    output:
+    tuple val(meta), path("*.bam") , emit: bam,  optional: true
+    tuple val(meta), path("*.cram"), emit: cram, optional: true
+    path "versions.yml"            , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def interval_command = intervals ? "--intervals $intervals" : ""
+
+    def avail_mem = 3
+    if (!task.memory) {
+        log.info '[GATK ApplyBQSRSpark] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
+    } else {
+        avail_mem = task.memory.giga
+    }
+    """
+    gatk --java-options "-Xmx${avail_mem}g" ApplyBQSRSpark \\
+        --input $input \\
+        --output ${prefix}.${input.getExtension()} \\
+        --reference $fasta \\
+        --bqsr-recal-file $bqsr_table \\
+        $interval_command \\
+        --spark-master local[${task.cpus}] \\
+        --tmp-dir . \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
+    END_VERSIONS
+    """
+}

modules/gatk4/applybqsrspark/meta.yml

@@ -0,0 +1,72 @@
+name: gatk4_applybqsr_spark
+description: Apply base quality score recalibration (BQSR) to a bam file
+keywords:
+  - bqsr
+  - bam
+tools:
+  - gatk4:
+    description: |
+      Developed in the Data Sciences Platform at the Broad Institute, the toolkit offers a wide variety of tools
+      with a primary focus on variant discovery and genotyping. Its powerful processing engine
+      and high-performance computing features make it capable of taking on projects of any size.
+    homepage: https://gatk.broadinstitute.org/hc/en-us
+    documentation: https://gatk.broadinstitute.org/hc/en-us/categories/360002369672s
+    doi: 10.1158/1538-7445.AM2017-3590
+    licence: ["Apache-2.0"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - input:
+      type: file
+      description: BAM/CRAM file from alignment
+      pattern: "*.{bam,cram}"
+  - input_index:
+      type: file
+      description: BAI/CRAI file from alignment
+      pattern: "*.{bai,crai}"
+  - bqsr_table:
+      type: file
+      description: Recalibration table from gatk4_baserecalibrator
+  - intervals:
+      type: file
+      description: Bed file with the genomic regions included in the library (optional)
+  - fasta:
+      type: file
+      description: The reference fasta file
+      pattern: "*.fasta"
+  - fai:
+      type: file
+      description: Index of reference fasta file
+      pattern: "*.fasta.fai"
+  - dict:
+      type: file
+      description: GATK sequence dictionary
+      pattern: "*.dict"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - bam:
+      type: file
+      description: Recalibrated BAM file
+      pattern: "*.{bam}"
+  - cram:
+      type: file
+      description: Recalibrated CRAM file
+      pattern: "*.{cram}"
+
+authors:
+  - "@yocra3"
+  - "@FriederikeHanssen"
+  - "@maxulysse"

modules/gatk4/applyvqsr/main.nf

@@ -8,13 +8,13 @@ process GATK4_APPLYVQSR {
         'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
 
     input:
-    tuple val(meta), path(vcf), path(tbi), path(recal), path(recalidx), path(tranches)
+    tuple val(meta), path(vcf), path(vcf_tbi), path(recal), path(recal_index), path(tranches)
     path  fasta
     path  fai
     path  dict
 
     output:
-    tuple val(meta), path("*.vcf.gz")     , emit: vcf
+    tuple val(meta), path("*.vcf.gz"), emit: vcf
     tuple val(meta), path("*.tbi")   , emit: tbi
     path "versions.yml"              , emit: versions
 
@@ -24,7 +24,7 @@ process GATK4_APPLYVQSR {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    refCommand = fasta ? "-R ${fasta} " : ''
+    def reference_command = fasta ? "--reference $fasta" : ''
 
     def avail_mem = 3
     if (!task.memory) {
@@ -34,11 +34,12 @@ process GATK4_APPLYVQSR {
     }
     """
     gatk --java-options "-Xmx${avail_mem}g" ApplyVQSR \\
-        ${refCommand} \\
+        --variant ${vcf} \\
-        -V ${vcf} \\
+        --output ${prefix}.vcf.gz \\
-        -O ${prefix}.vcf.gz \\
+        $reference_command \\
         --tranches-file $tranches \\
         --recal-file $recal \\
+        --tmp-dir . \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

modules/gatk4/applyvqsr/meta.yml

@@ -29,20 +29,20 @@ input:
       type: file
       description: VCF file to be recalibrated, this should be the same file as used for the first stage VariantRecalibrator.
       pattern: "*.vcf"
-  - tbi:
+  - vcf_tbi:
       type: file
-      description: Tbi index for the input vcf file.
+      description: tabix index for the input vcf file.
       pattern: "*.vcf.tbi"
   - recal:
       type: file
       description: Recalibration file produced when the input vcf was run through VariantRecalibrator in stage 1.
       pattern: "*.recal"
-  - recalidx:
+  - recal_index:
       type: file
       description: Index file for the recalibration file.
       pattern: ".recal.idx"
   - tranches:
-      type: boolean
+      type: file
       description: Tranches file produced when the input vcf was run through VariantRecalibrator in stage 1.
       pattern: ".tranches"
   - fasta:

modules/gatk4/baserecalibrator/main.nf

@@ -12,8 +12,8 @@ process GATK4_BASERECALIBRATOR {
     path  fasta
     path  fai
     path  dict
-    path knownSites
+    path  known_sites
-    path knownSites_tbi
+    path  known_sites_tbi
 
     output:
     tuple val(meta), path("*.table"), emit: table
@@ -25,8 +25,8 @@ process GATK4_BASERECALIBRATOR {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def intervalsCommand = intervals ? "-L ${intervals}" : ""
+    def interval_command = intervals ? "--intervals $intervals" : ""
-    def sitesCommand = knownSites.collect{"--known-sites ${it}"}.join(' ')
+    def sites_command = known_sites.collect{"--known-sites $it"}.join(' ')
 
     def avail_mem = 3
     if (!task.memory) {
@@ -34,16 +34,15 @@ process GATK4_BASERECALIBRATOR {
     } else {
         avail_mem = task.memory.giga
     }
-
     """
-    gatk --java-options "-Xmx${avail_mem}g" BaseRecalibrator  \
+    gatk --java-options "-Xmx${avail_mem}g" BaseRecalibrator  \\
-        -R $fasta \
+        --input $input \\
-        -I $input \
+        --output ${prefix}.table \\
-        $sitesCommand \
+        --reference $fasta \\
-        $intervalsCommand \
+        $interval_command \\
-        --tmp-dir . \
+        $sites_command \\
-        $args \
+        --tmp-dir . \\
-        -O ${prefix}.table
+        $args
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/gatk4/baserecalibrator/meta.yml

@@ -42,9 +42,14 @@ input:
       type: file
       description: GATK sequence dictionary
       pattern: "*.dict"
-  - knownSites:
+  - known_sites:
       type: file
-      description: Bed file with the genomic regions included in the library (optional)
+      description: VCF files with known sites for indels / snps (optional)
+      pattern: "*.vcf.gz"
+  - known_sites_tbi:
+      type: file
+      description: Tabix index of the known_sites (optional)
+      pattern: "*.vcf.gz.tbi"
 
 output:
   - meta:
@@ -64,3 +69,4 @@ output:
 authors:
   - "@yocra3"
   - "@FriederikeHanssen"
+  - "@maxulysse"

modules/gatk4/baserecalibratorspark/main.nf

@@ -0,0 +1,53 @@
+process GATK4_BASERECALIBRATOR_SPARK {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.3.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.3.0--hdfd78af_0' :
+        'broadinstitute/gatk:4.2.3.0' }"
+
+    input:
+    tuple val(meta), path(input), path(input_index), path(intervals)
+    path  fasta
+    path  fai
+    path  dict
+    path  known_sites
+    path  known_sites_tbi
+
+    output:
+    tuple val(meta), path("*.table"), emit: table
+    path "versions.yml"             , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def interval_command = intervals ? "--intervals $intervals" : ""
+    def sites_command = known_sites.collect{"--known-sites $it"}.join(' ')
+
+    def avail_mem = 3
+    if (!task.memory) {
+        log.info '[GATK BaseRecalibratorSpark] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
+    } else {
+        avail_mem = task.memory.giga
+    }
+    """
+    gatk --java-options "-Xmx${avail_mem}g" BaseRecalibratorSpark \\
+        --input $input \\
+        --output ${prefix}.table \\
+        --reference $fasta \\
+        $interval_command \\
+        $sites_command \\
+        --spark-master local[${task.cpus}] \\
+        --tmp-dir . \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
+    END_VERSIONS
+    """
+}

modules/gatk4/baserecalibratorspark/meta.yml

@@ -0,0 +1,72 @@
+name: gatk4_baserecalibrator_spark
+description: Generate recalibration table for Base Quality Score Recalibration (BQSR)
+keywords:
+  - sort
+tools:
+  - gatk4:
+    description: |
+      Developed in the Data Sciences Platform at the Broad Institute, the toolkit offers a wide variety of tools
+      with a primary focus on variant discovery and genotyping. Its powerful processing engine
+      and high-performance computing features make it capable of taking on projects of any size.
+    homepage: https://gatk.broadinstitute.org/hc/en-us
+    documentation: https://gatk.broadinstitute.org/hc/en-us/categories/360002369672s
+    doi: 10.1158/1538-7445.AM2017-3590
+    licence: ["Apache-2.0"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - input:
+      type: file
+      description: BAM/CRAM file from alignment
+      pattern: "*.{bam,cram}"
+  - input_index:
+      type: file
+      description: BAI/CRAI file from alignment
+      pattern: "*.{bai,crai}"
+  - intervals:
+      type: file
+      description: Bed file with the genomic regions included in the library (optional)
+  - fasta:
+      type: file
+      description: The reference fasta file
+      pattern: "*.fasta"
+  - fai:
+      type: file
+      description: Index of reference fasta file
+      pattern: "*.fasta.fai"
+  - dict:
+      type: file
+      description: GATK sequence dictionary
+      pattern: "*.dict"
+  - known_sites:
+      type: file
+      description: VCF files with known sites for indels / snps (optional)
+      pattern: "*.vcf.gz"
+  - known_sites_tbi:
+      type: file
+      description: Tabix index of the known_sites (optional)
+      pattern: "*.vcf.gz.tbi"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - table:
+      type: file
+      description: Recalibration table from BaseRecalibrator
+      pattern: "*.{table}"
+
+authors:
+  - "@yocra3"
+  - "@FriederikeHanssen"
+  - "@maxulysse"

modules/gatk4/bedtointervallist/main.nf

@@ -9,7 +9,7 @@ process GATK4_BEDTOINTERVALLIST {
 
     input:
     tuple val(meta), path(bed)
-    path sequence_dict
+    path  dict
 
     output:
     tuple val(meta), path('*.interval_list'), emit: interval_list
@@ -21,6 +21,7 @@ process GATK4_BEDTOINTERVALLIST {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+
     def avail_mem = 3
     if (!task.memory) {
         log.info '[GATK BedToIntervalList] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@@ -29,9 +30,10 @@ process GATK4_BEDTOINTERVALLIST {
     }
     """
     gatk --java-options "-Xmx${avail_mem}g" BedToIntervalList \\
-        -I $bed \\
+        --INPUT $bed \\
-        -SD $sequence_dict \\
+        --OUTPUT ${prefix}.interval_list \\
-        -O ${prefix}.interval_list \\
+        --SEQUENCE_DICTIONARY $dict \\
+        --TMP_DIR . \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

modules/gatk4/calculatecontamination/main.nf

@@ -9,7 +9,6 @@ process GATK4_CALCULATECONTAMINATION {
 
     input:
     tuple val(meta), path(pileup), path(matched)
-    val segmentout
 
     output:
     tuple val(meta), path('*.contamination.table'), emit: contamination
@@ -22,8 +21,8 @@ process GATK4_CALCULATECONTAMINATION {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def matched_command = matched ? " -matched ${matched} " : ''
+    def matched_command = matched ? "--matched-normal $matched" : ''
-    def segment_command = segmentout ? " -segments ${prefix}.segmentation.table" : ''
+
     def avail_mem = 3
     if (!task.memory) {
         log.info '[GATK CalculateContamination] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@@ -32,10 +31,10 @@ process GATK4_CALCULATECONTAMINATION {
     }
     """
     gatk --java-options "-Xmx${avail_mem}g" CalculateContamination \\
-        -I $pileup \\
+        --input $pileup \\
+        --output ${prefix}.contamination.table \\
         $matched_command \\
-        -O ${prefix}.contamination.table \\
+        --tmp-dir . \\
-        $segment_command \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

modules/gatk4/calculatecontamination/meta.yml

@@ -32,9 +32,6 @@ input:
       type: file
       description: File containing the pileups summary table of a normal sample that matches with the tumor sample specified in pileup argument. This is an optional input.
       pattern: "*.pileups.table"
-  - segmentout:
-      type: boolean
-      description: specifies whether to output the segmentation table.
 
 output:
   - contamination:
@@ -43,7 +40,7 @@ output:
       pattern: "*.contamination.table"
   - segmentation:
       type: file
-      description: optional output table containing segmentation of tumor minor allele fractions.
+      description: output table containing segmentation of tumor minor allele fractions (optional)
       pattern: "*.segmentation.table"
   - versions:
       type: file
@@ -52,3 +49,4 @@ output:
 
 authors:
   - "@GCJMackenzie"
+  - "@maxulysse"

modules/gatk4/combinegvcfs/main.nf

@@ -9,9 +9,9 @@ process GATK4_COMBINEGVCFS {
 
     input:
     tuple val(meta), path(vcf), path(vcf_idx)
-    path (fasta)
+    path  fasta
-    path (fasta_fai)
+    path  fai
-    path (fasta_dict)
+    path  dict
 
     output:
     tuple val(meta), path("*.combined.g.vcf.gz"), emit: combined_gvcf
@@ -23,21 +23,21 @@ process GATK4_COMBINEGVCFS {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+    def input_list = vcf.collect{"--variant $it"}.join(' ')
+
     def avail_mem = 3
     if (!task.memory) {
         log.info '[GATK COMBINEGVCFS] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
     } else {
         avail_mem = task.memory.giga
     }
-    def input_files = vcf.collect{"-V ${it}"}.join(' ') // add '-V' to each vcf file
     """
-    gatk \\
+    gatk --java-options "-Xmx${avail_mem}g" CombineGVCFs \\
-        --java-options "-Xmx${avail_mem}g" \\
+        $input_list \\
-        CombineGVCFs \\
+        --output ${prefix}.combined.g.vcf.gz \\
-        -R ${fasta} \\
+        --reference ${fasta} \\
-        -O ${prefix}.combined.g.vcf.gz \\
+        --tmp-dir . \\
-        ${args} \\
+        $args
-        ${input_files}
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/gatk4/combinegvcfs/meta.yml

