Merge branch 'master' into genomescope2

modules/arriba/main.nf

@@ -2,15 +2,20 @@ process ARRIBA {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::arriba=2.1.0" : null)
+    conda (params.enable_conda ? "bioconda::arriba=2.2.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/arriba:2.1.0--h3198e80_1' :
+        'https://depot.galaxyproject.org/singularity/arriba:2.2.1--hecb563c_2' :
-        'quay.io/biocontainers/arriba:2.1.0--h3198e80_1' }"
+        'quay.io/biocontainers/arriba:2.2.1--hecb563c_2' }"
 
     input:
     tuple val(meta), path(bam)
     path fasta
     path gtf
+    path blacklist
+    path known_fusions
+    path structural_variants
+    path tags
+    path protein_domains
 
     output:
     tuple val(meta), path("*.fusions.tsv")          , emit: fusions
@@ -23,7 +28,12 @@ process ARRIBA {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def blacklist = (args.contains('-b')) ? '' : '-f blacklist'
+    def blacklist = blacklist ? "-b $blacklist" : "-f blacklist"
+    def known_fusions = known_fusions ? "-k $known_fusions" : ""
+    def structural_variants = structural_variants ? "-d $structual_variants" : ""
+    def tags = tags ? "-t $tags" : ""
+    def protein_domains = protein_domains ? "-p $protein_domains" : ""
+
     """
     arriba \\
         -x $bam \\
@@ -32,6 +42,10 @@ process ARRIBA {
         -o ${prefix}.fusions.tsv \\
         -O ${prefix}.fusions.discarded.tsv \\
         $blacklist \\
+        $known_fusions \\
+        $structural_variants \\
+        $tags \\
+        $protein_domains \\
         $args
 
     cat <<-END_VERSIONS > versions.yml
@@ -39,4 +53,14 @@ process ARRIBA {
         arriba: \$(arriba -h | grep 'Version:' 2>&1 |  sed 's/Version:\s//')
     END_VERSIONS
     """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    echo stub > ${prefix}.fusions.tsv
+    echo stub > ${prefix}.fusions.discarded.tsv
+
+    echo "${task.process}:" > versions.yml
+    echo ' arriba: 2.2.1' >> versions.yml
+    """
 }

modules/arriba/meta.yml

@@ -30,6 +30,26 @@ input:
       type: file
       description: Annotation GTF file
       pattern: "*.{gtf}"
+  - blacklist:
+      type: file
+      description: Blacklist file
+      pattern: "*.{tsv}"
+  - known_fusions:
+      type: file
+      description: Known fusions file
+      pattern: "*.{tsv}"
+  - structural_variants:
+      type: file
+      description: Structural variants file
+      pattern: "*.{tsv}"
+  - tags:
+      type: file
+      description: Tags file
+      pattern: "*.{tsv}"
+  - protein_domains:
+      type: file
+      description: Protein domains file
+      pattern: "*.{gff3}"
 
 output:
   - meta:
@@ -51,4 +71,4 @@ output:
       pattern: "*.{fusions.discarded.tsv}"
 
 authors:
-  - "@praveenraj2018"
+  - "@praveenraj2018,@rannick"

