Merge branch 'master' into rp3-add-snippy

modules/antismash/antismashlite/main.nf

@@ -0,0 +1,68 @@
+process ANTISMASH_ANTISMASHLITE {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::antismash-lite=6.0.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/antismash-lite:6.0.1--pyhdfd78af_1' :
+        'quay.io/biocontainers/antismash-lite:6.0.1--pyhdfd78af_1' }"
+
+    containerOptions {
+        workflow.containerEngine == 'singularity' ?
+        "-B $antismash_dir:/usr/local/lib/python3.8/site-packages/antismash" :
+        workflow.containerEngine == 'docker' ?
+        "-v \$PWD/$antismash_dir:/usr/local/lib/python3.8/site-packages/antismash" :
+        ''
+        }
+
+    input:
+    tuple val(meta), path(sequence_input)
+    path(databases)
+    path(antismash_dir) // Optional input: AntiSMASH installation folder. It is not needed for using this module with conda, but required for docker/singularity (see meta.yml).
+    path(gff)
+
+    output:
+    tuple val(meta), path("${prefix}/clusterblast/*_c*.txt")                 , optional: true, emit: clusterblast_file
+    tuple val(meta), path("${prefix}/{css,images,js}")                       , emit: html_accessory_files
+    tuple val(meta), path("${prefix}/knownclusterblast/region*/ctg*.html")   , optional: true, emit: knownclusterblast_html
+    tuple val(meta), path("${prefix}/knownclusterblast/*_c*.txt")            , optional: true, emit: knownclusterblast_txt
+    tuple val(meta), path("${prefix}/svg/clusterblast*.svg")                 , optional: true, emit: svg_files_clusterblast
+    tuple val(meta), path("${prefix}/svg/knownclusterblast*.svg")            , optional: true, emit: svg_files_knownclusterblast
+    tuple val(meta), path("${prefix}/*.gbk")                                 , emit: gbk_input
+    tuple val(meta), path("${prefix}/*.json")                                , emit: json_results
+    tuple val(meta), path("${prefix}/*.log")                                 , emit: log
+    tuple val(meta), path("${prefix}/*.zip")                                 , emit: zip
+    tuple val(meta), path("${prefix}/*region*.gbk")                          , emit: gbk_results
+    tuple val(meta), path("${prefix}/clusterblastoutput.txt")                , optional: true, emit: clusterblastoutput
+    tuple val(meta), path("${prefix}/index.html")                            , emit: html
+    tuple val(meta), path("${prefix}/knownclusterblastoutput.txt")           , optional: true, emit: knownclusterblastoutput
+    tuple val(meta), path("${prefix}/regions.js")                            , emit: json_sideloading
+    path "versions.yml"                                                      , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    prefix = task.ext.suffix ? "${meta.id}${task.ext.suffix}" : "${meta.id}"
+    gff_flag = "--genefinding-gff3 ${gff}"
+
+    """
+    ## We specifically do not include annotations (--genefinding-tool none) as
+    ## this should be run as a separate module for versioning purposes
+    antismash \\
+        $args \\
+        $gff_flag \\
+        -c $task.cpus \\
+        --output-dir $prefix \\
+        --genefinding-tool none \\
+        --logfile $prefix/${prefix}.log \\
+        --databases $databases \\
+        $sequence_input
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        antismash-lite: \$(antismash --version | sed 's/antiSMASH //')
+    END_VERSIONS
+    """
+}

modules/antismash/antismashlite/meta.yml

@@ -0,0 +1,128 @@
+name: antismash_antismashlite
+description: |
+  antiSMASH allows the rapid genome-wide identification, annotation
+  and analysis of secondary metabolite biosynthesis gene clusters.
+keywords:
+  - secondary metabolites
+  - BGC
+  - biosynthetic gene cluster
+  - genome mining
+  - NRPS
+  - RiPP
+  - antibiotics
+  - prokaryotes
+  - bacteria
+  - eukaryotes
+  - fungi
+  - antismash
+
+tools:
+  - antismashlite:
+      description: "antiSMASH - the antibiotics and Secondary Metabolite Analysis SHell"
+      homepage: "https://docs.antismash.secondarymetabolites.org"
+      documentation: "https://docs.antismash.secondarymetabolites.org"
+      tool_dev_url: "https://github.com/antismash/antismash"
+      doi: "10.1093/nar/gkab335"
+      licence: "['AGPL v3']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - sequence_input:
+      type: file
+      description: nucleotide sequence file (annotated)
+      pattern: "*.{gbk, gb, gbff, genbank, embl, fasta, fna}"
+  - databases:
+      type: directory
+      description: downloaded AntiSMASH databases e.g. data/databases
+      pattern: "*/"
+  - antismash_dir:
+      type: directory
+      description: |
+        A local copy of an AntiSMASH installation folder. This is required when running with
+        docker and singularity (not required for conda), due to attempted 'modifications' of
+        files during database checks in the installation directory, something that cannot
+        be done in immutable docker/singularity containers. Therefore, a local installation
+        directory needs to be mounted (including all modified files from the downloading step)
+        to the container as a workaround.
+      pattern: "*/"
+  - gff:
+      type: file
+      pattern: "*.gff"
+
+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"
+  - clusterblast_file:
+      type: file
+      description: Output of ClusterBlast algorithm
+      pattern: "clusterblast/*_c*.txt"
+  - html_accessory_files:
+      type: directory
+      description: Accessory files for the HTML output
+      pattern: "{css/,images/,js/}"
+  - knownclusterblast_html:
+      type: file
+      description: Tables with MIBiG hits in HTML format
+      pattern: "knownclusterblast/region*/ctg*.html"
+  - knownclusterblast_txt:
+      type: file
+      description: Tables with MIBiG hits
+      pattern: "knownclusterblast/*_c*.txt"
+  - svg_files_clusterblast:
+      type: file
+      description: SVG images showing the % identity of the aligned hits against their queries
+      pattern: "svg/clusterblast*.svg"
+  - svg_files_knownclusterblast:
+      type: file
+      description: SVG images showing the % identity of the aligned hits against their queries
+      pattern: "svg/knownclusterblast*.svg"
+  - gbk_input:
+      type: file
+      description: Nucleotide sequence and annotations in GenBank format; converted from input file
+      pattern: "*.gbk"
+  - json_results:
+      type: file
+      description: Nucleotide sequence and annotations in JSON format; converted from GenBank file (gbk_input)
+      pattern: "*.json"
+  - log:
+      type: file
+      description: Contains all the logging output that antiSMASH produced during its run
+      pattern: "*.log"
+  - zip:
+      type: file
+      description: Contains a compressed version of the output folder in zip format
+      pattern: "*.zip"
+  - gbk_results:
+      type: file
+      description: Nucleotide sequence and annotations in GenBank format; one file per antiSMASH hit
+      pattern: "*region*.gbk"
+  - clusterblastoutput:
+      type: file
+      description: Raw BLAST output of known clusters previously predicted by antiSMASH using the built-in ClusterBlast algorithm
+      pattern: "clusterblastoutput.txt"
+  - html:
+      type: file
+      description: Graphical web view of results in HTML format
+      patterN: "index.html"
+  - knownclusterblastoutput:
+      type: file
+      description: Raw BLAST output of known clusters of the MIBiG database
+      pattern: "knownclusterblastoutput.txt"
+  - json_sideloading:
+      type: file
+      description: Sideloaded annotations of protoclusters and/or subregions (see antiSMASH documentation "Annotation sideloading")
+      pattern: "regions.js"
+
+authors:
+  - "@jasmezz"

modules/bcftools/roh/main.nf

@@ -0,0 +1,61 @@
+process BCFTOOLS_ROH {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::bcftools=1.15.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/bcftools:1.15.1--h0ea216a_0':
+        'quay.io/biocontainers/bcftools:1.15.1--h0ea216a_0' }"
+
+    input:
+    tuple val(meta), path(vcf), path(tbi)
+    path af_file
+    path genetic_map
+    path regions_file
+    path samples_file
+    path targets_file
+
+    output:
+    tuple val(meta), path("*.roh"), emit: roh
+    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 af_read   = af_file         ? "--AF-file ${af_file}"           : ''
+    def gen_map   = genetic_map     ? "--genetic-map ${genetic_map}"   : ''
+    def reg_file  = regions_file    ? "--regions-file ${regions_file}" : ''
+    def samp_file = samples_file    ? "--samples-file ${samples_file}" : ''
+    def targ_file = targets_file    ? "--targets-file ${targets_file}" : ''
+    """
+    bcftools \\
+        roh \\
+        $args \\
+        $af_read \\
+        $gen_map \\
+        $reg_file \\
+        $samp_file \\
+        $targ_file \\
+        -o ${prefix}.roh \\
+        $vcf
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bcftools: \$(bcftools --version 2>&1 | head -n1 | sed 's/^.*bcftools //; s/ .*\$//')
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix    = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.roh
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bcftools: \$(bcftools --version 2>&1 | head -n1 | sed 's/^.*bcftools //; s/ .*\$//')
+    END_VERSIONS
+    """
+}

modules/bcftools/roh/meta.yml

@@ -0,0 +1,55 @@
+name: "bcftools_roh"
+description: A program for detecting runs of homo/autozygosity. Only bi-allelic sites are considered.
+keywords:
+  - roh
+tools:
+  - "roh":
+      description: "A program for detecting runs of homo/autozygosity. Only bi-allelic sites are considered."
+      homepage: https://www.htslib.org/
+      documentation: http://www.htslib.org/doc/bcftools.html
+      doi: 10.1093/bioinformatics/btp352
+      licence: ["MIT"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - vcf:
+      type: file
+      description: VCF file
+      pattern: "*.{vcf,.vcf.gz}"
+  - af_file:
+      type: file
+      description: "Read allele frequencies from a tab-delimited file containing the columns: CHROM\tPOS\tREF,ALT\tAF."
+  - genetic_map:
+      type: file
+      description: "Genetic map in the format required also by IMPUTE2."
+  - regions_file:
+      type: file
+      description: "Regions can be specified either on command line or in a VCF, BED, or tab-delimited file (the default)."
+  - samples_file:
+      type: file
+      description: "File of sample names to include or exclude if prefixed with '^'."
+  - targets_file:
+      type: file
+      description: "Targets can be specified either on command line or in a VCF, BED, or tab-delimited file (the default)."
+
+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"
+  - roh:
+      type: file
+      description: Contains site-specific and/or per-region runs of homo/autozygosity calls.
+      pattern: "*.{roh}"
+
+authors:
+  - "@ramprasadn"

modules/bedtools/split/main.nf

@@ -0,0 +1,38 @@
+process BEDTOOLS_SPLIT {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::bedtools=2.30.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/bedtools:2.30.0--h468198e_3':
+        'quay.io/biocontainers/bedtools:2.30.0--h7d7f7ad_2' }"
+
+    input:
+    tuple val(meta), path(bed)
+    val(number_of_files)
+
+    output:
+    tuple val(meta), path("*.bed"), emit: beds
+    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}"
+
+    """
+    bedtools \\
+        split \\
+        $args \\
+        -i $bed \\
+        -p $prefix \\
+        -n $number_of_files
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bedtools: \$(bedtools --version | sed -e "s/bedtools v//g")
+    END_VERSIONS
+    """
+}

