Merge remote-tracking branch 'origin' into gatk_cnnscore

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/arriba/main.nf

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

modules/arriba/meta.yml

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

modules/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

@@ -1,81 +1,71 @@
 process BOWTIE2_ALIGN {
     tag "$meta.id"
-    label 'process_high'
+    label "process_high"
 
-    conda (params.enable_conda ? 'bioconda::bowtie2=2.4.4 bioconda::samtools=1.15.1 conda-forge::pigz=2.6' : null)
-    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/mulled-v2-ac74a7f02cebcfcc07d8e8d1d750af9c83b4d45a:1744f68fe955578c63054b55309e05b41c37a80d-0' :
-        'quay.io/biocontainers/mulled-v2-ac74a7f02cebcfcc07d8e8d1d750af9c83b4d45a:1744f68fe955578c63054b55309e05b41c37a80d-0' }"
+    conda (params.enable_conda ? "bioconda::bowtie2=2.4.4 bioconda::samtools=1.15.1 conda-forge::pigz=2.6" : null)
+    container "${ workflow.containerEngine == "singularity" && !task.ext.singularity_pull_docker_container ?
+        "https://depot.galaxyproject.org/singularity/mulled-v2-ac74a7f02cebcfcc07d8e8d1d750af9c83b4d45a:1744f68fe955578c63054b55309e05b41c37a80d-0" :
+        "quay.io/biocontainers/mulled-v2-ac74a7f02cebcfcc07d8e8d1d750af9c83b4d45a:1744f68fe955578c63054b55309e05b41c37a80d-0" }"
 
     input:
     tuple val(meta), path(reads)
     path  index
     val   save_unaligned
+    val   sort_bam
 
     output:
-    tuple val(meta), path('*.bam')    , emit: bam
-    tuple val(meta), path('*.log')    , emit: log
-    tuple val(meta), path('*fastq.gz'), emit: fastq, optional:true
+    tuple val(meta), path("*.bam")    , emit: bam
+    tuple val(meta), path("*.log")    , emit: log
+    tuple val(meta), path("*fastq.gz"), emit: fastq, optional:true
     path  "versions.yml"              , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
 
     script:
-    def args = task.ext.args ?: ''
-    def args2 = task.ext.args2 ?: ''
+    def args = task.ext.args ?: ""
+    def args2 = task.ext.args2 ?: ""
     def prefix = task.ext.prefix ?: "${meta.id}"
+
+    def unaligned = ""
+    def reads_args = ""
     if (meta.single_end) {
-        def unaligned = save_unaligned ? "--un-gz ${prefix}.unmapped.fastq.gz" : ''
-        """
-        INDEX=`find -L ./ -name "*.rev.1.bt2" | sed 's/.rev.1.bt2//'`
-        [ -z "\$INDEX" ] && INDEX=`find -L ./ -name "*.rev.1.bt2l" | sed 's/.rev.1.bt2l//'`
-        [ -z "\$INDEX" ] && echo "BT2 index files not found" 1>&2 && exit 1
-        bowtie2 \\
-            -x \$INDEX \\
-            -U $reads \\
-            --threads $task.cpus \\
-            $unaligned \\
-            $args \\
-            2> ${prefix}.bowtie2.log \\
-            | samtools view -@ $task.cpus $args2 -bhS -o ${prefix}.bam -
-
-        cat <<-END_VERSIONS > versions.yml
-        "${task.process}":
-            bowtie2: \$(echo \$(bowtie2 --version 2>&1) | sed 's/^.*bowtie2-align-s version //; s/ .*\$//')
-            samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
-            pigz: \$( pigz --version 2>&1 | sed 's/pigz //g' )
-        END_VERSIONS
-        """
+        unaligned = save_unaligned ? "--un-gz ${prefix}.unmapped.fastq.gz" : ""
+        reads_args = "-U ${reads}"
     } else {
-        def unaligned = save_unaligned ? "--un-conc-gz ${prefix}.unmapped.fastq.gz" : ''
-        """
-        INDEX=`find -L ./ -name "*.rev.1.bt2" | sed 's/.rev.1.bt2//'`
-        [ -z "\$INDEX" ] && INDEX=`find -L ./ -name "*.rev.1.bt2l" | sed 's/.rev.1.bt2l//'`
-        [ -z "\$INDEX" ] && echo "BT2 index files not found" 1>&2 && exit 1
-        bowtie2 \\
-            -x \$INDEX \\
-            -1 ${reads[0]} \\
-            -2 ${reads[1]} \\
-            --threads $task.cpus \\
-            $unaligned \\
-            $args \\
-            2> ${prefix}.bowtie2.log \\
-            | samtools view -@ $task.cpus $args2 -bhS -o ${prefix}.bam -
-
-        if [ -f ${prefix}.unmapped.fastq.1.gz ]; then
-            mv ${prefix}.unmapped.fastq.1.gz ${prefix}.unmapped_1.fastq.gz
-        fi
-        if [ -f ${prefix}.unmapped.fastq.2.gz ]; then
-            mv ${prefix}.unmapped.fastq.2.gz ${prefix}.unmapped_2.fastq.gz
-        fi
-
-        cat <<-END_VERSIONS > versions.yml
-        "${task.process}":
-            bowtie2: \$(echo \$(bowtie2 --version 2>&1) | sed 's/^.*bowtie2-align-s version //; s/ .*\$//')
-            samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
-            pigz: \$( pigz --version 2>&1 | sed 's/pigz //g' )
-        END_VERSIONS
-        """
+        unaligned = save_unaligned ? "--un-conc-gz ${prefix}.unmapped.fastq.gz" : ""
+        reads_args = "-1 ${reads[0]} -2 ${reads[1]}"
     }
+
+    def samtools_command = sort_bam ? 'sort' : 'view'
+
+    """
+    INDEX=`find -L ./ -name "*.rev.1.bt2" | sed "s/.rev.1.bt2//"`
+    [ -z "\$INDEX" ] && INDEX=`find -L ./ -name "*.rev.1.bt2l" | sed "s/.rev.1.bt2l//"`
+    [ -z "\$INDEX" ] && echo "Bowtie2 index files not found" 1>&2 && exit 1
+
+    bowtie2 \\
+        -x \$INDEX \\
+        $reads_args \\
+        --threads $task.cpus \\
+        $unaligned \\
+        $args \\
+        2> ${prefix}.bowtie2.log \\
+        | 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
+    fi
+
+    if [ -f ${prefix}.unmapped.fastq.2.gz ]; then
+        mv ${prefix}.unmapped.fastq.2.gz ${prefix}.unmapped_2.fastq.gz
+    fi
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bowtie2: \$(echo \$(bowtie2 --version 2>&1) | sed 's/^.*bowtie2-align-s version //; s/ .*\$//')
+        samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+        pigz: \$( pigz --version 2>&1 | sed 's/pigz //g' )
+    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/custom/sratoolsncbisettings/main.nf