modules/rtgtools/vcfeval/main.nf

@@ -0,0 +1,59 @@
+process RTGTOOLS_VCFEVAL {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::rtg-tools=3.12.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/rtg-tools:3.12.1--hdfd78af_0':
+        'quay.io/biocontainers/rtg-tools:3.12.1--hdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(query_vcf), path(query_vcf_tbi)
+    tuple path(truth_vcf), path(truth_vcf_tbi)
+    path(truth_regions)
+    path(evaluation_regions)
+    path(sdf)
+
+    output:
+    tuple val(meta), path("**results/{done,progress,*.log}") , emit: logs
+    tuple val(meta), path("**tp.vcf.gz"), path("**tp.vcf.gz.tbi") , emit: tp
+    tuple val(meta), path("**fn.vcf.gz"), path("**fn.vcf.gz.tbi") , emit: fn
+    tuple val(meta), path("**fp.vcf.gz"), path("**fp.vcf.gz.tbi") , emit: fp
+    tuple val(meta), path("**baseline.vcf.gz"), path("**baseline.vcf.gz.tbi") , emit: baseline
+    tuple val(meta), path("**.tsv.gz")                    , emit: roc
+    tuple val(meta), path("**results/summary.txt")        , emit: summary
+    tuple val(meta), path("**results/phasing.txt")        , emit: phasing
+    path "versions.yml"                                   , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ""
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def bed_regions = truth_regions ? "--bed-regions=$truth_regions" : ""
+    def eval_regions = evaluation_regions ? "--evaluation-regions=$evaluation_regions" : ""
+    def truth_index = truth_vcf_tbi ? "" : "rtg index $truth_vcf"
+    def query_index = query_vcf_tbi ? "" : "rtg index $query_vcf"
+
+    """
+    $truth_index
+    $query_index
+
+    rtg vcfeval \\
+        $args \\
+        --baseline=$truth_vcf \\
+        $bed_regions \\
+        $eval_regions \\
+        --calls=$query_vcf \\
+        --output=${prefix}_results \\
+        --template=$sdf \\
+        --threads=$task.cpus \\
+
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        rtg-tools: \$(echo \$(rtg version | head -n 1 | awk '{print \$4}'))
+    END_VERSIONS
+    """
+}

modules/rtgtools/vcfeval/meta.yml

@@ -0,0 +1,95 @@
+name: "rtgtools_vcfeval"
+description: The VCFeval tool of RTG tools. It is used to evaluate called variants for agreement with a baseline variant set
+keywords:
+  - benchmarking
+  - vcf
+  - rtg-tools
+tools:
+  - "rtgtools":
+      description: "RealTimeGenomics Tools -- Utilities for accurate VCF comparison and manipulation"
+      homepage: "https://www.realtimegenomics.com/products/rtg-tools"
+      documentation: "https://github.com/RealTimeGenomics/rtg-tools"
+      tool_dev_url: "https://github.com/RealTimeGenomics/rtg-tools"
+      doi: ""
+      licence: "['BSD']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - truth_vcf:
+      type: file
+      description: A standard VCF to compare against
+      pattern: "*.{vcf,vcf.gz}"
+  - truth_vcf_index:
+      type: file
+      description: The index of the standard VCF (optional)
+      pattern: "*.tbi"
+  - query_vcf:
+      type: file
+      description: A VCF with called variants to benchmark against the standard
+      pattern: "*.{vcf,vcf.gz}"
+  - query_vcf_index:
+      type: file
+      description: The index of the called VCF (optional)
+      pattern: "*.tbi"
+  - truth_regions:
+      type: file
+      description: A BED file containining the strict regions where VCFeval should only evaluate the fully overlapping variants (optional)
+      pattern: "*.bed"
+  - evaluation_regions:
+      type: file
+      description: A BED file containing the regions where VCFeval will evaluate every fully and partially overlapping variant (optional)
+      pattern: "*.bed"
+  - sdf:
+      type: file
+      description: The SDF (RTG Sequence Data File) folder of the reference genome
+      pattern: "*"
+
+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"
+  - logging:
+      type: file
+      description: Files containing logging from vcfeval
+      pattern: "*{done,progress,.log}"
+  - tp:
+      type: file
+      description: A tuple containing the VCF and TBI file for the true positive variants
+      pattern: "tp.vcf{.gz,.gz.tbi}"
+  - baseline:
+      type: file
+      description: A tuple containing the VCF and TBI file for the baseline true positive variants
+      pattern: "tp-baseline.vcf{.gz,.gz.tbi}"
+  - fp:
+      type: file
+      description: A tuple containing the VCF and TBI file for the false positive variants
+      pattern: "fp.vcf{.gz,.gz.tbi}"
+  - fn:
+      type: file
+      description: A tuple containing the VCF and TBI file for the false negative variants
+      pattern: "fn.vcf{.gz,.gz.tbi}"
+  - roc:
+      type: file
+      description: TSV files containing ROC data for the evaluated variants
+      pattern: "*.tsv.gz"
+  - summary:
+      type: file
+      description: A TXT file containing the summary of the evaluation
+      pattern: "summary.txt"
+  - phasing:
+      type: file
+      description: A TXT file containing the data on the phasing
+      pattern: "phasing.txt"
+
+authors:
+  - "@nvnieuwk"

tests/config/pytest_modules.yml

@@ -1623,6 +1623,10 @@ rseqc/tin:
   - modules/rseqc/tin/**
   - tests/modules/rseqc/tin/**
 
