Merge branch 'master' into kat_hist

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/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/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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.3.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'broadinstitute/gatk:4.2.3.0' }"
+        '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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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 +1,57 @@
+process GATK4_CNNSCOREVARIANTS {
+    tag "$meta.id"
+    label 'process_low'
+
+    //Conda is not supported at the moment: https://github.com/broadinstitute/gatk/issues/7811
+    if (params.enable_conda) {
+        exit 1, "Conda environments cannot be used for GATK4/CNNScoreVariants at the moment. Please use docker or singularity containers."
+    }
+    container 'broadinstitute/gatk:4.2.6.1' //Biocontainers is missing a package
+
+    input:
+    tuple val(meta), path(vcf), path(aligned_input), path(intervals)
+    path fasta
+    path fai
+    path dict
+    path architecture
+    path weights
+
+    output:
+    tuple val(meta), path("*.vcf.gz"), emit: vcf
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    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}.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 +1,72 @@
+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"
+  - 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"
+
+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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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/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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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':
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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' :
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
-        'quay.io/biocontainers/gatk4:4.2.5.0--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/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_sketch)
+    path fastx_db
+
+    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 \\
+        $query_sketch \\
+        $fastx_db \\
+        > ${prefix}.screen
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        mash: \$( mash --version )
+    END_VERSIONS
+    """
+}

modules/mash/screen/meta.yml

@@ -0,0 +1,47 @@
+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_sketch:
+      type: file
+      description: MinHash sketch of query sequences
+      pattern: "*.msh"
+  - fastx_db:
+      type: file
+      description: Sequence files to match against
+
+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/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/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 \\

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/**
@@ -218,6 +222,10 @@ 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 +234,10 @@ 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/**
@@ -719,6 +731,10 @@ 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/**
@@ -819,6 +835,10 @@ 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 +859,10 @@ genmap/mappability:
   - modules/genmap/mappability/**
   - tests/modules/genmap/mappability/**
 
+genomescope2:
+  - modules/genomescope2/**
+  - tests/modules/genomescope2/**
+
 genrich:
   - modules/genrich/**
   - tests/modules/genrich/**
@@ -954,6 +978,10 @@ hmmer/hmmsearch:
   - modules/hmmer/hmmsearch/**
   - tests/modules/hmmer/hmmsearch/**
 
+hmtnote:
+  - modules/hmtnote/**
+  - tests/modules/hmtnote/**
+
 homer/annotatepeaks:
   - modules/homer/annotatepeaks/**
   - tests/modules/homer/annotatepeaks/**
@@ -1190,6 +1218,10 @@ 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/**
@@ -1202,6 +1234,10 @@ maxbin2:
   - modules/maxbin2/**
   - tests/modules/maxbin2/**
 
+maxquant/lfq:
+  - modules/maxquant/lfq/**
+  - tests/modules/maxquant/lfq/**
+
 md5sum:
   - modules/md5sum/**
   - tests/modules/md5sum/**
@@ -1286,6 +1322,10 @@ 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/**
@@ -1651,14 +1691,14 @@ samtools/bam2fq:
   - modules/samtools/bam2fq/**
   - tests/modules/samtools/bam2fq/**
 
-samtools/convert:
-  - modules/samtools/convert/**
-  - tests/modules/samtools/convert/**
-
 samtools/collatefastq:
   - modules/samtools/collatefastq/**
   - tests/modules/samtools/collatefastq/**
 
+samtools/convert:
+  - modules/samtools/convert/**
+  - tests/modules/samtools/convert/**
+
 samtools/depth:
   - modules/samtools/depth/**
   - tests/modules/samtools/depth/**

tests/config/test_data.config

@@ -430,5 +430,17 @@ 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/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.bam
-    - path: output/bowtie2/test.bowtie2.log
+    - path: ./output/bowtie2/test.bowtie2.log
-      md5sum: 7b8a9e61b7646da1089b041333c41a87
+    - path: ./output/bowtie2/versions.yml
-    - 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.bam
-    - path: output/bowtie2/test.bowtie2.log
+    - path: ./output/bowtie2/test.bowtie2.log
-      md5sum: bd89ce1b28c93bf822bae391ffcedd19
+    - path: ./output/bowtie2/versions.yml
-    - 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/gatk4/applybqsr/test.yml

