Merge branch 'master' into maxquant

modules/bamtools/convert/main.nf

@@ -0,0 +1,38 @@
+process BAMTOOLS_CONVERT {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::bamtools=2.5.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/bamtools:2.5.1--h9a82719_9' :
+        'quay.io/biocontainers/bamtools:2.5.1--h9a82719_9' }"
+
+    input:
+    tuple val(meta), path(bam)
+
+    output:
+    tuple val(meta), path("*.{bed,fasta,fastq,json,pileup,sam,yaml}"), emit: data
+    path "versions.yml"                                              , emit: versions
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def test = args ==~ /-format (bed|fasta|fastq|json|pileup|sam|yaml)/
+    if ( test == false ) error "-format option must be provided in args. Possible values: bed fasta fastq json pileup sam yaml"
+    m = args =~ /-format ([a-z]+)/
+    ext = m[0][1]
+
+
+    """
+    bamtools \\
+        convert \\
+        $args \\
+        -in $bam \\
+        -out ${prefix}.${ext}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bamtools: \$( bamtools --version | grep -e 'bamtools' | sed 's/^.*bamtools //' )
+    END_VERSIONS
+    """
+}

modules/bamtools/convert/meta.yml

@@ -0,0 +1,52 @@
+name: bamtools_convert
+description: BamTools provides both a programmer's API and an end-user's toolkit for handling BAM files.
+keywords:
+  - bamtools
+  - bamtools/convert
+  - bam
+  - convert
+  - bed
+  - fasta
+  - fastq
+  - json
+  - pileup
+  - sam
+  - yaml
+tools:
+  - bamtools:
+      description: C++ API & command-line toolkit for working with BAM data
+      homepage: http://github.com/pezmaster31/bamtools
+      documentation: https://github.com/pezmaster31/bamtools/wiki
+      tool_dev_url: http://github.com/pezmaster31/bamtools
+      doi: ""
+      licence: ['MIT']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: BAM file
+      pattern: "*.bam"
+
+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"
+  ## TODO nf-core: Delete / customise this example output
+  - out:
+      type: file
+      description: The data in the asked format (bed, fasta, fastq, json, pileup, sam, yaml)
+      pattern: "*.{bed,fasta,fastq,json,pileup,sam,yaml}"
+
+authors:
+  - "@sguizard"

modules/cellranger/.gitignore

@@ -1 +1,2 @@
 cellranger-*.tar.gz
+bcl2fastq2-*.zip

modules/cellranger/Dockerfile

@@ -1,15 +1,22 @@
+# Dockerfile to create container with Cell Ranger v6.1.2
+# Push to nfcore/cellranger:<VER>
+
 FROM continuumio/miniconda3:4.8.2
 LABEL authors="Gisela Gabernet <gisela.gabernet@gmail.com>" \
     description="Docker image containing Cell Ranger"
-# Disclaimer: this container is not provided nor supported by 10x Genomics.
+# Disclaimer: this container is not provided nor supported by Illumina or 10x Genomics.
 
 # Install procps and clean apt cache
 RUN apt-get update --allow-releaseinfo-change \
-    && apt-get install -y procps \
+    && apt-get install -y \
+    cpio \
+    procps \
+    rpm2cpio \
+    unzip \
     && apt-get clean -y && rm -rf /var/lib/apt/lists/*
 
 # Copy pre-downloaded cellranger file
-ENV CELLRANGER_VER 6.0.2
+ENV CELLRANGER_VER=6.1.2
 COPY cellranger-$CELLRANGER_VER.tar.gz /opt/cellranger-$CELLRANGER_VER.tar.gz
 
 # Install cellranger

modules/cellranger/README.md

@@ -1,18 +1,24 @@
 # Updating the docker container and making a new module release
 
-Cell Ranger is a commercial tool by 10X Genomics. The container provided for the cellranger nf-core module is not provided nor supported by 10x Genomics. Updating the Cell Ranger version in the container and pushing the update to Dockerhub needs to be done manually.
+Cell Ranger is a commercial tool from 10X Genomics. The container provided for the cellranger nf-core module is not provided nor supported by 10x Genomics. Updating the Cell Ranger versions in the container and pushing the update to Dockerhub needs to be done manually.
 