+rtgtools/vcfeval:
+  - modules/rtgtools/vcfeval/**
+  - tests/modules/rtgtools/vcfeval/**
+
 salmon/index:
   - modules/salmon/index/**
   - tests/modules/salmon/index/**

tests/config/test_data.config

@@ -135,6 +135,7 @@ params {
                 transcriptome_fasta                            = "${test_data_dir}/genomics/homo_sapiens/genome/transcriptome.fasta"
                 genome2_fasta                                  = "${test_data_dir}/genomics/homo_sapiens/genome/genome2.fasta"
                 genome_chain_gz                                = "${test_data_dir}/genomics/homo_sapiens/genome/genome.chain.gz"
+                genome_21_sdf                                  = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome_sdf.tar.gz"
                 genome_21_fasta                                = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.fasta"
                 genome_21_fasta_fai                            = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.fasta.fai"
                 genome_21_dict                                 = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.dict"
@@ -212,7 +213,6 @@ params {
                 test_paired_end_hla                                     = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/example_hla_pe.bam"
                 test_paired_end_hla_sorted_bam                          = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/example_hla_pe.sorted.bam"
                 test_paired_end_hla_sorted_bam_bai                      = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/example_hla_pe.sorted.bam.bai"
-
                 test2_paired_end_sorted_bam                    = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.sorted.bam"
                 test2_paired_end_sorted_bam_bai                = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.sorted.bam.bai"
                 test2_paired_end_name_sorted_bam               = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.name.sorted.bam"
@@ -227,6 +227,7 @@ params {
                 test2_paired_end_umi_unsorted_bam              = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.umi_unsorted.bam"
                 test2_paired_end_umi_unsorted_tagged_bam       = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.unsorted_tagged.bam"
 
+
                 mitochon_standin_recalibrated_sorted_bam       = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/mitochon_standin.recalibrated.sorted.bam"
                 mitochon_standin_recalibrated_sorted_bam_bai   = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/mitochon_standin.recalibrated.sorted.bam.bai"
 
@@ -266,6 +267,9 @@ params {
                 test2_haplotc_ann_vcf_gz                       = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test2_haplotc.ann.vcf.gz"
                 test2_haplotc_ann_vcf_gz_tbi                   = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test2_haplotc.ann.vcf.gz.tbi"
 
+                test2_haplotc_vcf_gz                           = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test2_haplotc.vcf.gz"
+                test2_haplotc_vcf_gz_tbi                       = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test2_haplotc.vcf.gz.tbi"
+
                 test2_recal                                    = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2.recal"
                 test2_recal_idx                                = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2.recal.idx"
                 test2_tranches                                 = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2.tranches"

tests/modules/arriba/main.nf

@@ -20,7 +20,7 @@ workflow test_arriba_single_end {
 
     STAR_GENOMEGENERATE ( fasta, gtf )
     STAR_ALIGN ( input, STAR_GENOMEGENERATE.out.index, gtf, star_ignore_sjdbgtf, seq_platform, seq_center )
-    ARRIBA ( STAR_ALIGN.out.bam, fasta, gtf )
+    ARRIBA ( STAR_ALIGN.out.bam, fasta, gtf , [], [], [], [], [])
 }
 
 workflow test_arriba_paired_end {
@@ -38,5 +38,5 @@ workflow test_arriba_paired_end {
 
     STAR_GENOMEGENERATE ( fasta, gtf )
     STAR_ALIGN ( input, STAR_GENOMEGENERATE.out.index, gtf, star_ignore_sjdbgtf, seq_platform, seq_center )
-    ARRIBA ( STAR_ALIGN.out.bam, fasta, gtf )
+    ARRIBA ( STAR_ALIGN.out.bam, fasta, gtf, [], [], [], [], [])
 }

