Update intervals (#1278)

* Match target bed to input files

* Intervals in getpileupsumamries

* more interval updates

* change targets in strelka

* remove leftover channel

* fix checksums

* add new test vcfs

* add new test vcfs

* Update modules/freebayes/main.nf

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

modules/freebayes/main.nf

@@ -8,10 +8,9 @@ process FREEBAYES {
         'quay.io/biocontainers/freebayes:1.3.5--py38ha193a2f_3' }"
 
     input:
-    tuple val(meta), path(input_1), path(input_1_index), path(input_2), path(input_2_index)
+    tuple val(meta), path(input_1), path(input_1_index), path(input_2), path(input_2_index), path(target_bed)
     path fasta
     path fasta_fai
-    path targets
     path samples
     path populations
     path cnv
@@ -27,7 +26,7 @@ process FREEBAYES {
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
     def input            = input_2        ? "${input_1} ${input_2}"        : "${input_1}"
-    def targets_file     = targets        ? "--target ${targets}"          : ""
+    def targets_file     = target_bed     ? "--target ${target_bed}"       : ""
     def samples_file     = samples        ? "--samples ${samples}"         : ""
     def populations_file = populations    ? "--populations ${populations}" : ""
     def cnv_file         = cnv            ? "--cnv-map ${cnv}"             : ""

modules/freebayes/meta.yml

@@ -31,7 +31,11 @@ input:
   - input_index:
       type: file
       description: BAM/CRAM/SAM index file
-      pattern: "*.bam.bai"
+      pattern: "*.{bai,crai}"
+  - target_bed:
+      type: file
+      description: Optional - Limit analysis to targets listed in this BED-format FILE.
+      pattern: "*.bed"
   - fasta:
       type: file
       description: reference fasta file
@@ -40,10 +44,6 @@ input:
       type: file
       description: reference fasta file index
       pattern: "*.{fa,fasta}.fai"
-  - targets:
-      type: file
-      description: Optional - Limit analysis to targets listed in this BED-format FILE.
-      pattern: "*.bed"
   - samples:
       type: file
       description: Optional - Limit analysis to samples listed (one per line) in the FILE.

modules/gatk4/getpileupsummaries/main.nf

@@ -8,10 +8,12 @@ process GATK4_GETPILEUPSUMMARIES {
         'quay.io/biocontainers/gatk4:4.2.4.1--hdfd78af_0' }"
 
     input:
-    tuple val(meta), path(bam), path(bai)
+    tuple val(meta), path(input), path(index), path(intervals)
+    path fasta
+    path fai
+    path dict
     path variants
     path variants_tbi
-    path sites
 
     output:
     tuple val(meta), path('*.pileups.table'), emit: table
@@ -23,9 +25,8 @@ process GATK4_GETPILEUPSUMMARIES {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def sitesCommand = ''
+    def sitesCommand = intervals ? " -L ${intervals} " : " -L ${variants} "
-
+    def reference    = fasta ? " -R ${fasta}" :""
-    sitesCommand = sites ? " -L ${sites} " : " -L ${variants} "
 
     def avail_mem = 3
     if (!task.memory) {
@@ -35,9 +36,10 @@ process GATK4_GETPILEUPSUMMARIES {
     }
     """
     gatk --java-options "-Xmx${avail_mem}g" GetPileupSummaries \\
-        -I $bam \\
+        -I $input \\
         -V $variants \\
         $sitesCommand \\
+        ${reference} \\
         -O ${prefix}.pileups.table \\
         $args
 