@@ -0,0 +1,20 @@
+process CUSTOM_SRATOOLSNCBISETTINGS {
+    tag 'ncbi-settings'
+    label 'process_low'
+
+    conda (params.enable_conda ? 'bioconda::sra-tools=2.11.0' : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/sra-tools:2.11.0--pl5321ha49a11a_3' :
+        'quay.io/biocontainers/sra-tools:2.11.0--pl5321ha49a11a_3' }"
+
+    output:
+    path('*.mkfg')     , emit: ncbi_settings
+    path 'versions.yml', emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    shell:
+    config = "/LIBS/GUID = \"${UUID.randomUUID().toString()}\"\\n/libs/cloud/report_instance_identity = \"true\"\\n"
+    template 'detect_ncbi_settings.sh'
+}

modules/custom/sratoolsncbisettings/meta.yml

@@ -0,0 +1,28 @@
+name: "sratoolsncbisettings"
+description: Test for the presence of suitable NCBI settings or create them on the fly.
+keywords:
+  - NCBI
+  - settings
+  - sra-tools
+  - prefetch
+  - fasterq-dump
+tools:
+  - "sratools":
+      description: "SRA Toolkit and SDK from NCBI"
+      homepage: https://github.com/ncbi/sra-tools
+      documentation: https://github.com/ncbi/sra-tools/wiki
+      tool_dev_url: https://github.com/ncbi/sra-tools
+      licence: "['Public Domain']"
+
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - ncbi_settings:
+      type: file
+      description: An NCBI user settings file.
+      pattern: "*.mkfg"
+
+authors:
+  - "@Midnighter"

modules/custom/sratoolsncbisettings/templates/detect_ncbi_settings.sh

@@ -0,0 +1,45 @@
+#!/usr/bin/env bash
+
+set -u
+
+
+# Get the expected NCBI settings path and define the environment variable
+# `NCBI_SETTINGS`.
+eval "$(vdb-config -o n NCBI_SETTINGS | sed 's/[" ]//g')"
+
+# If the user settings do not exist yet, create a file suitable for `prefetch`
+# and `fasterq-dump`. If an existing settings file does not contain the required
+# values, error out with a helpful message.
+if [[ ! -f "${NCBI_SETTINGS}" ]]; then
+    printf '!{config}' > 'user-settings.mkfg'
+else
+    prefetch --help &> /dev/null
+    if [[ $? = 78 ]]; then
+        echo "You have an existing vdb-config at '${NCBI_SETTINGS}' but it is"\
+        "missing the required entries for /LIBS/GUID and"\
+        "/libs/cloud/report_instance_identity."\
+        "Feel free to add the following to your settings file:" >&2
+        echo "$(printf '!{config}')" >&2
+        exit 1
+    fi
+    fasterq-dump --help &> /dev/null
+    if [[ $? = 78 ]]; then
+        echo "You have an existing vdb-config at '${NCBI_SETTINGS}' but it is"\
+        "missing the required entries for /LIBS/GUID and"\
+        "/libs/cloud/report_instance_identity."\
+        "Feel free to add the following to your settings file:" >&2
+        echo "$(printf '!{config}')" >&2
+        exit 1
+    fi
+    if [[ "${NCBI_SETTINGS}" != *.mkfg ]]; then
+        echo "The detected settings '${NCBI_SETTINGS}' do not have the required"\
+        "file extension '.mkfg'." >&2
+        exit 1
+    fi
+    cp "${NCBI_SETTINGS}" ./
+fi
+
+cat <<-END_VERSIONS > versions.yml
+"!{task.process}":
+    sratools: $(vdb-config --version 2>&1 | grep -Eo '[0-9.]+')
+END_VERSIONS

modules/gatk4/applybqsr/main.nf

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

modules/gatk4/applybqsrspark/main.nf

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

modules/gatk4/applyvqsr/main.nf

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

modules/gatk4/baserecalibrator/main.nf

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

modules/gatk4/baserecalibratorspark/main.nf

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

modules/gatk4/bedtointervallist/main.nf

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

modules/gatk4/calculatecontamination/main.nf

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

modules/gatk4/combinegvcfs/main.nf

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

modules/gatk4/createsequencedictionary/main.nf

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

modules/gatk4/createsomaticpanelofnormals/main.nf

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

modules/gatk4/estimatelibrarycomplexity/main.nf

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

modules/gatk4/fastqtosam/main.nf

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

modules/gatk4/filtermutectcalls/main.nf

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

modules/gatk4/gatherbqsrreports/main.nf

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

modules/gatk4/gatherpileupsummaries/main.nf

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

modules/gatk4/genomicsdbimport/main.nf

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

modules/gatk4/genotypegvcfs/main.nf

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

modules/gatk4/getpileupsummaries/main.nf

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

modules/gatk4/haplotypecaller/main.nf

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

modules/gatk4/indexfeaturefile/main.nf

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

modules/gatk4/intervallisttobed/main.nf

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

modules/gatk4/intervallisttools/main.nf

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

modules/gatk4/learnreadorientationmodel/main.nf

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

modules/gatk4/markduplicates/main.nf

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

modules/gatk4/mergebamalignment/main.nf

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

modules/gatk4/mergemutectstats/main.nf

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

modules/gatk4/mergevcfs/main.nf

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

modules/gatk4/mutect2/main.nf

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

modules/gatk4/revertsam/main.nf

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

modules/gatk4/samtofastq/main.nf

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

modules/gatk4/selectvariants/main.nf

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

modules/gatk4/splitintervals/main.nf

@@ -0,0 +1,48 @@
+process GATK4_SPLITINTERVALS {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(intervals)
+    path(fasta)
+    path(fasta_fai)
+    path(dict)
+
+    output:
+    tuple val(meta), path("**.interval_list"), emit: split_intervals
+    path "versions.yml"                      , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def reference = fasta ? "--reference $fasta" : ""
+
+    def avail_mem = 3
+    if (!task.memory) {
+        log.info '[GATK SplitIntervals] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
+    } else {
+        avail_mem = task.memory.giga
+    }
+
+    """
+    gatk --java-options "-Xmx${avail_mem}g" SplitIntervals \\
+        --output ${prefix} \\
+        --intervals $intervals \\
+        $reference \\
+        --tmp-dir . \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
+    END_VERSIONS
+    """
+}

modules/gatk4/splitintervals/meta.yml

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

modules/gatk4/splitncigarreads/main.nf

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

modules/gatk4/variantfiltration/main.nf

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

modules/gatk4/variantrecalibrator/main.nf

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

modules/genomescope2/main.nf

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

modules/genomescope2/meta.yml

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

modules/hmtnote/main.nf

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

modules/hmtnote/meta.yml

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

modules/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/rtgtools/vcfeval/main.nf