@@ -19,18 +19,11 @@ tools:
       licence: ["Apache-2.0"]
 
 input:
-  - fasta:
+  - meta:
-      type: file
+      type: map
-      description: The reference fasta file
+      description: |
-      pattern: "*.fasta"
+        Groovy Map containing sample information
-  - fai:
+        e.g. [ id:'test' ]
-      type: file
-      description: FASTA index file
-      pattern: "*.{fai}"
-  - dict:
-      type: file
-      description: FASTA dictionary file
-      pattern: "*.{dict}"
   - vcf:
       type: file
       description: Compressed VCF files
@@ -38,7 +31,19 @@ input:
   - vcf_idx:
       type: file
       description: VCF Index file
-      pattern: "*.{fai}"
+      pattern: "*.vcf.gz.idx"
+  - fasta:
+      type: file
+      description: The reference fasta file
+      pattern: "*.fasta"
+  - fai:
+      type: file
+      description: FASTA index file
+      pattern: "*.fasta.fai"
+  - dict:
+      type: file
+      description: FASTA dictionary file
+      pattern: "*.dict"
 output:
   - gvcf:
       type: file
@@ -53,3 +58,4 @@ authors:
   - "@sateeshperi"
   - "@mjcipriano"
   - "@hseabolt"
+  - "@maxulysse"

modules/gatk4/createsequencedictionary/main.nf

@@ -19,6 +19,7 @@ process GATK4_CREATESEQUENCEDICTIONARY {
 
     script:
     def args = task.ext.args ?: ''
+
     def avail_mem = 6
     if (!task.memory) {
         log.info '[GATK CreateSequenceDictionary] Available memory not known - defaulting to 6GB. Specify process memory requirements to change this.'
@@ -26,10 +27,10 @@ process GATK4_CREATESEQUENCEDICTIONARY {
         avail_mem = task.memory.giga
     }
     """
-    gatk --java-options "-Xmx${avail_mem}g" \\
+    gatk --java-options "-Xmx${avail_mem}g" CreateSequenceDictionary \\
-        CreateSequenceDictionary \\
         --REFERENCE $fasta \\
         --URI $fasta \\
+        --TMP_DIR . \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

modules/gatk4/createsomaticpanelofnormals/main.nf

@@ -24,6 +24,7 @@ process GATK4_CREATESOMATICPANELOFNORMALS {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+
     def avail_mem = 3
     if (!task.memory) {
         log.info '[GATK CreateSomaticPanelOfNormals] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@@ -31,11 +32,11 @@ process GATK4_CREATESOMATICPANELOFNORMALS {
         avail_mem = task.memory.giga
     }
     """
-    gatk --java-options "-Xmx${avail_mem}g" \\
+    gatk --java-options "-Xmx${avail_mem}g" CreateSomaticPanelOfNormals \\
-        CreateSomaticPanelOfNormals \\
+        --variant gendb://$genomicsdb \\
-        -R $fasta \\
+        --output ${prefix}.vcf.gz \\
-        -V gendb://$genomicsdb \\
+        --reference $fasta \\
-        -O ${prefix}.vcf.gz \\
+        --tmp-dir . \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

modules/gatk4/createsomaticpanelofnormals/meta.yml

@@ -44,7 +44,7 @@ output:
       pattern: "*.vcf.gz"
   - tbi:
       type: file
-      description: Index of vcf file
+      description: Tabix index of vcf file
       pattern: "*vcf.gz.tbi"
   - versions:
       type: file

modules/gatk4/estimatelibrarycomplexity/main.nf

@@ -8,10 +8,10 @@ process GATK4_ESTIMATELIBRARYCOMPLEXITY {
         'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
 
     input:
-    tuple val(meta), path(cram)
+    tuple val(meta), path(input)
-    path(fasta)
+    path  fasta
-    path(fai)
+    path  fai
-    path(dict)
+    path  dict
 
     output:
     tuple val(meta), path('*.metrics'), emit: metrics
@@ -23,7 +23,7 @@ process GATK4_ESTIMATELIBRARYCOMPLEXITY {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def crams = cram.collect(){ x -> "-I ".concat(x.toString()) }.join(" ")
+    def input_list = input.collect(){"--INPUT $it"}.join(" ")
 
     def avail_mem = 3
     if (!task.memory) {
@@ -32,12 +32,12 @@ process GATK4_ESTIMATELIBRARYCOMPLEXITY {
         avail_mem = task.memory.giga
     }
     """
-    gatk --java-options "-Xmx${avail_mem}g" EstimateLibraryComplexity \
+    gatk --java-options "-Xmx${avail_mem}g" EstimateLibraryComplexity \\
-        ${crams} \
+        $input_list \\
-        -O ${prefix}.metrics \
+        --OUTPUT ${prefix}.metrics \\
-        --REFERENCE_SEQUENCE ${fasta} \
+        --REFERENCE_SEQUENCE ${fasta} \\
-        --VALIDATION_STRINGENCY SILENT \
+        --TMP_DIR . \\
-        --TMP_DIR . $args
+        $args
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/gatk4/estimatelibrarycomplexity/meta.yml

@@ -20,7 +20,7 @@ input:
       description: |
         Groovy Map containing sample information
         e.g. [ id:'test', single_end:false ]
-  - cram:
+  - input:
       type: file
       description: BAM/CRAM/SAM file
       pattern: "*.{bam,cram,sam}"
@@ -54,3 +54,4 @@ output:
 
 authors:
   - "@FriederikeHanssen"
+  - "@maxulysse"

modules/gatk4/fastqtosam/main.nf

@@ -20,7 +20,8 @@ process GATK4_FASTQTOSAM {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def read_files = meta.single_end ? "-F1 $reads" : "-F1 ${reads[0]} -F2 ${reads[1]}"
+    def reads_command = meta.single_end ? "--FASTQ $reads" : "--FASTQ ${reads[0]} --FASTQ2 ${reads[1]}"
+
     def avail_mem = 3
     if (!task.memory) {
         log.info '[GATK FastqToSam] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@@ -29,9 +30,10 @@ process GATK4_FASTQTOSAM {
     }
     """
     gatk --java-options "-Xmx${avail_mem}g" FastqToSam \\
-        $read_files \\
+        $reads_command \\
-        -O ${prefix}.bam \\
+        --OUTPUT ${prefix}.bam \\
-        -SM $prefix \\
+        --SAMPLE_NAME $prefix \\
+        --TMP_DIR . \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

modules/gatk4/fastqtosam/meta.yml

@@ -34,14 +34,14 @@ output:
       description: |
         Groovy Map containing sample information
         e.g. [ id:'test', single_end:false ]
-  - versions:
-      type: file
-      description: File containing software versions
-      pattern: "versions.yml"
   - bam:
       type: file
       description: Converted BAM file
       pattern: "*.bam"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
 
 authors:
   - "@ntoda03"

modules/gatk4/filtermutectcalls/main.nf

@@ -8,7 +8,7 @@ process GATK4_FILTERMUTECTCALLS {
         'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
 
     input:
-    tuple val(meta), path(vcf), path(tbi), path(stats), path(orientationbias), path(segmentation), path(contaminationfile), val(contaminationest)
+    tuple val(meta), path(vcf), path(vcf_tbi), path(stats), path(orientationbias), path(segmentation), path(table), val(estimate)
     path  fasta
     path  fai
     path  dict
@@ -26,20 +26,11 @@ process GATK4_FILTERMUTECTCALLS {
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
 
-    def orientationbias_options = ''
+    def orientationbias_command = orientationbias ? orientationbias.collect{"--orientation-bias-artifact-priors $it"}.join(' ') : ''
-    if (orientationbias) {
+    def segmentation_command    = segmentation    ? segmentation.collect{"--tumor-segmentation $it"}.join(' ')                  : ''
-        orientationbias_options = '--orientation-bias-artifact-priors ' + orientationbias.join(' --orientation-bias-artifact-priors ')
+    def estimate_command        = estimate        ? " --contamination-estimate ${estimate} "                                    : ''
-    }
+    def table_command           = table           ? " --contamination-table ${table} "                                          : ''
 
-    def segmentation_options = ''
-    if (segmentation) {
-        segmentation_options = '--tumor-segmentation ' + segmentation.join(' --tumor-segmentation ')
-    }
-
-    def contamination_options = contaminationest ? " --contamination-estimate ${contaminationest} " : ''
-    if (contaminationfile) {
-        contamination_options = '--contamination-table ' + contaminationfile.join(' --contamination-table ')
-    }
     def avail_mem = 3
     if (!task.memory) {
         log.info '[GATK FilterMutectCalls] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@@ -48,12 +39,14 @@ process GATK4_FILTERMUTECTCALLS {
     }
     """
     gatk --java-options "-Xmx${avail_mem}g" FilterMutectCalls \\
-        -R $fasta \\
+        --variant $vcf \\
-        -V $vcf \\
+        --output ${prefix}.vcf.gz \\
-        $orientationbias_options \\
+        --reference $fasta \\
-        $segmentation_options \\
+        $orientationbias_command \\
-        $contamination_options \\
+        $segmentation_command \\
-        -O ${prefix}.vcf.gz \\
+        $estimate_command \\
+        $table_command \\
+        --tmp-dir . \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

modules/gatk4/filtermutectcalls/meta.yml

@@ -26,9 +26,9 @@ input:
       type: file
       description: compressed vcf file of mutect2calls
       pattern: "*.vcf.gz"
-  - tbi:
+  - vcf_tbi:
       type: file
-      description: Index of vcf file
+      description: Tabix index of vcf file
       pattern: "*vcf.gz.tbi"
   - stats:
       type: file
@@ -42,13 +42,13 @@ input:
       type: list
       description: tables containing segmentation information for input vcf. Optional input.
       pattern: "*.segmentation.table"
-  - contaminationfile:
+  - table:
       type: list
-      description: table(s) containing contamination contamination data for input vcf. Optional input, takes priority over contaminationest.
+      description: table(s) containing contamination data for input vcf. Optional input, takes priority over estimate.
       pattern: "*.contamination.table"
-  - contaminationest:
+  - estimate:
       type: val
-      description: estimation of contamination value as a double. Optional input, will only be used if contaminationfile is not specified.
+      description: estimation of contamination value as a double. Optional input, will only be used if table is not specified.
   - fasta:
       type: file
       description: The reference fasta file
@@ -82,3 +82,4 @@ output:
 
 authors:
   - "@GCJMackenzie"
+  - "@maxulysse"

modules/gatk4/gatherbqsrreports/main.nf

@@ -8,7 +8,7 @@ process GATK4_GATHERBQSRREPORTS {
         'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
 
     input:
-    tuple val(meta), path(recal_table)
+    tuple val(meta), path(table)
 
     output:
     tuple val(meta), path("*.table"), emit: table
@@ -20,7 +20,7 @@ process GATK4_GATHERBQSRREPORTS {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def input = recal_table.collect{"-I ${it}"}.join(' ')
+    def input_list = table.collect{"--input $it"}.join(' ')
 
     def avail_mem = 3
     if (!task.memory) {
@@ -29,12 +29,11 @@ process GATK4_GATHERBQSRREPORTS {
         avail_mem = task.memory.giga
     }
     """
-    gatk --java-options "-Xmx${avail_mem}g" \\
+    gatk --java-options "-Xmx${avail_mem}g" GatherBQSRReports \\
-        GatherBQSRReports \
+        $input_list \\
-        ${input} \
+        --output ${prefix}.table \\
-        --tmp-dir . \
+        --tmp-dir . \\
-        $args \
+        $args
-        --output ${prefix}.table
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/gatk4/gatherbqsrreports/meta.yml

@@ -19,7 +19,7 @@ input:
       description: |
         Groovy Map containing sample information
         e.g. [ id:'test', single_end:false ]
-  - recal_table:
+  - table:
       type: file
       description: File(s) containing BQSR table(s)
       pattern: "*.table"
@@ -30,14 +30,14 @@ output:
       description: |
         Groovy Map containing sample information
         e.g. [ id:'test', single_end:false ]
+  - table:
+      type: file
+      description: File containing joined BQSR table
+      pattern: "*.table"
   - versions:
       type: file
       description: File containing software versions
       pattern: "versions.yml"
-  - recal_table:
-      type: file
-      description: File containing joined BQSR table
-      pattern: "*.table"
 
 authors:
   - "@FriederikeHanssen"

modules/gatk4/gatherpileupsummaries/main.nf

@@ -22,7 +22,7 @@ process GATK4_GATHERPILEUPSUMMARIES {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def input = pileup.collect{ "-I ${it} " }.join(' ')
+    def input_list = pileup.collect{ "--I $it" }.join(' ')
 
     def avail_mem = 3
     if (!task.memory) {
@@ -31,11 +31,12 @@ process GATK4_GATHERPILEUPSUMMARIES {
         avail_mem = task.memory.giga
     }
     """
-    gatk --java-options "-Xmx${avail_mem}g" \
+    gatk --java-options "-Xmx${avail_mem}g" GatherPileupSummaries \\
-        GatherPileupSummaries \
+        $input_list \\
-        --sequence-dictionary ${dict} \
+        --O ${prefix}.pileupsummaries.table \\
-        ${input} \
+        --sequence-dictionary $dict \\
-        -O ${prefix}.pileupsummaries.table
+        --tmp-dir . \\
+        $args
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/gatk4/gatherpileupsummaries/meta.yml

@@ -28,14 +28,15 @@ output:
       description: |
         Groovy Map containing sample information
         e.g. [ id:'test', single_end:false ]
+  - table:
+      type: file
+      description: pileup summaries table file
+      pattern: "*.pileupsummaries.table"
   - versions:
       type: file
       description: File containing software versions
       pattern: "versions.yml"
-  - table:
-      type: file
-      description: Pileup file
-      pattern: "*.pileups.table"
 
 authors:
   - "@FriederikeHanssen"
+  - "@maxulysse"

modules/gatk4/genomicsdbimport/main.nf

@@ -8,13 +8,13 @@ process GATK4_GENOMICSDBIMPORT {
         'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
 
     input:
-    tuple val(meta), path(vcf), path(tbi), path(intervalfile), val(intervalval), path(wspace)
+    tuple val(meta), path(vcf), path(tbi), path(interval_file), val(interval_value), path(wspace)
     val   run_intlist
     val   run_updatewspace
     val   input_map
 
     output:
-    tuple val(meta), path("${prefix}")      , optional:true, emit: genomicsdb
+    tuple val(meta), path("$prefix")        , optional:true, emit: genomicsdb
     tuple val(meta), path("$updated_db")    , optional:true, emit: updatedb
     tuple val(meta), path("*.interval_list"), optional:true, emit: intervallist
     path "versions.yml"                                    , emit: versions
@@ -27,22 +27,22 @@ process GATK4_GENOMICSDBIMPORT {
     prefix   = task.ext.prefix ?: "${meta.id}"
 
     // settings for running default create gendb mode
-    inputs_command = input_map ? "--sample-name-map ${vcf[0]}" : "${'-V ' + vcf.join(' -V ')}"
+    input_command = input_map ? "--sample-name-map ${vcf[0]}" : vcf.collect(){"--variant $it"}.join(' ')
-    dir_command = "--genomicsdb-workspace-path ${prefix}"
+
-    intervals_command = intervalfile ? " -L ${intervalfile} " : " -L ${intervalval} "
+    genomicsdb_command = "--genomicsdb-workspace-path ${prefix}"
+    interval_command = interval_file ? "--intervals ${interval_file}" : "--intervals ${interval_value}"
 
     // settings changed for running get intervals list mode if run_intlist is true
     if (run_intlist) {
-        inputs_command = ''
+        genomicsdb_command = "--genomicsdb-update-workspace-path ${wspace}"
-        dir_command = "--genomicsdb-update-workspace-path ${wspace}"
+        interval_command = "--output-interval-list-to-file ${prefix}.interval_list"
-        intervals_command = "--output-interval-list-to-file ${prefix}.interval_list"
     }
 