modules/gatk4/getpileupsummaries/meta.yml

@@ -23,14 +23,30 @@ input:
       description: |
         Groovy Map containing sample information
         e.g. [ id:'test' ]
-  - bam:
+  - input:
       type: file
-      description: BAM file to be summarised.
+      description: BAM/CRAM file to be summarised.
-      pattern: "*.bam"
+      pattern: "*.{bam,cram}"
-  - bai:
+  - input_index:
       type: file
-      description: BAM file index.
+      description: BAM/CRAM file index.
-      pattern: "*.bam.bai"
+      pattern: "*.{bai,crai}"
+  - intervals:
+      type: file
+      description: File containing specified sites to be used for the summary. If this option is not specified, variants file is used instead automatically.
+      pattern: "*.interval_list"
+  - 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"
   - variants:
       type: file
       description: Population vcf of germline sequencing, containing allele fractions. Is also used as sites file if no separate sites file is specified.
@@ -39,10 +55,7 @@ input:
       type: file
       description: Index file for the germline resource.
       pattern: "*.vcf.gz.tbi"
-  - sites:
+
-      type: file
-      description: File containing specified sites to be used for the summary. If this option is not specified, variants file is used instead automatically.
-      pattern: "*.interval_list"
 
 output:
   - pileup:

modules/gatk4/mutect2/main.nf

@@ -8,11 +8,10 @@ process GATK4_MUTECT2 {
         'quay.io/biocontainers/gatk4:4.2.4.1--hdfd78af_0' }"
 
     input:
-    tuple val(meta) , path(input) , path(input_index) , val(which_norm)
+    tuple val(meta) , path(input) , path(input_index) , path(intervals), val(which_norm)
     val  run_single
     val  run_pon
     val  run_mito
-    val  interval_label
     path fasta
     path fai
     path dict
@@ -38,6 +37,7 @@ process GATK4_MUTECT2 {
     def normals_command = ''
 
     def inputs_command = '-I ' + input.join( ' -I ')
+    def interval = intervals ? "-L ${intervals}" : ""
 
     if(run_pon) {
         panels_command = ''
@@ -48,7 +48,7 @@ process GATK4_MUTECT2 {
         normals_command = ''
 
     } else if(run_mito){
-        panels_command = "-L ${interval_label} --mitochondria-mode"
+        panels_command = "-L ${intervals} --mitochondria-mode"
         normals_command = ''
 
     } else {
@@ -68,6 +68,7 @@ process GATK4_MUTECT2 {
         ${inputs_command} \\
         ${normals_command} \\
         ${panels_command} \\
+        ${interval} \\
         -O ${prefix}.vcf.gz \\
         $args
 

modules/gatk4/mutect2/meta.yml

@@ -30,6 +30,10 @@ input:
       type: list
       description: list of BAM file indexes, also able to take CRAM indexes as an input
       pattern: "*.{bam.bai/cram.crai}"
+  - intervals:
+      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)
@@ -46,10 +50,6 @@ input:
       type: boolean
       description: Specify whether or not to run in mitochondria-mode instead of tumor_normal_pair mode
       pattern: "true/false"
-  - interval_label:
-      type: string
-      description: Specify the label used for mitochondrial chromosome when mutect2 is run in mitochondria mode.
-      pattern: "chrM"
   - fasta:
       type: file
       description: The reference fasta file

modules/strelka/germline/main.nf

@@ -8,11 +8,9 @@ process STRELKA_GERMLINE {
         'quay.io/biocontainers/strelka:2.9.10--0' }"
 
     input:
-    tuple val(meta), path(input), path(input_index)
+    tuple val(meta), path(input), path(input_index), path (target_bed), path (target_bed_tbi)
     path  fasta
     path  fai
-    path  target_bed
-    path  target_bed_tbi
 
     output:
     tuple val(meta), path("*variants.vcf.gz")    , emit: vcf
@@ -27,7 +25,7 @@ process STRELKA_GERMLINE {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def regions  = target_bed ? "--exome --callRegions ${target_bed}" : ""
+    def regions  = target_bed ? "--callRegions ${target_bed}" : ""
     """
     configureStrelkaGermlineWorkflow.py \\
         --bam $input \\

modules/strelka/somatic/main.nf

@@ -8,11 +8,9 @@ process STRELKA_SOMATIC {
         'quay.io/biocontainers/strelka:2.9.10--h9ee0642_1' }"
 