@@ -0,0 +1,60 @@
+process RTGTOOLS_VCFEVAL {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::rtg-tools=3.12.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/rtg-tools:3.12.1--hdfd78af_0':
+        'quay.io/biocontainers/rtg-tools:3.12.1--hdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(query_vcf), path(query_vcf_tbi)
+    tuple path(truth_vcf), path(truth_vcf_tbi)
+    path(truth_regions)
+    path(evaluation_regions)
+    path(sdf)
+
+    output:
+    tuple val(meta), path("**results/{done,progress,*.log}") , emit: logs
+    tuple val(meta), path("**tp.vcf.gz"), path("**tp.vcf.gz.tbi") , emit: tp
+    tuple val(meta), path("**fn.vcf.gz"), path("**fn.vcf.gz.tbi") , emit: fn
+    tuple val(meta), path("**fp.vcf.gz"), path("**fp.vcf.gz.tbi") , emit: fp
+    tuple val(meta), path("**baseline.vcf.gz"), path("**baseline.vcf.gz.tbi") , emit: baseline
+    tuple val(meta), path("**.tsv.gz")                    , emit: roc
+    tuple val(meta), path("**results/summary.txt")        , emit: summary
+    tuple val(meta), path("**results/phasing.txt")        , emit: phasing
+    path "versions.yml"                                   , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ""
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def bed_regions = truth_regions ? "--bed-regions=$truth_regions" : ""
+    def eval_regions = evaluation_regions ? "--evaluation-regions=$evaluation_regions" : ""
+    def truth_index = truth_vcf_tbi ? "" : "rtg index $truth_vcf"
+    def query_index = query_vcf_tbi ? "" : "rtg index $query_vcf"
+    def avail_mem = task.memory.toGiga() + "G"
+
+    """
+    $truth_index
+    $query_index
+
+    rtg RTG_MEM=$avail_mem vcfeval \\
+        $args \\
+        --baseline=$truth_vcf \\
+        $bed_regions \\
+        $eval_regions \\
+        --calls=$query_vcf \\
+        --output=${prefix}_results \\
+        --template=$sdf \\
+        --threads=$task.cpus \\
+
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        rtg-tools: \$(echo \$(rtg version | head -n 1 | awk '{print \$4}'))
+    END_VERSIONS
+    """
+}

modules/rtgtools/vcfeval/meta.yml

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

modules/sratools/fasterqdump/main.nf

@@ -9,6 +9,7 @@ process SRATOOLS_FASTERQDUMP {
 
     input:
     tuple val(meta), path(sra)
+    path ncbi_settings
 
     output:
     tuple val(meta), path(output), emit: reads
@@ -20,17 +21,12 @@ process SRATOOLS_FASTERQDUMP {
     script:
     def args = task.ext.args ?: ''
     def args2 = task.ext.args2 ?: ''
-    def config = "/LIBS/GUID = \"${UUID.randomUUID().toString()}\"\\n/libs/cloud/report_instance_identity = \"true\"\\n"
     // Paired-end data extracted by fasterq-dump (--split-3 the default) always creates
     // *_1.fastq *_2.fastq files but sometimes also an additional *.fastq file
     // for unpaired reads which we ignore here.
     output = meta.single_end ? '*.fastq.gz' : '*_{1,2}.fastq.gz'
     """
-    eval "\$(vdb-config -o n NCBI_SETTINGS | sed 's/[" ]//g')"
-    if [[ ! -f "\${NCBI_SETTINGS}" ]]; then
-        mkdir -p "\$(dirname "\${NCBI_SETTINGS}")"
-        printf '${config}' > "\${NCBI_SETTINGS}"
-    fi
+    export NCBI_SETTINGS="\$PWD/${ncbi_settings}"
 
     fasterq-dump \\
         $args \\

modules/sratools/fasterqdump/meta.yml

@@ -10,7 +10,7 @@ tools:
       homepage: https://github.com/ncbi/sra-tools
       documentation: https://github.com/ncbi/sra-tools/wiki
       tool_dev_url: https://github.com/ncbi/sra-tools
-      licence: ["US-Government-Work"]
+      licence: ["Public Domain"]
 
 input:
   - meta:
@@ -22,6 +22,11 @@ input:
       type: directory
       description: Directory containing ETL data for the given SRA.
       pattern: "*/*.sra"
+  - ncbi_settings:
+      type: file
+      description: >
+        An NCBI user settings file.
+      pattern: "*.mkfg"
 
 output:
   - meta:

modules/sratools/prefetch/main.nf

@@ -9,10 +9,11 @@ process SRATOOLS_PREFETCH {
 
     input:
     tuple val(meta), val(id)
+    path ncbi_settings
 
     output:
     tuple val(meta), path(id), emit: sra
-    path "versions.yml"         , emit: versions
+    path 'versions.yml'      , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
@@ -20,7 +21,5 @@ process SRATOOLS_PREFETCH {
     shell:
     args = task.ext.args ?: ''
     args2 = task.ext.args2 ?: '5 1 100'  // <num retries> <base delay in seconds> <max delay in seconds>
-    config = "/LIBS/GUID = \"${UUID.randomUUID().toString()}\"\\n/libs/cloud/report_instance_identity = \"true\"\\n"
-
     template 'retry_with_backoff.sh'
 }

modules/sratools/prefetch/meta.yml

@@ -10,7 +10,7 @@ tools:
       homepage: https://github.com/ncbi/sra-tools
       documentation: https://github.com/ncbi/sra-tools/wiki
       tool_dev_url: https://github.com/ncbi/sra-tools
-      licence: ["US-Government-Work"]
+      licence: ["Public Domain"]
 
 input:
   - meta:
@@ -22,6 +22,11 @@ input:
       type: val
       description: >
         A string denoting an SRA id.
+  - ncbi_settings:
+      type: file
+      description: >
+        An NCBI user settings file.
+      pattern: "*.mkfg"
 
 output:
   - meta:

modules/sratools/prefetch/templates/retry_with_backoff.sh

@@ -40,11 +40,7 @@ retry_with_backoff() {
     echo "${output}"
 }
 
-eval "$(vdb-config -o n NCBI_SETTINGS | sed 's/[" ]//g')"
-if [[ ! -f "${NCBI_SETTINGS}" ]]; then
-    mkdir -p "$(dirname "${NCBI_SETTINGS}")"
-    printf '!{config}' > "${NCBI_SETTINGS}"
-fi
+export NCBI_SETTINGS="$PWD/!{ncbi_settings}"
 
