Merge branch 'nf-core:master' into maxquant

.gitpod.yml

@@ -1,10 +1,14 @@
-# List the start up tasks. Learn more https://www.gitpod.io/docs/config-start-tasks/
+image: nfcore/gitpod:latest
-tasks:
-  - name: Install Nextflow
-    init: |
-      curl -s https://get.nextflow.io | bash
-      sudo mv nextflow /usr/local/bin
 
-  - name: Install pytest-workflow
+vscode:
-    init: |
+  extensions: # based on nf-core.nf-core-extensionpack
-      pip install pytest-workflow
+    - codezombiech.gitignore                 # Language support for .gitignore files
+    # - cssho.vscode-svgviewer                 # SVG viewer
+    - davidanson.vscode-markdownlint         # Markdown/CommonMark linting and style checking for Visual Studio Code
+    - eamodio.gitlens                        # Quickly glimpse into whom, why, and when a line or code block was changed
+    - EditorConfig.EditorConfig              # override user/workspace settings with settings found in .editorconfig files
+    - Gruntfuggly.todo-tree                  # Display TODO and FIXME in a tree view in the activity bar
+    - mechatroner.rainbow-csv                # Highlight columns in csv files in different colors
+    # - nextflow.nextflow                      # Nextflow syntax highlighting
+    - oderwat.indent-rainbow                 # Highlight indentation level
+    - streetsidesoftware.code-spell-checker  # Spelling checker for source code

.nf-core.yml

@@ -1,3 +1,4 @@
+repository_type: modules
 bump-versions:
   rseqc/junctionannotation: False
   rseqc/bamstat: False

modules/bamcmp/main.nf

@@ -0,0 +1,35 @@
+def VERSION = '2.2'
+process BAMCMP {
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::bamcmp=2.2" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/bamcmp:2.2--h05f6578_0' :
+        'quay.io/biocontainers/bamcmp:2.2--h05f6578_0' }"
+
+    input:
+    tuple val(meta), path(sample), path(contaminant)
+
+    output:
+    tuple val(meta), path("*primary.bam")      , emit: bam
+    tuple val(meta), path("*contamination.bam"), emit: contamination_bam
+    path "versions.yml"                        , emit: versions
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    bamcmp \\
+        -1 $sample \\
+        -2 $contaminant \\
+        -A ${prefix}_primary.bam \\
+        -B ${prefix}_contamination.bam \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bamcmp: $VERSION
+    END_VERSIONS
+    """
+
+}

modules/bamcmp/meta.yml

@@ -0,0 +1,57 @@
+name: bamcmp
+description: Bamcmp (Bam Compare) is a tool for assigning reads between a primary genome and a contamination genome. For instance, filtering out mouse reads from patient derived xenograft mouse models (PDX).
+keywords:
+  - filter
+  - xenograft
+  - host
+  - graft
+  - contamination
+  - mouse
+
+tools:
+  - bamcmp:
+      description: Bamcmp is a tool for deconvolving host and graft reads, using two bam files. Reads should be mapped to two genomes, and the mapped,
+                    sorted bam files supplied to the tool. It is highly recommended to use the "-s as" option not the "-s mapq" option, else
+                    reads which multimap to the contamination genome will be spuriously kept.
+      homepage: https://github.com/CRUKMI-ComputationalBiology/bamcmp
+      documentation: https://github.com/CRUKMI-ComputationalBiology/bamcmp
+      tool_dev_url: https://github.com/CRUKMI-ComputationalBiology/bamcmp
+      doi: "10.1158/1541-7786.MCR-16-0431"
+      licence: ['GPL v3']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test']
+
+  - sample:
+      type: file
+      description: BAM/CRAM/SAM file with the reads aligned to the primary genome (the one you want to keep)
+      pattern: "*.{bam,cram,sam}"
+
+  - contaminant:
+      type: file
+      description: BAM/CRAM/SAM file with the reads aligned to the contaminant genome (the one you want to filter out)
+      pattern: "*.{bam,cram,sam}"
+
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+  - bam:
+      type: file
+      description: Bam file containing the reads which align better to the primary genome.
+      pattern: "*.{bam,cram,sam}"
+
+  - bam:
+      type: file
+      description: Bam file containing the reads which align better to the contaminant genome.
+      pattern: "*.{bam,cram,sam}"
+
+authors:
+  - "@kmurat1"
+  - "@sppearce"

modules/bcftools/query/main.nf

@@ -8,30 +8,29 @@ process BCFTOOLS_QUERY {
         'quay.io/biocontainers/bcftools:1.14--h88f3f91_0' }"
 
     input:
-    tuple val(meta), path(vcf), path(index)
+    tuple val(meta), path(vcf), path(tbi)
-    path(regions)
+    path regions
-    path(targets)
+    path targets
-    path(samples)
+    path samples
 
     output:
-    tuple val(meta), path("*.gz") , emit: vcf
+    tuple val(meta), path("*.txt"), emit: txt
     path "versions.yml"           , emit: versions
 