     input:
-    tuple val(meta), path(input_normal), path(input_index_normal), path(input_tumor), path(input_index_tumor),  path(manta_candidate_small_indels), path(manta_candidate_small_indels_tbi)
+    tuple val(meta), path(input_normal), path(input_index_normal), path(input_tumor), path(input_index_tumor),  path(manta_candidate_small_indels), path(manta_candidate_small_indels_tbi), path(target_bed), path(target_bed_index)
     path  fasta
     path  fai
-    path  target_bed
-    path  target_bed_tbi
 
     output:
     tuple val(meta), path("*.somatic_indels.vcf.gz")    , emit: vcf_indels
@@ -27,15 +25,16 @@ process STRELKA_SOMATIC {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def options_target_bed = target_bed ? "--exome --callRegions ${target_bed}" : ""
+    def options_target_bed = target_bed ? "--callRegions ${target_bed}" : ""
     def options_manta = manta_candidate_small_indels ? "--indelCandidates ${manta_candidate_small_indels}" : ""
     """
+
     configureStrelkaSomaticWorkflow.py \\
         --tumor $input_tumor \\
         --normal $input_normal \\
         --referenceFasta $fasta \\
-        $options_target_bed \\
+        ${options_target_bed} \\
-        $options_manta \\
+        ${options_manta} \\
         $args \\
         --runDir strelka
 

modules/tabix/bgziptabix/main.nf

@@ -22,7 +22,7 @@ process TABIX_BGZIPTABIX {
     def args2 = task.ext.args2 ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
     """
-    bgzip -c $args $input > ${prefix}.gz
+    bgzip  --threads ${task.cpus} -c $args $input > ${prefix}.gz
     tabix $args2 ${prefix}.gz
 
     cat <<-END_VERSIONS > versions.yml

tests/config/test_data.config

@@ -122,6 +122,9 @@ params {
                 genome_21_fasta_fai                            = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.fasta.fai"
                 genome_21_dict                                 = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.dict"
                 genome_21_interval_list                        = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.interval_list"
+                genome_21_multi_interval_bed                   = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/multi_intervals.bed"
+                genome_21_multi_interval_bed_gz                = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/multi_intervals.bed.gz"
+                genome_21_multi_interval_bed_gz_tbi            = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/multi_intervals.bed.gz.tbi"
 
                 dbsnp_146_hg38_vcf_gz                          = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.vcf.gz"
                 dbsnp_146_hg38_vcf_gz_tbi                      = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.vcf.gz.tbi"
@@ -262,6 +265,9 @@ params {
                 test2_genome_vcf_gz_tbi                        = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test2.genome.vcf.gz.tbi"
                 test2_genome_vcf_idx                           = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test2.genome.vcf.idx"
 
+                test_genome21_indels_vcf_gz                    = "${test_data_dir}/genomics/homo_sapiens/illumina/vcf/test.genome_21.somatic_sv.vcf.gz"
+                test_genome21_indels_vcf_gz_tbi                = "${test_data_dir}/genomics/homo_sapiens/illumina/vcf/test.genome_21.somatic_sv.vcf.gz.tbi"
+
                 test_broadpeak                                 = "${test_data_dir}/genomics/homo_sapiens/illumina/broadpeak/test.broadPeak"
                 test2_broadpeak                                = "${test_data_dir}/genomics/homo_sapiens/illumina/broadpeak/test2.broadPeak"
 

tests/modules/freebayes/main.nf

@@ -5,91 +5,98 @@ nextflow.enable.dsl = 2
 include { FREEBAYES } from '../../../modules/freebayes/main.nf'
 
 workflow test_freebayes {
-
+    targets     = []
     input = [ [ id:'test', single_end:false ], // 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),
               [],
-              []
+              [],
+              targets
             ]
     fasta       = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
     fai         = file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true)
-    targets     = []
+
     samples     = []
     populations = []
     cnv         = []
 