 retry_with_backoff !{args2} \
     prefetch \

subworkflows/nf-core/sra_fastq/main.nf

@@ -1,34 +0,0 @@
-//
-// Download FASTQ sequencing reads from the NCBI's Sequence Read Archive (SRA).
-//
-
-params.prefetch_options    = [:]
-params.fasterqdump_options = [:]
-
-include { SRATOOLS_PREFETCH    } from '../../../modules/sratools/prefetch/main'    addParams( options: params.prefetch_options    )
-include { SRATOOLS_FASTERQDUMP } from '../../../modules/sratools/fasterqdump/main' addParams( options: params.fasterqdump_options )
-
-workflow SRA_FASTQ {
-    take:
-    sra_ids  // channel: [ val(meta), val(id) ]
-
-    main:
-
-    ch_versions = Channel.empty()
-
-    //
-    // Prefetch sequencing reads in SRA format.
-    //
-    SRATOOLS_PREFETCH ( sra_ids )
-    ch_versions = ch_versions.mix( SRATOOLS_PREFETCH.out.versions.first() )
-
-    //
-    // Convert the SRA format into one or more compressed FASTQ files.
-    //
-    SRATOOLS_FASTERQDUMP ( SRATOOLS_PREFETCH.out.sra )
-    ch_versions = ch_versions.mix( SRATOOLS_FASTERQDUMP.out.versions.first() )
-
-    emit:
-    reads    = SRATOOLS_FASTERQDUMP.out.reads  // channel: [ val(meta), [ reads ] ]
-    versions = ch_versions                     // channel: [ versions.yml ]
-}

subworkflows/nf-core/srafastq/main.nf

@@ -0,0 +1,38 @@
+include { CUSTOM_SRATOOLSNCBISETTINGS } from '../../../modules/custom/sratoolsncbisettings/main'
+include { SRATOOLS_PREFETCH           } from '../../../modules/sratools/prefetch/main'
+include { SRATOOLS_FASTERQDUMP        } from '../../../modules/sratools/fasterqdump/main'
+
+/**
+ * Download FASTQ sequencing reads from the NCBI's Sequence Read Archive (SRA).
+ */
+workflow SRAFASTQ {
+    take:
+    sra_ids  // channel: [ val(meta), val(id) ]
+
+    main:
+
+    ch_versions = Channel.empty()
+
+    //
+    // Detect existing NCBI user settings or create new ones.
+    //
+    CUSTOM_SRATOOLSNCBISETTINGS()
+    def settings = CUSTOM_SRATOOLSNCBISETTINGS.out.ncbi_settings
+    ch_versions = ch_versions.mix( CUSTOM_SRATOOLSNCBISETTINGS.out.versions )
+
+    //
+    // Prefetch sequencing reads in SRA format.
+    //
+    SRATOOLS_PREFETCH ( sra_ids, settings )
+    ch_versions = ch_versions.mix( SRATOOLS_PREFETCH.out.versions.first() )
+
+    //
+    // Convert the SRA format into one or more compressed FASTQ files.
+    //
+    SRATOOLS_FASTERQDUMP ( SRATOOLS_PREFETCH.out.sra, settings )
+    ch_versions = ch_versions.mix( SRATOOLS_FASTERQDUMP.out.versions.first() )
+
+    emit:
+    reads    = SRATOOLS_FASTERQDUMP.out.reads  // channel: [ val(meta), [ reads ] ]
+    versions = ch_versions                     // channel: [ versions.yml ]
+}

subworkflows/nf-core/srafastq/meta.yml

@@ -1,11 +1,14 @@
 name: sra_fastq
 description: Download FASTQ sequencing reads from the NCBI's Sequence Read Archive (SRA).
 keywords:
+  - SRA
+  - NCBI
   - sequencing
   - FASTQ
   - prefetch
-  - dump
+  - fasterq-dump
 modules:
+  - custom/sratoolsncbisettings
   - sratools/prefetch
   - sratools/fasterqdump
 input:
@@ -17,7 +20,7 @@ input:
   - id:
       type: string
       description: >
-        SRA identifier.
+        SRA run identifier.
 # TODO Update when we decide on a standard for subworkflow docs
 output:
   - meta:

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/**
@@ -495,6 +507,10 @@ custom/getchromsizes:
   - modules/custom/getchromsizes/**
   - tests/modules/custom/getchromsizes/**
 
+custom/sratoolsncbisettings:
+  - modules/custom/sratoolsncbisettings/**
+  - tests/modules/custom/sratoolsncbisettings/**
+
 cutadapt:
   - modules/cutadapt/**
   - tests/modules/cutadapt/**
@@ -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/**
@@ -1198,6 +1226,10 @@ maxbin2:
   - modules/maxbin2/**
   - tests/modules/maxbin2/**
 
+maxquant/lfq:
+  - modules/maxquant/lfq/**
+  - tests/modules/maxquant/lfq/**
+
 md5sum:
   - modules/md5sum/**
   - tests/modules/md5sum/**
@@ -1623,6 +1655,10 @@ rseqc/tin:
   - modules/rseqc/tin/**
   - tests/modules/rseqc/tin/**
 
+rtgtools/vcfeval:
+  - modules/rtgtools/vcfeval/**
+  - tests/modules/rtgtools/vcfeval/**
+
 salmon/index:
   - modules/salmon/index/**
   - tests/modules/salmon/index/**
@@ -1643,14 +1679,14 @@ 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

@@ -135,6 +135,7 @@ params {
                 transcriptome_fasta                            = "${test_data_dir}/genomics/homo_sapiens/genome/transcriptome.fasta"
                 genome2_fasta                                  = "${test_data_dir}/genomics/homo_sapiens/genome/genome2.fasta"
                 genome_chain_gz                                = "${test_data_dir}/genomics/homo_sapiens/genome/genome.chain.gz"
+                genome_21_sdf                                  = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome_sdf.tar.gz"
                 genome_21_fasta                                = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.fasta"
                 genome_21_fasta_fai                            = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.fasta.fai"
                 genome_21_dict                                 = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.dict"
@@ -212,110 +213,113 @@ params {
                 test_paired_end_hla                                     = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/example_hla_pe.bam"
                 test_paired_end_hla_sorted_bam                          = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/example_hla_pe.sorted.bam"
                 test_paired_end_hla_sorted_bam_bai                      = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/example_hla_pe.sorted.bam.bai"
+                test2_paired_end_sorted_bam                    = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.sorted.bam"
+                test2_paired_end_sorted_bam_bai                = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.sorted.bam.bai"
+                test2_paired_end_name_sorted_bam               = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.name.sorted.bam"
+                test2_paired_end_markduplicates_sorted_bam     = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.markduplicates.sorted.bam"
+                test2_paired_end_markduplicates_sorted_bam_bai = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.markduplicates.sorted.bam.bai"
+                test2_paired_end_recalibrated_sorted_bam       = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.recalibrated.sorted.bam"
+                test2_paired_end_recalibrated_sorted_bam_bai   = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.recalibrated.sorted.bam.bai"
+                test2_paired_end_umi_consensus_bam             = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.umi_consensus.bam"
+                test2_paired_end_umi_converted_bam             = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.umi_converted.bam"
+                test2_paired_end_umi_grouped_bam               = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.umi_grouped.bam"
+                test2_paired_end_umi_histogram_txt             = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.umi_histogram.txt"
+                test2_paired_end_umi_unsorted_bam              = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.umi_unsorted.bam"
+                test2_paired_end_umi_unsorted_tagged_bam       = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.unsorted_tagged.bam"
 