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def regions_file  = regions ? "--regions-file ${regions}" : ""
+    def regions_file = regions ? "--regions-file ${regions}" : ""
     def targets_file = targets ? "--targets-file ${targets}" : ""
     def samples_file =  samples ? "--samples-file ${samples}" : ""
-
     """
     bcftools query \\
-        --output ${prefix}.vcf.gz \\
+        --output ${prefix}.txt \\
-        ${regions_file} \\
+        $regions_file \\
-        ${targets_file} \\
+        $targets_file \\
-        ${samples_file} \\
+        $samples_file \\
         $args \\
-        ${vcf}
+        $vcf
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/bcftools/query/meta.yml

@@ -23,22 +23,20 @@ input:
         type: file
         description: |
           The vcf file to be qeuried.
-          e.g. 'file.vcf'
+        pattern: "*.{vcf.gz, vcf}"
-    - index:
+    - tbi:
         type: file
         description: |
           The tab index for the VCF file to be inspected.
-          e.g. 'file.tbi'
+        pattern: "*.tbi"
     - regions:
         type: file
         description: |
           Optionally, restrict the operation to regions listed in this file.
-          e.g. 'file.vcf'
     - targets:
         type: file
         description: |
           Optionally, restrict the operation to regions listed in this file (doesn't rely upon index files)
-          e.g. 'file.vcf'
     - samples:
         type: file
         description: |
@@ -50,13 +48,14 @@ output:
         description: |
           Groovy Map containing sample information
           e.g. [ id:'test', single_end:false ]
-    - vcf:
+    - txt:
         type: file
-        description: VCF query output file
+        description: BCFTools query output file
-        pattern: "*.{vcf.gz}"
+        pattern: "*.txt"
     - versions:
         type: file
         description: File containing software versions
         pattern: "versions.yml"
 authors:
   - "@abhi18av"
+  - "@drpatelh"

modules/freebayes/main.nf

@@ -41,7 +41,7 @@ process FREEBAYES {
             $args \\
             $input > ${prefix}.vcf
 
-        gzip --no-name ${prefix}.vcf
+        bgzip ${prefix}.vcf
 
         cat <<-END_VERSIONS > versions.yml
         "${task.process}":
@@ -60,7 +60,7 @@ process FREEBAYES {
             $args \\
             $input > ${prefix}.vcf
 
-        gzip --no-name ${prefix}.vcf
+        bgzip ${prefix}.vcf
 
         cat <<-END_VERSIONS > versions.yml
         "${task.process}":

modules/nextclade/datasetget/main.nf

@@ -2,10 +2,10 @@ process NEXTCLADE_DATASETGET {
     tag "$dataset"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::nextclade=1.10.1" : null)
+    conda (params.enable_conda ? "bioconda::nextclade=1.10.2" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/nextclade:1.10.1--h9ee0642_0' :
+        'https://depot.galaxyproject.org/singularity/nextclade:1.10.2--h9ee0642_0' :
-        'quay.io/biocontainers/nextclade:1.10.1--h9ee0642_0' }"
+        'quay.io/biocontainers/nextclade:1.10.2--h9ee0642_0' }"
 
     input:
     val dataset

modules/nextclade/run/main.nf

@@ -2,10 +2,10 @@ process NEXTCLADE_RUN {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::nextclade=1.10.1" : null)
+    conda (params.enable_conda ? "bioconda::nextclade=1.10.2" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/nextclade:1.10.1--h9ee0642_0' :
+        'https://depot.galaxyproject.org/singularity/nextclade:1.10.2--h9ee0642_0' :
-        'quay.io/biocontainers/nextclade:1.10.1--h9ee0642_0' }"
+        'quay.io/biocontainers/nextclade:1.10.2--h9ee0642_0' }"
 
     input:
     tuple val(meta), path(fasta)