modules/bedtools/split/meta.yml

@@ -0,0 +1,41 @@
+name: "bedtools_split"
+description: Split BED files into several smaller BED files
+keywords:
+  - sort
+tools:
+  - "bedtools":
+      description: "A powerful toolset for genome arithmetic"
+      documentation: "https://bedtools.readthedocs.io/en/latest/content/tools/sort.html"
+      licence: "['MIT', 'GPL v2']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bed:
+      type: file
+      description: BED file
+      pattern: "*.bed"
+  - bed:
+      type: value
+      description: The number of files to split the BED into
+
+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"
+  - beds:
+      type: file
+      description: list of split BED files
+      pattern: "*.bed"
+
+authors:
+  - "@nvnieuwk"

modules/biobambam/bammerge/main.nf

@@ -0,0 +1,38 @@
+process BIOBAMBAM_BAMMERGE {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::biobambam=2.0.183" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/biobambam:2.0.183--h9f5acd7_1':
+        'quay.io/biocontainers/biobambam:2.0.183--h9f5acd7_1' }"
+
+    input:
+    tuple val(meta), path(bam)
+
+    output:
+    tuple val(meta), path("${prefix}.bam")  ,emit: bam
+    tuple val(meta), path("*.bai")          ,optional:true, emit: bam_index
+    tuple val(meta), path("*.md5")          ,optional:true, emit: checksum
+    path "versions.yml"                     ,emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    prefix = task.ext.prefix ?: "${meta.id}"
+    def input_string = bam.join(" I=")
+
+    """
+    bammerge \\
+        I=${input_string} \\
+        $args \\
+        > ${prefix}.bam
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bammerge: \$( bammerge --version |& sed '1!d; s/.*version //; s/.\$//' )
+    END_VERSIONS
+    """
+}

modules/biobambam/bammerge/meta.yml

@@ -0,0 +1,46 @@
+name: biobambam_bammerge
+description: Merge a list of sorted bam files
+keywords:
+  - merge
+  - bam
+tools:
+  - biobambam:
+      description: |
+        biobambam is a set of tools for early stage alignment file processing.
+      homepage: https://gitlab.com/german.tischler/biobambam2
+      documentation: https://gitlab.com/german.tischler/biobambam2/-/blob/master/README.md
+      doi: 10.1186/1751-0473-9-13
+      licence: ["GPL v3"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: List containing 1 or more bam files
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: Merged BAM file
+      pattern: "*.bam"
+  - bam_index:
+      type: file
+      description: BAM index file
+      pattern: "*"
+  - checksum:
+      type: file
+      description: Checksum file
+      pattern: "*"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@matthdsm"

modules/bowtie2/align/main.nf

@@ -11,6 +11,7 @@ process BOWTIE2_ALIGN {
     tuple val(meta), path(reads)
     path  index
     val   save_unaligned
+    val   sort_bam
 
     output:
     tuple val(meta), path("*.bam")    , emit: bam
@@ -36,8 +37,7 @@ process BOWTIE2_ALIGN {
         reads_args = "-1 ${reads[0]} -2 ${reads[1]}"
     }
 
-    def samtools_command = "samtools view -@ $task.cpus --bam --with-header ${args2} > ${prefix}.bam"
-
+    def samtools_command = sort_bam ? 'sort' : 'view'
 
     """
     INDEX=`find -L ./ -name "*.rev.1.bt2" | sed "s/.rev.1.bt2//"`
@@ -51,7 +51,7 @@ process BOWTIE2_ALIGN {
         $unaligned \\
         $args \\
         2> ${prefix}.bowtie2.log \\
-        | $samtools_command
+        | samtools $samtools_command $args2 --threads $task.cpus -o ${prefix}.bam -
 
     if [ -f ${prefix}.unmapped.fastq.1.gz ]; then
         mv ${prefix}.unmapped.fastq.1.gz ${prefix}.unmapped_1.fastq.gz
@@ -69,4 +69,3 @@ process BOWTIE2_ALIGN {
     END_VERSIONS
     """
 }
-

modules/bowtie2/align/meta.yml

@@ -29,6 +29,15 @@ input:
       type: file
       description: Bowtie2 genome index files
       pattern: "*.ebwt"
+  - save_unaligned:
+      type: boolean
+      description: |
+        Save reads that do not map to the reference (true) or discard them (false)
+        (default: false)
+  - sort_bam:
+      type: boolean
+      description: use samtools sort (true) or samtools view (false)
+      pattern: "true or false"
 output:
   - bam:
       type: file

modules/cnvkit/antitarget/main.nf

@@ -0,0 +1,36 @@
+process CNVKIT_ANTITARGET {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::cnvkit=0.9.9" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/cnvkit:0.9.9--pyhdfd78af_0':
+        'quay.io/biocontainers/cnvkit:0.9.9--pyhdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(targets)
+
+    output:
+    tuple val(meta), path("*.bed"), emit: bed
+    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}"
+
+    """
+    cnvkit.py \\
+        antitarget \\
+        $targets \\
+        --output ${prefix}.antitarget.bed \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
+    END_VERSIONS
+    """
+}

modules/cnvkit/antitarget/meta.yml

@@ -0,0 +1,44 @@
+name: cnvkit_antitarget
+description:
+keywords:
+  - cvnkit
+  - antitarget
+tools:
+  - cnvkit:
+      description: |
+        CNVkit is a Python library and command-line software toolkit to infer and visualize copy number from high-throughput DNA sequencing data.
+        It is designed for use with hybrid capture, including both whole-exome and custom target panels, and short-read sequencing platforms such as Illumina and Ion Torrent.
+      homepage: https://cnvkit.readthedocs.io/en/stable/index.html
+      documentation: https://cnvkit.readthedocs.io/en/stable/index.html
+      tool_dev_url: "https://github.com/etal/cnvkit"
+      doi: 10.1371/journal.pcbi.1004873
+      licence: ["Apache-2.0"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - targets:
+      type: file
+      description: File containing genomic regions
+      pattern: "*.{bed}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bed:
+      type: file
+      description: File containing off-target regions
+      pattern: "*.{bed}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@SusiJo"

modules/cnvkit/batch/main.nf

@@ -2,10 +2,10 @@ process CNVKIT_BATCH {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? 'bioconda::cnvkit=0.9.9' : null)
+    conda (params.enable_conda ? 'bioconda::cnvkit=0.9.9 bioconda::samtools=1.15.1' : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/cnvkit:0.9.9--pyhdfd78af_0' :
-        'quay.io/biocontainers/cnvkit:0.9.9--pyhdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/mulled-v2-780d630a9bb6a0ff2e7b6f730906fd703e40e98f:304d1c5ab610f216e77c61420ebe85f1e7c5968a-0' :
+        'quay.io/biocontainers/mulled-v2-780d630a9bb6a0ff2e7b6f730906fd703e40e98f:304d1c5ab610f216e77c61420ebe85f1e7c5968a-0' }"
 
     input:
     tuple val(meta), path(tumor), path(normal)
@@ -18,6 +18,8 @@ process CNVKIT_BATCH {
     tuple val(meta), path("*.cnn"), emit: cnn, optional: true
     tuple val(meta), path("*.cnr"), emit: cnr, optional: true
     tuple val(meta), path("*.cns"), emit: cns, optional: true
+    tuple val(meta), path("*.pdf"), emit: pdf, optional: true
+    tuple val(meta), path("*.png"), emit: png, optional: true
     path "versions.yml"           , emit: versions
 
     when:
@@ -25,21 +27,39 @@ process CNVKIT_BATCH {
 
     script:
     def args = task.ext.args ?: ''
-    def normal_args = normal ? "--normal $normal" : ""
-    def fasta_args = fasta ? "--fasta $fasta" : ""
+
+    // execute samtools only when cram files are input, cnvkit runs natively on bam but is prohibitively slow
+    // input pair is assumed to have same extension if both exist
+    def is_cram = tumor.Extension == "cram" ? true : false
+    def tumor_out = is_cram ? tumor.BaseName + ".bam" : "${tumor}"
+
+    // do not run samtools on normal samples in tumor_only mode
+    def normal_exists = normal ? true: false
+    // tumor_only mode does not need fasta & target
+    // instead it requires a pre-computed reference.cnn which is built from fasta & target
+    def (normal_out, normal_args, fasta_args) = ["", "", ""]
+
+    if (normal_exists){
+        def normal_prefix = normal.BaseName
+        normal_out = is_cram ? "${normal_prefix}" + ".bam" : "${normal}"
+        normal_args = normal_prefix ? "--normal $normal_out" : ""
+        fasta_args = fasta ? "--fasta $fasta" : ""
+    }
+
+    def target_args = targets ? "--targets $targets" : ""
     def reference_args = reference ? "--reference $reference" : ""
 
-    def target_args = ""
-    if (args.contains("--method wgs") || args.contains("-m wgs")) {
-        target_args = targets ? "--targets $targets" : ""
-    }
-    else {
-        target_args = "--targets $targets"
-    }
     """
+    if $is_cram; then
+        samtools view -T $fasta $tumor -@ $task.cpus -o $tumor_out
+        if $normal_exists; then
+            samtools view -T $fasta $normal -@ $task.cpus -o $normal_out
+        fi
+    fi
+
     cnvkit.py \\
         batch \\
-        $tumor \\
+        $tumor_out \\
         $normal_args \\
         $fasta_args \\
         $reference_args \\

modules/cnvkit/batch/meta.yml

@@ -11,27 +11,6 @@ tools:
       homepage: https://cnvkit.readthedocs.io/en/stable/index.html
       documentation: https://cnvkit.readthedocs.io/en/stable/index.html
       licence: ["Apache-2.0"]
-params:
-  - outdir:
-      type: string
-      description: |
-        The pipeline's output directory. By default, the module will
-        output files into `$params.outdir/<SOFTWARE>`
-  - publish_dir_mode:
-      type: string
-      description: |
-        Value for the Nextflow `publishDir` mode parameter.
-        Available: symlink, rellink, link, copy, copyNoFollow, move.
-  - enable_conda:
-      type: boolean
-      description: |
-        Run the module with Conda using the software specified
-        via the `conda` directive
-  - singularity_pull_docker_container:
-      type: boolean
-      description: |
-        Instead of directly downloading Singularity images for use with Singularity,
-        force the workflow to pull and convert Docker containers instead.
 input:
   - meta:
       type: map
@@ -49,7 +28,7 @@ input:
   - fasta:
       type: file
       description: |
-        Input reference genome fasta file
+        Input reference genome fasta file (only needed for cram_input and/or when normal_samples are provided)
   - targetfile:
       type: file
       description: |
@@ -80,6 +59,14 @@ output:
       type: file
       description: File containing copy number segment information
       pattern: "*.{cns}"
+  - pdf:
+      type: file
+      description: File with plot of copy numbers or segments on chromosomes
+      pattern: "*.{pdf}"
+  - png:
+      type: file
+      description: File with plot of bin-level log2 coverages and segmentation calls
+      pattern: "*.{png}"
   - versions:
       type: file
       description: File containing software versions
@@ -91,3 +78,4 @@ authors:
   - "@drpatelh"
   - "@fbdtemme"
   - "@lassefolkersen"
+  - "@SusiJo"