-                test2_paired_end_sorted_bam                             = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.sorted.bam"
-                test2_paired_end_sorted_bam_bai                         = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.sorted.bam.bai"
-                test2_paired_end_name_sorted_bam                        = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.name.sorted.bam"
-                test2_paired_end_markduplicates_sorted_bam              = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.markduplicates.sorted.bam"
-                test2_paired_end_markduplicates_sorted_bam_bai          = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.markduplicates.sorted.bam.bai"
-                test2_paired_end_recalibrated_sorted_bam                = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.recalibrated.sorted.bam"
-                test2_paired_end_recalibrated_sorted_bam_bai            = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.recalibrated.sorted.bam.bai"
-                test2_paired_end_umi_consensus_bam                      = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.umi_consensus.bam"
-                test2_paired_end_umi_converted_bam                      = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.umi_converted.bam"
-                test2_paired_end_umi_grouped_bam                        = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.umi_grouped.bam"
-                test2_paired_end_umi_histogram_txt                      = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.umi_histogram.txt"
-                test2_paired_end_umi_unsorted_bam                       = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.umi_unsorted.bam"
-                test2_paired_end_umi_unsorted_tagged_bam                = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.unsorted_tagged.bam"
 
-                mitochon_standin_recalibrated_sorted_bam                = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/mitochon_standin.recalibrated.sorted.bam"
-                mitochon_standin_recalibrated_sorted_bam_bai            = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/mitochon_standin.recalibrated.sorted.bam.bai"
+                mitochon_standin_recalibrated_sorted_bam       = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/mitochon_standin.recalibrated.sorted.bam"
+                mitochon_standin_recalibrated_sorted_bam_bai   = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/mitochon_standin.recalibrated.sorted.bam.bai"
 
-                test_paired_end_sorted_cram                             = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test.paired_end.sorted.cram"
-                test_paired_end_sorted_cram_crai                        = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test.paired_end.sorted.cram.crai"
-                test_paired_end_markduplicates_sorted_cram              = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test.paired_end.markduplicates.sorted.cram"
-                test_paired_end_markduplicates_sorted_cram_crai         = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test.paired_end.markduplicates.sorted.cram.crai"
-                test_paired_end_recalibrated_sorted_cram                = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test.paired_end.recalibrated.sorted.cram"
-                test_paired_end_recalibrated_sorted_cram_crai           = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test.paired_end.recalibrated.sorted.cram.crai"
+                test_paired_end_sorted_cram                      = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test.paired_end.sorted.cram"
+                test_paired_end_sorted_cram_crai                 = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test.paired_end.sorted.cram.crai"
+                test_paired_end_markduplicates_sorted_cram       = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test.paired_end.markduplicates.sorted.cram"
+                test_paired_end_markduplicates_sorted_cram_crai  = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test.paired_end.markduplicates.sorted.cram.crai"
+                test_paired_end_recalibrated_sorted_cram         = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test.paired_end.recalibrated.sorted.cram"
+                test_paired_end_recalibrated_sorted_cram_crai    = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test.paired_end.recalibrated.sorted.cram.crai"
 
-                test2_paired_end_sorted_cram                            = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test2.paired_end.sorted.cram"
-                test2_paired_end_sorted_cram_crai                       = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test2.paired_end.sorted.cram.crai"
-                test2_paired_end_markduplicates_sorted_cram             = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test2.paired_end.markduplicates.sorted.cram"
-                test2_paired_end_markduplicates_sorted_cram_crai        = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test2.paired_end.markduplicates.sorted.cram.crai"
-                test2_paired_end_recalibrated_sorted_cram               = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test2.paired_end.recalibrated.sorted.cram"
-                test2_paired_end_recalibrated_sorted_cram_crai          = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test2.paired_end.recalibrated.sorted.cram.crai"
+                test2_paired_end_sorted_cram                     = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test2.paired_end.sorted.cram"
+                test2_paired_end_sorted_cram_crai                = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test2.paired_end.sorted.cram.crai"
+                test2_paired_end_markduplicates_sorted_cram      = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test2.paired_end.markduplicates.sorted.cram"
+                test2_paired_end_markduplicates_sorted_cram_crai = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test2.paired_end.markduplicates.sorted.cram.crai"
+                test2_paired_end_recalibrated_sorted_cram        = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test2.paired_end.recalibrated.sorted.cram"
+                test2_paired_end_recalibrated_sorted_cram_crai   = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test2.paired_end.recalibrated.sorted.cram.crai"
 
-                test_1_fastq_gz                                         = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test_1.fastq.gz"
-                test_2_fastq_gz                                         = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test_2.fastq.gz"
-                test_umi_1_fastq_gz                                     = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test.umi_1.fastq.gz"
-                test_umi_2_fastq_gz                                     = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test.umi_2.fastq.gz"
-                test2_1_fastq_gz                                        = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2_1.fastq.gz"
-                test2_2_fastq_gz                                        = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2_2.fastq.gz"
-                test2_umi_1_fastq_gz                                    = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2.umi_1.fastq.gz"
-                test2_umi_2_fastq_gz                                    = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2.umi_2.fastq.gz"
-                test_rnaseq_1_fastq_gz                                  = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test_rnaseq_1.fastq.gz"
-                test_rnaseq_2_fastq_gz                                  = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test_rnaseq_2.fastq.gz"
+                test_1_fastq_gz                                = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test_1.fastq.gz"
+                test_2_fastq_gz                                = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test_2.fastq.gz"
+                test_umi_1_fastq_gz                            = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test.umi_1.fastq.gz"
+                test_umi_2_fastq_gz                            = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test.umi_2.fastq.gz"
+                test2_1_fastq_gz                               = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2_1.fastq.gz"
+                test2_2_fastq_gz                               = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2_2.fastq.gz"
+                test2_umi_1_fastq_gz                           = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2.umi_1.fastq.gz"
+                test2_umi_2_fastq_gz                           = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2.umi_2.fastq.gz"
+                test_rnaseq_1_fastq_gz                         = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test_rnaseq_1.fastq.gz"
+                test_rnaseq_2_fastq_gz                         = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test_rnaseq_2.fastq.gz"
 
-                test_baserecalibrator_table                             = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test.baserecalibrator.table"
-                test2_baserecalibrator_table                            = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test2.baserecalibrator.table"
-                test_pileups_table                                      = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test.pileups.table"
-                test2_pileups_table                                     = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test2.pileups.table"
+                test_baserecalibrator_table                    = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test.baserecalibrator.table"
+                test2_baserecalibrator_table                   = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test2.baserecalibrator.table"
+                test_pileups_table                             = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test.pileups.table"
+                test2_pileups_table                            = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test2.pileups.table"
 