modules/pangolin/main.nf

@@ -2,10 +2,10 @@ process PANGOLIN {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? 'bioconda::pangolin=3.1.17' : null)
+    conda (params.enable_conda ? 'bioconda::pangolin=3.1.19' : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/pangolin:3.1.17--pyhdfd78af_0' :
+        'https://depot.galaxyproject.org/singularity/pangolin:3.1.19--pyhdfd78af_0' :
-        'quay.io/biocontainers/pangolin:3.1.17--pyhdfd78af_0' }"
+        'quay.io/biocontainers/pangolin:3.1.19--pyhdfd78af_0' }"
 
     input:
     tuple val(meta), path(fasta)

modules/raven/main.nf

@@ -0,0 +1,39 @@
+process RAVEN {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::raven-assembler=1.6.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/raven-assembler:1.6.1--h2e03b76_0' :
+        'quay.io/biocontainers/raven-assembler:1.6.1--h2e03b76_0' }"
+
+    input:
+    tuple val(meta), path(reads)
+
+    output:
+    tuple val(meta), path("*.fasta.gz"), emit: fasta
+    tuple val(meta), path("*.gfa.gz")  , emit: gfa
+    path "versions.yml"                , emit: versions
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    # run tool
+    raven \\
+        -t $task.cpus \\
+        --graphical-fragment-assembly ${prefix}.gfa \\
+        $args \\
+        $reads | \\
+        gzip -c > ${prefix}.fasta.gz
+
+    # compress assembly graph
+    gzip -c ${prefix}.gfa > ${prefix}.gfa.gz
+
+    # get tool version
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        raven: \$( raven --version )
+    END_VERSIONS
+    """
+}

modules/raven/meta.yml

@@ -0,0 +1,47 @@
+name: raven
+description: De novo genome assembler for long uncorrected reads.
+keywords:
+  - de novo
+  - assembly
+  - genome
+  - genome assembler
+  - long uncorrected reads
+tools:
+  - raven:
+      description: Raven is a de novo genome assembler for long uncorrected reads.
+      homepage: https://github.com/lbcb-sci/raven
+      documentation: https://github.com/lbcb-sci/raven#usage
+      tool_dev_url: https://github.com/lbcb-sci/raven
+      doi: doi.org/10.1038/s43588-021-00073-4
+      licence: ['MIT']
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', suffix:'bacteria' ]
+  - reads:
+      type: file
+      description: Input file in FASTA/FASTQ format.
+      pattern: "*.{fasta,fastq,fasta.gz,fastq.gz,fa,fq,fa.gz,fq.gz}"
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', suffix:'bacteria' ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - fasta:
+      type: file
+      description: Assembled FASTA file
+      pattern: "*.fasta.gz"
+  - gfa:
+      type: file
+      description: Repeat graph
+      pattern: "*.gfa.gz"
+
+authors:
+  - "@fmalmeida"

modules/svdb/query/main.nf

@@ -0,0 +1,34 @@
+process SVDB_QUERY {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::svdb=2.5.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/svdb:2.5.0--py39hcbe4a3b_0':
+        'quay.io/biocontainers/svdb:2.5.0--py39hcbe4a3b_0' }"
+
+    input:
+    tuple val(meta), path(vcf)
+    path (vcf_db)
+
+    output:
+    tuple val(meta), path("*_ann_svdbq.vcf"), emit: vcf
+    path "versions.yml"                     , emit: versions
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    svdb \\
+        --query \\
+        $args \\
+        --db $vcf_db \\
+        --query_vcf $vcf \\
+        >${prefix}_ann_svdbq.vcf
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        svdb: \$( echo \$(svdb) | head -1 | sed 's/usage: SVDB-\\([0-9]\\.[0-9]\\.[0-9]\\).*/\\1/' )
+    END_VERSIONS
+    """
+}

modules/svdb/query/meta.yml

@@ -0,0 +1,43 @@
+name: svdb_query
+description: Query a structural variant database, using a vcf file as query
+keywords:
+  - structural variants
+tools:
+  - svdb:
+      description: structural variant database software
+      homepage: https://github.com/J35P312/SVDB
+      documentation: https://github.com/J35P312/SVDB/blob/master/README.md
+      licence: ['MIT']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - vcf:
+      type: file
+      description: query vcf file
+      pattern: "*.{vcf,vcf.gz}"
+  - vcf_db:
+      type: file
+      description: database vcf file
+      pattern: "*.{vcf,vcf.gz}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - vcf:
+      type: file
+      description:  Annotated output VCF file
+      pattern: "*_ann_svdbq.vcf"
+
+authors:
+  - "@ramprasadn"