modules/cnvkit/reference/main.nf

@@ -0,0 +1,40 @@
+process CNVKIT_REFERENCE {
+    tag "$fasta"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::cnvkit=0.9.9" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/cnvkit:0.9.9--pyhdfd78af_0':
+        'quay.io/biocontainers/cnvkit:0.9.9--pyhdfd78af_0' }"
+
+    input:
+    path fasta
+    path targets
+    path antitargets
+
+    output:
+    path "*.cnn"       , emit: cnn
+    path "versions.yml", emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: targets.BaseName
+
+    """
+    cnvkit.py \\
+        reference \\
+        --fasta $fasta \\
+        --targets $targets \\
+        --antitargets $antitargets \\
+        --output ${prefix}.reference.cnn \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
+    END_VERSIONS
+    """
+}

modules/cnvkit/reference/meta.yml

@@ -0,0 +1,47 @@
+name: cnvkit_reference
+description:
+keywords:
+  - cnvkit
+  - reference
+tools:
+  - cnvkit:
+      description: |
+        CNVkit is a Python library and command-line software toolkit to infer and visualize copy number from high-throughput DNA sequencing data.
+        It is designed for use with hybrid capture, including both whole-exome and custom target panels, and short-read sequencing platforms such as Illumina and Ion Torrent.
+      homepage: https://cnvkit.readthedocs.io/en/stable/index.html
+      documentation: https://cnvkit.readthedocs.io/en/stable/index.html
+      tool_dev_url: https://github.com/etal/cnvkit
+      doi: 10.1371/journal.pcbi.1004873
+      licence: ["Apache-2.0"]
+
+input:
+  - fasta:
+      type: file
+      description: File containing reference genome
+      pattern: "*.{fasta}"
+  - targets:
+      type: file
+      description: File containing genomic regions
+      pattern: "*.{bed}"
+  - antitargets:
+      type: file
+      description: File containing off-target genomic regions
+      pattern: "*.{bed}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reference:
+      type: file
+      description: File containing a copy-number reference (required for CNV calling in tumor_only mode)
+      pattern: "*.{cnn}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@SusiJo"

modules/gamma/gamma/main.nf

@@ -1,6 +1,6 @@
 def VERSION = '2.1' // Version information not provided by tool on CLI
 
-process GAMMA {
+process GAMMA_GAMMA {
     tag "$meta.id"
     label 'process_low'
 
@@ -26,13 +26,24 @@ process GAMMA {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+
     """
-    GAMMA.py \\
+    if [[ ${fasta} == *.gz ]]
+    then
+        FNAME=\$(basename ${fasta} .gz)
+        gunzip -f ${fasta}
+        GAMMA.py \\
+        $args \\
+        "\${FNAME}" \\
+        $db \\
+        $prefix
+    else
+        GAMMA.py \\
         $args \\
         $fasta \\
         $db \\
         $prefix
-
+    fi
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
         gamma: $VERSION

modules/gamma/gamma/meta.yml

@@ -1,4 +1,4 @@
-name: "gamma"
+name: "gamma_gamma"
 description: Gene Allele Mutation Microbial Assessment
 keywords:
   - gamma
@@ -61,3 +61,4 @@ output:
 authors:
   - "@sateeshperi"
   - "@rastanton"
+  - "@jvhagey"

modules/gatk4/applybqsr/main.nf

@@ -2,10 +2,10 @@ process GATK4_APPLYBQSR {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(input), path(input_index), path(bqsr_table), path(intervals)

modules/gatk4/applybqsrspark/main.nf

@@ -2,10 +2,10 @@ process GATK4_APPLYBQSR_SPARK {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.3.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : 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' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(input), path(input_index), path(bqsr_table), path(intervals)

modules/gatk4/applyvqsr/main.nf

@@ -2,10 +2,10 @@ process GATK4_APPLYVQSR {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(vcf), path(vcf_tbi), path(recal), path(recal_index), path(tranches)

modules/gatk4/baserecalibrator/main.nf

@@ -2,10 +2,10 @@ process GATK4_BASERECALIBRATOR {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(input), path(input_index), path(intervals)

modules/gatk4/baserecalibratorspark/main.nf

@@ -2,10 +2,10 @@ process GATK4_BASERECALIBRATOR_SPARK {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.3.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : 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' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(input), path(input_index), path(intervals)

modules/gatk4/bedtointervallist/main.nf

@@ -2,10 +2,10 @@ process GATK4_BEDTOINTERVALLIST {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(bed)

modules/gatk4/calculatecontamination/main.nf

@@ -2,10 +2,10 @@ process GATK4_CALCULATECONTAMINATION {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(pileup), path(matched)

modules/gatk4/cnnscorevariants/main.nf

@@ -0,0 +1,58 @@
+process GATK4_CNNSCOREVARIANTS {
+    tag "$meta.id"
+    label 'process_low'
+
+    //Conda is not supported at the moment: https://github.com/broadinstitute/gatk/issues/7811
+    if (params.enable_conda) {
+        exit 1, "Conda environments cannot be used for GATK4/CNNScoreVariants at the moment. Please use docker or singularity containers."
+    }
+    container 'broadinstitute/gatk:4.2.6.1' //Biocontainers is missing a package
+
+    input:
+    tuple val(meta), path(vcf), path(tbi), path(aligned_input), path(intervals)
+    path fasta
+    path fai
+    path dict
+    path architecture
+    path weights
+
+    output:
+    tuple val(meta), path("*cnn.vcf.gz")    , emit: vcf
+    tuple val(meta), path("*cnn.vcf.gz.tbi"), emit: tbi
+    path "versions.yml"                     , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def aligned_input = aligned_input ? "--input $aligned_input" : ""
+    def interval_command = intervals ? "--intervals $intervals" : ""
+    def architecture = architecture ? "--architecture $architecture" : ""
+    def weights = weights ? "--weights $weights" : ""
+
+    def avail_mem = 3
+    if (!task.memory) {
+        log.info '[GATK CnnScoreVariants] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
+    } else {
+        avail_mem = task.memory.giga
+    }
+    """
+    gatk --java-options "-Xmx${avail_mem}g" CNNScoreVariants \\
+        --variant $vcf \\
+        --output ${prefix}.cnn.vcf.gz \\
+        --reference $fasta \\
+        $interval_command \\
+        $aligned_input \\
+        $architecture \\
+        $weights \\
+        --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/cnnscorevariants/meta.yml

@@ -0,0 +1,80 @@
+name: "gatk4_cnnscorevariants"
+description: Apply a Convolutional Neural Net to filter annotated variants
+keywords:
+  - gatk4_cnnscorevariants
+  - gatk4
+  - variants
+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 ]
+  - vcf:
+      type: file
+      description: VCF file
+      pattern: "*.vcf.gz"
+  - tbi:
+      type: file
+      description: VCF index file
+      pattern: "*.vcf.gz.tbi"
+  - aligned_input:
+      type: file
+      description: BAM/CRAM file from alignment (optional)
+      pattern: "*.{bam,cram}"
+  - 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"
+  - architecture:
+      type: file
+      description: Neural Net architecture configuration json file (optional)
+      pattern: "*.json"
+  - weights:
+      type: file
+      description: Keras model HD5 file with neural net weights. (optional)
+      pattern: "*.hd5"
+
+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"
+  - vcf:
+      type: file
+      description: Annotated VCF file
+      pattern: "*.vcf"
+  - tbi:
+      type: file
+      description: VCF index file
+      pattern: "*.vcf.gz.tbi"
+
+authors:
+  - "@FriederikeHanssen"

modules/gatk4/combinegvcfs/main.nf

@@ -2,10 +2,10 @@ process GATK4_COMBINEGVCFS {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(vcf), path(vcf_idx)

modules/gatk4/createsequencedictionary/main.nf

@@ -2,10 +2,10 @@ process GATK4_CREATESEQUENCEDICTIONARY {
     tag "$fasta"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     path fasta

modules/gatk4/createsomaticpanelofnormals/main.nf

@@ -2,10 +2,10 @@ process GATK4_CREATESOMATICPANELOFNORMALS {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(genomicsdb)

modules/gatk4/estimatelibrarycomplexity/main.nf

@@ -2,10 +2,10 @@ process GATK4_ESTIMATELIBRARYCOMPLEXITY {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(input)

modules/gatk4/fastqtosam/main.nf

@@ -2,10 +2,10 @@ process GATK4_FASTQTOSAM {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(reads)

modules/gatk4/filtermutectcalls/main.nf

@@ -2,10 +2,10 @@ process GATK4_FILTERMUTECTCALLS {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(vcf), path(vcf_tbi), path(stats), path(orientationbias), path(segmentation), path(table), val(estimate)

modules/gatk4/filtervarianttranches/main.nf

@@ -0,0 +1,51 @@
+process GATK4_FILTERVARIANTTRANCHES {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(vcf), path(tbi), path(intervals)
+    path resources
+    path resources_index
+    path fasta
+    path fai
+    path dict
+
+
+    output:
+    tuple val(meta), path("*.vcf.gz")    , emit: vcf
+    tuple val(meta), path("*.vcf.gz.tbi"), emit: tbi
+    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 resources = resources.collect{"--resource $it"}.join(' ')
+    def avail_mem = 3
+    if (!task.memory) {
+        log.info '[GATK FilterVariantTranches] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
+    } else {
+        avail_mem = task.memory.giga
+    }
+    """
+    gatk --java-options "-Xmx${avail_mem}g" FilterVariantTranches \\
+        --variant $vcf \\
+        $resources \\
+        --output ${prefix}.filtered.vcf.gz \\
+        --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/filtervarianttranches/meta.yml

@@ -0,0 +1,68 @@
+name: "gatk4_filtervarianttranches"
+description: Apply tranche filtering
+keywords:
+  - gatk4
+  - filtervarianttranches
+
+tools:
+  - "gatk4":
+      description: Genome Analysis Toolkit (GATK4)
+      homepage: https://gatk.broadinstitute.org/hc/en-us
+      documentation: https://gatk.broadinstitute.org/hc/en-us
+      tool_dev_url: https://github.com/broadinstitute/gatk
+      doi: "10.1158/1538-7445.AM2017-3590"
+      licence: ["BSD-3-clause"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - vcf:
+      type: file
+      description: a VCF file containing variants, must have info key:CNN_2D
+      pattern: "*.vcf.gz"
+  - tbi:
+      type: file
+      description: tbi file matching with -vcf
+      pattern: "*.vcf.gz.tbi"
+  - resources:
+      type: list
+      description: resource A VCF containing known SNP and or INDEL sites. Can be supplied as many times as necessary
+      pattern: "*.vcf.gz"
+  - resources_index:
+      type: list
+      description: Index of resource VCF containing known SNP and or INDEL sites. Can be supplied as many times as necessary
+      pattern: "*.vcf.gz"
+  - fasta:
+      type: file
+      description: The reference fasta file
+      pattern: "*.fasta"
+  - fai:
+      type: file
+      description: Index of reference fasta file
+      pattern: "fasta.fai"
+  - 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"
+  - vcf:
+      type: file
+      description: VCF file
+      pattern: "*.vcf.gz"
+  - tbi:
+      type: file
+      description: VCF index file
+      pattern: "*.vcf.gz.tbi"
+
+authors:
+  - "@FriederikeHanssen"

modules/gatk4/gatherbqsrreports/main.nf

@@ -2,10 +2,10 @@ process GATK4_GATHERBQSRREPORTS {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(table)