-                test_genomicsdb_tar_gz                                  = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_genomicsdb.tar.gz"
-                test_pon_genomicsdb_tar_gz                              = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_pon_genomicsdb.tar.gz"
+                test_genomicsdb_tar_gz                         = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_genomicsdb.tar.gz"
+                test_pon_genomicsdb_tar_gz                     = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_pon_genomicsdb.tar.gz"
 
-                test2_haplotc_ann_vcf_gz                                = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test2_haplotc.ann.vcf.gz"
-                test2_haplotc_ann_vcf_gz_tbi                            = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test2_haplotc.ann.vcf.gz.tbi"
+                test2_haplotc_ann_vcf_gz                       = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test2_haplotc.ann.vcf.gz"
+                test2_haplotc_ann_vcf_gz_tbi                   = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test2_haplotc.ann.vcf.gz.tbi"
 
-                test2_recal                                             = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2.recal"
-                test2_recal_idx                                         = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2.recal.idx"
-                test2_tranches                                          = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2.tranches"
-                test2_allele_specific_recal                             = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2_allele_specific.recal"
-                test2_allele_specific_recal_idx                         = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2_allele_specific.recal.idx"
-                test2_allele_specific_tranches                          = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2_allele_specific.tranches"
+                test2_haplotc_vcf_gz                           = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test2_haplotc.vcf.gz"
+                test2_haplotc_vcf_gz_tbi                       = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test2_haplotc.vcf.gz.tbi"
 
-                test_test2_paired_mutect2_calls_vcf_gz                  = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.vcf.gz"
-                test_test2_paired_mutect2_calls_vcf_gz_tbi              = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.vcf.gz.tbi"
-                test_test2_paired_mutect2_calls_vcf_gz_stats            = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.vcf.gz.stats"
-                test_test2_paired_mutect2_calls_f1r2_tar_gz             = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.f1r2.tar.gz"
-                test_test2_paired_mutect2_calls_artifact_prior_tar_gz   = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_test2_paired_mutect2_calls.artifact-prior.tar.gz"
-                test_test2_paired_segmentation_table                    = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_test2_paired.segmentation.table"
-                test_test2_paired_contamination_table                   = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_test2_paired.contamination.table"
+                test2_recal                                    = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2.recal"
+                test2_recal_idx                                = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2.recal.idx"
+                test2_tranches                                 = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2.tranches"
+                test2_allele_specific_recal                    = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2_allele_specific.recal"
+                test2_allele_specific_recal_idx                = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2_allele_specific.recal.idx"
+                test2_allele_specific_tranches                 = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2_allele_specific.tranches"
 
-                test_genome_vcf                                         = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test.genome.vcf"
-                test_genome_vcf_gz                                      = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test.genome.vcf.gz"
-                test_genome_vcf_gz_tbi                                  = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test.genome.vcf.gz.tbi"
-                test_genome_vcf_idx                                     = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test.genome.vcf.idx"
+                test_test2_paired_mutect2_calls_vcf_gz         = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.vcf.gz"
+                test_test2_paired_mutect2_calls_vcf_gz_tbi     = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.vcf.gz.tbi"
+                test_test2_paired_mutect2_calls_vcf_gz_stats   = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.vcf.gz.stats"
+                test_test2_paired_mutect2_calls_f1r2_tar_gz    = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.f1r2.tar.gz"
+                test_test2_paired_mutect2_calls_artifact_prior_tar_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_test2_paired_mutect2_calls.artifact-prior.tar.gz"
+                test_test2_paired_segmentation_table           = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_test2_paired.segmentation.table"
+                test_test2_paired_contamination_table          = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_test2_paired.contamination.table"
 
-                test2_genome_vcf                                        = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test2.genome.vcf"
-                test2_genome_vcf_gz                                     = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test2.genome.vcf.gz"
-                test2_genome_vcf_gz_tbi                                 = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test2.genome.vcf.gz.tbi"
-                test2_genome_vcf_idx                                    = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test2.genome.vcf.idx"
+                test_genome_vcf                                = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test.genome.vcf"
+                test_genome_vcf_gz                             = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test.genome.vcf.gz"
+                test_genome_vcf_gz_tbi                         = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test.genome.vcf.gz.tbi"
+                test_genome_vcf_idx                            = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test.genome.vcf.idx"
 
-                test_genome21_indels_vcf_gz                             = "${test_data_dir}/genomics/homo_sapiens/illumina/vcf/test.genome_21.somatic_sv.vcf.gz"
-                test_genome21_indels_vcf_gz_tbi                         = "${test_data_dir}/genomics/homo_sapiens/illumina/vcf/test.genome_21.somatic_sv.vcf.gz.tbi"
+                test2_genome_vcf                               = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test2.genome.vcf"
+                test2_genome_vcf_gz                            = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test2.genome.vcf.gz"
+                test2_genome_vcf_gz_tbi                        = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test2.genome.vcf.gz.tbi"
+                test2_genome_vcf_idx                           = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test2.genome.vcf.idx"
 
-                test_mpileup                                            = "${test_data_dir}/genomics/homo_sapiens/illumina/mpileup/test.mpileup.gz"
-                test2_mpileup                                           = "${test_data_dir}/genomics/homo_sapiens/illumina/mpileup/test2.mpileup.gz"
+                test_genome21_indels_vcf_gz                    = "${test_data_dir}/genomics/homo_sapiens/illumina/vcf/test.genome_21.somatic_sv.vcf.gz"
+                test_genome21_indels_vcf_gz_tbi                = "${test_data_dir}/genomics/homo_sapiens/illumina/vcf/test.genome_21.somatic_sv.vcf.gz.tbi"
 
-                test_broadpeak                                          = "${test_data_dir}/genomics/homo_sapiens/illumina/broadpeak/test.broadPeak"
-                test2_broadpeak                                         = "${test_data_dir}/genomics/homo_sapiens/illumina/broadpeak/test2.broadPeak"
+                test_mpileup                                   = "${test_data_dir}/genomics/homo_sapiens/illumina/mpileup/test.mpileup.gz"
+                test2_mpileup                                  = "${test_data_dir}/genomics/homo_sapiens/illumina/mpileup/test2.mpileup.gz"
 
-                test_narrowpeak                                         = "${test_data_dir}/genomics/homo_sapiens/illumina/narrowpeak/test.narrowPeak"
-                test2_narrowpeak                                        = "${test_data_dir}/genomics/homo_sapiens/illumina/narrowpeak/test2.narrowPeak"
+                test_broadpeak                                 = "${test_data_dir}/genomics/homo_sapiens/illumina/broadpeak/test.broadPeak"
+                test2_broadpeak                                = "${test_data_dir}/genomics/homo_sapiens/illumina/broadpeak/test2.broadPeak"
 