modules/transdecoder/longorf/main.nf

@@ -0,0 +1,37 @@
+process TRANSDECODER_LONGORF {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::transdecoder=5.5.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+    'https://depot.galaxyproject.org/singularity/transdecoder:5.5.0--pl5262hdfd78af_4' :
+    'quay.io/comp-bio-aging/transdecoder' }"
+
+    input:
+    tuple val(meta), path(fasta)
+
+    output:
+    tuple val(meta), path("${meta.id}/*.pep") , emit: pep
+    tuple val(meta), path("${meta.id}/*.gff3"), emit: gff3
+    tuple val(meta), path("${meta.id}/*.cds") , emit: cds
+    tuple val(meta), path("${meta.id}/*.dat") , emit: dat
+    path("${meta.id}/")                       , emit: folder
+    path "versions.yml"                       , emit: versions
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    TransDecoder.LongOrfs \\
+        $args \\
+        -O $prefix \\
+        -t \\
+        $fasta
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        transdecoder: \$(echo \$(TransDecoder.LongOrfs --version) | sed -e "s/TransDecoder.LongOrfs //g")
+    END_VERSIONS
+    """
+}

modules/transdecoder/longorf/meta.yml

@@ -0,0 +1,57 @@
+name: transdecoder_longorf
+description: TransDecoder itentifies candidate coding regions within transcript sequences. it is used to build gff file.
+keywords:
+  - eucaryotes
+  - gff
+tools:
+  - transdecoder:
+      description: TransDecoder identifies candidate coding regions within transcript sequences, such as those generated by de novo RNA-Seq transcript assembly using Trinity, or constructed based on RNA-Seq alignments to the genome using Tophat and Cufflinks.
+      homepage: https://github.com/TransDecoder
+      documentation: https://github.com/TransDecoder/TransDecoder/wiki
+      tool_dev_url: https://github.com/TransDecoder/TransDecoder
+      doi: ""
+      licence: ['Broad Institute']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - fasta:
+      type: file
+      description: fasta file
+      pattern: "*.{fasta}"
+
+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"
+  - pep:
+      type: Amino acids fasta file
+      description: all ORFs meeting the minimum length criteria, regardless of coding potential. file
+      pattern: "*.{pep}"
+  - gff3:
+      type: gff file
+      description: positions of all ORFs as found in the target transcripts. file
+      pattern: "*.{gff3}"
+  - cds:
+      type: fasta file
+      description: the nucleotide coding sequence for all detected ORFs. file
+      pattern: "*{cds}"
+  - dat:
+      type: tsv file
+      description: nucleotide frequencies
+      pattern: "*{dat}"
+  - folder:
+      type: folder
+      description: contains all the files from the run
+
+authors:
+  - "@Danilo2771"

modules/transdecoder/predict/main.nf

@@ -0,0 +1,37 @@
+process TRANSDECODER_PREDICT {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::transdecoder=5.5.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/transdecoder:5.5.0--pl5262hdfd78af_4':
+        'quay.io/comp-bio-aging/transdecoder' }"
+
+    input:
+    tuple val(meta), path(fasta)
+    path(fold)
+
+    output:
+    tuple val(meta), path("*.transdecoder.pep")  , emit: pep
+    tuple val(meta), path("*.transdecoder.gff3") , emit: gff3
+    tuple val(meta), path("*.transdecoder.cds")  , emit: cds
+    tuple val(meta), path("*.transdecoder.bed")  , emit: bed
+    path "versions.yml"                          , emit: versions
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    TransDecoder.Predict \\
+        $args \\
+        -O ${prefix} \\
+        -t \\
+        $fasta
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        transdecoder: \$(echo \$(TransDecoder.Predict --version) | sed -e "s/TransDecoder.Predict //g")
+    END_VERSIONS
+    """
+}