-1. Navigate to the [Cell Ranger download page](https://support.10xgenomics.com/single-cell-gene-expression/software/downloads/latest) and download the tar ball of the desired Cell Ranger version with `curl` or `wget`. Place this file in the same folder where the Dockerfile lies.
+1. Navigate to the appropriate download page.
+        - [Cell Ranger](https://support.10xgenomics.com/single-cell-gene-expression/software/downloads/latest): download the tar ball of the desired Cell Ranger version with `curl` or `wget`. Place this file in the same folder where the Dockerfile lies.
 
-2. Edit the Dockerfile: update the Cell Ranger version in this line:
+2. Edit the Dockerfile. Update the Cell Ranger versions in this line:
 
     ```bash
-    ENV CELLRANGER_VER <VERSION>
+    ENV CELLRANGER_VER=<VERSION>
     ```
 
-3. Create the container:
+3. Create and test the container:
 
     ```bash
     docker build . -t nfcore/cellranger:<VERSION>
+    ```
+
+4. Access rights are needed to push the container to the Dockerhub nfcore organization, please ask a core team member to do so.
+
+    ```bash
     docker push nfcore/cellranger:<VERSION>
     ```

modules/cellranger/count/main.nf

@@ -5,7 +5,7 @@ process CELLRANGER_COUNT {
     if (params.enable_conda) {
         exit 1, "Conda environments cannot be used when using the Cell Ranger tool. Please use docker or singularity containers."
     }
-    container "nfcore/cellranger:6.0.2"
+    container "nfcore/cellranger:6.1.2"
 
     input:
     tuple val(meta), path(reads)

modules/cellranger/mkfastq/Dockerfile

@@ -0,0 +1,40 @@
+# Dockerfile to create container with Cell Ranger v6.1.2 and bcl2fastq v2.20.0
+# Push to nfcore/cellrangermkfastq:<VER>
+
+FROM continuumio/miniconda3:4.8.2
+LABEL authors="Regina Reynolds, Gisela Gabernet <gisela.gabernet@gmail.com>" \
+    description="Docker image containing bcl2fastq2 and Cell Ranger"
+# Disclaimer: this container is not provided nor supported by Illumina or 10x Genomics.
+
+# Install procps and clean apt cache
+RUN apt-get update --allow-releaseinfo-change \
+    && apt-get install -y \
+    cpio \
+    procps \
+    rpm2cpio \
+    unzip \
+    && apt-get clean -y && rm -rf /var/lib/apt/lists/*
+
+# Copy pre-downloaded bcl2fastq2 and cellranger file
+ENV BCL2FASTQ2_VER=v2-20-0-linux-x86-64 \
+    CELLRANGER_VER=6.1.2
+COPY bcl2fastq2-$BCL2FASTQ2_VER.zip /tmp/bcl2fastq2-$BCL2FASTQ2_VER.zip
+COPY cellranger-$CELLRANGER_VER.tar.gz /opt/cellranger-$CELLRANGER_VER.tar.gz
+
+# Install bcl2fastq2
+RUN \
+    cd /tmp && \
+    unzip bcl2fastq2-$BCL2FASTQ2_VER.zip && \
+    mv *.rpm bcl2fastq2-$BCL2FASTQ2_VER.rpm && \
+    rpm2cpio ./bcl2fastq2-$BCL2FASTQ2_VER.rpm | cpio -idmv && \
+    export PATH=/tmp/usr/local/bin/:$PATH && \
+    ln -s /tmp/usr/local/bin/bcl2fastq /usr/bin/bcl2fastq && \
+    rm -rf bcl2fastq2-$BCL2FASTQ2_VER.*
+
+# Install cellranger
+RUN \
+    cd /opt && \
+    tar -xzvf cellranger-$CELLRANGER_VER.tar.gz && \
+    export PATH=/opt/cellranger-$CELLRANGER_VER:$PATH && \
+    ln -s /opt/cellranger-$CELLRANGER_VER/cellranger /usr/bin/cellranger && \
+    rm -rf /opt/cellranger-$CELLRANGER_VER.tar.gz