-    // settings changed for running update gendb mode. inputs_command same as default, update_db forces module to emit the updated gendb
+    // settings changed for running update gendb mode. input_command same as default, update_db forces module to emit the updated gendb
     if (run_updatewspace) {
-        dir_command = "--genomicsdb-update-workspace-path ${wspace}"
+        genomicsdb_command = "--genomicsdb-update-workspace-path ${wspace}"
-        intervals_command = ''
+        interval_command = ''
-        updated_db = wspace.toString()
+        updated_db = "${wspace}"
     }
 
     def avail_mem = 3
@@ -53,9 +53,10 @@ process GATK4_GENOMICSDBIMPORT {
     }
     """
     gatk --java-options "-Xmx${avail_mem}g" GenomicsDBImport \\
-        $inputs_command \\
+        $input_command \\
-        $dir_command \\
+        $genomicsdb_command \\
-        $intervals_command \\
+        $interval_command \\
+        --tmp-dir . \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

modules/gatk4/genotypegvcfs/main.nf

@@ -10,10 +10,10 @@ process GATK4_GENOTYPEGVCFS {
     input:
     tuple val(meta), path(gvcf), path(gvcf_index), path(intervals), path(intervals_index)
     path  fasta
-    path  fasta_index
+    path  fai
-    path  fasta_dict
+    path  dict
     path  dbsnp
-    path  dbsnp_index
+    path  dbsnp_tbi
 
     output:
     tuple val(meta), path("*.vcf.gz"), emit: vcf
@@ -26,9 +26,10 @@ process GATK4_GENOTYPEGVCFS {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def dbsnp_options    = dbsnp ? "-D ${dbsnp}" : ""
+    def gvcf_command = gvcf.name.endsWith(".vcf") || gvcf.name.endsWith(".vcf.gz") ? "$gvcf" : "gendb://$gvcf"
-    def interval_options = intervals ? "-L ${intervals}" : ""
+    def dbsnp_command = dbsnp ? "--dbsnp $dbsnp" : ""
-    def gvcf_options     = gvcf.name.endsWith(".vcf") || gvcf.name.endsWith(".vcf.gz") ? "$gvcf" : "gendb://$gvcf"
+    def interval_command = intervals ? "--intervals $intervals" : ""
+
     def avail_mem = 3
     if (!task.memory) {
         log.info '[GATK GenotypeGVCFs] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@@ -36,14 +37,14 @@ process GATK4_GENOTYPEGVCFS {
         avail_mem = task.memory.giga
     }
     """
-    gatk --java-options "-Xmx${avail_mem}g" \\
+    gatk --java-options "-Xmx${avail_mem}g" GenotypeGVCFs \\
-        GenotypeGVCFs \\
+        --variant $gvcf_command \\
-        $args \\
+        --output ${prefix}.vcf.gz \\
-        $interval_options \\
+        --reference $fasta \\
-        $dbsnp_options \\
+        $interval_command \\
-        -R $fasta \\
+        $dbsnp_command \\
-        -V $gvcf_options \\
+        --tmp-dir . \\
-        -O ${prefix}.vcf.gz
+        $args
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/gatk4/genotypegvcfs/meta.yml

@@ -21,10 +21,15 @@ input:
         Groovy Map containing sample information
         e.g. [ id:'test', single_end:false ]
   - gvcf:
-      type: tuple of files
+      type: file
       description: |
-        Tuple of gVCF(.gz) file (first) and its index (second) or the path to a GenomicsDB (and empty)
+        gVCF(.gz) file or to a GenomicsDB
-      pattern: ["*.{vcf,vcf.gz}", "*.{idx,tbi}"]
+      pattern: "*.{vcf,vcf.gz}"
+  - gvcf_index:
+      type: file
+      description: |
+        index of gvcf file, or empty when providing GenomicsDB
+      pattern: "*.{idx,tbi}"
   - intervals:
       type: file
       description: Interval file with the genomic regions included in the library (optional)
@@ -35,11 +40,11 @@ input:
       type: file
       description: Reference fasta file
       pattern: "*.fasta"
-  - fasta_index:
+  - fai:
       type: file
       description: Reference fasta index file
       pattern: "*.fai"
-  - fasta_dict:
+  - dict:
       type: file
       description: Reference fasta sequence dict file
       pattern: "*.dict"
@@ -47,8 +52,8 @@ input:
       type: file
       description: dbSNP VCF file
       pattern: "*.vcf.gz"
-  - dbsnp_index:
+  - dbsnp_tbi:
-      type: tuple of files
+      type: file
       description: dbSNP VCF index file
       pattern: "*.tbi"
 
@@ -73,3 +78,4 @@ output:
 
 authors:
   - "@santiagorevale"
+  - "@maxulysse"

modules/gatk4/getpileupsummaries/main.nf

@@ -25,8 +25,8 @@ process GATK4_GETPILEUPSUMMARIES {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def sitesCommand = intervals ? " -L ${intervals} " : " -L ${variants} "
+    def interval_command = intervals ? "--intervals $intervals" : ""
-    def reference    = fasta ? " -R ${fasta}" :""
+    def reference_command = fasta ? "--reference $fasta" : ''
 
     def avail_mem = 3
     if (!task.memory) {
@@ -36,11 +36,12 @@ process GATK4_GETPILEUPSUMMARIES {
     }
     """
     gatk --java-options "-Xmx${avail_mem}g" GetPileupSummaries \\
-        -I $input \\
+        --input $input \\
-        -V $variants \\
+        --variant $variants \\
-        $sitesCommand \\
+        --output ${prefix}.pileups.table \\
-        ${reference} \\
+        $reference_command \\
-        -O ${prefix}.pileups.table \\
+        $sites_command \\
+        --tmp-dir . \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

modules/gatk4/haplotypecaller/main.nf

@@ -26,8 +26,9 @@ process GATK4_HAPLOTYPECALLER {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def interval_option = intervals ? "-L ${intervals}" : ""
+    def dbsnp_command = dbsnp ? "--dbsnp $dbsnp" : ""
-    def dbsnp_option    = dbsnp ? "-D ${dbsnp}" : ""
+    def interval_command = intervals ? "--intervals $intervals" : ""
+
     def avail_mem = 3
     if (!task.memory) {
         log.info '[GATK HaplotypeCaller] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@@ -35,16 +36,14 @@ process GATK4_HAPLOTYPECALLER {
         avail_mem = task.memory.giga
     }
     """
-    gatk \\
+    gatk --java-options "-Xmx${avail_mem}g" HaplotypeCaller \\
-        --java-options "-Xmx${avail_mem}g" \\
+        --input $input \\
-        HaplotypeCaller \\
+        --output ${prefix}.vcf.gz \\
-        -R $fasta \\
+        --reference $fasta \\
-        -I $input \\
+        $dbsnp_command \\
-        ${dbsnp_option} \\
+        $interval_command \\
-        ${interval_option} \\
+        --tmp-dir . \\
-        -O ${prefix}.vcf.gz \\
+        $args
-        $args \\
-        --tmp-dir .
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/gatk4/indexfeaturefile/main.nf

@@ -19,6 +19,7 @@ process GATK4_INDEXFEATUREFILE {
 
     script:
     def args = task.ext.args ?: ''
+
     def avail_mem = 3
     if (!task.memory) {
         log.info '[GATK IndexFeatureFile] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@@ -26,10 +27,10 @@ process GATK4_INDEXFEATUREFILE {
         avail_mem = task.memory.giga
     }
     """
-    gatk --java-options "-Xmx${avail_mem}g" \\
+    gatk --java-options "-Xmx${avail_mem}g" IndexFeatureFile \\
-        IndexFeatureFile \\
+        --input $feature_file \\
-        $args \\
+        --tmp-dir . \\
-        -I $feature_file
+        $args
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/gatk4/intervallisttobed/main.nf

@@ -8,7 +8,7 @@ process GATK4_INTERVALLISTTOBED {
         'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
 
     input:
-    tuple val(meta), path(interval)
+    tuple val(meta), path(intervals)
 
     output:
     tuple val(meta), path("*.bed"), emit: bed
@@ -29,8 +29,9 @@ process GATK4_INTERVALLISTTOBED {
     }
     """
     gatk --java-options "-Xmx${avail_mem}g" IntervalListToBed \\
-        --INPUT ${interval} \\
+        --INPUT $intervals \\
         --OUTPUT ${prefix}.bed \\
+        --TMP_DIR . \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

modules/gatk4/intervallisttools/main.nf

@@ -8,7 +8,7 @@ process GATK4_INTERVALLISTTOOLS {
         'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
 
     input:
-    tuple val(meta), path(interval_list)
+    tuple val(meta), path(intervals)
 
     output:
     tuple val(meta), path("*_split/*/*.interval_list"), emit: interval_list
@@ -20,6 +20,7 @@ process GATK4_INTERVALLISTTOOLS {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+
     def avail_mem = 3
     if (!task.memory) {
         log.info '[GATK IntervalListTools] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@@ -30,10 +31,10 @@ process GATK4_INTERVALLISTTOOLS {
 
     mkdir ${prefix}_split
 
-    gatk --java-options "-Xmx${avail_mem}g" \\
+    gatk --java-options "-Xmx${avail_mem}g" IntervalListTools \\
-        IntervalListTools \\
+        --INPUT $intervals \\
-        -I ${interval_list} \\
+        --OUTPUT ${prefix}_split \\
-        -O ${prefix}_split \\
+        --TMP_DIR . \\
         $args
 
     python3 <<CODE

modules/gatk4/learnreadorientationmodel/main.nf

@@ -20,8 +20,8 @@ process GATK4_LEARNREADORIENTATIONMODEL {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def inputs_list = []
+    def input_list = f1r2.collect{"--input $it"}.join(' ')
-    f1r2.each() { a -> inputs_list.add(" -I " + a) }
+
     def avail_mem = 3
     if (!task.memory) {
         log.info '[GATK LearnReadOrientationModel] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@@ -29,10 +29,10 @@ process GATK4_LEARNREADORIENTATIONMODEL {
         avail_mem = task.memory.giga
     }
     """
-    gatk --java-options "-Xmx${avail_mem}g" \\
+    gatk --java-options "-Xmx${avail_mem}g" LearnReadOrientationModel \\
-        LearnReadOrientationModel \\
+        $input_list \\
-        ${inputs_list.join(' ')} \\
+        --output ${prefix}.tar.gz \\
-        -O ${prefix}.tar.gz \\
+        --tmp-dir . \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

modules/gatk4/markduplicates/main.nf

@@ -8,7 +8,7 @@ process GATK4_MARKDUPLICATES {
         'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
 
     input:
-    tuple val(meta), path(bams)
+    tuple val(meta), path(bam)
 
     output:
     tuple val(meta), path("*.bam")    , emit: bam
@@ -22,7 +22,8 @@ process GATK4_MARKDUPLICATES {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def bam_list = bams.collect(){ bam -> "--INPUT ".concat(bam.toString()) }.join(" ")
+    def input_list = bam.collect{"--INPUT $it"}.join(' ')
+
     def avail_mem = 3
     if (!task.memory) {
         log.info '[GATK MarkDuplicates] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@@ -31,11 +32,10 @@ process GATK4_MARKDUPLICATES {
     }
     """
     gatk --java-options "-Xmx${avail_mem}g" MarkDuplicates \\
-        $bam_list \\
+        $input_list \\
+        --OUTPUT ${prefix}.bam \\
         --METRICS_FILE ${prefix}.metrics \\
         --TMP_DIR . \\
-        --CREATE_INDEX true \\
-        --OUTPUT ${prefix}.bam \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

modules/gatk4/markduplicates/meta.yml

@@ -49,3 +49,4 @@ output:
 authors:
   - "@ajodeh-juma"
   - "@FriederikeHanssen"
+  - "@maxulysse"

modules/gatk4/markduplicatesspark/main.nf

@@ -0,0 +1,50 @@
+process GATK4_MARKDUPLICATES_SPARK {
+    tag "$meta.id"
+    label 'process_high'
+
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.3.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.3.0--hdfd78af_0' :
+        'broadinstitute/gatk:4.2.3.0' }"
+
+    input:
+    tuple val(meta), path(bam)
+    path  fasta
+    path  fasta_fai
+    path  dict
+
+    output:
+    tuple val(meta), path("${prefix}"), emit: output
+    path "versions.yml"               , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    prefix = task.ext.prefix ?: "${meta.id}"
+    def input_list = bam.collect{"--INPUT $it"}.join(' ')
+
+    def avail_mem = 3
+    if (!task.memory) {
+        log.info '[GATK MarkDuplicatesSpark] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
+    } else {
+        avail_mem = task.memory.giga
+    }
+    """
+    export SPARK_USER=spark3
+
+    gatk --java-options "-Xmx${avail_mem}g" MarkDuplicatesSpark \\
+        $input_list \\
+        --output $prefix \\
+        --reference $fasta \\
+        --spark-master local[${task.cpus}] \\
+        --tmp-dir . \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
+    END_VERSIONS
+    """
+}

modules/gatk4/markduplicatesspark/meta.yml

@@ -0,0 +1,60 @@
+name: gatk4_markduplicates_spark
+description: This tool locates and tags duplicate reads in a BAM or SAM file, where duplicate reads are defined as originating from a single fragment of DNA.
+keywords:
+  - markduplicates
+  - bam
+  - sort
+tools:
+  - gatk4:
+      description:
+        Developed in the Data Sciences Platform at the Broad Institute, the toolkit offers a wide variety of tools
+        with a primary focus on variant discovery and genotyping. Its powerful processing engine
+        and high-performance computing features make it capable of taking on projects of any size.
+      homepage: https://gatk.broadinstitute.org/hc/en-us
+      documentation: https://gatk.broadinstitute.org/hc/en-us/articles/360037052812-MarkDuplicates-Picard-
+      tool_dev_url: https://github.com/broadinstitute/gatk
+      doi: 10.1158/1538-7445.AM2017-3590
+      licence: ["MIT"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: Sorted BAM file
+      pattern: "*.{bam}"
+  - fasta:
+      type: file
+      description: The reference fasta file
+      pattern: "*.fasta"
+  - fai:
+      type: file
+      description: Index of reference fasta file
+      pattern: "*.fasta.fai"
+  - dict:
+      type: file
+      description: GATK sequence dictionary
+      pattern: "*.dict"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - bam:
+      type: file
+      description: Marked duplicates BAM file
+      pattern: "*.{bam}"
+
+authors:
+  - "@ajodeh-juma"
+  - "@FriederikeHanssen"
+  - "@maxulysse"

modules/gatk4/mergebamalignment/main.nf

@@ -22,6 +22,7 @@ process GATK4_MERGEBAMALIGNMENT {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+
     def avail_mem = 3
     if (!task.memory) {
         log.info '[GATK MergeBamAlignment] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@@ -30,10 +31,11 @@ process GATK4_MERGEBAMALIGNMENT {
     }
     """
     gatk --java-options "-Xmx${avail_mem}g" MergeBamAlignment \\
-        -ALIGNED $aligned \\
+        --UNMAPPED_BAM $unmapped \\
-        -UNMAPPED $unmapped \\
+        --ALIGNED_BAM $aligned \\
-        -R $fasta \\
+        --OUTPUT ${prefix}.bam \\
-        -O ${prefix}.bam \\
+        --REFERENCE_SEQUENCE $fasta \\
+        --TMP_DIR . \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

modules/gatk4/mergemutectstats/main.nf

@@ -9,6 +9,7 @@ process GATK4_MERGEMUTECTSTATS {
 
     input:
     tuple val(meta), path(stats)
+
     output:
     tuple val(meta), path("*.vcf.gz.stats"), emit: stats
     path "versions.yml"                    , emit: versions
@@ -19,7 +20,7 @@ process GATK4_MERGEMUTECTSTATS {
     script:
     def args = task.ext.args ?: ''
     prefix = task.ext.prefix ?: "${meta.id}"
-    def input = stats.collect{ " -stats ${it} "}.join()
+    def input_list = stats.collect{ "--stats ${it}"}.join(' ')
 
     def avail_mem = 3
     if (!task.memory) {
@@ -29,8 +30,9 @@ process GATK4_MERGEMUTECTSTATS {
     }
     """
     gatk --java-options "-Xmx${avail_mem}g" MergeMutectStats \\
-        ${input} \\
+        $input_list \\
-        -output ${meta.id}.vcf.gz.stats \\
+        --output ${prefix}.vcf.gz.stats \\
+        --tmp-dir . \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

modules/gatk4/mergevcfs/main.nf

@@ -8,9 +8,8 @@ process GATK4_MERGEVCFS {
         'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
 
     input:
-    tuple val(meta), path(vcfs)
+    tuple val(meta), path(vcf)
-    path  ref_dict
+    path  dict
-    val   use_ref_dict
 
     output:
     tuple val(meta), path('*.vcf.gz'), emit: vcf
@@ -22,13 +21,9 @@ process GATK4_MERGEVCFS {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+    def input_list = vcf.collect{ "--INPUT $it"}.join(' ')
+    def reference_command = dict ? "--SEQUENCE_DICTIONARY $dict" : ""
 