modules/transdecoder/predict/meta.yml

@@ -0,0 +1,59 @@
+name: transdecoder_predict
+description: TransDecoder identifies candidate coding regions within transcript sequences. It is used to build gff file. You can use this module after transdecoder_longorf
+keywords:
+  - eukaryotes
+  - gff
+
+tools:
+  - transdecoder:
+      description: TransDecoder identifies candidate coding regions within transcript sequences, such as those generated by de novo RNA-Seq transcript assembly using Trinity, or constructed based on RNA-Seq alignments to the genome using Tophat and Cufflinks.
+      homepage: https://github.com/TransDecoder
+      documentation: https://github.com/TransDecoder/TransDecoder/wiki
+      tool_dev_url: https://github.com/TransDecoder/TransDecoder
+      doi: ""
+      licence: ['Broad Institute']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - fasta:
+      type: file
+      description: fasta file
+      pattern: "*.{fasta}"
+  - fold:
+      type: folder
+      description: Output from the module transdecoder_longorf
+      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"
+  - pep:
+      type: amino acids fasta file
+      description: All ORFs meeting the minimum length criteria, regardless of coding potential
+      pattern: "*.{pep}"
+  - gff3:
+      type: gff3 file
+      description: Positions of all ORFs as found in the target transcripts
+      pattern: "*.{gff3}"
+  - cds:
+      type: nucleotide fasta file
+      description: the nucleotide coding sequence for all detected ORFs
+      pattern: "*{cds}"
+  - bed:
+      type: bed file
+      description: bed file
+      pattern: "*{bed}"
+
+authors:
+  - "@Danilo2771"

tests/config/pytest_modules.yml

@@ -46,6 +46,10 @@ bamaligncleaner:
   - modules/bamaligncleaner/**
   - tests/modules/bamaligncleaner/**
 
+bamcmp:
+  - modules/bamcmp/**
+  - tests/modules/bamcmp/**
+
 bamtools/convert:
   - modules/bamtools/convert/**
   - tests/modules/bamtools/convert/**
@@ -1209,6 +1213,10 @@ rasusa:
   - modules/rasusa/**
   - tests/modules/rasusa/**
 
+raven:
+  - modules/raven/**
+  - tests/modules/raven/**
+
 raxmlng:
   - modules/raxmlng/**
   - tests/modules/raxmlng/**
@@ -1437,6 +1445,10 @@ subread/featurecounts:
   - modules/subread/featurecounts/**
   - tests/modules/subread/featurecounts/**
 
+svdb/query:
+  - modules/svdb/query/**
+  - tests/modules/svdb/query/**
+
 tabix/bgzip:
   - modules/tabix/bgzip/**
   - tests/modules/tabix/bgzip/**
@@ -1453,6 +1465,10 @@ tbprofiler/profile:
   - modules/tbprofiler/profile/**
   - tests/modules/tbprofiler/profile/**
 
+test/template:
+  - modules/test/template/**
+  - tests/modules/test/template/**
+
 tiddit/cov:
   - modules/tiddit/cov/**
   - tests/modules/tiddit/cov/**
@@ -1461,6 +1477,14 @@ tiddit/sv:
   - modules/tiddit/sv/**
   - tests/modules/tiddit/sv/**
 
+transdecoder/longorf:
+  - modules/transdecoder/longorf/**
+  - tests/modules/transdecoder/longorf/**
+
+transdecoder/predict:
+  - modules/transdecoder/predict/**
+  - tests/modules/transdecoder/predict/**
+
 trimgalore:
   - modules/trimgalore/**
   - tests/modules/trimgalore/**

tests/config/test_data.config

@@ -131,6 +131,7 @@ params {
                 mills_and_1000g_indels_vcf_gz_tbi              = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/mills_and_1000G.indels.vcf.gz.tbi"
                 syntheticvcf_short_vcf_gz                      = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/syntheticvcf_short.vcf.gz"
                 syntheticvcf_short_vcf_gz_tbi                  = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/syntheticvcf_short.vcf.gz.tbi"
+                gnomad_r2_1_1_sv_vcf_gz                        = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/gnomAD.r2.1.1-sv.vcf.gz"
 
                 hapmap_3_3_hg38_21_vcf_gz                      = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/germlineresources/hapmap_3.3.hg38.vcf.gz"
                 hapmap_3_3_hg38_21_vcf_gz_tbi                  = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/germlineresources/hapmap_3.3.hg38.vcf.gz.tbi"
@@ -277,6 +278,7 @@ params {
                 cutandrun_bedgraph_test_2                     = "${test_data_dir}/genomics/homo_sapiens/illumina/bedgraph/cutandtag_igg_test_1.bedGraph"
 