@@ -5,7 +5,7 @@
     - gatk4/applybqsr
   files:
     - path: output/gatk4/test.bam
-      md5sum: d088422be886dc8507ff97fcc7dd968a
+      md5sum: e11b7eaf2034740a953626518e3c3d6e
     - path: output/gatk4/versions.yml
 
 - name: gatk4 applybqsr test_gatk4_applybqsr_intervals
@@ -15,7 +15,7 @@
     - gatk4/applybqsr
   files:
     - path: output/gatk4/test.bam
-      md5sum: 4bfa18d651abd945e240b05e70107716
+      md5sum: e9e9aa753c106e43f936ad573e23d2e6
     - path: output/gatk4/versions.yml
 
 - name: gatk4 applybqsr test_gatk4_applybqsr_cram
@@ -25,5 +25,5 @@
     - gatk4/applybqsr
   files:
     - path: output/gatk4/test.cram
-      md5sum: 2e0bca197af4f043a4a85152e6edbe04
+      md5sum: bca9d234a5d484ce2a6f4826ca2ea308
     - path: output/gatk4/versions.yml

tests/modules/gatk4/applybqsrspark/test.yml

@@ -5,7 +5,7 @@
     - gatk4/applybqsrspark
   files:
     - path: output/gatk4/test.bam
-      md5sum: d088422be886dc8507ff97fcc7dd968a
+      md5sum: 1901c819fcba0fdd5e2482e6dc8285ef
     - path: output/gatk4/versions.yml
 
 - name: gatk4 applybqsr test_gatk4_applybqsr_spark_intervals
@@ -15,7 +15,7 @@
     - gatk4/applybqsrspark
   files:
     - path: output/gatk4/test.bam
-      md5sum: 4bfa18d651abd945e240b05e70107716
+      md5sum: 2ca2446f0125890280056fd7da822732
     - path: output/gatk4/versions.yml
 
 - name: gatk4 applybqsr test_gatk4_applybqsr_spark_cram
@@ -25,5 +25,5 @@
     - gatk4/applybqsrspark
   files:
     - path: output/gatk4/test.cram
-      md5sum: 2e0bca197af4f043a4a85152e6edbe04
+      md5sum: 60f7c822a9f2833e11eb7bfd16e4421f
     - path: output/gatk4/versions.yml

tests/modules/gatk4/cnnscorevariants/main.nf

@@ -0,0 +1,18 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GATK4_CNNSCOREVARIANTS } from '../../../../modules/gatk4/cnnscorevariants/main.nf'
+
+workflow test_gatk4_cnnscorevariants {
+
+    input     = [ [ id:'test' ], // meta map
+                    file(params.test_data['homo_sapiens']['illumina']['test_genome_vcf'], checkIfExists: true),
+                    [],
+                    []
+                ]
+    fasta  = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    fai    = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+    dict   = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
+    GATK4_CNNSCOREVARIANTS ( input, fasta, fai, dict, [], [] )
+}

tests/modules/gatk4/cnnscorevariants/nextflow.config

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

tests/modules/gatk4/cnnscorevariants/test.yml

@@ -0,0 +1,9 @@
+- name: gatk4 cnnscorevariants test_gatk4_cnnscorevariants
+  command: nextflow run ./tests/modules/gatk4/cnnscorevariants -entry test_gatk4_cnnscorevariants -c ./tests/config/nextflow.config  -c ./tests/modules/gatk4/cnnscorevariants/nextflow.config
+  tags:
+    - gatk4
+    - gatk4/cnnscorevariants
+  files:
+    - path: output/gatk4/test.vcf.gz
+      contains:
+        - "##ALT=<ID=NON_REF,Description="

tests/modules/gatk4/combinegvcfs/nextflow.config

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

tests/modules/gatk4/genotypegvcfs/main.nf

@@ -65,7 +65,9 @@ workflow test_gatk4_genotypegvcfs_gz_input_intervals {
     input = [ [ id:'test' ], // meta map
             file(params.test_data['homo_sapiens']['illumina']['test_genome_vcf_gz'], checkIfExists: true),
             file(params.test_data['homo_sapiens']['illumina']['test_genome_vcf_gz_tbi'], checkIfExists: true),
-            file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true) ]
+            file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true) ,
+            []
+            ]
 
     fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
     fai   = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
@@ -80,7 +82,8 @@ workflow test_gatk4_genotypegvcfs_gz_input_dbsnp_intervals {
     input = [ [ id:'test' ], // meta map
             file(params.test_data['homo_sapiens']['illumina']['test_genome_vcf_gz'], checkIfExists: true),
             file(params.test_data['homo_sapiens']['illumina']['test_genome_vcf_gz_tbi'], checkIfExists: true),
-            file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true)
+            file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true),
+            []
         ]
 
     fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
@@ -106,6 +109,7 @@ workflow test_gatk4_genotypegvcfs_gendb_input {
     gendb = UNTAR.out.untar.map{ it[1] }.collect()
     gendb.add([])
     gendb.add([])
+    gendb.add([])
 
     input = Channel.of([ id:'test' ]).combine(gendb)
 
@@ -128,6 +132,7 @@ workflow test_gatk4_genotypegvcfs_gendb_input_dbsnp {
     gendb = UNTAR.out.untar.map{ it[1] }.collect()
     gendb.add([])
     gendb.add([])
+    gendb.add([])
     input = Channel.of([ id:'test' ]).combine(gendb)
 
     GATK4_GENOTYPEGVCFS ( input, fasta, fai, dict, dbsnp, dbsnp_tbi)
@@ -146,6 +151,8 @@ workflow test_gatk4_genotypegvcfs_gendb_input_intervals {
     gendb = UNTAR.out.untar.map{ it[1] }.collect()
     gendb.add([])
     gendb.add([file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true)])
+    gendb.add([])
+
     input = Channel.of([ id:'test' ]).combine(gendb)
 
     GATK4_GENOTYPEGVCFS ( input, fasta, fai, dict, [], [] )
@@ -167,6 +174,8 @@ workflow test_gatk4_genotypegvcfs_gendb_input_dbsnp_intervals {
     gendb = UNTAR.out.untar.map{ it[1] }.collect()
     gendb.add([])
     gendb.add([file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true)])
+    gendb.add([])
+
     input = Channel.of([ id:'test' ]).combine(gendb)
 
     GATK4_GENOTYPEGVCFS ( input, fasta, fai, dict, dbsnp, dbsnp_tbi )

tests/modules/gatk4/getpileupsummaries/main.nf

@@ -4,21 +4,6 @@ nextflow.enable.dsl = 2
 
 include { GATK4_GETPILEUPSUMMARIES } from '../../../../modules/gatk4/getpileupsummaries/main.nf'
 
-workflow test_gatk4_getpileupsummaries_just_variants {
-
-    input = [ [ id:'test' ], // meta map
-        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_bam'], checkIfExists: true) ,
-        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_bam_bai'], checkIfExists: true),
-        []
-        ]
-
-    variants = file(params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz'], checkIfExists: true)
-    variants_tbi = file(params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz_tbi'], checkIfExists: true)
-    fasta = []
-    fai = []
-    dict = []
-    GATK4_GETPILEUPSUMMARIES ( input , fasta, fai, dict, variants , variants_tbi )
-}
 
 workflow test_gatk4_getpileupsummaries_separate_sites {
 

tests/modules/gatk4/getpileupsummaries/test.yml

@@ -1,13 +1,3 @@
-- name: gatk4 getpileupsummaries test_gatk4_getpileupsummaries_just_variants
-  command: nextflow run tests/modules/gatk4/getpileupsummaries -entry test_gatk4_getpileupsummaries_just_variants -c tests/config/nextflow.config
-  tags:
-    - gatk4/getpileupsummaries
-    - gatk4
-  files:
-    - path: output/gatk4/test.pileups.table
-      md5sum: 8e0ca6f66e112bd2f7ec1d31a2d62469
-    - path: output/gatk4/versions.yml
-
 - name: gatk4 getpileupsummaries test_gatk4_getpileupsummaries_separate_sites
   command: nextflow run tests/modules/gatk4/getpileupsummaries -entry test_gatk4_getpileupsummaries_separate_sites -c tests/config/nextflow.config
   tags:

tests/modules/gatk4/intervallisttools/test.yml

@@ -7,11 +7,11 @@
     - path: output/gatk4/test.interval_list
       md5sum: e51101c9357fb2d59fd30e370eefa39c
     - path: output/gatk4/test_split/temp_0001_of_6/1scattered.interval_list
-      md5sum: b8ba8a387200df76a0d1c577626dc265
+      md5sum: 39385d38ac6cb7c05190026fc3b81411
     - path: output/gatk4/test_split/temp_0002_of_6/2scattered.interval_list
-      md5sum: 0728d164666d9264ef442a493e008dee
+      md5sum: 59f1978c5f4ef3fce3b110816283d9f5
     - path: output/gatk4/test_split/temp_0003_of_6/3scattered.interval_list
-      md5sum: 55da0f3c69504148f4e7002a0e072cfe
+      md5sum: 709fe81bfcf700bd80d96c62a71629fd
     - path: output/gatk4/test_split/temp_0004_of_6/4scattered.interval_list
-      md5sum: d29ca4447f32547f2936567fa902796a
+      md5sum: c24044490cfedbcba61dbc646d3aa570
     - path: output/gatk4/versions.yml

tests/modules/gatk4/markduplicates/test.yml

@@ -5,9 +5,9 @@
     - gatk4/markduplicates
   files:
     - path: output/gatk4/test.bai
-      md5sum: e9c125e82553209933883b4fe2b8d7c2
+      md5sum: c8f7a9e426c768577f88f59cb1336bf3
     - path: output/gatk4/test.bam
-      md5sum: 2efd50b2e6b7fd9bdf242cd9e266cfa9
+      md5sum: 58533ddab47f7ac07f7b10e7f4aac234
     - path: output/gatk4/test.metrics
     - path: output/gatk4/versions.yml
 
@@ -20,6 +20,6 @@
     - path: output/gatk4/test.bai
       md5sum: bad71df9c876e72a5bc0a3e0fd755f92
     - path: output/gatk4/test.bam
-      md5sum: 8187febc6108ffef7f907e89b9c091a4
+      md5sum: 112580c24b43331950f24f9adea30788
     - path: output/gatk4/test.metrics
     - path: output/gatk4/versions.yml

tests/modules/gatk4/splitintervals/main.nf

@@ -0,0 +1,33 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GATK4_SPLITINTERVALS } from '../../../../modules/gatk4/splitintervals/main.nf'
+
+workflow test_gatk4_splitintervals_bed {
+    
+    input = [
+        [ id:'test' ], // meta map
+        file(params.test_data['homo_sapiens']['genome']['genome_multi_interval_bed'], checkIfExists: true)
+    ]
+
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    fasta_fai = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+    fasta_dict = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
+
+    GATK4_SPLITINTERVALS ( input, fasta, fasta_fai, fasta_dict)
+}
+
+workflow test_gatk4_splitintervals_intervals {
+    
+    input = [
+        [ id:'test' ], // meta map
+        file(params.test_data['homo_sapiens']['genome']['genome_interval_list'], checkIfExists: true)
+    ]
+
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    fasta_fai = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+    fasta_dict = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
+
+    GATK4_SPLITINTERVALS ( input, fasta, fasta_fai, fasta_dict)
+}

tests/modules/gatk4/splitintervals/nextflow.config

@@ -0,0 +1,9 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    
+
+    withName: GATK4_SPLITINTERVALS {
+        ext.args = "--scatter-count 2"
+    }
+}