-                test_10x_1_fastq_gz                                     = "${test_data_dir}/genomics/homo_sapiens/illumina/10xgenomics/test_10x_S1_L001_R1_001.fastq.gz"
-                test_10x_2_fastq_gz                                     = "${test_data_dir}/genomics/homo_sapiens/illumina/10xgenomics/test_10x_S1_L001_R2_001.fastq.gz"
+                test_narrowpeak                                = "${test_data_dir}/genomics/homo_sapiens/illumina/narrowpeak/test.narrowPeak"
+                test2_narrowpeak                               = "${test_data_dir}/genomics/homo_sapiens/illumina/narrowpeak/test2.narrowPeak"
 
-                test_yak                                                = "${test_data_dir}/genomics/homo_sapiens/illumina/yak/test.yak"
-                test2_yak                                               = "${test_data_dir}/genomics/homo_sapiens/illumina/yak/test2.yak"
+                test_10x_1_fastq_gz                           = "${test_data_dir}/genomics/homo_sapiens/illumina/10xgenomics/test_10x_S1_L001_R1_001.fastq.gz"
+                test_10x_2_fastq_gz                           = "${test_data_dir}/genomics/homo_sapiens/illumina/10xgenomics/test_10x_S1_L001_R2_001.fastq.gz"
 
-                cutandrun_bedgraph_test_1                               = "${test_data_dir}/genomics/homo_sapiens/illumina/bedgraph/cutandtag_h3k27me3_test_1.bedGraph"
-                cutandrun_bedgraph_test_2                               = "${test_data_dir}/genomics/homo_sapiens/illumina/bedgraph/cutandtag_igg_test_1.bedGraph"
+                test_yak                                      = "${test_data_dir}/genomics/homo_sapiens/illumina/yak/test.yak"
+                test2_yak                                     = "${test_data_dir}/genomics/homo_sapiens/illumina/yak/test2.yak"
 
-                test_rnaseq_vcf                                         =  "${test_data_dir}/genomics/homo_sapiens/illumina/vcf/test.rnaseq.vcf"
-                test_sv_vcf                                             =  "${test_data_dir}/genomics/homo_sapiens/illumina/vcf/sv_query.vcf.gz"
+                cutandrun_bedgraph_test_1                     = "${test_data_dir}/genomics/homo_sapiens/illumina/bedgraph/cutandtag_h3k27me3_test_1.bedGraph"
+                cutandrun_bedgraph_test_2                     = "${test_data_dir}/genomics/homo_sapiens/illumina/bedgraph/cutandtag_igg_test_1.bedGraph"
 
-                test_pytor                                              = "${test_data_dir}/genomics/homo_sapiens/illumina/pytor/test.pytor"
+                test_rnaseq_vcf                               =  "${test_data_dir}/genomics/homo_sapiens/illumina/vcf/test.rnaseq.vcf"
+                test_sv_vcf                                   =  "${test_data_dir}/genomics/homo_sapiens/illumina/vcf/sv_query.vcf.gz"
+
+                test_pytor                                    = "${test_data_dir}/genomics/homo_sapiens/illumina/pytor/test.pytor"
             }
             'pacbio' {
                 primers                         = "${test_data_dir}/genomics/homo_sapiens/pacbio/fasta/primers.fasta"
@@ -378,7 +382,7 @@ params {
                 test3_gff                       = "${test_data_dir}/genomics/prokaryotes/candidatus_portiera_aleyrodidarum/genome/gff/test3.gff"
             }
             'illumina' {
-                test_1_fastq_gz                 = "${test_data_dir}/genomics/prokaryotes/candidatus_portiera_aleyrodidarum/illumina/fasta/test_1.fastq.gz"
+                test_1_fastq_gz                 = "${test_data_dir}/genomics/prokaryotes/candidatus_portiera_aleyrodidarum/illumina/fastq/test_1.fastq.gz"
                 test_2_fastq_gz                 = "${test_data_dir}/genomics/prokaryotes/candidatus_portiera_aleyrodidarum/illumina/fastq/test_2.fastq.gz"
                 test_se_fastq_gz                = "${test_data_dir}/genomics/prokaryotes/candidatus_portiera_aleyrodidarum/illumina/fastq/test_se.fastq.gz"
             }
@@ -422,6 +426,21 @@ params {
                 test_merge_cool_cp2             = "${test_data_dir}/genomics/homo_sapiens/cooler/merge/toy/toy.symm.upper.2.cp2.cool"
 
             }
+            'config' {
+                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/arriba/main.nf

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

tests/modules/arriba/test.yml

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

tests/modules/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

@@ -1,4 +1,4 @@
-- name: bowtie2 align single-end
+- 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
@@ -6,78 +6,44 @@
   files:
     - path: ./output/bowtie2/test.bam
     - path: ./output/bowtie2/test.bowtie2.log
-    - path: ./output/bowtie2/bowtie2/genome.3.bt2
-      md5sum: 4ed93abba181d8dfab2e303e33114777
-    - path: ./output/bowtie2/bowtie2/genome.2.bt2
-      md5sum: 47b153cd1319abc88dda532462651fcf
-    - path: ./output/bowtie2/bowtie2/genome.1.bt2
-      md5sum: cbe3d0bbea55bc57c99b4bfa25b5fbdf
-    - path: ./output/bowtie2/bowtie2/genome.4.bt2
-      md5sum: c25be5f8b0378abf7a58c8a880b87626
-    - path: ./output/bowtie2/bowtie2/genome.rev.1.bt2
-      md5sum: 52be6950579598a990570fbcf5372184
-    - path: ./output/bowtie2/bowtie2/genome.rev.2.bt2
-      md5sum: e3b4ef343dea4dd571642010a7d09597
+    - path: ./output/bowtie2/versions.yml
 
-- name: 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
+- 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/bowtie2/genome.3.bt2
-      md5sum: 4ed93abba181d8dfab2e303e33114777
-    - path: ./output/bowtie2/bowtie2/genome.2.bt2
-      md5sum: 47b153cd1319abc88dda532462651fcf
-    - path: ./output/bowtie2/bowtie2/genome.1.bt2
-      md5sum: cbe3d0bbea55bc57c99b4bfa25b5fbdf
-    - path: ./output/bowtie2/bowtie2/genome.4.bt2
-      md5sum: c25be5f8b0378abf7a58c8a880b87626
-    - path: ./output/bowtie2/bowtie2/genome.rev.1.bt2
-      md5sum: 52be6950579598a990570fbcf5372184
-    - path: ./output/bowtie2/bowtie2/genome.rev.2.bt2
-      md5sum: e3b4ef343dea4dd571642010a7d09597
+    - path: ./output/bowtie2/versions.yml
 