                 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"
             }
             'pacbio' {
                 primers                                       = "${test_data_dir}/genomics/homo_sapiens/pacbio/fasta/primers.fasta"

tests/modules/bamcmp/main.nf

@@ -0,0 +1,36 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { BWA_INDEX } from '../../../modules/bwa/index/main.nf'
+include { BWA_MEM   } from '../../../modules/bwa/mem/main.nf'
+include { BWA_INDEX as BWA_INDEX_COV2 } from '../../../modules/bwa/index/main.nf'
+include { BWA_MEM as BWA_MEM_COV2   } from '../../../modules/bwa/mem/main.nf'
+
+include { SAMTOOLS_SORT } from '../../../modules/samtools/sort/main.nf'
+include { SAMTOOLS_SORT as SAMTOOLS_SORT_COV2   } from '../../../modules/samtools/sort/main.nf'
+
+include { BAMCMP } from '../../../modules/bamcmp/main.nf'
+
+workflow test_bamcmp {
+
+    input = [
+        [ id:'test'], // meta map
+        [ file(params.test_data['homo_sapiens']['illumina']['test_1_fastq_gz'], checkIfExists: true) ]
+    ]
+
+    fasta1 = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    fasta2 = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+
+    BWA_INDEX ( fasta1 )
+    BWA_MEM ( input, BWA_INDEX.out.index, false )
+    SAMTOOLS_SORT (BWA_MEM.out.bam)
+
+
+    BWA_INDEX_COV2 ( fasta2 )
+    BWA_MEM_COV2 ( input, BWA_INDEX_COV2.out.index, false )
+    SAMTOOLS_SORT_COV2 (BWA_MEM_COV2.out.bam)
+
+    BAMCMP (SAMTOOLS_SORT.out.bam.join(SAMTOOLS_SORT_COV2.out.bam, by: [0]))
+
+}

tests/modules/bamcmp/nextflow.config

@@ -0,0 +1,27 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName: BWA_MEM {
+        ext.prefix = "human"
+    }
+
+    withName: BWA_MEM_COV2 {
+        ext.prefix = "cov2"
+    }
+
+    withName: SAMTOOLS_SORT {
+        ext.args = '-n'
+        ext.prefix = "sorted"
+    }
+
+    withName: SAMTOOLS_SORT_COV2 {
+        ext.args = '-n'
+        ext.prefix = "sorted_cov2"
+    }
+    
+    withName: BAMCMP {
+        ext.args = '-s "as"'
+    }
+
+}

tests/modules/bamcmp/test.yml

@@ -0,0 +1,11 @@
+- name: bamcmp test_bamcmp
+  command: nextflow run tests/modules/bamcmp -entry test_bamcmp -c tests/config/nextflow.config
+  tags:
+    - bamcmp
+  files:
+    - path: output/bamcmp/test_contamination.bam
+      md5sum: 1fe730936d489c637479c1e51dd8ca55
+    - path: output/bamcmp/test_primary.bam
+      md5sum: 80b9abd8ef83e63548a9b8b82be2a034
+    - path: output/bamcmp/versions.yml
+      md5sum: 34d569665ff0459e84114e966dd3483b

tests/modules/bcftools/query/main.nf

@@ -6,26 +6,24 @@ include { BCFTOOLS_QUERY } from '../../../../modules/bcftools/query/main.nf'
 
 workflow test_bcftools_query {
 
-    regions = []
-    targets = []
-    samples = []
-
     input = [ [ id:'out' ], // meta map
              file(params.test_data['sarscov2']['illumina']['test_vcf_gz'], checkIfExists: true),
              file(params.test_data['sarscov2']['illumina']['test_vcf_gz_tbi'], checkIfExists: true)]
+    regions = []
+    targets = []
+    samples = []
 
     BCFTOOLS_QUERY ( input, regions, targets, samples )
 }
 
 workflow test_bcftools_query_with_optional_files {
 
+    input = [ [ id:'out' ], // meta map
+             file(params.test_data['sarscov2']['illumina']['test_vcf_gz'], checkIfExists: true),
+             file(params.test_data['sarscov2']['illumina']['test_vcf_gz_tbi'], checkIfExists: true)]
     regions = file(params.test_data['sarscov2']['illumina']['test3_vcf_gz'], checkIfExists: true)
     targets = file(params.test_data['sarscov2']['illumina']['test2_vcf_targets_tsv_gz'], checkIfExists: true)
     samples = []
 
-    input = [ [ id:'out' ], // meta map
-             file(params.test_data['sarscov2']['illumina']['test_vcf_gz'], checkIfExists: true),
-             file(params.test_data['sarscov2']['illumina']['test_vcf_gz_tbi'], checkIfExists: true)]
-
     BCFTOOLS_QUERY ( input, regions, targets, samples )
 }

tests/modules/bcftools/query/test.yml

@@ -4,7 +4,7 @@
     - bcftools
     - bcftools/query
   files:
-    - path: output/bcftools/out.vcf.gz
+    - path: output/bcftools/out.txt
       md5sum: c32a6d28f185822d8fe1eeb7e42ec155
 