tests/modules/arriba/test.yml

@@ -4,7 +4,7 @@
     - arriba
   files:
     - path: output/arriba/test.fusions.discarded.tsv
-      md5sum: cad8c215b938d1e45b747a5b7898a4c2
+      md5sum: 7602ab4ccbbb0c54fbca12a942877e6d
     - path: output/arriba/test.fusions.tsv
       md5sum: 7c3383f7eb6d79b84b0bd30a7ef02d70
     - path: output/star/star/Genome
@@ -39,6 +39,7 @@
     - path: output/star/star/transcriptInfo.tab
       md5sum: 0c3a5adb49d15e5feff81db8e29f2e36
     - path: output/star/test.Aligned.out.bam
+      md5sum: 4fa079d11f8938e51015e3e477fa7149
     - path: output/star/test.Log.final.out
     - path: output/star/test.Log.out
     - path: output/star/test.Log.progress.out
@@ -50,7 +51,7 @@
     - arriba
   files:
     - path: output/arriba/test.fusions.discarded.tsv
-      md5sum: 85e36c887464e4deaa65f45174d3b8fd
+      md5sum: cdc6cfbc75e68ce29a766f50f390274d
     - path: output/arriba/test.fusions.tsv
       md5sum: 7c3383f7eb6d79b84b0bd30a7ef02d70
     - path: output/star/star/Genome

tests/modules/rtgtools/vcfeval/main.nf

@@ -0,0 +1,69 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { RTGTOOLS_VCFEVAL } from '../../../../modules/rtgtools/vcfeval/main.nf'
+include { UNTAR } from '../../../modules/untar/main.nf'
+
+workflow test_rtgtools_vcfeval {
+    
+    input = [
+        [ id:'test' ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test2_haplotc_vcf_gz'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test2_haplotc_vcf_gz_tbi'], checkIfExists: true),        
+    ]
+
+    truth = [
+        file(params.test_data['homo_sapiens']['illumina']['test2_haplotc_ann_vcf_gz'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test2_haplotc_ann_vcf_gz_tbi'], checkIfExists: true)
+    ]
+
+    truth_regions = file(params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed'], checkIfExists: true)
+
+    evaluation_regions = file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true)
+
+    compressed_sdf = [
+        [],
+        file(params.test_data['homo_sapiens']['genome']['genome_21_sdf'])
+    ]
+
+    sdf = UNTAR( compressed_sdf ).untar
+        .map({
+            meta, folder ->
+                folder
+        })
+    
+
+    RTGTOOLS_VCFEVAL ( input, truth, truth_regions, evaluation_regions, sdf )
+}
+
+workflow test_rtgtools_vcfeval_no_optional_inputs {
+    
+    input = [
+        [ id:'test' ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test2_haplotc_vcf_gz'], checkIfExists: true),
+        [],
+    ]
+
+    truth = [
+        file(params.test_data['homo_sapiens']['illumina']['test2_haplotc_ann_vcf_gz'], checkIfExists: true),
+        []
+    ]
+
+    truth_regions = []
+
+    evaluation_regions = []
+
+    compressed_sdf = [
+        [],
+        file(params.test_data['homo_sapiens']['genome']['genome_21_sdf'])
+    ]
+
+    sdf = UNTAR( compressed_sdf ).untar
+        .map({
+            meta, folder ->
+                [folder]
+        })
+
+    RTGTOOLS_VCFEVAL ( input, truth, truth_regions, evaluation_regions, sdf )
+}