-    // Make list of VCFs to merge
-    def input = ""
-    for (vcf in vcfs) {
-        input += " I=${vcf}"
-    }
-    def ref = use_ref_dict ? "D=${ref_dict}" : ""
     def avail_mem = 3
     if (!task.memory) {
         log.info '[GATK MergeVcfs] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@@ -37,9 +32,10 @@ process GATK4_MERGEVCFS {
     }
     """
     gatk --java-options "-Xmx${avail_mem}g" MergeVcfs \\
-        $input \\
+        $input_list \\
-        O=${prefix}.vcf.gz \\
+        --OUTPUT ${prefix}.vcf.gz \\
-        $ref \\
+        $reference_command \\
+        --TMP_DIR . \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

modules/gatk4/mutect2/main.nf

@@ -8,10 +8,7 @@ process GATK4_MUTECT2 {
         'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
 
     input:
-    tuple val(meta) , path(input) , path(input_index) , path(intervals), val(which_norm)
+    tuple val(meta), path(input), path(input_index), path(intervals)
-    val  run_single
-    val  run_pon
-    val  run_mito
     path fasta
     path fai
     path dict
@@ -33,28 +30,10 @@ process GATK4_MUTECT2 {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def panels_command = ''
+    def inputs = input.collect{ "--input $it"}.join(" ")
-    def normals_command = ''
+    def interval_command = intervals ? "--intervals $intervals" : ""
-
+    def pon_command = panel_of_normals ? "--panel-of-normals $panel_of_normals" : ""
-    def inputs_command = '-I ' + input.join( ' -I ')
+    def gr_command = germline_resource ? "--germline-resource $germline_resource" : ""
-    def interval = intervals ? "-L ${intervals}" : ""
-
-    if(run_pon) {
-        panels_command = ''
-        normals_command = ''
-
-    } else if(run_single) {
-        panels_command = " --germline-resource $germline_resource --panel-of-normals $panel_of_normals"
-        normals_command = ''
-
-    } else if(run_mito){
-        panels_command = "-L ${intervals} --mitochondria-mode"
-        normals_command = ''
-
-    } else {
-        panels_command = " --germline-resource $germline_resource --panel-of-normals $panel_of_normals --f1r2-tar-gz ${prefix}.f1r2.tar.gz"
-        normals_command = '-normal ' + which_norm.join( ' -normal ')
-    }
 
     def avail_mem = 3
     if (!task.memory) {
@@ -64,12 +43,13 @@ process GATK4_MUTECT2 {
     }
     """
     gatk --java-options "-Xmx${avail_mem}g" Mutect2 \\
-        -R ${fasta} \\
+        $inputs \\
-        ${inputs_command} \\
+        --output ${prefix}.vcf.gz \\
-        ${normals_command} \\
+        --reference $fasta \\
-        ${panels_command} \\
+        $pon_command \\
-        ${interval} \\
+        $gr_command \\
-        -O ${prefix}.vcf.gz \\
+        $interval_command \\
+        --tmp-dir . \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

modules/gatk4/mutect2/meta.yml

@@ -34,22 +34,6 @@ input:
       type: File/string
       description: Specify region the tools is run on.
       pattern: ".{bed,interval_list}/chrM"
-  - which_norm:
-      type: list
-      description: optional list of sample headers contained in the normal sample bam files (these are required for tumor_normal_pair mode)
-      pattern: "testN"
-  - run_single:
-      type: boolean
-      description: Specify whether or not to run in tumor_single mode instead of tumor_normal_pair mode (will be ignored if run_pon is also true)
-      pattern: "true/false"
-  - run_pon:
-      type: boolean
-      description: Specify whether or not to run in panel_of_normal mode instead of tumor_normal_pair mode
-      pattern: "true/false"
-  - run_mito:
-      type: boolean
-      description: Specify whether or not to run in mitochondria-mode instead of tumor_normal_pair mode
-      pattern: "true/false"
   - fasta:
       type: file
       description: The reference fasta file

modules/gatk4/revertsam/main.nf

@@ -20,6 +20,7 @@ process GATK4_REVERTSAM {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+
     def avail_mem = 3
     if (!task.memory) {
         log.info '[GATK RevertSam] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@@ -28,8 +29,9 @@ process GATK4_REVERTSAM {
     }
     """
     gatk --java-options "-Xmx${avail_mem}g" RevertSam \\
-        I=$bam \\
+        --INPUT $bam \\
-        O=${prefix}.reverted.bam \\
+        --OUTPUT ${prefix}.reverted.bam \\
+        --TMP_DIR . \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

modules/gatk4/samtofastq/main.nf

@@ -20,7 +20,8 @@ process GATK4_SAMTOFASTQ {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def output   = meta.single_end ? "FASTQ=${prefix}.fastq.gz" : "FASTQ=${prefix}_1.fastq.gz SECOND_END_FASTQ=${prefix}_2.fastq.gz"
+    def output = meta.single_end ? "--FASTQ ${prefix}.fastq.gz" : "--FASTQ ${prefix}_1.fastq.gz --SECOND_END_FASTQ ${prefix}_2.fastq.gz"
+
     def avail_mem = 3
     if (!task.memory) {
         log.info '[GATK SamToFastq] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@@ -29,8 +30,9 @@ process GATK4_SAMTOFASTQ {
     }
     """
     gatk --java-options "-Xmx${avail_mem}g" SamToFastq \\
-        I=$bam \\
+        --INPUT $bam \\
         $output \\
+        --TMP_DIR . \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

modules/gatk4/selectvariants/main.nf

@@ -21,6 +21,7 @@ process GATK4_SELECTVARIANTS {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+
     def avail_mem = 3
     if (!task.memory) {
         log.info '[GATK VariantFiltration] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@@ -29,8 +30,9 @@ process GATK4_SELECTVARIANTS {
     }
     """
     gatk --java-options "-Xmx${avail_mem}G" SelectVariants \\
-        -V $vcf \\
+        --variant $vcf \\
-        -O ${prefix}.selectvariants.vcf.gz \\
+        --output ${prefix}.selectvariants.vcf.gz \\
+        --tmp-dir . \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

modules/gatk4/splitncigarreads/main.nf

@@ -23,6 +23,7 @@ process GATK4_SPLITNCIGARREADS {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+
     def avail_mem = 3
     if (!task.memory) {
         log.info '[GATK SplitNCigarReads] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@@ -31,9 +32,10 @@ process GATK4_SPLITNCIGARREADS {
     }
     """
     gatk --java-options "-Xmx${avail_mem}g" SplitNCigarReads \\
-        -R $fasta \\
+        --input $bam \\
-        -I $bam \\
+        --output ${prefix}.bam \\
-        -O ${prefix}.bam \\
+        --reference $fasta \\
+        --tmp-dir . \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

modules/gatk4/variantfiltration/main.nf

@@ -8,7 +8,7 @@ process GATK4_VARIANTFILTRATION {
         'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
 
     input:
-    tuple val(meta), path(vcf), path(vcf_tbi)
+    tuple val(meta), path(vcf), path(tbi)
     path  fasta
     path  fai
     path  dict
@@ -24,6 +24,7 @@ process GATK4_VARIANTFILTRATION {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+
     def avail_mem = 3
     if (!task.memory) {
         log.info '[GATK VariantFiltration] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@@ -32,9 +33,10 @@ process GATK4_VARIANTFILTRATION {
     }
     """
     gatk --java-options "-Xmx${avail_mem}G" VariantFiltration \\
-        -R $fasta \\
+        --variant $vcf \\
-        -V $vcf \\
+        --output ${prefix}.vcf.gz \\
-        -O ${prefix}.vcf.gz \\
+        --reference $fasta \\
+        --tmp-dir . \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

modules/gatk4/variantrecalibrator/main.nf

@@ -8,11 +8,11 @@ process GATK4_VARIANTRECALIBRATOR {
         'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
 
     input:
-    tuple val(meta), path(vcf) , path(tbi)
+    tuple val(meta), path(vcf), path(tbi)
+    tuple path(vcfs), path(tbis), val(labels)
     path  fasta
     path  fai
     path  dict
-    tuple path(resvcfs), path(restbis), val(reslabels)
 
     output:
     tuple val(meta), path("*.recal")   , emit: recal
@@ -27,8 +27,8 @@ process GATK4_VARIANTRECALIBRATOR {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    refCommand = fasta ? "-R ${fasta} " : ''
+    def reference_command = fasta ? "--reference $fasta " : ''
-    resourceCommand = '--resource:' + reslabels.join( ' --resource:')
+    def resource_command = labels.collect{"--resource:$it"}.join(' ')
 
     def avail_mem = 3
     if (!task.memory) {
@@ -38,11 +38,12 @@ process GATK4_VARIANTRECALIBRATOR {
     }
     """
     gatk --java-options "-Xmx${avail_mem}g" VariantRecalibrator \\
-        ${refCommand} \\
+        --variant $vcf \\
-        -V ${vcf} \\
+        --output ${prefix}.recal \\
-        -O ${prefix}.recal \\
         --tranches-file ${prefix}.tranches \\
-        ${resourceCommand} \\
+        $reference_command \\
+        $resource_command \\
+        --tmp-dir . \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

tests/modules/gatk4/applybqsr/test.yml

@@ -7,7 +7,6 @@
     - path: output/gatk4/test.bam
       md5sum: d088422be886dc8507ff97fcc7dd968a
     - path: output/gatk4/versions.yml
-      md5sum: d5c6455d8a77aecc63f87c795fc3443e
 
 - name: gatk4 applybqsr test_gatk4_applybqsr_intervals
   command: nextflow run tests/modules/gatk4/applybqsr -entry test_gatk4_applybqsr_intervals -c tests/config/nextflow.config -c ./tests/modules/gatk4/applybqsr/nextflow.config
@@ -18,7 +17,6 @@
     - path: output/gatk4/test.bam
       md5sum: 4bfa18d651abd945e240b05e70107716
     - path: output/gatk4/versions.yml
-      md5sum: cb4cb8a62e117b4adc643ae47883d53c
 
 - name: gatk4 applybqsr test_gatk4_applybqsr_cram
   command: nextflow run tests/modules/gatk4/applybqsr -entry test_gatk4_applybqsr_cram -c tests/config/nextflow.config -c ./tests/modules/gatk4/applybqsr/nextflow.config
@@ -29,4 +27,3 @@
     - path: output/gatk4/test.cram
       md5sum: 2e0bca197af4f043a4a85152e6edbe04
     - path: output/gatk4/versions.yml
-      md5sum: 1efaa18be943bab4e4c54191d6eaa260

tests/modules/gatk4/applybqsrspark/main.nf

@@ -0,0 +1,47 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GATK4_APPLYBQSR_SPARK } from '../../../../modules/gatk4/applybqsrspark/main.nf'
+
+workflow test_gatk4_applybqsr_spark {
+    input = [ [ id:'test' ], // meta map
+              file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+              file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true),
+              file(params.test_data['sarscov2']['illumina']['test_baserecalibrator_table'], 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)
+    dict = file(params.test_data['sarscov2']['genome']['genome_dict'], checkIfExists: true)
+
+    GATK4_APPLYBQSR_SPARK ( input, fasta, fai, dict )
+}
+
+workflow test_gatk4_applybqsr_spark_intervals {
+    input = [ [ id:'test' ], // meta map
+                file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+                file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true),
+                file(params.test_data['sarscov2']['illumina']['test_baserecalibrator_table'], checkIfExists: true),
+                file(params.test_data['sarscov2']['genome']['test_bed'], 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)
+    dict  = file(params.test_data['sarscov2']['genome']['genome_dict'], checkIfExists: true)
+
+  GATK4_APPLYBQSR_SPARK ( input, fasta, fai, dict )
+}
+
+workflow test_gatk4_applybqsr_spark_cram {
+    input = [ [ id:'test' ], // meta map
+                file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram'], checkIfExists: true),
+                file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram_crai'], checkIfExists: true),
+                file(params.test_data['homo_sapiens']['illumina']['test_baserecalibrator_table'], checkIfExists: true),
+                file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true)
+              ]
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    fai = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+    dict = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
+
+  GATK4_APPLYBQSR_SPARK ( input, fasta, fai, dict )
+}

tests/modules/gatk4/applybqsrspark/nextflow.config

@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+}

tests/modules/gatk4/applybqsrspark/test.yml

@@ -0,0 +1,29 @@
+- name: gatk4 applybqsr test_gatk4_applybqsr_spark
+  command: nextflow run tests/modules/gatk4/applybqsrspark -entry test_gatk4_applybqsr_spark -c tests/config/nextflow.config -c ./tests/modules/gatk4/applybqsrspark/nextflow.config
+  tags:
+    - gatk4
+    - gatk4/applybqsrspark
+  files:
+    - path: output/gatk4/test.bam
+      md5sum: d088422be886dc8507ff97fcc7dd968a
+    - path: output/gatk4/versions.yml
+
+- name: gatk4 applybqsr test_gatk4_applybqsr_spark_intervals
+  command: nextflow run tests/modules/gatk4/applybqsrspark -entry test_gatk4_applybqsr_spark_intervals -c tests/config/nextflow.config -c ./tests/modules/gatk4/applybqsrspark/nextflow.config
+  tags:
+    - gatk4
+    - gatk4/applybqsrspark
+  files:
+    - path: output/gatk4/test.bam
+      md5sum: 4bfa18d651abd945e240b05e70107716
+    - path: output/gatk4/versions.yml
+
+- name: gatk4 applybqsr test_gatk4_applybqsr_spark_cram
+  command: nextflow run tests/modules/gatk4/applybqsrspark -entry test_gatk4_applybqsr_spark_cram -c tests/config/nextflow.config -c ./tests/modules/gatk4/applybqsrspark/nextflow.config
+  tags:
+    - gatk4
+    - gatk4/applybqsrspark
+  files:
+    - path: output/gatk4/test.cram
+      md5sum: 2e0bca197af4f043a4a85152e6edbe04
+    - path: output/gatk4/versions.yml

tests/modules/gatk4/applyvqsr/test.yml

@@ -7,7 +7,6 @@
     - path: output/gatk4/test.vcf.gz
     - path: output/gatk4/test.vcf.gz.tbi
     - path: output/gatk4/versions.yml
-      md5sum: ce9c443375683e7f2958fe958759ad29
 