 - name: bcftools query with optional files
@@ -13,5 +13,5 @@
     - bcftools
     - bcftools/query
   files:
-    - path: output/bcftools/out.vcf.gz
+    - path: output/bcftools/out.txt
       md5sum: 6bb5df49bfb5af39f7037cdf95032aac

tests/modules/freebayes/test.yml

@@ -1,34 +1,49 @@
 - name: freebayes test_freebayes
-  command: nextflow run ./tests/modules/freebayes -entry test_freebayes -c ./tests/config/nextflow.config -c ./tests/modules/freebayes/nextflow.config
+  command: nextflow run tests/modules/freebayes -entry test_freebayes -c tests/config/nextflow.config
   tags:
     - freebayes
   files:
     - path: output/freebayes/test.vcf.gz
+      md5sum: 81d3e6ce7b6343d088b779567c3803eb
+    - path: output/freebayes/versions.yml
+      md5sum: 53651eb835af65df829241257584a7d2
 
 - name: freebayes test_freebayes_bed
-  command: nextflow run ./tests/modules/freebayes -entry test_freebayes_bed -c ./tests/config/nextflow.config -c ./tests/modules/freebayes/nextflow.config
+  command: nextflow run tests/modules/freebayes -entry test_freebayes_bed -c tests/config/nextflow.config
   tags:
     - freebayes
   files:
     - path: output/freebayes/test.vcf.gz
+      md5sum: 02645d014a63485162a7789007373b2a
+    - path: output/freebayes/versions.yml
+      md5sum: becc93c8a0be580c09d55b955d60a5e1
 
 - name: freebayes test_freebayes_cram
-  command: nextflow run ./tests/modules/freebayes -entry test_freebayes_cram -c ./tests/config/nextflow.config -c ./tests/modules/freebayes/nextflow.config
+  command: nextflow run tests/modules/freebayes -entry test_freebayes_cram -c tests/config/nextflow.config
   tags:
     - freebayes
   files:
     - path: output/freebayes/test.vcf.gz
+      md5sum: 3d0bfcd2129c62f8863952fa4c1054db
+    - path: output/freebayes/versions.yml
+      md5sum: 2e5b266edfc6cab81353cfc72c00f67c
 
 - name: freebayes test_freebayes_somatic
-  command: nextflow run ./tests/modules/freebayes -entry test_freebayes_somatic -c ./tests/config/nextflow.config -c ./tests/modules/freebayes/nextflow.config
+  command: nextflow run tests/modules/freebayes -entry test_freebayes_somatic -c tests/config/nextflow.config
   tags:
     - freebayes
   files:
     - path: output/freebayes/test.vcf.gz
+      md5sum: 22fec868210ba3baf685b214bfd8e74b
+    - path: output/freebayes/versions.yml
+      md5sum: 8fbdb4c052fb3e42b5508a966125fa05
 
 - name: freebayes test_freebayes_somatic_cram_intervals
-  command: nextflow run ./tests/modules/freebayes -entry test_freebayes_somatic_cram_intervals -c ./tests/config/nextflow.config -c ./tests/modules/freebayes/nextflow.config
+  command: nextflow run tests/modules/freebayes -entry test_freebayes_somatic_cram_intervals -c tests/config/nextflow.config
   tags:
     - freebayes
   files:
     - path: output/freebayes/test.vcf.gz
+      md5sum: 527cf2937067bbd4117d95fd472bb928
+    - path: output/freebayes/versions.yml
+      md5sum: af97e3dfdc086188739907c3460e49e0

tests/modules/pangolin/test.yml

@@ -4,4 +4,4 @@
     - pangolin
   files:
     - path: ./output/pangolin/test.pangolin.csv
-      md5sum: 2563856ee31ba2a4a05705ff940a28cc
+      md5sum: d92ede51bf3886f696f2089e86189125

tests/modules/raven/main.nf

@@ -0,0 +1,15 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { RAVEN } from '../../../modules/raven/main.nf'
+
+workflow test_raven {
+    
+    input = [ 
+              [ id:'test', single_end:false ], // meta map
+              [ file(params.test_data['bacteroides_fragilis']['nanopore']['test_fastq_gz'], checkIfExists: true) ] 
+            ]
+
+    RAVEN ( input )
+}