modules/gatk4/gatherpileupsummaries/main.nf

@@ -2,10 +2,10 @@ process GATK4_GATHERPILEUPSUMMARIES {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
 
     input:

modules/gatk4/genomicsdbimport/main.nf

@@ -2,10 +2,10 @@ process GATK4_GENOMICSDBIMPORT {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(vcf), path(tbi), path(interval_file), val(interval_value), path(wspace)

modules/gatk4/genotypegvcfs/main.nf

@@ -2,10 +2,10 @@ process GATK4_GENOTYPEGVCFS {
     tag "$meta.id"
     label 'process_high'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(gvcf), path(gvcf_index), path(intervals), path(intervals_index)

modules/gatk4/getpileupsummaries/main.nf

@@ -2,10 +2,10 @@ process GATK4_GETPILEUPSUMMARIES {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(input), path(index), path(intervals)
@@ -40,7 +40,7 @@ process GATK4_GETPILEUPSUMMARIES {
         --variant $variants \\
         --output ${prefix}.pileups.table \\
         $reference_command \\
-        $sites_command \\
+        $interval_command \\
         --tmp-dir . \\
         $args
 

modules/gatk4/haplotypecaller/main.nf

@@ -2,10 +2,10 @@ process GATK4_HAPLOTYPECALLER {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(input), path(input_index), path(intervals)

modules/gatk4/indexfeaturefile/main.nf

@@ -2,10 +2,10 @@ process GATK4_INDEXFEATUREFILE {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(feature_file)

modules/gatk4/intervallisttobed/main.nf

@@ -2,10 +2,10 @@ process GATK4_INTERVALLISTTOBED {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(intervals)

modules/gatk4/intervallisttools/main.nf

@@ -2,10 +2,10 @@ process GATK4_INTERVALLISTTOOLS {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(intervals)

modules/gatk4/learnreadorientationmodel/main.nf

@@ -2,10 +2,10 @@ process GATK4_LEARNREADORIENTATIONMODEL {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(f1r2)

modules/gatk4/markduplicates/main.nf

@@ -1,11 +1,11 @@
 process GATK4_MARKDUPLICATES {
     tag "$meta.id"
-    label 'process_low'
+    label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(bam)

modules/gatk4/mergebamalignment/main.nf

@@ -2,10 +2,10 @@ process GATK4_MERGEBAMALIGNMENT {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(aligned), path(unmapped)

modules/gatk4/mergemutectstats/main.nf

@@ -2,10 +2,10 @@ process GATK4_MERGEMUTECTSTATS {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(stats)

modules/gatk4/mergevcfs/main.nf

@@ -2,10 +2,10 @@ process GATK4_MERGEVCFS {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(vcf)

modules/gatk4/mutect2/main.nf

@@ -2,10 +2,10 @@ process GATK4_MUTECT2 {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(input), path(input_index), path(intervals)

modules/gatk4/revertsam/main.nf

@@ -2,10 +2,10 @@ process GATK4_REVERTSAM {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(bam)

modules/gatk4/samtofastq/main.nf

@@ -2,10 +2,10 @@ process GATK4_SAMTOFASTQ {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(bam)

modules/gatk4/selectvariants/main.nf

@@ -2,10 +2,10 @@ process GATK4_SELECTVARIANTS {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(vcf), path(vcf_idx)

modules/gatk4/splitintervals/main.nf

@@ -0,0 +1,48 @@
+process GATK4_SPLITINTERVALS {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(intervals)
+    path(fasta)
+    path(fasta_fai)
+    path(dict)
+
+    output:
+    tuple val(meta), path("**.interval_list"), emit: split_intervals
+    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 reference = fasta ? "--reference $fasta" : ""
+
+    def avail_mem = 3
+    if (!task.memory) {
+        log.info '[GATK SplitIntervals] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
+    } else {
+        avail_mem = task.memory.giga
+    }
+
+    """
+    gatk --java-options "-Xmx${avail_mem}g" SplitIntervals \\
+        --output ${prefix} \\
+        --intervals $intervals \\
+        $reference \\
+        --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/splitintervals/meta.yml

@@ -0,0 +1,53 @@
+name: gatk4_splitintervals
+keywords:
+  - interval
+  - bed
+tools:
+  - gatk4:
+      description: Genome Analysis Toolkit (GATK4)
+      homepage: https://gatk.broadinstitute.org/hc/en-us
+      documentation: https://gatk.broadinstitute.org/hc/en-us/categories/360002369672s
+      tool_dev_url: https://github.com/broadinstitute/gatk
+      doi: "10.1158/1538-7445.AM2017-3590"
+      licence: ["BSD-3-clause"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - interval:
+      type: file
+      description: Interval list or BED
+      pattern: "*.{interval,interval_list,bed}"
+  - fasta:
+      type: file
+      description: Reference FASTA
+      pattern: "*.{fa,fasta}"
+  - fasta_fai:
+      type: file
+      description: Reference FASTA index
+      pattern: "*.fai"
+  - dict:
+      type: file
+      description: Reference sequence dictionary
+      pattern: "*.dict"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - bed:
+      type: file
+      description: A list of scattered interval lists
+      pattern: "*.interval_list"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@nvnieuwk"

modules/gatk4/splitncigarreads/main.nf

@@ -2,10 +2,10 @@ process GATK4_SPLITNCIGARREADS {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(bam), path(bai), path(intervals)

modules/gatk4/variantfiltration/main.nf

@@ -2,10 +2,10 @@ process GATK4_VARIANTFILTRATION {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(vcf), path(tbi)

modules/gatk4/variantrecalibrator/main.nf

@@ -2,10 +2,10 @@ process GATK4_VARIANTRECALIBRATOR {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.5.0--hdfd78af_0' :
-        'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(vcf), path(tbi)

modules/genomescope2/main.nf

@@ -0,0 +1,40 @@
+process GENOMESCOPE2 {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::genomescope2=2.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/genomescope2:2.0--py310r41hdfd78af_5':
+        'quay.io/biocontainers/genomescope2:2.0--py310r41hdfd78af_5' }"
+
+    input:
+    tuple val(meta), path(histogram)
+
+    output:
+    tuple val(meta), path("*_linear_plot.png")            , emit: linear_plot_png
+    tuple val(meta), path("*_transformed_linear_plot.png"), emit: transformed_linear_plot_png
+    tuple val(meta), path("*_log_plot.png")               , emit: log_plot_png
+    tuple val(meta), path("*_transformed_log_plot.png")   , emit: transformed_log_plot_png
+    tuple val(meta), path("*_model.txt")                  , emit: model
+    tuple val(meta), path("*_summary.txt")                , emit: summary
+    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}"
+    """
+    genomescope2 \\
+        --input $histogram \\
+        $args \\
+        --output . \\
+        --name_prefix $prefix
+
+    cat <<-END_VERSIONS > versions.yml
+    '${task.process}':
+        genomescope2: \$( genomescope2 -v | sed 's/GenomeScope //' )
+    END_VERSIONS
+    """
+}

modules/genomescope2/meta.yml

@@ -0,0 +1,67 @@
+name: "genomescope2"
+description: Estimate genome heterozygosity, repeat content, and size from sequencing reads using a kmer-based statistical approach
+keywords:
+  - "genome size"
+  - "genome heterozygosity"
+  - "repeat content"
+tools:
+  - "genomescope2":
+      description: "Reference-free profiling of polyploid genomes"
+      homepage: "http://qb.cshl.edu/genomescope/genomescope2.0/"
+      documentation: "https://github.com/tbenavi1/genomescope2.0/blob/master/README.md"
+      tool_dev_url: "https://github.com/tbenavi1/genomescope2.0"
+      doi: "https://doi.org/10.1038/s41467-020-14998-3"
+      licence: "['Apache License, Version 2.0 (Apache-2.0)']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - histogram:
+      type: file
+      description: A K-mer histogram file
+      pattern: "*.hist"
+
+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"
+  - linear_plot_png:
+      type: file
+      description: A genomescope2 linear plot in PNG format
+      pattern: "*_linear_plot.png"
+  - linear_plot_png:
+      type: file
+      description: A genomescope2 linear plot in PNG format
+      pattern: "*_linear_plot.png"
+  - transformed_linear_plot_png:
+      type: file
+      description: A genomescope2 transformed linear plot in PNG format
+      pattern: "*_transformed_linear_plot.png"
+  - log_plot_png:
+      type: file
+      description: A genomescope2 log plot in PNG format
+      pattern: "*_log_plot.png"
+  - transformed_log_plot_png:
+      type: file
+      description: A genomescope2 transformed log plot in PNG format
+      pattern: "*_transformed_log_plot.png"
+  - model:
+      type: file
+      description: Genomescope2 model fit summary
+      pattern: "*_model.txt"
+  - summary:
+      type: file
+      description: Genomescope2 histogram summary
+      pattern: "*_summary.txt"
+
+authors:
+  - "@mahesh-panchal"

modules/hmtnote/main.nf

@@ -0,0 +1,45 @@
+process HMTNOTE {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::hmtnote=0.7.2" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/hmtnote:0.7.2--pyhdfd78af_0':
+        'quay.io/biocontainers/hmtnote:0.7.2--pyhdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(vcf)
+
+    output:
+    tuple val(meta), path("*_annotated.vcf"), emit: vcf
+    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}"
+
+    """
+    hmtnote \\
+        annotate \\
+        $vcf \\
+        ${prefix}_annotated.vcf \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        hmtnote: \$(echo \$(hmtnote --version 2>&1) | sed 's/^.*hmtnote, version //; s/Using.*\$//' ))
+    END_VERSIONS
+    """
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}_annotated.vcf
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        hmtnote: \$(echo \$(hmtnote --version 2>&1) | sed 's/^.*hmtnote, version //; s/Using.*\$//' ))
+    END_VERSIONS
+    """
+}

modules/hmtnote/meta.yml

@@ -0,0 +1,39 @@
+name: hmtnote
+description: Human mitochondrial variants annotation using HmtVar.
+keywords:
+  - hmtnote mitochondria annotation
+tools:
+  - hmtnote:
+      description: Human mitochondrial variants annotation using HmtVar.
+      homepage: https://github.com/robertopreste/HmtNote
+      documentation: https://hmtnote.readthedocs.io/en/latest/usage.html
+      tool_dev_url: None
+      doi: "https://doi.org/10.1101/600619"
+      licence: ["MIT"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+  - vcf:
+      type: file
+      description: vcf file
+      pattern: "*.vcf"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - vcf:
+      type: file
+      description: annotated vcf
+      pattern: "*_annotated.vcf"
+
+authors:
+  - "@sysbiocoder"

modules/kat/hist/main.nf

@@ -0,0 +1,42 @@
+process KAT_HIST {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::kat=2.4.2" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/kat:2.4.2--py38hfc5f9d8_2':
+        'quay.io/biocontainers/kat:2.4.2--py38hfc5f9d8_2' }"
+
+    input:
+    tuple val(meta), path(reads)
+
+    output:
+    tuple val(meta), path("*.hist")                   , emit: hist
+    tuple val(meta), path("*.hist.dist_analysis.json"), emit: json
+    tuple val(meta), path("*.png")                    , emit: png           , optional: true
+    tuple val(meta), path("*.ps")                     , emit: ps            , optional: true
+    tuple val(meta), path("*.pdf")                    , emit: pdf           , optional: true
+    tuple val(meta), path("*-hash.jf*")               , emit: jellyfish_hash, 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}"
+    """
+    kat hist \\
+        --threads $task.cpus \\
+        --output_prefix ${prefix}.hist \\
+        $args \\
+        $reads
+
+    ls -l
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        kat: \$( kat hist --version | sed 's/kat //' )
+    END_VERSIONS
+    """
+}