-    FREEBAYES (input, fasta, fai, targets, samples, populations, cnv)
+    FREEBAYES (input, fasta, fai, samples, populations, cnv)
 }
 
 workflow test_freebayes_bed {
 
+    targets     = file(params.test_data['sarscov2']['genome']['test_bed'], checkIfExists: true)
     input = [ [ id:'test', single_end:false ], // 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),
               [],
-              []
+              [],
+              targets
             ]
     fasta       = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
     fai         = file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true)
-    targets     = file(params.test_data['sarscov2']['genome']['test_bed'], checkIfExists: true)
+
     samples     = []
     populations = []
     cnv         = []
 
-    FREEBAYES (input, fasta, fai, targets, samples, populations, cnv)
+    FREEBAYES (input, fasta, fai, samples, populations, cnv)
 }
 
 workflow test_freebayes_cram {
 
+    targets     = []
     input = [ [ id:'test', single_end:false ], // 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),
               [],
-              []
+              [],
+              targets
             ]
     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)
-    targets     = []
     samples     = []
     populations = []
     cnv         = []
 
-    FREEBAYES (input, fasta, fai, targets, samples, populations, cnv)
+    FREEBAYES (input, fasta, fai, samples, populations, cnv)
 }
 
 workflow test_freebayes_somatic {
 
+    targets     = []
     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']['test_paired_end_sorted_bam_bai'], checkIfExists: true),
                 file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_bam'], checkIfExists: true),
-                file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_bam_bai'], checkIfExists: true)
+                file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_bam_bai'], checkIfExists: true),
+                targets
             ]
     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)
-    targets     = []
+
     samples     = []
     populations = []
     cnv         = []
 
-    FREEBAYES (input, fasta, fai, targets, samples, populations, cnv)
+    FREEBAYES (input, fasta, fai, samples, populations, cnv)
 }
 
 workflow test_freebayes_somatic_cram_intervals {
 
+    targets     = file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true)
     input = [ [ id:'test', single_end:false ], // 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']['test2_paired_end_sorted_cram'], checkIfExists: true),
-                file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_cram_crai'], checkIfExists: true)
+                file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_cram_crai'], checkIfExists: true),
+                targets
             ]
     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)
-    targets     = file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true)
     samples     = []
     populations = []
     cnv         = []
 
-    FREEBAYES (input, fasta, fai, targets, samples, populations, cnv)
+    FREEBAYES (input, fasta, fai, samples, populations, cnv)
 }

tests/modules/freebayes/test.yml

@@ -4,7 +4,7 @@
     - freebayes
   files:
     - path: output/freebayes/test.vcf.gz
-      md5sum: 81d3e6ce7b6343d088b779567c3803eb
+      md5sum: f28d0b8e2ccedeac0e590ca2ecaac83d
     - path: output/freebayes/versions.yml
       md5sum: 53651eb835af65df829241257584a7d2
 
@@ -14,7 +14,7 @@
     - freebayes
   files:
     - path: output/freebayes/test.vcf.gz
-      md5sum: 02645d014a63485162a7789007373b2a
+      md5sum: 1927441d1b7a4c48cbb61821de300ad4
     - path: output/freebayes/versions.yml
       md5sum: becc93c8a0be580c09d55b955d60a5e1
 
@@ -24,7 +24,7 @@
     - freebayes
   files:
     - path: output/freebayes/test.vcf.gz
-      md5sum: 3d0bfcd2129c62f8863952fa4c1054db
+      md5sum: 9b8d1d51d779bbea4086c7f7a2ece641
     - path: output/freebayes/versions.yml
       md5sum: 2e5b266edfc6cab81353cfc72c00f67c
 
@@ -34,7 +34,7 @@
     - freebayes
   files:
     - path: output/freebayes/test.vcf.gz
-      md5sum: 22fec868210ba3baf685b214bfd8e74b
+      md5sum: dcaa639912174055c1380913d6102c01
     - path: output/freebayes/versions.yml
       md5sum: 8fbdb4c052fb3e42b5508a966125fa05
 