tests/modules/raven/nextflow.config

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

tests/modules/raven/test.yml

@@ -0,0 +1,9 @@
+- name: raven test_raven
+  command: nextflow run ./tests/modules/raven -entry test_raven -c ./tests/config/nextflow.config -c ./tests/modules/raven/nextflow.config
+  tags:
+    - raven
+  files:
+    - path: output/raven/test.fasta.gz
+      md5sum: b026b6aba793a9f2bbfb17f732c91926
+    - path: output/raven/test.gfa.gz
+      md5sum: 09053490495f6deb7a3941e559cda626

tests/modules/svdb/query/main.nf

@@ -0,0 +1,18 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SVDB_QUERY } from '../../../../modules/svdb/query/main.nf'
+
+workflow test_svdb_query {
+
+    input = [ [ id:'test' ], // meta map
+              [ file(params.test_data['homo_sapiens']['illumina']['test_sv_vcf'], checkIfExists: true) ]
+            ]
+
+    vcf_db = [
+                file(params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_sv_vcf_gz'], checkIfExists: true)
+            ]
+
+    SVDB_QUERY ( input, vcf_db )
+}

tests/modules/svdb/query/nextflow.config

@@ -0,0 +1,9 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName: SVDB_QUERY {
+         ext.args = '--in_occ AC --out_occ gnomad_svAC --in_frq AF --out_frq gnomad_svAF'
+     }
+
+}

tests/modules/svdb/query/test.yml

@@ -0,0 +1,7 @@
+- name: svdb query
+  command: nextflow run ./tests/modules/svdb/query -entry test_svdb_query -c ./tests/config/nextflow.config -c ./tests/modules/svdb/query/nextflow.config
+  tags:
+    - svdb
+    - svdb/query
+  files:
+    - path: output/svdb/test_ann_svdbq.vcf

tests/modules/transdecoder/longorf/main.nf

@@ -0,0 +1,15 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { TRANSDECODER_LONGORF } from '../../../../modules/transdecoder/longorf/main.nf'
+
+workflow test_transdecoder_longorf {
+    
+    input = [ 
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) 
+    ]
+
+    TRANSDECODER_LONGORF ( input )
+}

tests/modules/transdecoder/longorf/nextflow.config

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

tests/modules/transdecoder/longorf/test.yml

@@ -0,0 +1,16 @@
+- name: transdecoder longorf test_transdecoder_longorf
+  command: nextflow run tests/modules/transdecoder/longorf -entry test_transdecoder_longorf -c tests/config/nextflow.config
+  tags:
+    - transdecoder
+    - transdecoder/longorf
+  files:
+    - path: output/transdecoder/versions.yml
+      md5sum: 15cffd5b1119e63d52dc754caf0f2d3c
+    - path: output/transdecoder/test/base_freqs.dat
+      md5sum: 5226ef383532e9b16c16b03e35ce181e
+    - path: output/transdecoder/test/longest_orfs.cds
+      md5sum: 041ac609e4c4ffb38676b1f88365be0f
+    - path: output/transdecoder/test/longest_orfs.gff3
+      md5sum: 96062ef88364f6bf1368d65cd1aad350
+    - path: output/transdecoder/test/longest_orfs.pep
+      md5sum: 0b903d36040676efeb2c50ab5ba46bbd

tests/modules/transdecoder/predict/main.nf

@@ -0,0 +1,18 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { TRANSDECODER_PREDICT } from '../../../../modules/transdecoder/predict/main.nf'
+include { TRANSDECODER_LONGORF } from '../../../../modules/transdecoder/longorf/main.nf'
+
+workflow test_transdecoder_predict {
+    
+    input = [ 
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)]
+    
+    TRANSDECODER_LONGORF ( input )
+    TRANSDECODER_PREDICT ( input, TRANSDECODER_LONGORF.out.folder )
+
+}
+

tests/modules/transdecoder/predict/nextflow.config

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

tests/modules/transdecoder/predict/test.yml

@@ -0,0 +1,12 @@
+- name: transdecoder predict test_transdecoder_predict
+  command: nextflow run tests/modules/transdecoder/predict -entry test_transdecoder_predict -c tests/config/nextflow.config
+  tags:
+    - transdecoder
+    - transdecoder/predict
+  files:
+    - path: output/transdecoder/genome.fasta.transdecoder.bed
+    - path: output/transdecoder/genome.fasta.transdecoder.cds
+    - path: output/transdecoder/genome.fasta.transdecoder.gff3
+    - path: output/transdecoder/genome.fasta.transdecoder.pep
+    - path: output/transdecoder/versions.yml
+      md5sum: 2847cc159dc93e9014b57d76987623ea