 - name: gatk4 applyvqsr test_gatk4_applyvqsr_allele_specific
   command: nextflow run tests/modules/gatk4/applyvqsr -entry test_gatk4_applyvqsr_allele_specific -c tests/config/nextflow.config -c ./tests/modules/gatk4/applyvqsr/nextflow.config
@@ -18,4 +17,3 @@
     - path: output/gatk4/test.vcf.gz
     - path: output/gatk4/test.vcf.gz.tbi
     - path: output/gatk4/versions.yml
-      md5sum: 521353d12d576de2864f1d18a3e54f14

tests/modules/gatk4/baserecalibrator/test.yml

@@ -6,6 +6,7 @@
   files:
     - path: output/gatk4/test.table
       md5sum: e2e43abdc0c943c1a54dae816d0b9ea7
+    - path: output/gatk4/versions.yml
 
 - name: gatk4 baserecalibrator test_gatk4_baserecalibrator_cram
   command: nextflow run ./tests/modules/gatk4/baserecalibrator -entry test_gatk4_baserecalibrator_cram -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/baserecalibrator/nextflow.config
@@ -15,6 +16,7 @@
   files:
     - path: output/gatk4/test.table
       md5sum: 35d89a3811aa31711fc9815b6b80e6ec
+    - path: output/gatk4/versions.yml
 
 - name: gatk4 baserecalibrator test_gatk4_baserecalibrator_intervals
   command: nextflow run ./tests/modules/gatk4/baserecalibrator -entry test_gatk4_baserecalibrator_intervals -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/baserecalibrator/nextflow.config
@@ -24,6 +26,7 @@
   files:
     - path: output/gatk4/test.table
       md5sum: 9ecb5f00a2229291705addc09c0ec231
+    - path: output/gatk4/versions.yml
 
 - name: gatk4 baserecalibrator test_gatk4_baserecalibrator_multiple_sites
   command: nextflow run ./tests/modules/gatk4/baserecalibrator -entry test_gatk4_baserecalibrator_multiple_sites -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/baserecalibrator/nextflow.config
@@ -33,3 +36,4 @@
   files:
     - path: output/gatk4/test.table
       md5sum: e2e43abdc0c943c1a54dae816d0b9ea7
+    - path: output/gatk4/versions.yml

tests/modules/gatk4/baserecalibratorspark/main.nf

@@ -0,0 +1,69 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GATK4_BASERECALIBRATOR_SPARK } from '../../../../modules/gatk4/baserecalibratorspark/main.nf'
+
+workflow test_gatk4_baserecalibrator_spark {
+    input     = [ [ id:'test' ], // meta map
+                    file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+                    file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], 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)
+    dict = file(params.test_data['sarscov2']['genome']['genome_dict'], checkIfExists: true)
+    sites = file(params.test_data['sarscov2']['illumina']['test_vcf_gz'], checkIfExists: true)
+    sites_tbi = file(params.test_data['sarscov2']['illumina']['test_vcf_gz_tbi'], checkIfExists: true)
+
+    GATK4_BASERECALIBRATOR_SPARK ( input, fasta, fai, dict, sites, sites_tbi )
+}
+
+workflow test_gatk4_baserecalibrator_spark_cram {
+   input = [ [ id:'test' ], // meta map
+                file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram'], checkIfExists: true),
+                file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram_crai'], checkIfExists: true),
+                []
+              ]
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    fai = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+    dict = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
+    sites = file(params.test_data['homo_sapiens']['genome']['dbsnp_146_hg38_vcf_gz'], checkIfExists: true)
+    sites_tbi = file(params.test_data['homo_sapiens']['genome']['dbsnp_146_hg38_vcf_gz_tbi'], checkIfExists: true)
+
+    GATK4_BASERECALIBRATOR_SPARK ( input, fasta, fai, dict, sites, sites_tbi )
+}
+
+workflow test_gatk4_baserecalibrator_spark_intervals {
+    input     = [ [ id:'test' ], // meta map
+                  file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+                  file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true),
+                  file(params.test_data['sarscov2']['genome']['test_bed'], 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)
+    dict = file(params.test_data['sarscov2']['genome']['genome_dict'], checkIfExists: true)
+    sites = file(params.test_data['sarscov2']['illumina']['test_vcf_gz'], checkIfExists: true)
+    sites_tbi = file(params.test_data['sarscov2']['illumina']['test_vcf_gz_tbi'], checkIfExists: true)
+
+    GATK4_BASERECALIBRATOR_SPARK ( input, fasta, fai, dict, sites, sites_tbi )
+}
+
+workflow test_gatk4_baserecalibrator_spark_multiple_sites {
+    input     = [ [ id:'test' ], // meta map
+                  file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+                  file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], 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)
+    dict = file(params.test_data['sarscov2']['genome']['genome_dict'], checkIfExists: true)
+    sites =     [ file(params.test_data['sarscov2']['illumina']['test_vcf_gz'], checkIfExists: true),
+                  file(params.test_data['sarscov2']['illumina']['test2_vcf_gz'], checkIfExists: true)
+                ]
+    sites_tbi = [ file(params.test_data['sarscov2']['illumina']['test_vcf_gz_tbi'], checkIfExists: true),
+                  file(params.test_data['sarscov2']['illumina']['test2_vcf_gz_tbi'], checkIfExists: true)
+                ]
+
+  GATK4_BASERECALIBRATOR_SPARK ( input, fasta, fai, dict, sites, sites_tbi )
+}

tests/modules/gatk4/baserecalibratorspark/nextflow.config

@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+}

tests/modules/gatk4/baserecalibratorspark/test.yml

@@ -0,0 +1,39 @@
+- name: gatk4 baserecalibrator test_gatk4_baserecalibrator_spark
+  command: nextflow run ./tests/modules/gatk4/baserecalibratorspark -entry test_gatk4_baserecalibrator_spark -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/baserecalibratorspark/nextflow.config
+  tags:
+    - gatk4
+    - gatk4/baserecalibratorspark
+  files:
+    - path: output/gatk4/test.table
+      md5sum: e2e43abdc0c943c1a54dae816d0b9ea7
+    - path: output/gatk4/versions.yml
+
+- name: gatk4 baserecalibrator test_gatk4_baserecalibrator_spark_cram
+  command: nextflow run ./tests/modules/gatk4/baserecalibratorspark -entry test_gatk4_baserecalibrator_spark_cram -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/baserecalibratorspark/nextflow.config
+  tags:
+    - gatk4
+    - gatk4/baserecalibratorspark
+  files:
+    - path: output/gatk4/test.table
+      md5sum: 35d89a3811aa31711fc9815b6b80e6ec
+    - path: output/gatk4/versions.yml
+
+- name: gatk4 baserecalibrator test_gatk4_baserecalibrator_spark_intervals
+  command: nextflow run ./tests/modules/gatk4/baserecalibratorspark -entry test_gatk4_baserecalibrator_spark_intervals -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/baserecalibratorspark/nextflow.config
+  tags:
+    - gatk4
+    - gatk4/baserecalibratorspark
+  files:
+    - path: output/gatk4/test.table
+      md5sum: 9ecb5f00a2229291705addc09c0ec231
+    - path: output/gatk4/versions.yml
+
+- name: gatk4 baserecalibrator test_gatk4_baserecalibrator_spark_multiple_sites
+  command: nextflow run ./tests/modules/gatk4/baserecalibratorspark -entry test_gatk4_baserecalibrator_spark_multiple_sites -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/baserecalibratorspark/nextflow.config
+  tags:
+    - gatk4
+    - gatk4/baserecalibratorspark
+  files:
+    - path: output/gatk4/test.table
+      md5sum: e2e43abdc0c943c1a54dae816d0b9ea7
+    - path: output/gatk4/versions.yml

tests/modules/gatk4/bedtointervallist/test.yml

@@ -6,3 +6,4 @@
   files:
     - path: output/gatk4/test.interval_list
       md5sum: e51101c9357fb2d59fd30e370eefa39c
+    - path: output/gatk4/versions.yml

tests/modules/gatk4/calculatecontamination/main.nf

@@ -3,6 +3,7 @@
 nextflow.enable.dsl = 2
 
 include { GATK4_CALCULATECONTAMINATION                                              } from '../../../../modules/gatk4/calculatecontamination/main.nf'
+include { GATK4_CALCULATECONTAMINATION as GATK4_CALCULATECONTAMINATION_SEGMENTATION } from '../../../../modules/gatk4/calculatecontamination/main.nf'
 
 workflow test_gatk4_calculatecontamination_tumor_only {
 
@@ -10,9 +11,7 @@ workflow test_gatk4_calculatecontamination_tumor_only {
               file(params.test_data['homo_sapiens']['illumina']['test2_pileups_table'], checkIfExists: true),
               [] ]
 
-    segmentout = false
+    GATK4_CALCULATECONTAMINATION ( input )
-
-    GATK4_CALCULATECONTAMINATION ( input, segmentout )
 }
 
 workflow test_gatk4_calculatecontamination_matched_pair {
@@ -21,9 +20,7 @@ workflow test_gatk4_calculatecontamination_matched_pair {
               file(params.test_data['homo_sapiens']['illumina']['test2_pileups_table'], checkIfExists: true),
               file(params.test_data['homo_sapiens']['illumina']['test_pileups_table'], checkIfExists: true) ]
 
-    segmentout = false
+    GATK4_CALCULATECONTAMINATION ( input )
-
-    GATK4_CALCULATECONTAMINATION ( input, segmentout )
 }
 
 workflow test_gatk4_calculatecontamination_segmentation {
@@ -32,7 +29,5 @@ workflow test_gatk4_calculatecontamination_segmentation {
               file(params.test_data['homo_sapiens']['illumina']['test2_pileups_table'], checkIfExists: true),
               file(params.test_data['homo_sapiens']['illumina']['test_pileups_table'], checkIfExists: true) ]
 
-    segmentout = true
+    GATK4_CALCULATECONTAMINATION_SEGMENTATION ( input )
-
-    GATK4_CALCULATECONTAMINATION ( input, segmentout )
 }

tests/modules/gatk4/calculatecontamination/nextflow.config

@@ -2,4 +2,8 @@ process {
 
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
 
+    withName: GATK4_CALCULATECONTAMINATION_SEGMENTATION {
+        ext.args = { "--tumor-segmentation ${meta.id}.segmentation.table" }
+    }
+
 }

tests/modules/gatk4/calculatecontamination/test.yml

@@ -7,7 +7,6 @@
     - path: output/gatk4/test.contamination.table
       md5sum: 46c708c943b453da89a3da08acfdb2a7
     - path: output/gatk4/versions.yml
-      md5sum: 3da8f1c0de968886330a3f7a3a1c6616
 
 - name: gatk4 calculatecontamination test_gatk4_calculatecontamination_matched_pair
   command: nextflow run tests/modules/gatk4/calculatecontamination -entry test_gatk4_calculatecontamination_matched_pair -c tests/config/nextflow.config -c ./tests/modules/gatk4/calculatecontamination/nextflow.config
@@ -18,7 +17,6 @@
     - path: output/gatk4/test.contamination.table
       md5sum: 46c708c943b453da89a3da08acfdb2a7
     - path: output/gatk4/versions.yml
-      md5sum: 14ab12a71b0c2b87d8cd53639a991b3a
 
 - name: gatk4 calculatecontamination test_gatk4_calculatecontamination_segmentation
   command: nextflow run tests/modules/gatk4/calculatecontamination -entry test_gatk4_calculatecontamination_segmentation -c tests/config/nextflow.config -c ./tests/modules/gatk4/calculatecontamination/nextflow.config
@@ -31,4 +29,3 @@
     - path: output/gatk4/test.segmentation.table
       md5sum: f4643d9319bde4efbfbe516d6fb13052
     - path: output/gatk4/versions.yml
-      md5sum: d2e61315de31f512e448f0cb4b77db54

tests/modules/gatk4/combinegvcfs/test.yml

@@ -7,4 +7,3 @@
     - path: output/gatk4/test.combined.g.vcf.gz
       contains: ["VCFv4.2"]
     - path: output/gatk4/versions.yml
-      md5sum: 49d9c467f84b6a99a4da3ef161af26bd

tests/modules/gatk4/createsequencedictionary/test.yml

@@ -6,3 +6,4 @@
   files:
     - path: output/gatk4/genome.dict
       md5sum: 7362679f176e0f52add03c08f457f646
+    - path: output/gatk4/versions.yml

tests/modules/gatk4/createsomaticpanelofnormals/test.yml

@@ -7,3 +7,4 @@
     - path: output/gatk4/test.pon.vcf.gz
     - path: output/gatk4/test.pon.vcf.gz.tbi
       md5sum: e7ca7e9fe76ce12198fd54ec9a64fad4
+    - path: output/gatk4/versions.yml

tests/modules/gatk4/estimatelibrarycomplexity/test.yml

@@ -5,3 +5,4 @@
     - gatk4
   files:
     - path: output/gatk4/test.metrics
+    - path: output/gatk4/versions.yml

tests/modules/gatk4/fastqtosam/test.yml

@@ -6,7 +6,6 @@
   files:
     - path: output/gatk4/test.bam
     - path: output/gatk4/versions.yml
-      md5sum: 381cdb2496b2fcc7bbc371a6e4156c7e
 
 - name: gatk4 fastqtosam test_gatk4_fastqtosam_paired_end
   command: nextflow run tests/modules/gatk4/fastqtosam -entry test_gatk4_fastqtosam_paired_end -c tests/config/nextflow.config  -c ./tests/modules/gatk4/fastqtosam/nextflow.config
@@ -16,4 +15,3 @@
   files:
     - path: output/gatk4/test.bam
     - path: output/gatk4/versions.yml
-      md5sum: 1d07c90cbd31992c9ba003f02d1b3502

tests/modules/gatk4/filtermutectcalls/test.yml

@@ -8,6 +8,7 @@
     - path: output/gatk4/test.filtered.vcf.gz.filteringStats.tsv
       md5sum: 55f228e5520c8b9fbac017d3a3a6c5fd
     - path: output/gatk4/test.filtered.vcf.gz.tbi
+    - path: output/gatk4/versions.yml
 
 - name: gatk4 filtermutectcalls test_gatk4_filtermutectcalls_with_files
   command: nextflow run ./tests/modules/gatk4/filtermutectcalls -entry test_gatk4_filtermutectcalls_with_files -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/filtermutectcalls/nextflow.config
@@ -19,6 +20,7 @@
     - path: output/gatk4/test.filtered.vcf.gz.filteringStats.tsv
       md5sum: 9ae27fbd04af1a2ea574e2ff1c3a683b
     - path: output/gatk4/test.filtered.vcf.gz.tbi
+    - path: output/gatk4/versions.yml
 
 - name: gatk4 filtermutectcalls test_gatk4_filtermutectcalls_use_val
   command: nextflow run ./tests/modules/gatk4/filtermutectcalls -entry test_gatk4_filtermutectcalls_use_val -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/filtermutectcalls/nextflow.config
@@ -30,3 +32,4 @@
     - path: output/gatk4/test.filtered.vcf.gz.filteringStats.tsv
       md5sum: 95cc3e37705bd3b97a292c5d46ab82f3
     - path: output/gatk4/test.filtered.vcf.gz.tbi
+    - path: output/gatk4/versions.yml

tests/modules/gatk4/gatherbqsrreports/test.yml

@@ -7,7 +7,6 @@
     - path: output/gatk4/test.table
       md5sum: 9603b69fdc3b5090de2e0dd78bfcc4bf
     - path: output/gatk4/versions.yml
-      md5sum: 8d52c5aaab73294e9ea5491b95f3e1e1
 