tests/modules/gatk4/splitintervals/test.yml

@@ -0,0 +1,23 @@
+- name: gatk4 splitintervals test_gatk4_splitintervals_bed
+  command: nextflow run tests/modules/gatk4/splitintervals -entry test_gatk4_splitintervals_bed -c tests/config/nextflow.config
+  tags:
+    - gatk4/splitintervals
+    - gatk4
+  files:
+    - path: output/gatk4/test/0000-scattered.interval_list
+      md5sum: c8d6b19e7a92535b6ce9608eae558faa
+    - path: output/gatk4/test/0001-scattered.interval_list
+      md5sum: b1877ad96aec308906594c50ebbe3ded
+    - path: output/gatk4/versions.yml
+
+- name: gatk4 splitintervals test_gatk4_splitintervals_intervals
+  command: nextflow run tests/modules/gatk4/splitintervals -entry test_gatk4_splitintervals_intervals -c tests/config/nextflow.config
+  tags:
+    - gatk4/splitintervals
+    - gatk4
+  files:
+    - path: output/gatk4/test/0000-scattered.interval_list
+      md5sum: ebd6b34a335efc6732ff541936c6d2d5
+    - path: output/gatk4/test/0001-scattered.interval_list
+      md5sum: 9459b0e124fa84ec1e64ac4615bc9af7
+    - path: output/gatk4/versions.yml

tests/modules/gatk4/splitncigarreads/test.yml

@@ -5,7 +5,7 @@
     - gatk4/splitncigarreads
   files:
     - path: output/gatk4/test.bam
-      md5sum: 436d8e31285c6b588bdd1c7f1d07f6f2
+      md5sum: 37e5dbce8692b54c3292b539c91dfbd7
     - path: output/gatk4/versions.yml
 - name: gatk4 splitncigarreads test_gatk4_splitncigarreads_intervals
   command: nextflow run tests/modules/gatk4/splitncigarreads -entry test_gatk4_splitncigarreads_intervals -c tests/config/nextflow.config
@@ -14,5 +14,5 @@
     - gatk4/splitncigarreads
   files:
     - path: output/gatk4/test.bam
-      md5sum: cd56e3225950f519fd47164cca60a0bb
+      md5sum: e5cd2fd1822298a9bf7bc8b8d42146af
     - path: output/gatk4/versions.yml

tests/modules/gatk4/variantrecalibrator/test.yml

@@ -9,7 +9,7 @@
         - "#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO"
     - path: output/gatk4/test.recal.idx
     - path: output/gatk4/test.tranches
-      md5sum: d238e97bf996863969dac7751e345549
+      md5sum: c029e52fd63a893e1154cc9144a19eeb
     - path: output/gatk4/versions.yml
 
 - name: gatk4 variantrecalibrator test_gatk4_variantrecalibrator_allele_specific
@@ -23,5 +23,5 @@
         - "#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO"
     - path: output/gatk4/test.recal.idx
     - path: output/gatk4/test.tranches
-      md5sum: 444438d46716593634a6817958099292
+      md5sum: ad52fa69325c758f458a30ee5b43d6b5
     - path: output/gatk4/versions.yml

tests/modules/genomescope2/main.nf

@@ -0,0 +1,19 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { MERYL_COUNT     } from '../../../modules/meryl/count/main.nf'
+include { MERYL_HISTOGRAM } from '../../../modules/meryl/histogram/main.nf'
+include { GENOMESCOPE2    } from '../../../modules/genomescope2/main.nf'
+
+workflow test_genomescope2 {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['bacteroides_fragilis']['illumina']['test1_1_fastq_gz'], checkIfExists: true)
+    ]
+
+    MERYL_COUNT ( input )
+    MERYL_HISTOGRAM ( MERYL_COUNT.out.meryl_db )
+    GENOMESCOPE2 ( MERYL_HISTOGRAM.out.hist )
+}

tests/modules/genomescope2/nextflow.config

@@ -0,0 +1,13 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName: 'MERYL.*' {
+        ext.args = 'k=21'
+    }
+
+    withName: 'GENOMESCOPE2' {
+        ext.args = '-k 21 -p 1'
+    }
+
+}