tests/modules/rtgtools/vcfeval/nextflow.config

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

tests/modules/rtgtools/vcfeval/test.yml

@@ -0,0 +1,75 @@
+- name: rtgtools vcfeval test_rtgtools_vcfeval
+  command: nextflow run tests/modules/rtgtools/vcfeval -entry test_rtgtools_vcfeval -c tests/config/nextflow.config
+  tags:
+    - rtgtools
+    - rtgtools/vcfeval
+  files:
+    - path: output/rtgtools/test_results/done
+    - path: output/rtgtools/test_results/fn.vcf.gz
+      md5sum: be9c9106055bfad4c5985bc0d33efd56
+    - path: output/rtgtools/test_results/fn.vcf.gz.tbi
+      md5sum: 092a7a3162e7cff25d273525751eb284
+    - path: output/rtgtools/test_results/fp.vcf.gz
+      md5sum: e0f0ff841dc63e9fb61fd3a5db137ced
+    - path: output/rtgtools/test_results/fp.vcf.gz.tbi
+      md5sum: 092a7a3162e7cff25d273525751eb284
+    - path: output/rtgtools/test_results/non_snp_roc.tsv.gz
+      md5sum: ad5bad32c48f05aef232e2c0e708877a
+    - path: output/rtgtools/test_results/phasing.txt
+      md5sum: 133677dbd8be657439ea2b03fdfb8795
+    - path: output/rtgtools/test_results/progress
+    - path: output/rtgtools/test_results/snp_roc.tsv.gz
+      md5sum: 6785b83d66486e7e6c75c5a5b1574c09
+    - path: output/rtgtools/test_results/summary.txt
+      md5sum: f4c8df93c8bdab603036bbc27b4a28c3
+    - path: output/rtgtools/test_results/tp-baseline.vcf.gz
+      md5sum: be9c9106055bfad4c5985bc0d33efd56
+    - path: output/rtgtools/test_results/tp-baseline.vcf.gz.tbi
+      md5sum: 092a7a3162e7cff25d273525751eb284
+    - path: output/rtgtools/test_results/tp.vcf.gz
+      md5sum: e0f0ff841dc63e9fb61fd3a5db137ced
+    - path: output/rtgtools/test_results/tp.vcf.gz.tbi
+      md5sum: 092a7a3162e7cff25d273525751eb284
+    - path: output/rtgtools/test_results/vcfeval.log
+    - path: output/rtgtools/test_results/weighted_roc.tsv.gz
+      md5sum: fa7c046ea0084172f1ef91f19de07b2b
+    - path: output/rtgtools/versions.yml
+      md5sum: 270ed7a5a8e347b251eb4aa2198f98e8
+
+- name: rtgtools vcfeval test_rtgtools_vcfeval_no_optional_inputs
+  command: nextflow run tests/modules/rtgtools/vcfeval -entry test_rtgtools_vcfeval_no_optional_inputs -c tests/config/nextflow.config
+  tags:
+    - rtgtools
+    - rtgtools/vcfeval
+  files:
+    - path: output/rtgtools/test_results/done
+    - path: output/rtgtools/test_results/fn.vcf.gz
+      md5sum: c11c889a4f42c8ea325748bd768ea34d
+    - path: output/rtgtools/test_results/fn.vcf.gz.tbi
+      md5sum: 092a7a3162e7cff25d273525751eb284
+    - path: output/rtgtools/test_results/fp.vcf.gz
+      md5sum: 138e85c1cd79f8fea9a33e81ce0c734c
+    - path: output/rtgtools/test_results/fp.vcf.gz.tbi
+      md5sum: 092a7a3162e7cff25d273525751eb284
+    - path: output/rtgtools/test_results/non_snp_roc.tsv.gz
+      md5sum: 34fb78a008dfc0bef02807b8a7012b07
+    - path: output/rtgtools/test_results/phasing.txt
+      md5sum: 133677dbd8be657439ea2b03fdfb8795
+    - path: output/rtgtools/test_results/progress
+    - path: output/rtgtools/test_results/snp_roc.tsv.gz
+      md5sum: a4c5761c2653e2d04fc84c1cea13b1f0
+    - path: output/rtgtools/test_results/summary.txt
+      md5sum: f33feb32f84958fb931063044fba369b
+    - path: output/rtgtools/test_results/tp-baseline.vcf.gz
+      md5sum: d1c2d990899edf127ea5fcca8866fcb0
+    - path: output/rtgtools/test_results/tp-baseline.vcf.gz.tbi
+      md5sum: 3307008fea47adb75c46d395c5567bc0
+    - path: output/rtgtools/test_results/tp.vcf.gz
+      md5sum: e35b4dab82894eee9b77c81f9bc89cca
+    - path: output/rtgtools/test_results/tp.vcf.gz.tbi
+      md5sum: 45d8f8793140944f129e728299918c88
+    - path: output/rtgtools/test_results/vcfeval.log
+    - path: output/rtgtools/test_results/weighted_roc.tsv.gz
+      md5sum: 5b8efc9e9381f604880412800f58e4e9
+    - path: output/rtgtools/versions.yml
+      md5sum: 55568e4bbe5ab7e634a1f392abb89cc4