 - name: gatk4 gatherbqsrreports test_gatk4_gatherbqsrreports_multiple
   command: nextflow run tests/modules/gatk4/gatherbqsrreports -entry test_gatk4_gatherbqsrreports_multiple -c tests/config/nextflow.config
@@ -18,4 +17,3 @@
     - path: output/gatk4/test.table
       md5sum: 0c1257eececf95db8ca378272d0f21f9
     - path: output/gatk4/versions.yml
-      md5sum: 91cad396b9f2045c3cd8c0f256672e80

tests/modules/gatk4/gatherpileupsummaries/test.yml

@@ -6,3 +6,4 @@
   files:
     - path: output/gatk4/test.pileupsummaries.table
       md5sum: 8e0ca6f66e112bd2f7ec1d31a2d62469
+    - path: output/gatk4/versions.yml

tests/modules/gatk4/genomicsdbimport/test.yml

@@ -5,11 +5,9 @@
     - gatk4/genomicsdbimport
   files:
     - path: output/gatk4/test/__tiledb_workspace.tdb
-      md5sum: d41d8cd98f00b204e9800998ecf8427e
     - path: output/gatk4/test/callset.json
       md5sum: a7d07d1c86449bbb1091ff29368da07a
     - path: output/gatk4/test/chr22$1$40001/.__consolidation_lock
-      md5sum: d41d8cd98f00b204e9800998ecf8427e
     - path: output/gatk4/test/chr22$1$40001/__array_schema.tdb
     - path: output/gatk4/test/chr22$1$40001/genomicsdb_meta_dir/genomicsdb_column_bounds.json
       md5sum: 2502f79658bc000578ebcfddfc1194c0
@@ -19,7 +17,6 @@
     - path: output/gatk4/test/vidmap.json
       md5sum: 18d3f68bd2cb6f4474990507ff95017a
     - path: output/gatk4/versions.yml
-      md5sum: 91f5c3e9529982f9c819860b403576ce
 
 - name: gatk4 genomicsdbimport test_gatk4_genomicsdbimport_get_intervalslist
   command: nextflow run tests/modules/gatk4/genomicsdbimport -entry test_gatk4_genomicsdbimport_get_intervalslist -c tests/config/nextflow.config -c ./tests/modules/gatk4/genomicsdbimport/nextflow.config
@@ -30,9 +27,7 @@
     - path: output/gatk4/test.interval_list
       md5sum: 4c85812ac15fc1cd29711a851d23c0bf
     - path: output/gatk4/versions.yml
-      md5sum: a898fe1cbc4acfa5936c0ffdcf121401
     - path: output/untar/versions.yml
-      md5sum: 8f080677b109aea2cfca50208b077534
 
 - name: gatk4 genomicsdbimport test_gatk4_genomicsdbimport_update_genomicsdb
   command: nextflow run tests/modules/gatk4/genomicsdbimport -entry test_gatk4_genomicsdbimport_update_genomicsdb -c tests/config/nextflow.config -c ./tests/modules/gatk4/genomicsdbimport/nextflow.config
@@ -41,11 +36,9 @@
     - gatk4/genomicsdbimport
   files:
     - path: output/gatk4/test_genomicsdb/__tiledb_workspace.tdb
-      md5sum: d41d8cd98f00b204e9800998ecf8427e
     - path: output/gatk4/test_genomicsdb/callset.json
       md5sum: 1ea31b59b9a218dd5681164aff4a5e07
     - path: output/gatk4/test_genomicsdb/chr22$1$40001/.__consolidation_lock
-      md5sum: d41d8cd98f00b204e9800998ecf8427e
     - path: output/gatk4/test_genomicsdb/chr22$1$40001/__array_schema.tdb
       md5sum: 6709e67921ae840bf61fbfb192554eda
     - path: output/gatk4/test_genomicsdb/chr22$1$40001/genomicsdb_meta_dir/genomicsdb_column_bounds.json
@@ -55,6 +48,4 @@
     - path: output/gatk4/test_genomicsdb/vidmap.json
       md5sum: 18d3f68bd2cb6f4474990507ff95017a
     - path: output/gatk4/versions.yml
-      md5sum: d87baa3f4218c5554cad3c008cb6cbc4
     - path: output/untar/versions.yml
-      md5sum: 9b2916aea9790bdf427c0cb38109110c

tests/modules/gatk4/genotypegvcfs/main.nf

@@ -11,14 +11,15 @@ 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),
+            [],
             []
         ]
 
     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)
+    fai   = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
-    fastaDict    = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
+    dict  = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
 
-    GATK4_GENOTYPEGVCFS ( input, fasta, fastaIndex, fastaDict, [], [])
+    GATK4_GENOTYPEGVCFS ( input, fasta, fai, dict, [], [])
 }
 
 // Basic parameters with compressed VCF input
@@ -27,14 +28,15 @@ 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),
+            [],
             []
         ]
 
     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)
+    fai   = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
-    fastaDict    = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
+    dict  = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
 
-    GATK4_GENOTYPEGVCFS ( input, fasta, fastaIndex, fastaDict, [], [])
+    GATK4_GENOTYPEGVCFS ( input, fasta, fai, dict, [], [])
 }
 
 // Basic parameters + optional dbSNP
@@ -43,17 +45,18 @@ 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),
+            [],
             []
         ]
 
     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)
+    fai   = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
-    fastaDict    = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
+    dict  = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
 
     dbsnp     = file(params.test_data['homo_sapiens']['genome']['dbsnp_146_hg38_vcf_gz'], checkIfExists: true)
-    dbsnpIndex   = file(params.test_data['homo_sapiens']['genome']['dbsnp_146_hg38_vcf_gz_tbi'], checkIfExists: true)
+    dbsnp_tbi = file(params.test_data['homo_sapiens']['genome']['dbsnp_146_hg38_vcf_gz_tbi'], checkIfExists: true)
 
-    GATK4_GENOTYPEGVCFS ( input, fasta, fastaIndex, fastaDict, dbsnp, dbsnpIndex)
+    GATK4_GENOTYPEGVCFS ( input, fasta, fai, dict, dbsnp, dbsnp_tbi)
 }
 
 // Basic parameters + optional intervals
@@ -65,10 +68,10 @@ workflow test_gatk4_genotypegvcfs_gz_input_intervals {
             file(params.test_data['homo_sapiens']['genome']['genome_bed'], 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)
+    fai   = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
-    fastaDict    = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
+    dict  = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
 
-    GATK4_GENOTYPEGVCFS ( input, fasta, fastaIndex, fastaDict, [], [])
+    GATK4_GENOTYPEGVCFS ( input, fasta, fai, dict, [], [])
 }
 
 // Basic parameters + optional dbSNP + optional intervals
@@ -81,21 +84,21 @@ workflow test_gatk4_genotypegvcfs_gz_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)
+    fai   = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
-    fastaDict    = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
+    dict  = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
 
     dbsnp     = file(params.test_data['homo_sapiens']['genome']['dbsnp_146_hg38_vcf_gz'], checkIfExists: true)
-    dbsnpIndex   = file(params.test_data['homo_sapiens']['genome']['dbsnp_146_hg38_vcf_gz_tbi'], checkIfExists: true)
+    dbsnp_tbi = file(params.test_data['homo_sapiens']['genome']['dbsnp_146_hg38_vcf_gz_tbi'], checkIfExists: true)
 
-    GATK4_GENOTYPEGVCFS ( input, fasta, fastaIndex, fastaDict, dbsnp, dbsnpIndex )
+    GATK4_GENOTYPEGVCFS ( input, fasta, fai, dict, dbsnp, dbsnp_tbi )
 }
 
 // Basic parameters with GenomicsDB input
 workflow test_gatk4_genotypegvcfs_gendb_input {
 
     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)
+    fai   = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
-    fastaDict       = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
+    dict  = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
 
     test_genomicsdb = [ [], file(params.test_data['homo_sapiens']['illumina']['test_genomicsdb_tar_gz'], checkIfExists: true) ]
 
@@ -106,18 +109,18 @@ workflow test_gatk4_genotypegvcfs_gendb_input {
 
     input = Channel.of([ id:'test' ]).combine(gendb)
 
-    GATK4_GENOTYPEGVCFS ( input, fasta, fastaIndex, fastaDict, [], [])
+    GATK4_GENOTYPEGVCFS ( input, fasta, fai, dict, [], [])
 }
 
 // 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)
+    fai   = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
-    fastaDict    = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
+    dict  = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
 
     dbsnp     = file(params.test_data['homo_sapiens']['genome']['dbsnp_146_hg38_vcf_gz'], checkIfExists: true)
-    dbsnpIndex   = file(params.test_data['homo_sapiens']['genome']['dbsnp_146_hg38_vcf_gz_tbi'], checkIfExists: true)
+    dbsnp_tbi = file(params.test_data['homo_sapiens']['genome']['dbsnp_146_hg38_vcf_gz_tbi'], checkIfExists: true)
 
     test_genomicsdb = [ [], file(params.test_data['homo_sapiens']['illumina']['test_genomicsdb_tar_gz'], checkIfExists: true) ]
 
@@ -127,15 +130,15 @@ workflow test_gatk4_genotypegvcfs_gendb_input_dbsnp {
     gendb.add([])
     input = Channel.of([ id:'test' ]).combine(gendb)
 
-    GATK4_GENOTYPEGVCFS ( input, fasta, fastaIndex, fastaDict, dbsnp, dbsnpIndex)
+    GATK4_GENOTYPEGVCFS ( input, fasta, fai, dict, dbsnp, dbsnp_tbi)
 }
 
 // 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)
+    fai   = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
-    fastaDict    = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
+    dict  = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
 
     test_genomicsdb = [ [], file(params.test_data['homo_sapiens']['illumina']['test_genomicsdb_tar_gz'], checkIfExists: true) ]
 
@@ -145,18 +148,18 @@ workflow test_gatk4_genotypegvcfs_gendb_input_intervals {
     gendb.add([file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true)])
     input = Channel.of([ id:'test' ]).combine(gendb)
 
-    GATK4_GENOTYPEGVCFS ( input, fasta, fastaIndex, fastaDict, [], [] )
+    GATK4_GENOTYPEGVCFS ( input, fasta, fai, dict, [], [] )
 }
 
 // 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)
+    fai   = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
-    fastaDict    = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
+    dict  = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
 
     dbsnp     = file(params.test_data['homo_sapiens']['genome']['dbsnp_146_hg38_vcf_gz'], checkIfExists: true)
-    dbsnpIndex   = file(params.test_data['homo_sapiens']['genome']['dbsnp_146_hg38_vcf_gz_tbi'], checkIfExists: true)
+    dbsnp_tbi = file(params.test_data['homo_sapiens']['genome']['dbsnp_146_hg38_vcf_gz_tbi'], checkIfExists: true)
 
     test_genomicsdb = [ [], file(params.test_data['homo_sapiens']['illumina']['test_genomicsdb_tar_gz'], checkIfExists: true) ]
 
@@ -166,5 +169,5 @@ workflow test_gatk4_genotypegvcfs_gendb_input_dbsnp_intervals {
     gendb.add([file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true)])
     input = Channel.of([ id:'test' ]).combine(gendb)
 
-    GATK4_GENOTYPEGVCFS ( input, fasta, fastaIndex, fastaDict, dbsnp, dbsnpIndex )
+    GATK4_GENOTYPEGVCFS ( input, fasta, fai, dict, dbsnp, dbsnp_tbi )
 }

tests/modules/gatk4/genotypegvcfs/test.yml

@@ -10,6 +10,7 @@
           "AC=1;AF=0.500;AN=2;BaseQRankSum=0.00;DP=211;ExcessHet=0.0000;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
+    - path: output/gatk4/versions.yml
 
 - 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
@@ -23,6 +24,7 @@
           "AC=1;AF=0.500;AN=2;BaseQRankSum=0.00;DP=211;ExcessHet=0.0000;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
+    - path: output/gatk4/versions.yml
 
 - 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
@@ -36,6 +38,7 @@
           "AC=1;AF=0.500;AN=2;BaseQRankSum=0.00;DB;DP=211;ExcessHet=0.0000;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
+    - path: output/gatk4/versions.yml
 
 - 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
@@ -49,6 +52,7 @@
           "AC=1;AF=0.500;AN=2;BaseQRankSum=0.00;DP=211;ExcessHet=0.0000;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
+    - path: output/gatk4/versions.yml
 
 - 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
@@ -59,6 +63,7 @@
     - path: output/gatk4/test.genotyped.vcf.gz
       contains: ["AC=2;AF=1.00;AN=2;DB;DP=20;ExcessHet=0.0000;FS=0.000;MLEAC=2;MLEAF=1.00;MQ=60.00;QD=24.05;SOR=0.693"]
     - path: output/gatk4/test.genotyped.vcf.gz.tbi
+    - path: output/gatk4/versions.yml
 
 - 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
@@ -72,6 +77,7 @@
           "AC=1;AF=0.500;AN=2;BaseQRankSum=0.00;DP=211;ExcessHet=0.0000;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
+    - path: output/gatk4/versions.yml
 
 - 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
@@ -85,6 +91,7 @@
           "AC=1;AF=0.500;AN=2;BaseQRankSum=0.00;DB;DP=211;ExcessHet=0.0000;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
+    - path: output/gatk4/versions.yml
 
 - 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
@@ -98,6 +105,7 @@
           "AC=1;AF=0.500;AN=2;BaseQRankSum=0.00;DP=211;ExcessHet=0.0000;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
+    - path: output/gatk4/versions.yml
 
 - 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
@@ -108,3 +116,4 @@
     - path: output/gatk4/test.genotyped.vcf.gz
       contains: ["AC=2;AF=1.00;AN=2;DP=2;ExcessHet=0.0000;FS=0.000;MLEAC=1;MLEAF=0.500;MQ=60.00;QD=18.66;SOR=0.693"]
     - path: output/gatk4/test.genotyped.vcf.gz.tbi
+    - path: output/gatk4/versions.yml

tests/modules/gatk4/getpileupsummaries/test.yml

@@ -7,7 +7,6 @@
     - path: output/gatk4/test.pileups.table
       md5sum: 8e0ca6f66e112bd2f7ec1d31a2d62469
     - path: output/gatk4/versions.yml
-      md5sum: 059123619f3ed8d4cd178c4390b81e69
 
 - name: gatk4 getpileupsummaries test_gatk4_getpileupsummaries_separate_sites
   command: nextflow run tests/modules/gatk4/getpileupsummaries -entry test_gatk4_getpileupsummaries_separate_sites -c tests/config/nextflow.config
@@ -18,7 +17,6 @@
     - path: output/gatk4/test.pileups.table
       md5sum: 8e0ca6f66e112bd2f7ec1d31a2d62469
     - path: output/gatk4/versions.yml
-      md5sum: 76b5388b0c5b5762d8d33e34b23f181d
 
 - name: gatk4 getpileupsummaries test_gatk4_getpileupsummaries_separate_sites_cram
   command: nextflow run tests/modules/gatk4/getpileupsummaries -entry test_gatk4_getpileupsummaries_separate_sites_cram -c tests/config/nextflow.config
@@ -29,4 +27,3 @@
     - path: output/gatk4/test.pileups.table
       md5sum: 8e0ca6f66e112bd2f7ec1d31a2d62469
     - path: output/gatk4/versions.yml
-      md5sum: 2fa51319c2b1d678ee00ab09512cf268

tests/modules/gatk4/haplotypecaller/test.yml

@@ -6,6 +6,7 @@
   files:
     - path: output/gatk4/test.vcf.gz
     - path: output/gatk4/test.vcf.gz.tbi
+    - path: output/gatk4/versions.yml
 