modules/kat/hist/meta.yml

@@ -0,0 +1,64 @@
+name: "kat_hist"
+description: Creates a histogram of the number of distinct k-mers having a given frequency.
+keywords:
+  - k-mer
+  - histogram
+  - count
+tools:
+  - "kat":
+      description: "KAT is a suite of tools that analyse jellyfish hashes or sequence files (fasta or fastq) using kmer counts"
+      homepage: https://www.earlham.ac.uk/kat-tools
+      documentation: https://kat.readthedocs.io/en/latest/index.html
+      tool_dev_url: https://github.com/TGAC/KAT
+      doi: http://bioinformatics.oxfordjournals.org/content/early/2016/10/20/bioinformatics.btw663.abstract
+      licence: "['GPL v3']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: |
+        List of input FastQ files of size 1 and 2 for single-end and paired-end data,
+        respectively.
+
+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"
+  - hist:
+      type: file
+      description: KAT histogram of k-mer counts
+      pattern: "*.hist"
+  - json:
+      type: file
+      description: KAT histogram summary of distance analysis
+      pattern: "*.hist.dist_analysis.json"
+  - png:
+      type: file
+      description: KAT plot of k-mer histogram in PNG format
+      pattern: "*.png"
+  - ps:
+      type: file
+      description: KAT plot of k-mer histogram in PS format
+      pattern: "*.ps"
+  - pdf:
+      type: file
+      description: KAT plot of k-mer histogram in PDF format
+      pattern: "*.pdf"
+  - jellyfish_hash:
+      type: file
+      description: Jellyfish hash file
+      pattern: "*-hist.jf*"
+
+authors:
+  - "@mahesh-panchal"

modules/mash/screen/main.nf

@@ -0,0 +1,38 @@
+process MASH_SCREEN {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::mash=2.3" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/mash:2.3--he348c14_1':
+        'quay.io/biocontainers/mash:2.3--he348c14_1' }"
+
+    input:
+    tuple val(meta), path(query)
+    path sequences_sketch
+
+    output:
+    tuple val(meta), path("*.screen"), emit: screen
+    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}"
+    """
+    mash \\
+        screen \\
+        $args \\
+        -p $task.cpus \\
+        $sequences_sketch \\
+        $query \\
+        > ${prefix}.screen
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        mash: \$( mash --version )
+    END_VERSIONS
+    """
+}

modules/mash/screen/meta.yml

@@ -0,0 +1,48 @@
+name: "mash_screen"
+description: Screens query sequences against large sequence databases
+keywords:
+  - screen
+  - containment
+  - contamination
+  - taxonomic assignment
+tools:
+  - "mash":
+      description: Fast sequence distance estimator that uses MinHash
+      homepage: https://github.com/marbl/Mash
+      documentation: https://mash.readthedocs.io/en/latest/sketches.html
+      tool_dev_url: https://github.com/marbl/Mash
+      doi: "10.1186/s13059-016-0997-x"
+      licence: ["https://github.com/marbl/Mash/blob/master/LICENSE.txt"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - query:
+      type: file
+      description: Query sequences
+      pattern: "*.fastq.gz"
+  - sequence_sketch:
+      type: file
+      description: Sequence files to match against
+      pattern: "*.msh"
+
+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"
+  - screen:
+      type: file
+      description: List of sequences from fastx_db similar to query sequences
+      pattern: "*.screen"
+
+authors:
+  - "@mahesh-panchal"

modules/maxquant/lfq/main.nf

@@ -0,0 +1,37 @@
+process MAXQUANT_LFQ {
+    tag "$meta.id"
+    label 'process_long'
+    conda (params.enable_conda ? "bioconda::maxquant=2.0.3.0=py310hdfd78af_1" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/maxquant:2.0.3.0--py310hdfd78af_1"
+    } else {
+        container "quay.io/biocontainers/maxquant:2.0.3.0--py310hdfd78af_1"
+    }
+
+    input:
+    tuple val(meta), path(fasta), path(paramfile)
+    path raw
+
+    output:
+    tuple val(meta), path("*.txt"), emit: maxquant_txt
+    path "versions.yml"          , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            maxquant: \$(maxquant --version 2>&1 > /dev/null | cut -f2 -d\" \")
+    END_VERSIONS
+    sed \"s_<numThreads>.*_<numThreads>$task.cpus</numThreads>_\" ${paramfile} > mqpar_changed.xml
+    sed -i \"s|PLACEHOLDER|\$PWD/|g\" mqpar_changed.xml
+    mkdir temp
+    maxquant mqpar_changed.xml
+    mv combined/txt/*.txt .
+    """
+}

modules/maxquant/lfq/meta.yml

@@ -0,0 +1,52 @@
+name: maxquant_lfq
+description: Run standard proteomics data analysis with MaxQuant, mostly dedicated to label-free. Paths to fasta and raw files needs to be marked by "PLACEHOLDER"
+keywords:
+  - sort
+tools:
+  - maxquant:
+      description: MaxQuant is a quantitative proteomics software package designed for analyzing large mass-spectrometric data sets. License restricted.
+      homepage: None
+      documentation: None
+      tool_dev_url: None
+      doi: ""
+      licence: ["http://www.coxdocs.org/lib/exe/fetch.php?media=license_agreement.pdf"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+
+  - raw:
+      type: file
+      description: raw files with mass spectra
+      pattern: "*.{raw,RAW,Raw}"
+
+  - fasta:
+      type: file
+      description: fasta file with protein sequences
+      pattern: "*.{fasta}"
+
+  - parfile:
+      type: file
+      description: MaxQuant parameter file (XML)
+      pattern: "*.{xml}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software version
+      pattern: "versions.yml"
+  - maxquant_txt:
+      type: file
+      description: tables with peptides and protein information
+      pattern: "*.{txt}"
+
+authors:
+  - "@veitveit"

modules/mosdepth/main.nf

@@ -10,18 +10,22 @@ process MOSDEPTH {
     input:
     tuple val(meta), path(bam), path(bai)
     path  bed
-    val   window_size
+    path  fasta
 
     output:
-    tuple val(meta), path('*.global.dist.txt')    , emit: global_txt
-    tuple val(meta), path('*.region.dist.txt')    , emit: regions_txt , optional:true
-    tuple val(meta), path('*.summary.txt')        , emit: summary_txt
-    tuple val(meta), path('*.per-base.d4')        , emit: d4          , optional:true
-    tuple val(meta), path('*.per-base.bed.gz')    , emit: per_base_bed, optional:true
-    tuple val(meta), path('*.per-base.bed.gz.csi'), emit: per_base_csi, optional:true
-    tuple val(meta), path('*.regions.bed.gz')     , emit: regions_bed , optional:true
-    tuple val(meta), path('*.regions.bed.gz.csi') , emit: regions_csi , optional:true
-    path  "versions.yml"                          , emit: versions
+    tuple val(meta), path('*.global.dist.txt')      , emit: global_txt
+    tuple val(meta), path('*.summary.txt')          , emit: summary_txt
+    tuple val(meta), path('*.region.dist.txt')      , optional:true, emit: regions_txt
+    tuple val(meta), path('*.per-base.d4')          , optional:true, emit: per_base_d4
+    tuple val(meta), path('*.per-base.bed.gz')      , optional:true, emit: per_base_bed
+    tuple val(meta), path('*.per-base.bed.gz.csi')  , optional:true, emit: per_base_csi
+    tuple val(meta), path('*.regions.bed.gz')       , optional:true, emit: regions_bed
+    tuple val(meta), path('*.regions.bed.gz.csi')   , optional:true, emit: regions_csi
+    tuple val(meta), path('*.quantized.bed.gz')     , optional:true, emit: quantized_bed
+    tuple val(meta), path('*.quantized.bed.gz.csi') , optional:true, emit: quantized_csi
+    tuple val(meta), path('*.thresholds.bed.gz')    , optional:true, emit: thresholds_bed
+    tuple val(meta), path('*.thresholds.bed.gz.csi'), optional:true, emit: thresholds_csi
+    path  "versions.yml"                            , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
@@ -29,19 +33,24 @@ process MOSDEPTH {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    if (window_size) {
-        interval = "--by ${window_size}"
-    } else if ( bed ) {
-        interval = "--by ${bed}"
-    } else {
-        interval = ""
+    def reference = fasta ? "--fasta ${fasta}" : ""
+    def interval = bed ? "--by ${bed}" : ""
+    if (bed && args.contains("--by")) {
+        exit 1, "'--by' can only be specified once when running mosdepth! Either remove input BED file definition or remove '--by' from 'ext.args' definition"
     }
+    if (!bed && args.contains("--thresholds")) {
+        exit 1, "'--thresholds' can only be specified in conjunction with '--by'"
+    }
+
     """
     mosdepth \\
+        --threads $task.cpus \\
         $interval \\
+        $reference \\
         $args \\
         $prefix \\
         $bam
+
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
         mosdepth: \$(mosdepth --version 2>&1 | sed 's/^.*mosdepth //; s/ .*\$//')
@@ -59,6 +68,10 @@ process MOSDEPTH {
     touch ${prefix}.per-base.bed.gz.csi
     touch ${prefix}.regions.bed.gz
     touch ${prefix}.regions.bed.gz.csi
+    touch ${prefix}.quantized.bed.gz
+    touch ${prefix}.quantized.bed.gz.csi
+    touch ${prefix}.thresholds.bed.gz
+    touch ${prefix}.thresholds.bed.gz.csi
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/mosdepth/meta.yml