-- name: bowtie2 align single-end large-index
-  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 --force_large_index
+- 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
   tags:
     - bowtie2
     - bowtie2/align
   files:
     - path: ./output/bowtie2/test.bam
     - path: ./output/bowtie2/test.bowtie2.log
-    - path: ./output/bowtie2/bowtie2/genome.3.bt2l
-      md5sum: 8952b3e0b1ce9a7a5916f2e147180853
-    - path: ./output/bowtie2/bowtie2/genome.2.bt2l
-      md5sum: 22c284084784a0720989595e0c9461fd
-    - path: ./output/bowtie2/bowtie2/genome.1.bt2l
-      md5sum: 07d811cd4e350d56267183d2ac7023a5
-    - path: ./output/bowtie2/bowtie2/genome.4.bt2l
-      md5sum: c25be5f8b0378abf7a58c8a880b87626
-    - path: ./output/bowtie2/bowtie2/genome.rev.1.bt2l
-      md5sum: fda48e35925fb24d1c0785f021981e25
-    - path: ./output/bowtie2/bowtie2/genome.rev.2.bt2l
-      md5sum: 802c26d32b970e1b105032b7ce7348b4
+    - path: ./output/bowtie2/versions.yml
 
-- name: bowtie2 align paired-end large-index
-  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 --force_large_index
+- 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/bowtie2/genome.3.bt2l
-      md5sum: 8952b3e0b1ce9a7a5916f2e147180853
-    - path: ./output/bowtie2/bowtie2/genome.2.bt2l
-      md5sum: 22c284084784a0720989595e0c9461fd
-    - path: ./output/bowtie2/bowtie2/genome.1.bt2l
-      md5sum: 07d811cd4e350d56267183d2ac7023a5
-    - path: ./output/bowtie2/bowtie2/genome.4.bt2l
-      md5sum: c25be5f8b0378abf7a58c8a880b87626
-    - path: ./output/bowtie2/bowtie2/genome.rev.1.bt2l
-      md5sum: fda48e35925fb24d1c0785f021981e25
-    - path: ./output/bowtie2/bowtie2/genome.rev.2.bt2l
-      md5sum: 802c26d32b970e1b105032b7ce7348b4
+    - 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/custom/sratoolsncbisettings/main.nf

@@ -0,0 +1,44 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CUSTOM_SRATOOLSNCBISETTINGS } from '../../../../modules/custom/sratoolsncbisettings/main.nf'
+
+workflow test_sratoolsncbisettings_with_good_existing {
+
+    file(params.settings_path).mkdirs()
+    def settings = file(params.test_data['generic']['config']['ncbi_user_settings'], checkIfExists: true)
+    settings.copyTo(params.settings_file)
+
+    CUSTOM_SRATOOLSNCBISETTINGS()
+}
+
+workflow test_sratoolsncbisettings_with_bad_existing {
+
+    file(params.settings_path).mkdirs()
+    def settings = file(params.settings_file)
+    settings.text = '''
+    ## auto-generated configuration file - DO NOT EDIT ##
+
+    config/default = "false"
+    /repository/remote/main/CGI/resolver-cgi = "https://trace.ncbi.nlm.nih.gov/Traces/names/names.fcgi"
+    /repository/remote/protected/CGI/resolver-cgi = "https://trace.ncbi.nlm.nih.gov/Traces/names/names.fcgi"
+    /repository/user/ad/public/apps/file/volumes/flatAd = "."
+    /repository/user/ad/public/apps/refseq/volumes/refseqAd = "."
+    /repository/user/ad/public/apps/sra/volumes/sraAd = "."
+    /repository/user/ad/public/apps/sraPileup/volumes/ad = "."
+    /repository/user/ad/public/apps/sraRealign/volumes/ad = "."
+    /repository/user/ad/public/apps/wgs/volumes/wgsAd = "."
+    /repository/user/ad/public/root = "."
+    /repository/user/default-path = "/root/ncbi"
+    '''.stripIndent()
+
+    CUSTOM_SRATOOLSNCBISETTINGS()
+}
+
+workflow test_sratoolsncbisettings_with_nonexisting {
+    def settings = file(params.settings_file)
+    settings.delete()
+
+    CUSTOM_SRATOOLSNCBISETTINGS()
+}

tests/modules/custom/sratoolsncbisettings/nextflow.config

@@ -0,0 +1,8 @@
+params.settings_path = '/tmp/.ncbi'
+params.settings_file = "${params.settings_path}/user-settings.mkfg"
+
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+}

tests/modules/custom/sratoolsncbisettings/nextflow_mount.config

@@ -0,0 +1,17 @@
+params.settings_path = '/tmp/.ncbi'
+params.settings_file = "${params.settings_path}/user-settings.mkfg"
+
+env.NCBI_SETTINGS = params.settings_file
+
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName: CUSTOM_SRATOOLSNCBISETTINGS {
+        containerOptions = {
+            (workflow.containerEngine == 'singularity') ?
+            "-B ${params.settings_path}:${params.settings_path}" :
+            "-v ${params.settings_path}:${params.settings_path}"
+        }
+    }
+}

tests/modules/custom/sratoolsncbisettings/test.yml

@@ -0,0 +1,44 @@
+- name: "custom sratoolsncbisettings test_sratoolsncbisettings_with_good_existing"
+  command: nextflow run ./tests/modules/custom/sratoolsncbisettings -entry test_sratoolsncbisettings_with_good_existing -c ./tests/config/nextflow.config -c ./tests/modules/custom/sratoolsncbisettings/nextflow_mount.config
+  tags:
+    - "custom"
+    - "custom/sratoolsncbisettings"
+  files:
+    - path: "output/custom/user-settings.mkfg"
+      md5sum: 955e27aff2c277c2f1f0943a098888c1
+    - path: output/custom/versions.yml
+      contains:
+        - "sratools: 2.11.0"
+
+- name: "custom sratoolsncbisettings test_sratoolsncbisettings_with_bad_existing"
+  command: nextflow run ./tests/modules/custom/sratoolsncbisettings -entry test_sratoolsncbisettings_with_bad_existing -c ./tests/config/nextflow.config -c ./tests/modules/custom/sratoolsncbisettings/nextflow_mount.config
+  tags:
+    - "custom"
+    - "custom/sratoolsncbisettings"
+  exit_code: 1
+  stdout:
+    contains:
+      - "Command error:"
+      - "missing the required entries"
+      - "/LIBS/GUID"
+      - "/libs/cloud/report_instance_identity"
+      - "Feel free to add the following"
+  files:
+    - path: "output/custom/user-settings.mkfg"
+      should_exist: false
+    - path: output/custom/versions.yml
+      should_exist: false
+
+- name: "custom sratoolsncbisettings test_sratoolsncbisettings_with_nonexisting"
+  command: nextflow run ./tests/modules/custom/sratoolsncbisettings -entry test_sratoolsncbisettings_with_nonexisting -c ./tests/config/nextflow.config -c ./tests/modules/custom/sratoolsncbisettings/nextflow.config
+  tags:
+    - "custom"
+    - "custom/sratoolsncbisettings"
+  files:
+    - path: "output/custom/user-settings.mkfg"
+      contains:
+        - "/LIBS/GUID"
+        - "/libs/cloud/report_instance_identity"
+    - path: output/custom/versions.yml
+      contains:
+        - "sratools: 2.11.0"

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/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