tests/modules/genomescope2/test.yml

@@ -0,0 +1,22 @@
+- name: genomescope2 test_genomescope2
+  command: nextflow run tests/modules/genomescope2 -entry test_genomescope2 -c tests/config/nextflow.config
+  tags:
+    - genomescope2
+  files:
+    - path: output/genomescope2/test_linear_plot.png
+      md5sum: 94c165c5028156299a1d4d05766cac51
+    - path: output/genomescope2/test_log_plot.png
+      md5sum: 9d25ca463d92a0c73a893da7fd3979ba
+    - path: output/genomescope2/test_model.txt
+      md5sum: 3caf62f715f64a2f2b8fdff5d079cb84
+    - path: output/genomescope2/test_summary.txt
+      md5sum: 7452860e2cea99b85f3ff60daeac77f5
+    - path: output/genomescope2/test_transformed_linear_plot.png
+      md5sum: 99a64c1c18d8670f64cb863d4334abbb
+    - path: output/genomescope2/test_transformed_log_plot.png
+      md5sum: b4e029c9fb9987ca33b17392a691c1b4
+    - path: output/genomescope2/versions.yml
+      md5sum: 18afeb26f62a47f680b2bb3e27da9cbc
+    - path: output/meryl/test.hist
+      md5sum: f75362ab9cd70d96621b3690e952085f
+    - path: output/meryl/versions.yml

tests/modules/hmtnote/main.nf

@@ -0,0 +1,14 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { HMTNOTE } from '../../../modules/hmtnote/main.nf'
+
+workflow test_hmtnote {
+    
+    input = [ [ id:'test' ], // meta map
+              file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true)
+            ]
+
+    HMTNOTE ( input)
+}

tests/modules/hmtnote/nextflow.config

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

tests/modules/hmtnote/test.yml

@@ -0,0 +1,6 @@
+- name: hmtnote test_hmtnote
+  command: nextflow run ./tests/modules/hmtnote -entry test_hmtnote -c ./tests/config/nextflow.config -c ./tests/modules/hmtnote/nextflow.config
+  tags:
+    - hmtnote
+  files:
+    - path: output/hmtnote/test_annotated.vcf

tests/modules/mash/screen/main.nf

@@ -0,0 +1,21 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { MASH_SKETCH } from '../../../../modules/mash/sketch/main.nf'
+include { MASH_SCREEN } from '../../../../modules/mash/screen/main.nf'
+
+workflow test_mash_screen {
+
+    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)
+        ]
+    ]
+    fastx_db = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+
+    MASH_SKETCH ( input )
+    MASH_SCREEN ( MASH_SKETCH.out.mash, fastx_db )
+}

tests/modules/mash/screen/nextflow.config

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

tests/modules/mash/screen/test.yml

@@ -0,0 +1,12 @@
+- name: mash screen test_mash_screen
+  command: nextflow run ./tests/modules/mash/screen -entry test_mash_screen -c ./tests/config/nextflow.config  -c ./tests/modules/mash/screen/nextflow.config
+  tags:
+    - mash
+    - mash/screen
+  files:
+    - path: output/mash/test.mash_stats
+      md5sum: 2a6f297d8e69a5e4160243bc6c89129c
+    - path: output/mash/test.msh
+      md5sum: d747145a43dad5f82342036f8f5d9133
+    - path: output/mash/test.screen
+      md5sum: d3c871dccd5cd57ab54781fa5c5d7278

tests/modules/maxquant/lfq/main.nf

@@ -0,0 +1,17 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { MAXQUANT_LFQ } from '../../../../modules/maxquant/lfq/main.nf' addParams( options: [:] )
+
+workflow test_maxquant_lfq {
+        
+    input = [ [ id:'test' ], // meta map
+              file(params.test_data['proteomics']['database']['yeast_ups'], checkIfExists: true), file(params.test_data['proteomics']['parameter']['maxquant'] , checkIfExists: true)
+            ]
+
+
+    rawfiles = [file(params.test_data['proteomics']['msspectra']['ups_file1']) , file(params.test_data['proteomics']['msspectra']['ups_file2'])]
+
+    MAXQUANT_LFQ ( input, rawfiles.collect() )
+}

tests/modules/maxquant/lfq/nextflow.config

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

tests/modules/maxquant/lfq/test.yml

@@ -0,0 +1,8 @@
+- name: maxquant lfq
+  command: nextflow run ./tests/modules/maxquant/lfq -entry test_maxquant_lfq  -c tests/config/nextflow.config
+  tags:
+    - maxquant
+    - maxquant/lfq
+  files:
+    - path: output/maxquant/proteinGroups.txt
+      md5sum: 0d0f6aab54fe6dc717d1307bbc207324