@@ -30,10 +30,10 @@ input:
       type: file
       description: BED file with intersected intervals
       pattern: "*.{bed}"
-  - window_size:
-      type: integer
-      description: Window size
-      pattern: "[0-9]+"
+  - fasta:
+      type: file
+      description: Reference genome FASTA file
+      pattern: "*.{fa,fasta}"
 output:
   - meta:
       type: map
@@ -60,6 +60,10 @@ output:
       type: file
       description: Index file for BED file with per-base coverage
       pattern: "*.{per-base.bed.gz.csi}"
+  - per_base_d4:
+      type: file
+      description: D4 file with per-base coverage
+      pattern: "*.{per-base.d4}"
   - regions_bed:
       type: file
       description: BED file with per-region coverage
@@ -68,6 +72,22 @@ output:
       type: file
       description: Index file for BED file with per-region coverage
       pattern: "*.{regions.bed.gz.csi}"
+  - quantized_bed:
+      type: file
+      description: BED file with binned coverage
+      pattern: "*.{quantized.bed.gz}"
+  - quantized_csi:
+      type: file
+      description: Index file for BED file with binned coverage
+      pattern: "*.{quantized.bed.gz.csi}"
+  - thresholds_bed:
+      type: file
+      description: BED file with the number of bases in each region that are covered at or above each threshold
+      pattern: "*.{thresholds.bed.gz}"
+  - thresholds_csi:
+      type: file
+      description: Index file for BED file with threshold coverage
+      pattern: "*.{thresholds.bed.gz.csi}"
   - versions:
       type: file
       description: File containing software versions
@@ -76,3 +96,4 @@ authors:
   - "@joseespinosa"
   - "@drpatelh"
   - "@ramprasadn"
+  - "@matthdsm"

modules/motus/profile/main.nf

@@ -0,0 +1,54 @@
+process MOTUS_PROFILE {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::motus=3.0.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/motus:3.0.1--pyhdfd78af_0':
+        'quay.io/biocontainers/motus:3.0.1--pyhdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(reads)
+    path db
+
+    output:
+    tuple val(meta), path("*.out"), emit: out
+    tuple val(meta), path("*.bam"), optional: true, emit: bam
+    tuple val(meta), path("*.mgc"), optional: true, emit: mgc
+    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 inputs = reads[0].getExtension() == 'bam' ?
+                    "-i ${reads}" :
+                    reads[0].getExtension() == 'mgc' ? "-m $reads" :
+                        meta.single_end ?
+                            "-s $reads" : "-f ${reads[0]} -r ${reads[1]}"
+    def refdb = db ? "-db ${db}" : ""
+    """
+    motus profile \\
+        $args \\
+        $inputs \\
+        $refdb \\
+        -t $task.cpus \\
+        -n $prefix \\
+        -o ${prefix}.out
+
+    ## mOTUs version number is not available from command line.
+    ## mOTUs save the version number in index database folder.
+    ## mOTUs will check the database version is same version as exec version.
+    if [ "$db" == "" ]; then
+        VERSION=\$(echo \$(motus -h 2>&1) | sed 's/^.*Version: //; s/References.*\$//')
+    else
+        VERSION=\$(grep motus $db/db_mOTU_versions | sed 's/motus\\t//g')
+    fi
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        mOTUs: \$VERSION
+    END_VERSIONS
+    """
+}

modules/motus/profile/meta.yml

@@ -0,0 +1,61 @@
+name: "motus_profile"
+description: Taxonomic meta-omics profiling using universal marker genes
+keywords:
+  - classify
+  - metagenomics
+  - fastq
+  - taxonomic profiling
+tools:
+  - "motus":
+      description: "Marker gene-based OTU (mOTU) profiling"
+      homepage: "https://motu-tool.org/"
+      documentation: "https://github.com/motu-tool/mOTUs/wiki"
+      tool_dev_url: "https://github.com/motu-tool/mOTUs"
+      doi: "10.1038/s41467-019-08844-4"
+      licence: "['GPL v3']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: |
+        List of input fastq/fasta files of size 1 and 2 for single-end and paired-end data,
+        respectively.
+        Or the intermediate bam file mapped by bwa to the mOTUs database or
+        the output bam file from motus profile.
+        Or the intermediate mgc read counts table.
+      pattern: "*.{fastq,fq,fasta,fa,fastq.gz,fq.gz,fasta.gz,fa.gz,.bam,.mgc}"
+  - db:
+      type: directory
+      description: |
+        mOTUs database downloaded by `motus downloadDB`
+
+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"
+  - out:
+      type: file
+      description: Results with taxonomic classification of each read
+      pattern: "*.out"
+  - bam:
+      type: file
+      description: Optional intermediate sorted BAM file from BWA
+      pattern: "*.{bam}"
+  - mgc:
+      type: file
+      description: Optional intermediate mgc read count table file saved with `-M`.
+      pattern: "*.{mgc}"
+
+authors:
+  - "@jianhong"

modules/picard/collecthsmetrics/main.nf

@@ -24,7 +24,7 @@ process PICARD_COLLECTHSMETRICS {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def reference = fasta ? "-R $fasta" : ""
+    def reference = fasta ? "--REFERENCE_SEQUENCE ${fasta}" : ""
 
     def avail_mem = 3
     if (!task.memory) {

modules/picard/collectmultiplemetrics/main.nf

@@ -22,6 +22,7 @@ process PICARD_COLLECTMULTIPLEMETRICS {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+    def reference = fasta ? "--REFERENCE_SEQUENCE ${fasta}" : ""
     def avail_mem = 3
     if (!task.memory) {
         log.info '[Picard CollectMultipleMetrics] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@@ -35,7 +36,7 @@ process PICARD_COLLECTMULTIPLEMETRICS {
         $args \\
         --INPUT $bam \\
         --OUTPUT ${prefix}.CollectMultipleMetrics \\
-        --REFERENCE_SEQUENCE $fasta
+        $reference
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/picard/collectwgsmetrics/main.nf

@@ -34,7 +34,7 @@ process PICARD_COLLECTWGSMETRICS {
         $args \\
         --INPUT $bam \\
         --OUTPUT ${prefix}.CollectWgsMetrics.coverage_metrics \\
-        --REFERENCE_SEQUENCE $fasta
+        --REFERENCE_SEQUENCE ${fasta}
 
 
     cat <<-END_VERSIONS > versions.yml

modules/rtgtools/vcfeval/main.nf

@@ -35,12 +35,13 @@ process RTGTOOLS_VCFEVAL {
     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"
+    def avail_mem = task.memory.toGiga() + "G"
 
     """
     $truth_index
     $query_index
 
-    rtg vcfeval \\
+    rtg RTG_MEM=$avail_mem vcfeval \\
         $args \\
         --baseline=$truth_vcf \\
         $bed_regions \\

modules/umitools/dedup/main.nf

@@ -9,12 +9,13 @@ process UMITOOLS_DEDUP {
 
     input:
     tuple val(meta), path(bam), path(bai)
+    val get_output_stats
 
     output:
     tuple val(meta), path("*.bam")             , emit: bam
-    tuple val(meta), path("*edit_distance.tsv"), emit: tsv_edit_distance
-    tuple val(meta), path("*per_umi.tsv")      , emit: tsv_per_umi
-    tuple val(meta), path("*per_position.tsv") , emit: tsv_umi_per_position
+    tuple val(meta), path("*edit_distance.tsv"), optional:true, emit: tsv_edit_distance
+    tuple val(meta), path("*per_umi.tsv")      , optional:true, emit: tsv_per_umi
+    tuple val(meta), path("*per_position.tsv") , optional:true, emit: tsv_umi_per_position
     path  "versions.yml"                       , emit: versions
 
     when:
@@ -24,12 +25,13 @@ process UMITOOLS_DEDUP {
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
     def paired = meta.single_end ? "" : "--paired"
+    def stats = get_output_stats ? "--output-stats $prefix" : ""
     """
     umi_tools \\
         dedup \\
         -I $bam \\
         -S ${prefix}.bam \\
-        --output-stats $prefix \\
+        $stats \\
         $paired \\
         $args
 

modules/umitools/dedup/meta.yml

@@ -26,6 +26,10 @@ input:
     description: |
       BAM index files corresponding to the input BAM file.
     pattern: "*.{bai}"
+  - get_output_stats:
+    type: boolean
+    description: |
+      Whether or not to generate output stats.
 output:
   - meta:
     type: map

tests/config/nextflow.config

@@ -19,6 +19,7 @@ if ("$PROFILE" == "singularity") {
 } else {
     docker.enabled = true
     docker.userEmulation = true
+    docker.runOptions = "--platform linux/x86_64"
 }
 
 // Increase time available to build Conda environment

tests/config/pytest_modules.yml

@@ -42,6 +42,10 @@ amrfinderplus/update:
   - modules/amrfinderplus/update/**
   - tests/modules/amrfinderplus/update/**
 
+antismash/antismashlite:
+  - modules/antismash/antismashlite/**
+  - tests/modules/antismash/antismashlite/**
+
 antismash/antismashlitedownloaddatabases:
   - modules/antismash/antismashlitedownloaddatabases/**
   - tests/modules/antismash/antismashlitedownloaddatabases/**
@@ -162,6 +166,10 @@ bcftools/reheader:
   - modules/bcftools/reheader/**
   - tests/modules/bcftools/reheader/**
 
+bcftools/roh:
+  - modules/bcftools/roh/**
+  - tests/modules/bcftools/roh/**
+
 bcftools/sort:
   - modules/bcftools/sort/**
   - tests/modules/bcftools/sort/**
@@ -218,6 +226,10 @@ bedtools/sort:
   - modules/bedtools/sort/**
   - tests/modules/bedtools/sort/**
 
+bedtools/split:
+  - modules/bedtools/split/**
+  - tests/modules/bedtools/split/**
+
 bedtools/subtract:
   - modules/bedtools/subtract/**
   - tests/modules/bedtools/subtract/**
@@ -226,6 +238,10 @@ biobambam/bammarkduplicates2:
   - modules/biobambam/bammarkduplicates2/**
   - tests/modules/biobambam/bammarkduplicates2/**
 
+biobambam/bammerge:
+  - modules/biobambam/bammerge/**
+  - tests/modules/biobambam/bammerge/**
+
 biobambam/bamsormadup:
   - modules/biobambam/bamsormadup/**
   - tests/modules/biobambam/bamsormadup/**
@@ -435,10 +451,18 @@ cmseq/polymut:
   - modules/cmseq/polymut/**
   - tests/modules/cmseq/polymut/**
 
+cnvkit/antitarget:
+  - modules/cnvkit/antitarget/**
+  - tests/modules/cnvkit/antitarget/**
+
 cnvkit/batch:
   - modules/cnvkit/batch/**
   - tests/modules/cnvkit/batch/**
 
+cnvkit/reference:
+  - modules/cnvkit/reference/**
+  - tests/modules/cnvkit/reference/**
+
 controlfreec/assesssignificance:
   - modules/controlfreec/assesssignificance/**
   - tests/modules/controlfreec/assesssignificance/**
@@ -687,9 +711,9 @@ freebayes:
   - modules/freebayes/**
   - tests/modules/freebayes/**
 
-gamma:
-  - modules/gamma/**
-  - tests/modules/gamma/**
+gamma/gamma:
+  - modules/gamma/gamma/**
+  - tests/modules/gamma/gamma/**
 
 gatk4/applybqsr:
   - modules/gatk4/applybqsr/**
@@ -719,6 +743,10 @@ gatk4/calculatecontamination:
   - modules/gatk4/calculatecontamination/**
   - tests/modules/gatk4/calculatecontamination/**
 
+gatk4/cnnscorevariants:
+  - modules/gatk4/cnnscorevariants/**
+  - tests/modules/gatk4/cnnscorevariants/**
+
 gatk4/combinegvcfs:
   - modules/gatk4/combinegvcfs/**
   - tests/modules/gatk4/combinegvcfs/**
@@ -743,6 +771,10 @@ gatk4/filtermutectcalls:
   - modules/gatk4/filtermutectcalls/**
   - tests/modules/gatk4/filtermutectcalls/**
 
+gatk4/filtervarianttranches:
+  - modules/gatk4/filtervarianttranches/**
+  - tests/modules/gatk4/filtervarianttranches/**
+
 gatk4/gatherbqsrreports:
   - modules/gatk4/gatherbqsrreports/**
   - tests/modules/gatk4/gatherbqsrreports/**
@@ -819,6 +851,10 @@ gatk4/selectvariants:
   - modules/gatk4/selectvariants/**
   - tests/modules/gatk4/selectvariants/**
 