@@ -44,6 +44,6 @@
     - freebayes
   files:
     - path: output/freebayes/test.vcf.gz
-      md5sum: 527cf2937067bbd4117d95fd472bb928
+      md5sum: b0052a2b83c0ba1b9686d0c96e61712f
     - path: output/freebayes/versions.yml
       md5sum: af97e3dfdc086188739907c3460e49e0

tests/modules/gatk4/getpileupsummaries/main.nf

@@ -8,24 +8,45 @@ workflow test_gatk4_getpileupsummaries_just_variants {
 
     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) ]
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_bam_bai'], checkIfExists: true),
+        []
+        ]
 
     variants = file(params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz'], checkIfExists: true)
     variants_tbi = file(params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz_tbi'], checkIfExists: true)
-    sites = []
+    fasta = []
-
+    fai = []
-    GATK4_GETPILEUPSUMMARIES ( input , variants , variants_tbi , sites )
+    dict = []
+    GATK4_GETPILEUPSUMMARIES ( input , fasta, fai, dict, variants , variants_tbi )
 }
 
 workflow test_gatk4_getpileupsummaries_separate_sites {
 
     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) ]
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_bam_bai'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['genome']['genome_21_interval_list'], checkIfExists: true) ]
 
     variants = file(params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz'], checkIfExists: true)
     variants_tbi = file(params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz_tbi'], checkIfExists: true)
-    sites = file(params.test_data['homo_sapiens']['genome']['genome_21_interval_list'], checkIfExists: true)
+    fasta = []
-
+    fai = []
-    GATK4_GETPILEUPSUMMARIES ( input , variants , variants_tbi , sites )
+    dict = []
+    GATK4_GETPILEUPSUMMARIES ( input , fasta, fai, dict, variants , variants_tbi)
+}
+
+workflow test_gatk4_getpileupsummaries_separate_sites_cram {
+
+    input = [ [ id:'test' ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_cram'], checkIfExists: true) ,
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_cram_crai'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['genome']['genome_21_interval_list'], checkIfExists: true)
+        ]
+
+    variants = file(params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz'], checkIfExists: true)
+    variants_tbi = file(params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz_tbi'], 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_GETPILEUPSUMMARIES ( input , fasta, fai, dict, variants , variants_tbi)
 }

tests/modules/gatk4/getpileupsummaries/test.yml

@@ -1,17 +1,32 @@
 - name: gatk4 getpileupsummaries test_gatk4_getpileupsummaries_just_variants
-  command: nextflow run ./tests/modules/gatk4/getpileupsummaries -entry test_gatk4_getpileupsummaries_just_variants -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/getpileupsummaries/nextflow.config
+  command: nextflow run tests/modules/gatk4/getpileupsummaries -entry test_gatk4_getpileupsummaries_just_variants -c tests/config/nextflow.config
   tags:
-    - gatk4
     - gatk4/getpileupsummaries
+    - gatk4
   files:
     - path: output/gatk4/test.pileups.table
       md5sum: 8e0ca6f66e112bd2f7ec1d31a2d62469
+    - path:  output/gatk4/versions.yml
+      md5sum: dd98374e3b5d35ddd1c6b3fa7e662dc5
 
 - 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 -c ./tests/modules/gatk4/getpileupsummaries/nextflow.config
+  command: nextflow run tests/modules/gatk4/getpileupsummaries -entry test_gatk4_getpileupsummaries_separate_sites -c tests/config/nextflow.config
   tags:
-    - gatk4
     - gatk4/getpileupsummaries
+    - gatk4
   files:
     - path:  output/gatk4/test.pileups.table
       md5sum: 8e0ca6f66e112bd2f7ec1d31a2d62469
+    - path:  output/gatk4/versions.yml
+      md5sum: 080b6af7df182558aeab117668388d59
+
+- 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
+  tags:
+    - gatk4/getpileupsummaries
+    - gatk4
+  files:
+    - path:  output/gatk4/test.pileups.table
+      md5sum: 8e0ca6f66e112bd2f7ec1d31a2d62469
+    - path:  output/gatk4/versions.yml
+      md5sum: 33458a9efa6d61c713af9f7b722d7134