 - name: gatk4 haplotypecaller test_gatk4_haplotypecaller_cram
   command: nextflow run ./tests/modules/gatk4/haplotypecaller -entry test_gatk4_haplotypecaller_cram -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/haplotypecaller/nextflow.config
@@ -15,6 +16,7 @@
   files:
     - path: output/gatk4/test.vcf.gz
     - path: output/gatk4/test.vcf.gz.tbi
+    - path: output/gatk4/versions.yml
 
 - name: gatk4 haplotypecaller test_gatk4_haplotypecaller_intervals_dbsnp
   command: nextflow run ./tests/modules/gatk4/haplotypecaller -entry test_gatk4_haplotypecaller_intervals_dbsnp -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/haplotypecaller/nextflow.config
@@ -24,3 +26,4 @@
   files:
     - path: output/gatk4/test.vcf.gz
     - path: output/gatk4/test.vcf.gz.tbi
+    - path: output/gatk4/versions.yml

tests/modules/gatk4/indexfeaturefile/test.yml

@@ -5,6 +5,7 @@
     - gatk4/indexfeaturefile
   files:
     - path: output/gatk4/genome.bed.idx
+    - path: output/gatk4/versions.yml
 
 - name: gatk4 indexfeaturefile test_gatk4_indexfeaturefile_bed_gz
   command: nextflow run tests/modules/gatk4/indexfeaturefile -entry test_gatk4_indexfeaturefile_bed_gz -c tests/config/nextflow.config -c ./tests/modules/gatk4/indexfeaturefile/nextflow.config
@@ -15,7 +16,6 @@
     - path: output/gatk4/genome.bed.gz.tbi
       md5sum: 4bc51e2351a6e83f20e13be75861f941
     - path: output/gatk4/versions.yml
-      md5sum: e5003204702f83aabdb4141272c704d2
 
 - name: gatk4 indexfeaturefile test_gatk4_indexfeaturefile_vcf
   command: nextflow run tests/modules/gatk4/indexfeaturefile -entry test_gatk4_indexfeaturefile_vcf -c tests/config/nextflow.config -c ./tests/modules/gatk4/indexfeaturefile/nextflow.config
@@ -25,7 +25,6 @@
   files:
     - path: output/gatk4/test.genome.vcf.idx
     - path: output/gatk4/versions.yml
-      md5sum: 08cd7c49cfb752fc2905f600106a0345
 
 - name: gatk4 indexfeaturefile test_gatk4_indexfeaturefile_vcf_gz
   command: nextflow run tests/modules/gatk4/indexfeaturefile -entry test_gatk4_indexfeaturefile_vcf_gz -c tests/config/nextflow.config
@@ -36,4 +35,3 @@
     - path: output/gatk4/test.genome.vcf.gz.tbi
       md5sum: fedd68eaddf8d31257853d9da8325bd3
     - path: output/gatk4/versions.yml
-      md5sum: b388d1681831a40264a7a27f67a8b247

tests/modules/gatk4/intervallisttobed/test.yml

@@ -6,3 +6,4 @@
   files:
     - path: output/gatk4/test.bed
       md5sum: 9046675d01199fbbee79f2bc1c5dce52
+    - path: output/gatk4/versions.yml

tests/modules/gatk4/intervallisttools/test.yml

@@ -14,3 +14,4 @@
       md5sum: 55da0f3c69504148f4e7002a0e072cfe
     - path: output/gatk4/test_split/temp_0004_of_6/4scattered.interval_list
       md5sum: d29ca4447f32547f2936567fa902796a
+    - path: output/gatk4/versions.yml

tests/modules/gatk4/learnreadorientationmodel/test.yml

@@ -5,3 +5,4 @@
     - gatk4/learnreadorientationmodel
   files:
     - path: output/gatk4/test.artifact-prior.tar.gz
+    - path: output/gatk4/versions.yml

tests/modules/gatk4/markduplicates/nextflow.config

@@ -2,4 +2,8 @@ process {
 
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
 
+    withName: GATK4_MARKDUPLICATES {
+        ext.args = '--CREATE_INDEX true'
+    }
+
 }

tests/modules/gatk4/markduplicates/test.yml

@@ -10,7 +10,6 @@
       md5sum: 2efd50b2e6b7fd9bdf242cd9e266cfa9
     - path: output/gatk4/test.metrics
     - path: output/gatk4/versions.yml
-      md5sum: 0bc949aaa8792cd6c537cdaab0e2c145
 
 - name: gatk4 markduplicates test_gatk4_markduplicates_multiple_bams
   command: nextflow run tests/modules/gatk4/markduplicates -entry test_gatk4_markduplicates_multiple_bams -c tests/config/nextflow.config -c ./tests/modules/gatk4/markduplicates/nextflow.config
@@ -24,4 +23,3 @@
       md5sum: 8187febc6108ffef7f907e89b9c091a4
     - path: output/gatk4/test.metrics
     - path: output/gatk4/versions.yml
-      md5sum: b10d63cf7b2b672915cb30cea081ccd5

tests/modules/gatk4/markduplicatesspark/main.nf

@@ -0,0 +1,28 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GATK4_MARKDUPLICATES_SPARK } from '../../../../modules/gatk4/markduplicatesspark/main.nf'
+
+workflow test_gatk4_markduplicates_spark {
+    input = [ [ id:'test', single_end:false ], // meta map
+              file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true)
+            ]
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta'], checkIfExists: true)
+    fai = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta_fai'], checkIfExists: true)
+    dict = file(params.test_data['homo_sapiens']['genome']['genome_21_dict'], checkIfExists: true)
+
+    GATK4_MARKDUPLICATES_SPARK ( input, fasta, fai, dict )
+}
+
+workflow test_gatk4_markduplicates_spark_multiple_bams {
+    input = [ [ id:'test', single_end:false ], // meta map
+              [ file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+                file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_bam'], checkIfExists: true)
+            ] ]
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta'], checkIfExists: true)
+    fai = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta_fai'], checkIfExists: true)
+    dict = file(params.test_data['homo_sapiens']['genome']['genome_21_dict'], checkIfExists: true)
+
+    GATK4_MARKDUPLICATES_SPARK ( input, fasta, fai, dict )
+}

tests/modules/gatk4/markduplicatesspark/nextflow.config

@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+}

tests/modules/gatk4/markduplicatesspark/test.yml

@@ -0,0 +1,25 @@
+- name: gatk4 markduplicates test_gatk4_markduplicates_spark
+  command: nextflow run tests/modules/gatk4/markduplicatesspark -entry test_gatk4_markduplicates_spark -c tests/config/nextflow.config -c ./tests/modules/gatk4/markduplicatesspark/nextflow.config
+  tags:
+    - gatk4
+    - gatk4/markduplicatesspark
+  files:
+    - path: output/gatk4/test.bai
+      md5sum: e9c125e82553209933883b4fe2b8d7c2
+    - path: output/gatk4/test.bam
+      md5sum: 2efd50b2e6b7fd9bdf242cd9e266cfa9
+    - path: output/gatk4/test.metrics
+    - path: output/gatk4/versions.yml
+
+- name: gatk4 markduplicates test_gatk4_markduplicates_spark_multiple_bams
+  command: nextflow run tests/modules/gatk4/markduplicatesspark -entry test_gatk4_markduplicates_spark_multiple_bams -c tests/config/nextflow.config -c ./tests/modules/gatk4/markduplicatesspark/nextflow.config
+  tags:
+    - gatk4
+    - gatk4/markduplicatesspark
+  files:
+    - path: output/gatk4/test.bai
+      md5sum: bad71df9c876e72a5bc0a3e0fd755f92
+    - path: output/gatk4/test.bam
+      md5sum: 8187febc6108ffef7f907e89b9c091a4
+    - path: output/gatk4/test.metrics
+    - path: output/gatk4/versions.yml

tests/modules/gatk4/mergebamalignment/test.yml

@@ -6,3 +6,4 @@
   files:
     - path: output/gatk4/test.bam
       md5sum: e6f1b343700b7ccb94e81ae127433988
+    - path: output/gatk4/versions.yml

tests/modules/gatk4/mergemutectstats/test.yml

@@ -6,3 +6,4 @@
   files:
     - path: output/gatk4/test.vcf.gz.stats
       md5sum: 17d2091015d04cbd4a26b7a67dc659e6
+    - path: output/gatk4/versions.yml

tests/modules/gatk4/mergevcfs/main.nf

@@ -5,22 +5,22 @@ nextflow.enable.dsl = 2
 include { GATK4_MERGEVCFS } from '../../../../modules/gatk4/mergevcfs/main.nf'
 
 workflow test_gatk4_mergevcfs {
-    input = [ [ id:'test' ], // meta map
-              [ file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true),
-                file(params.test_data['sarscov2']['illumina']['test2_vcf'], checkIfExists: true) ] 
-            ]
-    dict = file(params.test_data['sarscov2']['genome']['genome_dict'], checkIfExists: true)
-
-    GATK4_MERGEVCFS ( input, dict, false )
-}
-
-workflow test_gatk4_mergevcfs_refdict {
     def input = []
     input = [ [ id:'test' ], // meta map
               [ file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true),
                 file(params.test_data['sarscov2']['illumina']['test2_vcf'], checkIfExists: true) ]
             ]
+
     dict  = file(params.test_data['sarscov2']['genome']['genome_dict'], checkIfExists: true)
 
-    GATK4_MERGEVCFS ( input, dict, true )
+    GATK4_MERGEVCFS ( input, dict )
+}
+
+workflow test_gatk4_mergevcfs_no_dict {
+    input = [ [ id:'test' ], // meta map
+              [ file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true),
+                file(params.test_data['sarscov2']['illumina']['test2_vcf'], checkIfExists: true) ]
+            ]
+
+    GATK4_MERGEVCFS ( input, [] )
 }

tests/modules/gatk4/mergevcfs/test.yml

@@ -6,12 +6,14 @@
   files:
     - path: output/gatk4/test.vcf.gz
       md5sum: 5b289bda88d3a3504f2e19ee8cff177c
+    - path: output/gatk4/versions.yml
 
-- name: gatk4 mergevcfs test_gatk4_mergevcfs_refdict
+- name: gatk4 mergevcfs test_gatk4_mergevcfs_no_dict
-  command: nextflow run ./tests/modules/gatk4/mergevcfs -entry test_gatk4_mergevcfs_refdict -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/mergevcfs/nextflow.config
+  command: nextflow run ./tests/modules/gatk4/mergevcfs -entry test_gatk4_mergevcfs_no_dict -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/mergevcfs/nextflow.config
   tags:
     - gatk4/mergevcfs
     - gatk4
   files:
     - path: output/gatk4/test.vcf.gz
       md5sum: 5b289bda88d3a3504f2e19ee8cff177c
+    - path: output/gatk4/versions.yml

tests/modules/gatk4/mutect2/main.nf

@@ -3,21 +3,21 @@
 nextflow.enable.dsl = 2
 
 include { GATK4_MUTECT2                       } from '../../../../modules/gatk4/mutect2/main.nf'
+include { GATK4_MUTECT2 as GATK4_MUTECT2_PAIR } from '../../../../modules/gatk4/mutect2/main.nf'
+include { GATK4_MUTECT2 as GATK4_MUTECT2_MITO } from '../../../../modules/gatk4/mutect2/main.nf'
+include { GATK4_MUTECT2 as GATK4_MUTECT2_F1R2 } from '../../../../modules/gatk4/mutect2/main.nf'
 
 workflow test_gatk4_mutect2_tumor_normal_pair {
-    input = [ [ id:'test'], // meta map
+    input = [ [ id:'test', normal_id:'normal', tumor_id:'tumour' ], // meta map
               [ file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_bam'], checkIfExists: true),
                 file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_sorted_bam'], checkIfExists: true)
                 ],
               [ file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_bam_bai'], checkIfExists: true),
                 file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_sorted_bam_bai'], checkIfExists: true)
                 ],
-              [],
+              []
-              ["normal"]
             ]
-    run_single = false
+
-    run_pon = false
-    run_mito = false
     fasta = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta'], checkIfExists: true)
     fai = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta_fai'], checkIfExists: true)
     dict = file(params.test_data['homo_sapiens']['genome']['genome_21_dict'], checkIfExists: true)
@@ -26,19 +26,38 @@ workflow test_gatk4_mutect2_tumor_normal_pair {
     panel_of_normals = file(params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz'], checkIfExists: true)
     panel_of_normals_tbi = file(params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz_tbi'], checkIfExists: true)
 
-    GATK4_MUTECT2 ( input, run_single, run_pon, run_mito, fasta, fai, dict, germline_resource, germline_resource_tbi, panel_of_normals, panel_of_normals_tbi )
+    GATK4_MUTECT2_PAIR ( input, fasta, fai, dict, germline_resource, germline_resource_tbi, panel_of_normals, panel_of_normals_tbi )
+}
+
+workflow test_gatk4_mutect2_tumor_normal_pair_f1r2 {
+    input = [ [ id:'test', normal_id:'normal', tumor_id:'tumour' ], // meta map
+              [ file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_bam'], checkIfExists: true),
+                file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_sorted_bam'], checkIfExists: true)
+                ],
+              [ file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_bam_bai'], checkIfExists: true),
+                file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_sorted_bam_bai'], checkIfExists: true)
+                ],
+              []
+            ]
+
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta'], checkIfExists: true)
+    fai = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta_fai'], checkIfExists: true)
+    dict = file(params.test_data['homo_sapiens']['genome']['genome_21_dict'], checkIfExists: true)
+    germline_resource = file(params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz'], checkIfExists: true)
+    germline_resource_tbi = file(params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz_tbi'], checkIfExists: true)
+    panel_of_normals = file(params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz'], checkIfExists: true)
+    panel_of_normals_tbi = file(params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz_tbi'], checkIfExists: true)
+
+    GATK4_MUTECT2_F1R2 ( input, fasta, fai, dict, germline_resource, germline_resource_tbi, panel_of_normals, panel_of_normals_tbi )
 }
 
 workflow test_gatk4_mutect2_tumor_single {
     input = [ [ id:'test'], // meta map
               [ file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_sorted_bam'], checkIfExists: true)],
               [ file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_sorted_bam_bai'], checkIfExists: true)],
-              [],
               []
             ]
-    run_single = true
+
-    run_pon = false
-    run_mito = false
     fasta = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta'], checkIfExists: true)
     fai = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta_fai'], checkIfExists: true)
     dict = file(params.test_data['homo_sapiens']['genome']['genome_21_dict'], checkIfExists: true)
@@ -47,19 +66,16 @@ workflow test_gatk4_mutect2_tumor_single {
     panel_of_normals = file(params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz'], checkIfExists: true)
     panel_of_normals_tbi = file(params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz_tbi'], checkIfExists: true)
 