+gatk4/splitintervals:
+  - modules/gatk4/splitintervals/**
+  - tests/modules/gatk4/splitintervals/**
+
 gatk4/splitncigarreads:
   - modules/gatk4/splitncigarreads/**
   - tests/modules/gatk4/splitncigarreads/**
@@ -839,6 +875,10 @@ genmap/mappability:
   - modules/genmap/mappability/**
   - tests/modules/genmap/mappability/**
 
+genomescope2:
+  - modules/genomescope2/**
+  - tests/modules/genomescope2/**
+
 genrich:
   - modules/genrich/**
   - tests/modules/genrich/**
@@ -954,6 +994,10 @@ hmmer/hmmsearch:
   - modules/hmmer/hmmsearch/**
   - tests/modules/hmmer/hmmsearch/**
 
+hmtnote:
+  - modules/hmtnote/**
+  - tests/modules/hmtnote/**
+
 homer/annotatepeaks:
   - modules/homer/annotatepeaks/**
   - tests/modules/homer/annotatepeaks/**
@@ -1049,6 +1093,10 @@ kallistobustools/ref:
   - modules/kallistobustools/ref/**
   - tests/modules/kallistobustools/ref/**
 
+kat/hist:
+  - modules/kat/hist/**
+  - tests/modules/kat/hist/**
+
 khmer/normalizebymedian:
   - modules/khmer/normalizebymedian/**
   - tests/modules/khmer/normalizebymedian/**
@@ -1186,6 +1234,10 @@ mash/dist:
   - modules/mash/dist/**
   - tests/modules/mash/dist/**
 
+mash/screen:
+  - modules/mash/screen/**
+  - tests/modules/mash/screen/**
+
 mash/sketch:
   - modules/mash/sketch/**
   - tests/modules/mash/sketch/**
@@ -1198,6 +1250,10 @@ maxbin2:
   - modules/maxbin2/**
   - tests/modules/maxbin2/**
 
+maxquant/lfq:
+  - modules/maxquant/lfq/**
+  - tests/modules/maxquant/lfq/**
+
 md5sum:
   - modules/md5sum/**
   - tests/modules/md5sum/**
@@ -1282,6 +1338,10 @@ motus/downloaddb:
   - modules/motus/downloaddb/**
   - tests/modules/motus/downloaddb/**
 
+motus/profile:
+  - modules/motus/profile/**
+  - tests/modules/motus/profile/**
+
 msisensor/msi:
   - modules/msisensor/msi/**
   - tests/modules/msisensor/msi/**

tests/config/test_data.config

@@ -142,6 +142,7 @@ params {
                 genome_21_sizes                                = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.sizes"
                 genome_21_interval_list                        = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.interval_list"
                 genome_21_multi_interval_bed                   = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/multi_intervals.bed"
+                genome_21_multi_interval_antitarget_bed        = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/multi_intervals.antitarget.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"
                 genome_21_chromosomes_dir                      = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/chromosomes.tar.gz"
@@ -266,6 +267,8 @@ 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"
+                test_haplotc_cnn_vcf_gz                        = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test_haplotcaller.cnn.vcf.gz"
+                test_haplotc_cnn_vcf_gz_tbi                    = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test_haplotcaller.cnn.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"
@@ -430,5 +433,17 @@ params {
                 ncbi_user_settings              = "${test_data_dir}/generic/config/ncbi_user_settings.mkfg"
             }
         }
+	'proteomics' {
+	    'msspectra' {
+	        ups_file1                       = "${test_data_dir}/proteomics/msspectra/OVEMB150205_12.raw"
+	        ups_file2                       = "${test_data_dir}/proteomics/msspectra/OVEMB150205_14.raw"
+	    }
+	    'database' {
+            yeast_ups                       = "${test_data_dir}/proteomics/database/yeast_UPS.fasta"
+        }
+	    'parameter' {
+	        maxquant                        = "${test_data_dir}/proteomics/parameter/mqpar.xml"
+	    }
+	}
     }
 }

tests/modules/antismash/antismashlite/main.nf

@@ -0,0 +1,46 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { ANTISMASH_ANTISMASHLITE                  } from '../../../../modules/antismash/antismashlite/main.nf'
+include { ANTISMASH_ANTISMASHLITEDOWNLOADDATABASES } from '../../../modules/antismash/antismashlitedownloaddatabases/main.nf'
+include { GUNZIP as GUNZIP1 } from '../../../../modules/gunzip/main.nf'
+include { GUNZIP as GUNZIP2 } from '../../../../modules/gunzip/main.nf'
+include { UNTAR as UNTAR1 } from '../../../../modules/untar/main.nf'
+include { UNTAR as UNTAR2 } from '../../../../modules/untar/main.nf'
+include { UNTAR as UNTAR3 } from '../../../../modules/untar/main.nf'
+
+workflow test_antismashlite {
+    genome_fna = [
+        [ id:'test' ],
+        file(params.test_data['bacteroides_fragilis']['genome']['genome_fna_gz'], checkIfExists: true)
+    ]
+
+    genome_gff = [
+        [],
+        file(params.test_data['bacteroides_fragilis']['genome']['genome_gff_gz'], checkIfExists: true)
+    ]
+
+    antismash_css = [
+        [],
+        file('https://github.com/nf-core/test-datasets/raw/modules/data/delete_me/antismash/css.tar.gz', checkIfExists: true)
+    ]
+
+    antismash_detection = [
+        [],
+        file('https://github.com/nf-core/test-datasets/raw/modules/data/delete_me/antismash/detection.tar.gz', checkIfExists: true)
+    ]
+
+    antismash_modules = [
+        [],
+        file('https://github.com/nf-core/test-datasets/raw/modules/data/delete_me/antismash/modules.tar.gz', checkIfExists: true)
+    ]
+
+    GUNZIP1 ( genome_fna )
+    GUNZIP2 ( genome_gff )
+    UNTAR1 ( antismash_css )
+    UNTAR2 ( antismash_detection )
+    UNTAR3 ( antismash_modules )
+    ANTISMASH_ANTISMASHLITEDOWNLOADDATABASES ( UNTAR1.out.untar.map{ it[1] },  UNTAR2.out.untar.map{ it[1] }, UNTAR3.out.untar.map{ it[1] } )
+    ANTISMASH_ANTISMASHLITE ( GUNZIP1.out.gunzip, ANTISMASH_ANTISMASHLITEDOWNLOADDATABASES.out.database, ANTISMASH_ANTISMASHLITEDOWNLOADDATABASES.out.antismash_dir, GUNZIP2.out.gunzip.map{ it[1] } )
+}

tests/modules/antismash/antismashlite/nextflow.config

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

tests/modules/antismash/antismashlite/test.yml

@@ -0,0 +1,35 @@
+- name: antismash antismashlite test_antismashlite
+  command: nextflow run tests/modules/antismash/antismashlite -entry test_antismashlite -c tests/config/nextflow.config
+  tags:
+    - antismash/antismashlite
+    - antismash
+  files:
+    - path: output/antismash/test/NZ_CP069563.1.region001.gbk
+      contains: ['/tool="antismash"']
+    - path: output/antismash/test/NZ_CP069563.1.region002.gbk
+      contains: ['/tool="antismash"']
+    - path: output/antismash/test/css/bacteria.css
+      md5sum: 8b3c2f8b143d5245a5f42f55803c532c
+    - path: output/antismash/test/genome.gbk
+      contains: ['/tool="antismash"']
+    - path: output/antismash/test/genome.json
+      contains: ['{"version": "6.0.1", "input_file": "genome.fna", "records": [{"id": "NZ_CP069563.1", "seq": {"data":']
+    - path: output/antismash/test/genome.zip
+    - path: output/antismash/test/index.html
+      md5sum: de787e865c3a1eec143a19d2facb4de4
+    - path: output/antismash/test/js/antismash.js
+      md5sum: 58e90c3d783ae014cc3d51849bcb50a2
+    - path: output/antismash/test/js/jquery.js
+      md5sum: 397754ba49e9e0cf4e7c190da78dda05
+    - path: output/antismash/test/js/jquery.tablesorter.min.js
+      md5sum: 5e9e08cef4d1be0eaa538e6eb28809a7
+    - path: output/antismash/test/regions.js
+      contains: ['"seq_id": "NZ_CP069563.1"']
+    - path: output/antismash/test/test.log
+      contains: ["antiSMASH version: 6.0.1"]
+    - path: output/antismash/versions.yml
+      md5sum: 759431a43da33e2ef8e2d0ebd79a439b
+    - path: output/gunzip1/genome.fna
+      md5sum: dafd38f5454b54fbea38245d773062a5
+    - path: output/gunzip2/genome.gff
+      md5sum: 9b9c848b1946d43fa68128f4d6316052

tests/modules/bcftools/roh/main.nf

@@ -0,0 +1,35 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { BCFTOOLS_ROH } from '../../../../modules/bcftools/roh/main.nf'
+
+workflow test_bcftools_roh {
+
+    input = [ [ id:'test' ], // meta map
+             file(params.test_data['sarscov2']['illumina']['test_vcf_gz'], checkIfExists: true),
+             file(params.test_data['sarscov2']['illumina']['test_vcf_gz_tbi'], checkIfExists: true)]
+
+    af_file = []
+    gen_map = []
+    regions = []
+    targets = []
+    samples = []
+
+    BCFTOOLS_ROH ( input, af_file, gen_map, regions, samples, targets )
+}
+
+workflow test_bcftools_roh_stub {
+
+    input = [ [ id:'test' ], // meta map
+             file(params.test_data['sarscov2']['illumina']['test_vcf_gz'], checkIfExists: true),
+             file(params.test_data['sarscov2']['illumina']['test_vcf_gz_tbi'], checkIfExists: true)]
+
+    af_file = []
+    gen_map = []
+    regions = []
+    targets = []
+    samples = []
+
+    BCFTOOLS_ROH ( input, af_file, gen_map, regions, samples, targets )
+}

tests/modules/bcftools/roh/nextflow.config

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

tests/modules/bcftools/roh/test.yml

@@ -0,0 +1,17 @@
+- name: "bcftools roh"
+  command: nextflow run ./tests/modules/bcftools/roh -entry test_bcftools_roh -c ./tests/config/nextflow.config -c ./tests/modules/bcftools/roh/nextflow.config
+  tags:
+    - "bcftools"
+    - "bcftools/roh"
+  files:
+    - path: "output/bcftools/test.roh"
+    - path: "output/bcftools/versions.yml"
+
+- name: "bcftools roh stub"
+  command: nextflow run ./tests/modules/bcftools/roh -entry test_bcftools_roh_stub -c ./tests/config/nextflow.config -c ./tests/modules/bcftools/roh/nextflow.config
+  tags:
+    - "bcftools"
+    - "bcftools/roh"
+  files:
+    - path: "output/bcftools/test.roh"
+    - path: "output/bcftools/versions.yml"

tests/modules/bedtools/split/main.nf

@@ -0,0 +1,17 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { BEDTOOLS_SPLIT } from '../../../../modules/bedtools/split/main.nf'
+
+workflow test_bedtools_split {
+    
+    input = [
+        [ id:'test' ], // meta map
+        file(params.test_data['homo_sapiens']['genome']['genome_multi_interval_bed'], checkIfExists: true)
+    ]
+
+    number_of_files = 2
+
+    BEDTOOLS_SPLIT ( input, number_of_files )
+}