tests/modules/gatk4/mutect2/main.nf

@@ -12,12 +12,12 @@ workflow test_gatk4_mutect2_tumor_normal_pair {
               [ 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
-    interval_label = []
     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 +26,19 @@ 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, interval_label, fasta, fai, dict, 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 )
 }
 
 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
-    interval_label = []
     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 +47,19 @@ 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, interval_label, fasta, fai, dict, 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 )
 }
 
 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
-    interval_label = []
     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)
@@ -68,19 +68,19 @@ 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, interval_label, fasta, fai, dict, 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 )
 }
 
 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
-    interval_label = []
     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)
@@ -89,7 +89,7 @@ workflow test_gatk4_mutect2_generate_pon {
     panel_of_normals = []
     panel_of_normals_tbi = []
 
-    GATK4_MUTECT2 ( input, run_single, run_pon, run_mito, interval_label, fasta, fai, dict, 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 )
 }
 
 // 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.
@@ -97,12 +97,12 @@ 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)],
               []
             ]
     run_single = false
     run_pon = false
     run_mito = true
-    interval_label = 'chr22'
     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)
@@ -111,5 +111,5 @@ workflow test_gatk4_mutect2_mitochondria {
     panel_of_normals = []
     panel_of_normals_tbi = []
 
-    GATK4_MUTECT2 ( input, run_single, run_pon, run_mito, interval_label, fasta, fai, dict, 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 )
 }

tests/modules/gatk4/mutect2/nextflow.config

@@ -2,8 +2,4 @@ process {
 
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
 
-    withName: GATK4_TEMPFIX_MUTECT2 {
-        ext.args = '--mitochondria-mode'
-    }
-
 }

tests/modules/strelka/germline/main.nf

@@ -9,28 +9,29 @@ workflow test_strelka_germline {
         [ id:'test'], // meta map
         file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_cram'], checkIfExists: true),
         file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_cram_crai'], checkIfExists: true),
+        [],
+        []
     ]
 
-    fasta   = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta'], checkIfExists: true)
-    fai     = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+    fai = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta_fai'], checkIfExists: true)
-    target_bed     = []
-    target_bed_tbi = []
 
-    STRELKA_GERMLINE ( input, fasta, fai, target_bed, target_bed_tbi )
+    STRELKA_GERMLINE ( input, fasta, fai)
 }
 
 workflow test_strelka_germline_target_bed {
+
     input = [
         [ id:'test'], // meta map
-        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_cram'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_sorted_cram'], checkIfExists: true),
-        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_cram_crai'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_sorted_cram_crai'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed_gz'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed_gz_tbi'], checkIfExists: true)
     ]
 
-    fasta          = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta'], checkIfExists: true)
-    fai            = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+    fai = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta_fai'], checkIfExists: true)
-    target_bed     = file(params.test_data['homo_sapiens']['genome']['genome_bed_gz'], checkIfExists: true)
-    target_bed_tbi = file(params.test_data['homo_sapiens']['genome']['genome_bed_gz_tbi'], checkIfExists: true)
 
-    STRELKA_GERMLINE ( input, fasta, fai, target_bed, target_bed_tbi )
+    STRELKA_GERMLINE ( input, fasta, fai)
 }
 

tests/modules/strelka/germline/nextflow.config

@@ -1,5 +1,7 @@
 process {
 
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
-
+    withName: STRELKA_GERMLINE {
+        ext.args = '--exome'
+    }
 }

tests/modules/strelka/somatic/main.nf

@@ -12,18 +12,19 @@ workflow test_strelka_somatic {
         file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_cram_crai'], checkIfExists: true),
         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),
-        [],[]
+        [],[],
+        file(params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed_gz'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed_gz_tbi'], checkIfExists: true)
     ]
 