-    GATK4_MUTECT2 ( input, run_single, run_pon, run_mito, fasta, fai, dict, germline_resource, germline_resource_tbi, panel_of_normals, panel_of_normals_tbi )
+    GATK4_MUTECT2 ( input, fasta, fai, dict, germline_resource, germline_resource_tbi, panel_of_normals, panel_of_normals_tbi )
 }
 
 workflow test_gatk4_mutect2_cram_input {
     input = [ [ id:'test'], // meta map
               [ file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_sorted_cram'], checkIfExists: true)],
               [ file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_sorted_cram_crai'], checkIfExists: true)],
-              [],
               []
             ]
-    run_single = true
+
-    run_pon = false
-    run_mito = false
     fasta = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta'], checkIfExists: true)
     fai = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta_fai'], checkIfExists: true)
     dict = file(params.test_data['homo_sapiens']['genome']['genome_21_dict'], checkIfExists: true)
@@ -68,48 +84,37 @@ workflow test_gatk4_mutect2_cram_input {
     panel_of_normals = file(params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz'], checkIfExists: true)
     panel_of_normals_tbi = file(params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz_tbi'], checkIfExists: true)
 
-    GATK4_MUTECT2 ( input, run_single, run_pon, run_mito, fasta, fai, dict, germline_resource, germline_resource_tbi, panel_of_normals, panel_of_normals_tbi )
+    GATK4_MUTECT2 ( input, fasta, fai, dict, germline_resource, germline_resource_tbi, panel_of_normals, panel_of_normals_tbi )
 }
 
 workflow test_gatk4_mutect2_generate_pon {
     input = [ [ id:'test'], // meta map
               [ file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_bam'], checkIfExists: true)],
               [ file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_bam_bai'], checkIfExists: true)],
-              [],
               []
             ]
-    run_single = false
+
-    run_pon = true
-    run_mito = false
     fasta = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta'], checkIfExists: true)
     fai = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta_fai'], checkIfExists: true)
     dict = file(params.test_data['homo_sapiens']['genome']['genome_21_dict'], checkIfExists: true)
-    germline_resource = []
-    germline_resource_tbi = []
-    panel_of_normals = []
-    panel_of_normals_tbi = []
 
-    GATK4_MUTECT2 ( input, run_single, run_pon, run_mito, fasta, fai, dict, germline_resource, germline_resource_tbi, panel_of_normals, panel_of_normals_tbi )
+    GATK4_MUTECT2 ( input, fasta, fai, dict, [], [], [], [] )
 }
 
-// mitochondria mode would ideally have some mitochondria test data, but since the mitochondria settings only increase detection sensitivity, we can use the chr22 data as a stand in as it is already a small dataset, the extra variants detected compared to generate_pon shows the mode is working.
+// mitochondria mode would ideally have some mitochondria test data
+// but since the mitochondria settings only increase detection sensitivity
+// we can use the chr22 data as a stand in as it is already a small dataset
+// the extra variants detected compared to generate_pon shows the mode is working
 workflow test_gatk4_mutect2_mitochondria {
     input = [ [ id:'test'], // meta map
               [ file(params.test_data['homo_sapiens']['illumina']['mitochon_standin_recalibrated_sorted_bam'], checkIfExists: true)],
               [ file(params.test_data['homo_sapiens']['illumina']['mitochon_standin_recalibrated_sorted_bam_bai'], checkIfExists: true)],
-              [ file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true)],
+              [ file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true)]
-              []
             ]
-    run_single = false
+
-    run_pon = false
-    run_mito = true
     fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
     fai = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
     dict = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
-    germline_resource = []
-    germline_resource_tbi = []
-    panel_of_normals = []
-    panel_of_normals_tbi = []
 
-    GATK4_MUTECT2 ( input, run_single, run_pon, run_mito, fasta, fai, dict, germline_resource, germline_resource_tbi, panel_of_normals, panel_of_normals_tbi )
+    GATK4_MUTECT2_MITO ( input, fasta, fai, dict, [], [], [], [] )
 }

tests/modules/gatk4/mutect2/nextflow.config

@@ -2,4 +2,16 @@ process {
 
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
 
+    withName: GATK4_MUTECT2_PAIR {
+        ext.args = { "--normal-sample $meta.normal_id" }
+    }
+
+    withName: GATK4_MUTECT2_MITO {
+        ext.args = { "--mitochondria-mode" }
+    }
+
+    withName: GATK4_MUTECT2_F1R2 {
+        ext.args = { "--normal-sample $meta.normal_id --f1r2-tar-gz ${meta.id}.f1r2.tar.gz" }
+    }
+
 }

tests/modules/gatk4/mutect2/test.yml

@@ -1,5 +1,16 @@
 - name: gatk4 mutect2 test_gatk4_mutect2_tumor_normal_pair
   command: nextflow run ./tests/modules/gatk4/mutect2 -entry test_gatk4_mutect2_tumor_normal_pair -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/mutect2/nextflow.config
+  tags:
+    - gatk4
+    - gatk4/mutect2
+  files:
+    - path: output/gatk4/test.vcf.gz
+    - path: output/gatk4/test.vcf.gz.stats
+      md5sum: 17d2091015d04cbd4a26b7a67dc659e6
+    - path: output/gatk4/test.vcf.gz.tbi
+
+- name: gatk4 mutect2 test_gatk4_mutect2_tumor_normal_pair_f1r2
+  command: nextflow run ./tests/modules/gatk4/mutect2 -entry test_gatk4_mutect2_tumor_normal_pair_f1r2 -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/mutect2/nextflow.config
   tags:
     - gatk4
     - gatk4/mutect2
@@ -9,6 +20,7 @@
     - path: output/gatk4/test.vcf.gz.stats
       md5sum: 17d2091015d04cbd4a26b7a67dc659e6
     - path: output/gatk4/test.vcf.gz.tbi
+    - path: output/gatk4/versions.yml
 
 - name: gatk4 mutect2 test_gatk4_mutect2_tumor_single
   command: nextflow run ./tests/modules/gatk4/mutect2 -entry test_gatk4_mutect2_tumor_single -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/mutect2/nextflow.config
@@ -20,6 +32,7 @@
     - path: output/gatk4/test.vcf.gz.stats
       md5sum: 55ed641e16089afb33cdbc478e202d3d
     - path: output/gatk4/test.vcf.gz.tbi
+    - path: output/gatk4/versions.yml
 
 - name: gatk4 mutect2 test_gatk4_mutect2_cram_input
   command: nextflow run ./tests/modules/gatk4/mutect2 -entry test_gatk4_mutect2_cram_input -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/mutect2/nextflow.config
@@ -31,6 +44,7 @@
     - path: output/gatk4/test.vcf.gz.stats
       md5sum: 55ed641e16089afb33cdbc478e202d3d
     - path: output/gatk4/test.vcf.gz.tbi
+    - path: output/gatk4/versions.yml
 
 - name: gatk4 mutect2 test_gatk4_mutect2_generate_pon
   command: nextflow run ./tests/modules/gatk4/mutect2 -entry test_gatk4_mutect2_generate_pon -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/mutect2/nextflow.config
@@ -42,6 +56,7 @@
     - path: output/gatk4/test.vcf.gz.stats
       md5sum: b569ce66bbffe9588b3d221e821023ee
     - path: output/gatk4/test.vcf.gz.tbi
+    - path: output/gatk4/versions.yml
 
 - name: gatk4 mutect2 test_gatk4_mutect2_mitochondria
   command: nextflow run ./tests/modules/gatk4/mutect2 -entry test_gatk4_mutect2_mitochondria -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/mutect2/nextflow.config
@@ -53,3 +68,4 @@
     - path: output/gatk4/test.vcf.gz.stats
       md5sum: fc6ea14ca2da346babe78161beea28c9
     - path: output/gatk4/test.vcf.gz.tbi
+    - path: output/gatk4/versions.yml

tests/modules/gatk4/revertsam/test.yml

@@ -6,3 +6,4 @@
   files:
     - path: output/gatk4/test.reverted.bam
       md5sum: f783a88deb45c3a2c20ca12cbe1c5652
+    - path: output/gatk4/versions.yml

tests/modules/gatk4/samtofastq/test.yml

@@ -6,6 +6,7 @@
   files:
     - path: output/gatk4/test.fastq.gz
       md5sum: 50ace41d4c24467f24f8b929540a7797
+    - path: output/gatk4/versions.yml
 
 - name: gatk4 samtofastq test_gatk4_samtofastq_paired_end
   command: nextflow run ./tests/modules/gatk4/samtofastq -entry test_gatk4_samtofastq_paired_end -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/samtofastq/nextflow.config
@@ -17,3 +18,4 @@
       md5sum: cfea607c9d75fd9ea9704780ad3a499c
     - path: output/gatk4/test_2.fastq.gz
       md5sum: 613bf64c023609e1c62ad6ce9e4be8d7
+    - path: output/gatk4/versions.yml

tests/modules/gatk4/selectvariants/test.yml

@@ -7,7 +7,6 @@
     - path: output/gatk4/test.selectvariants.vcf.gz
     - path: output/gatk4/test.selectvariants.vcf.gz.tbi
     - path: output/gatk4/versions.yml
-      md5sum: a35d78af179f43652274bc7405d5a785
 
 - name: gatk4 selectvariants test_gatk4_selectvariants_gz_input
   command: nextflow run tests/modules/gatk4/selectvariants -entry test_gatk4_selectvariants_gz_input -c tests/config/nextflow.config
@@ -18,4 +17,3 @@
     - path: output/gatk4/test.selectvariants.vcf.gz
     - path: output/gatk4/test.selectvariants.vcf.gz.tbi
     - path: output/gatk4/versions.yml
-      md5sum: c943f3579a369968ca63444eb43fb6e7

tests/modules/gatk4/splitncigarreads/test.yml

@@ -7,4 +7,3 @@
     - path: output/gatk4/test.bam
       md5sum: ceed15c0bd64ff5c38d3816905933b0b
     - path: output/gatk4/versions.yml
-      md5sum: 27fceace2528a905ddca2b4db47c4bf5

tests/modules/gatk4/variantfiltration/test.yml

@@ -10,6 +10,7 @@
           "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
+    - path: output/gatk4/versions.yml
 
 - 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 -c ./tests/modules/gatk4/variantfiltration/nextflow.config
@@ -23,3 +24,4 @@
           "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
+    - path: output/gatk4/versions.yml

tests/modules/gatk4/variantrecalibrator/main.nf

@@ -12,31 +12,28 @@ workflow test_gatk4_variantrecalibrator {
                 file(params.test_data['homo_sapiens']['illumina']['test2_haplotc_ann_vcf_gz_tbi'], checkIfExists: true)
             ]
 
-    fasta = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta'], checkIfExists: true)
+    resources = [[
-    fai = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta_fai'], checkIfExists: true)
-    dict = file(params.test_data['homo_sapiens']['genome']['genome_21_dict'], checkIfExists: true)
-    resources = [
-                 [
                     file(params.test_data['homo_sapiens']['genome']['hapmap_3_3_hg38_21_vcf_gz'], checkIfExists: true),
                     file(params.test_data['homo_sapiens']['genome']['res_1000g_omni2_5_hg38_21_vcf_gz'], checkIfExists: true),
                     file(params.test_data['homo_sapiens']['genome']['res_1000g_phase1_snps_hg38_21_vcf_gz'], checkIfExists: true),
                     file(params.test_data['homo_sapiens']['genome']['dbsnp_138_hg38_21_vcf_gz'], checkIfExists: true)
-                 ],
+                ], [
-                 [
                     file(params.test_data['homo_sapiens']['genome']['hapmap_3_3_hg38_21_vcf_gz_tbi'], checkIfExists: true),
                     file(params.test_data['homo_sapiens']['genome']['res_1000g_omni2_5_hg38_21_vcf_gz_tbi'], checkIfExists: true),
                     file(params.test_data['homo_sapiens']['genome']['res_1000g_phase1_snps_hg38_21_vcf_gz_tbi'], checkIfExists: true),
                     file(params.test_data['homo_sapiens']['genome']['dbsnp_138_hg38_21_vcf_gz_tbi'], checkIfExists: true)
-                 ],
+                ], [
-                 [
                     'hapmap,known=false,training=true,truth=true,prior=15.0 hapmap_3.3.hg38.vcf.gz',
                     'omni,known=false,training=true,truth=false,prior=12.0 1000G_omni2.5.hg38.vcf.gz',
                     '1000G,known=false,training=true,truth=false,prior=10.0 1000G_phase1.snps.hg38.vcf.gz',
                     'dbsnp,known=true,training=false,truth=false,prior=2.0 dbsnp_138.hg38.vcf.gz'
-                 ]
+                ]]
-                ]
 
-    GATK4_VARIANTRECALIBRATOR_NO_ALLELESPECIFICTY ( input, fasta, fai, dict, resources)
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta'], checkIfExists: true)
+    fai = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta_fai'], checkIfExists: true)
+    dict = file(params.test_data['homo_sapiens']['genome']['genome_21_dict'], checkIfExists: true)
+
+    GATK4_VARIANTRECALIBRATOR_NO_ALLELESPECIFICTY(input, resources, fasta, fai, dict)
 }
 
 workflow test_gatk4_variantrecalibrator_allele_specific {
@@ -46,29 +43,26 @@ workflow test_gatk4_variantrecalibrator_allele_specific {
                 file(params.test_data['homo_sapiens']['illumina']['test2_haplotc_ann_vcf_gz_tbi'], checkIfExists: true)
             ]
 
-    fasta = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta'], checkIfExists: true)
+    resources = [[
-    fai = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta_fai'], checkIfExists: true)
-    dict = file(params.test_data['homo_sapiens']['genome']['genome_21_dict'], checkIfExists: true)
-    resources = [
-                 [
                     file(params.test_data['homo_sapiens']['genome']['hapmap_3_3_hg38_21_vcf_gz'], checkIfExists: true),
                     file(params.test_data['homo_sapiens']['genome']['res_1000g_omni2_5_hg38_21_vcf_gz'], checkIfExists: true),
                     file(params.test_data['homo_sapiens']['genome']['res_1000g_phase1_snps_hg38_21_vcf_gz'], checkIfExists: true),
                     file(params.test_data['homo_sapiens']['genome']['dbsnp_138_hg38_21_vcf_gz'], checkIfExists: true)
-                 ],
+                ], [
-                 [
                     file(params.test_data['homo_sapiens']['genome']['hapmap_3_3_hg38_21_vcf_gz_tbi'], checkIfExists: true),
                     file(params.test_data['homo_sapiens']['genome']['res_1000g_omni2_5_hg38_21_vcf_gz_tbi'], checkIfExists: true),
                     file(params.test_data['homo_sapiens']['genome']['res_1000g_phase1_snps_hg38_21_vcf_gz_tbi'], checkIfExists: true),
                     file(params.test_data['homo_sapiens']['genome']['dbsnp_138_hg38_21_vcf_gz_tbi'], checkIfExists: true)
-                 ],
+                ], [
-                 [
                     'hapmap,known=false,training=true,truth=true,prior=15.0 hapmap_3.3.hg38.vcf.gz',
                     'omni,known=false,training=true,truth=false,prior=12.0 1000G_omni2.5.hg38.vcf.gz',
                     '1000G,known=false,training=true,truth=false,prior=10.0 1000G_phase1.snps.hg38.vcf.gz',
                     'dbsnp,known=true,training=false,truth=false,prior=2.0 dbsnp_138.hg38.vcf.gz'
-                 ]
+                ]]
-                ]
 
-    GATK4_VARIANTRECALIBRATOR_WITH_ALLELESPECIFICTY ( input, fasta, fai, dict, resources)
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta'], checkIfExists: true)
+    fai = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta_fai'], checkIfExists: true)
+    dict = file(params.test_data['homo_sapiens']['genome']['genome_21_dict'], checkIfExists: true)
+
+    GATK4_VARIANTRECALIBRATOR_WITH_ALLELESPECIFICTY(input, resources, fasta, fai, dict)
 }