tests/modules/bedtools/split/nextflow.config

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

tests/modules/bedtools/split/test.yml

@@ -0,0 +1,10 @@
+- name: bedtools split test_bedtools_split
+  command: nextflow run ./tests/modules/bedtools/split -entry test_bedtools_split -c ./tests/config/nextflow.config  -c ./tests/modules/bedtools/split/nextflow.config
+  tags:
+    - bedtools
+    - bedtools/split
+  files:
+    - path: output/bedtools/test.00001.bed
+      md5sum: d58e5e46c2fcc3b8be5db0f023e93cb5
+    - path: output/bedtools/test.00002.bed
+      md5sum: 03caf952e9297a54620d2bbba8dc2823

tests/modules/biobambam/bammerge/main.nf

@@ -0,0 +1,30 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { BIOBAMBAM_BAMMERGE } from '../../../../modules/biobambam/bammerge/main.nf'
+
+workflow test_biobambam_bammerge_paired {
+
+    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)
+        ]
+    ]
+
+    BIOBAMBAM_BAMMERGE ( input )
+}
+
+workflow test_biobambam_bammerge_single {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        [
+            file(params.test_data['sarscov2']['illumina']['test_single_end_sorted_bam'], checkIfExists: true),
+        ]
+    ]
+
+    BIOBAMBAM_BAMMERGE ( input )
+}

tests/modules/biobambam/bammerge/nextflow.config

@@ -0,0 +1,13 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    withName: BIOBAMBAM_BAMMERGE {
+        ext.args = {[
+            "md5=1",
+            "md5filename=${meta.id}.md5",
+            "index=1",
+            "indexfilename=${meta.id}.bam.bai"
+        ].join(" ").trim()}
+    }
+
+}

tests/modules/biobambam/bammerge/test.yml

@@ -0,0 +1,25 @@
+- name: biobambam bammerge test_biobambam_bammerge_paired
+  command: nextflow run ./tests/modules/biobambam/bammerge -entry test_biobambam_bammerge_paired -c ./tests/config/nextflow.config  -c ./tests/modules/biobambam/bammerge/nextflow.config
+  tags:
+    - biobambam/bammerge
+    - biobambam
+  files:
+    - path: output/biobambam/test.bam
+      md5sum: bc3d32ab6a54d1894ca7cc79387dec57
+    - path: output/biobambam/test.bam.bai
+      md5sum: b8ae542a37a73d79de1c15c765207c53
+    - path: output/biobambam/test.md5
+      md5sum: 31c59857990ceb392242136429e30243
+
+- name: biobambam bammerge test_biobambam_bammerge_single
+  command: nextflow run ./tests/modules/biobambam/bammerge -entry test_biobambam_bammerge_single -c ./tests/config/nextflow.config  -c ./tests/modules/biobambam/bammerge/nextflow.config
+  tags:
+    - biobambam/bammerge
+    - biobambam
+  files:
+    - path: output/biobambam/test.bam
+      md5sum: 86185d3d6895a7722d3b3a09c6f91bfc
+    - path: output/biobambam/test.bam.bai
+      md5sum: 973680feb6bc73cd1051ea83c7219418
+    - path: output/biobambam/test.md5
+      md5sum: 244a9d1cbc6d74724285c80220e5e427

tests/modules/bowtie2/align/main.nf

@@ -14,9 +14,25 @@ workflow test_bowtie2_align_single_end {
     ]
     fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
     save_unaligned = false
+    sort = false
 
     BOWTIE2_BUILD ( fasta )
-    BOWTIE2_ALIGN ( input, BOWTIE2_BUILD.out.index, save_unaligned )
+    BOWTIE2_ALIGN ( input, BOWTIE2_BUILD.out.index, save_unaligned, sort )
+}
+
+workflow test_bowtie2_align_single_end_sorted {
+    input = [
+        [ id:'test', single_end:true ], // meta map
+        [
+            file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)
+        ]
+    ]
+    fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    save_unaligned = false
+    sort = true
+
+    BOWTIE2_BUILD ( fasta )
+    BOWTIE2_ALIGN ( input, BOWTIE2_BUILD.out.index, save_unaligned, sort )
 }
 
 workflow test_bowtie2_align_paired_end {
@@ -29,7 +45,55 @@ workflow test_bowtie2_align_paired_end {
     ]
     fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
     save_unaligned = false
+    sort = false
 
     BOWTIE2_BUILD ( fasta )
-    BOWTIE2_ALIGN ( input, BOWTIE2_BUILD.out.index, save_unaligned )
-}
+    BOWTIE2_ALIGN ( input, BOWTIE2_BUILD.out.index, save_unaligned, sort )
+}
+
+workflow test_bowtie2_align_paired_end_sorted {
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        [
+            file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+            file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true)
+        ]
+    ]
+    fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    save_unaligned = false
+    sort = true
+
+    BOWTIE2_BUILD ( fasta )
+    BOWTIE2_ALIGN ( input, BOWTIE2_BUILD.out.index, save_unaligned, sort )
+}
+
+workflow test_bowtie2_align_single_end_large_index {
+    input = [
+        [ id:'test', single_end:true ], // meta map
+        [
+            file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)
+        ]
+    ]
+    fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    save_unaligned = false
+    sort = false
+
+    BOWTIE2_BUILD ( fasta )
+    BOWTIE2_ALIGN ( input, BOWTIE2_BUILD.out.index, save_unaligned, sort )
+}
+
+workflow test_bowtie2_align_paired_end_large_index {
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        [
+            file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+            file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true)
+        ]
+    ]
+    fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    save_unaligned = false
+    sort = false
+
+    BOWTIE2_BUILD ( fasta )
+    BOWTIE2_ALIGN ( input, BOWTIE2_BUILD.out.index, save_unaligned, sort )
+}

tests/modules/bowtie2/align/nextflow.config

@@ -5,6 +5,7 @@ params {
 process {
 
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
 }
 
 if (params.force_large_index) {

tests/modules/bowtie2/align/test.yml

@@ -1,21 +1,49 @@
 - name: bowtie2 align test_bowtie2_align_single_end
   command: nextflow run ./tests/modules/bowtie2/align -entry test_bowtie2_align_single_end -c ./tests/config/nextflow.config -c ./tests/modules/bowtie2/align/nextflow.config
   tags:
-    - bowtie2/align
     - bowtie2
+    - bowtie2/align
   files:
-    - path: output/bowtie2/test.bam
-    - path: output/bowtie2/test.bowtie2.log
-      md5sum: 7b8a9e61b7646da1089b041333c41a87
-    - path: output/bowtie2/versions.yml
+    - path: ./output/bowtie2/test.bam
+    - path: ./output/bowtie2/test.bowtie2.log
+    - path: ./output/bowtie2/versions.yml
+
+- name: bowtie2 align test_bowtie2_align_single_end_sorted
+  command: nextflow run ./tests/modules/bowtie2/align -entry test_bowtie2_align_single_end_sorted -c ./tests/config/nextflow.config -c ./tests/modules/bowtie2/align/nextflow.config
+  tags:
+    - bowtie2
+    - bowtie2/align
+  files:
+    - path: ./output/bowtie2/test.bam
+    - path: ./output/bowtie2/test.bowtie2.log
+    - path: ./output/bowtie2/versions.yml
 
 - name: bowtie2 align test_bowtie2_align_paired_end
-  command: nextflow run ./tests/modules/bowtie2/align -entry test_bowtie2_align_paired_end -c ./tests/config/nextflow.config -c ./tests/modules/bowtie2/align/nextflow.config
+  command: nextflow run tests/modules/bowtie2/align -entry test_bowtie2_align_paired_end -c tests/config/nextflow.config -c tests/modules/bowtie2/align/nextflow.config
   tags:
-    - bowtie2/align
     - bowtie2
+    - bowtie2/align
   files:
-    - path: output/bowtie2/test.bam
-    - path: output/bowtie2/test.bowtie2.log
-      md5sum: bd89ce1b28c93bf822bae391ffcedd19
-    - path: output/bowtie2/versions.yml
+    - path: ./output/bowtie2/test.bam
+    - path: ./output/bowtie2/test.bowtie2.log
+    - path: ./output/bowtie2/versions.yml
+
+- name: bowtie2 align test_bowtie2_align_single_end_large_index
+  command: nextflow run tests/modules/bowtie2/align -entry test_bowtie2_align_single_end_large_index -c tests/config/nextflow.config -c tests/modules/bowtie2/align/nextflow.config --force_large_index
+  tags:
+    - bowtie2
+    - bowtie2/align
+  files:
+    - path: ./output/bowtie2/test.bam
+    - path: ./output/bowtie2/test.bowtie2.log
+    - path: ./output/bowtie2/versions.yml
+
+- name: bowtie2 align test_bowtie2_align_paired_end_large_index
+  command: nextflow run tests/modules/bowtie2/align -entry test_bowtie2_align_paired_end_large_index -c tests/config/nextflow.config -c tests/modules/bowtie2/align/nextflow.config --force_large_index
+  tags:
+    - bowtie2
+    - bowtie2/align
+  files:
+    - path: ./output/bowtie2/test.bam
+    - path: ./output/bowtie2/test.bowtie2.log
+    - path: ./output/bowtie2/versions.yml

tests/modules/cnvkit/antitarget/main.nf

@@ -0,0 +1,16 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CNVKIT_ANTITARGET } from '../../../../modules/cnvkit/antitarget/main.nf'
+
+workflow test_cnvkit_antitarget {
+
+    input = [
+        [ id:'test' ], // meta map
+        file(params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed'], checkIfExists: true)
+    ]
+
+    CNVKIT_ANTITARGET ( input )
+}
+

tests/modules/cnvkit/antitarget/nextflow.config

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

tests/modules/cnvkit/antitarget/test.yml

@@ -0,0 +1,8 @@
+- name: cnvkit antitarget test_cnvkit_antitarget
+  command: nextflow run ./tests/modules/cnvkit/antitarget -entry test_cnvkit_antitarget -c ./tests/config/nextflow.config  -c ./tests/modules/cnvkit/antitarget/nextflow.config
+  tags:
+    - cnvkit
+    - cnvkit/antitarget
+  files:
+    - path: output/cnvkit/test.antitarget.bed
+      md5sum: 3d4d20f9f23b39970865d29ef239d20b

tests/modules/cnvkit/batch/main.nf

@@ -35,8 +35,8 @@ workflow test_cnvkit_cram {
 
     input = [
         [ id:'test'], // meta map
-        file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_bam'], checkIfExists: true),
-        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_cram'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram'], checkIfExists: true)
     ]
     fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
 
@@ -50,8 +50,20 @@ workflow test_cnvkit_tumoronly {
         file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_bam'], checkIfExists: true),
         []
     ]
-    fasta     = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
     reference = file(params.test_data['generic']['cnn']['reference'], checkIfExists: true)
 
     CNVKIT_TUMORONLY ( input, [], [], reference )
 }
+
+workflow test_cnvkit_tumoronly_cram {
+
+    input = [
+        [ id:'test'], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_cram'], checkIfExists: true),
+        []
+    ]
+    fasta     = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    reference = file(params.test_data['generic']['cnn']['reference'], checkIfExists: true)
+
+    CNVKIT_TUMORONLY ( input, fasta, [], reference )
+}