-    fasta   = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta'], checkIfExists: true)
-    fai     = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+    fai = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta_fai'], checkIfExists: true)
-    bed     = file(params.test_data['homo_sapiens']['genome']['genome_bed_gz'], checkIfExists: true)
-    bed_tbi = file(params.test_data['homo_sapiens']['genome']['genome_bed_gz_tbi'], checkIfExists: true)
 
-    STRELKA_SOMATIC (input, fasta, fai, bed, bed_tbi )
+    STRELKA_SOMATIC (input, fasta, fai )
 }
 
-workflow test_strelka__best_practices_somatic {
+workflow test_strelka_best_practices_somatic {
+
 
     input = [
         [ id:'test', single_end:false ], // meta map
@@ -31,14 +32,14 @@ workflow test_strelka__best_practices_somatic {
         file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_cram_crai'], checkIfExists: true),
         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),
-        file(params.test_data['homo_sapiens']['illumina']['test_genome_vcf_gz'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test_genome21_indels_vcf_gz'], checkIfExists: true),
-        file(params.test_data['homo_sapiens']['illumina']['test_genome_vcf_gz_tbi'], checkIfExists: true)
+        file(params.test_data['homo_sapiens']['illumina']['test_genome21_indels_vcf_gz_tbi'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed_gz'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed_gz_tbi'], checkIfExists: true)
     ]
 
-    fasta   = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta'], checkIfExists: true)
-    fai     = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+    fai   = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta_fai'], checkIfExists: true)
-    bed     = file(params.test_data['homo_sapiens']['genome']['genome_bed_gz'], checkIfExists: true)
-    bed_tbi = file(params.test_data['homo_sapiens']['genome']['genome_bed_gz_tbi'], checkIfExists: true)
 
-    STRELKA_SOMATIC ( input, fasta, fai, bed, bed_tbi )
+    STRELKA_SOMATIC ( input, fasta, fai )
 }

tests/modules/strelka/somatic/nextflow.config

@@ -1,5 +1,7 @@
 process {
 
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
-
+    withName: STRELKA_SOMATIC {
+        ext.args = '--exome'
+    }
 }

tests/modules/strelka/somatic/test.yml

@@ -6,20 +6,16 @@
   files:
     - path: output/strelka/test.somatic_indels.vcf.gz
     - path: output/strelka/test.somatic_indels.vcf.gz.tbi
-      md5sum: 4cb176febbc8c26d717a6c6e67b9c905
     - path: output/strelka/test.somatic_snvs.vcf.gz
     - path: output/strelka/test.somatic_snvs.vcf.gz.tbi
-      md5sum: 4cb176febbc8c26d717a6c6e67b9c905
 
-- name: strelka somatic test_strelka__best_practices_somatic
+- name: strelka somatic test_strelka_best_practices_somatic
-  command: nextflow run ./tests/modules/strelka/somatic -entry test_strelka__best_practices_somatic -c ./tests/config/nextflow.config -c ./tests/modules/strelka/somatic/nextflow.config
+  command: nextflow run ./tests/modules/strelka/somatic -entry test_strelka_best_practices_somatic -c ./tests/config/nextflow.config -c ./tests/modules/strelka/somatic/nextflow.config
   tags:
     - strelka
     - strelka/somatic
   files:
     - path: output/strelka/test.somatic_indels.vcf.gz
     - path: output/strelka/test.somatic_indels.vcf.gz.tbi
-      md5sum: 4cb176febbc8c26d717a6c6e67b9c905
     - path: output/strelka/test.somatic_snvs.vcf.gz
     - path: output/strelka/test.somatic_snvs.vcf.gz.tbi
-      md5sum: 4cb176febbc8c26d717a6c6e67b9c905