modules/cellranger/mkfastq/README.md

@@ -0,0 +1,26 @@
+# Updating the docker container and making a new module release
+
+Bcl2fastq2 and Cell Ranger are commercial tools from Illumina and 10X Genomics, respectively. The container provided for the cellranger nf-core module is not provided nor supported by either Illumina or 10x Genomics. Updating the bcl2fastq2 or Cell Ranger versions in the container and pushing the update to Dockerhub needs to be done manually.
+
+1. Navigate to the appropriate download pages.
+        - [bcl2fastq2](https://emea.support.illumina.com/sequencing/sequencing_software/bcl2fastq-conversion-software.html): download the linux rpm installer of the desired bcl2fastq2 version with `curl` or `wget`. Place this file in the same folder where the Dockerfile lies.
+        - [Cell Ranger](https://support.10xgenomics.com/single-cell-gene-expression/software/downloads/latest): download the tar ball of the desired Cell Ranger version with `curl` or `wget`. Place this file in the same folder where the Dockerfile lies.
+
+2. Edit the Dockerfile. Update the bcl2fastq2 and Cell Ranger versions in this line:
+
+    ```bash
+    ENV BCL2FASTQ2_VER=<VERSION> \
+        CELLRANGER_VER=<VERSION>
+    ```
+
+3. Create and test the container:
+
+    ```bash
+    docker build . -t nfcore/cellrangermkfastq:<CELLRANGER_VERSION>
+    ```
+
+4. Access rights are needed to push the container to the Dockerhub nfcore organization, please ask a core team member to do so.
+
+    ```bash
+    docker push nfcore/cellrangermkfastq:<CELLRANGER_VERSION>
+    ```

modules/cellranger/mkfastq/main.nf

@@ -5,7 +5,7 @@ process CELLRANGER_MKFASTQ {
     if (params.enable_conda) {
         exit 1, "Conda environments cannot be used when using the Cell Ranger tool. Please use docker or singularity containers."
     }
-    container "litd/docker-cellranger:v6.1.1" // FIXME Add bcl2fastq to nf-core docker image
+    container "nfcore/cellrangermkfastq:6.1.2"
 
     input:
     path bcl
@@ -13,14 +13,14 @@ process CELLRANGER_MKFASTQ {
 
     output:
     path "versions.yml", emit: versions
-    path "*.fastq.gz"  , emit: fastq
+    path "${bcl.getSimpleName()}/outs/fastq_path/*.fastq.gz"  , emit: fastq
 
     script:
     def args = task.ext.args ?: ''
     """
     cellranger mkfastq --id=${bcl.getSimpleName()} \
         --run=$bcl \
-        --csv=$csv
+        --csv=$csv \
         $args
 
     cat <<-END_VERSIONS > versions.yml
@@ -28,4 +28,15 @@ process CELLRANGER_MKFASTQ {
         cellranger: \$(echo \$( cellranger --version 2>&1) | sed 's/^.*[^0-9]\\([0-9]*\\.[0-9]*\\.[0-9]*\\).*\$/\\1/' )
     END_VERSIONS
     """
+
+    stub:
+    """
+    mkdir -p "${bcl.getSimpleName()}/outs/fastq_path/"
+    touch ${bcl.getSimpleName()}/outs/fastq_path/fake_file.fastq.gz
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        cellranger: \$(echo \$( cellranger --version 2>&1) | sed 's/^.*[^0-9]\\([0-9]*\\.[0-9]*\\.[0-9]*\\).*\$/\\1/' )
+    END_VERSIONS
+    """
 }

modules/cellranger/mkgtf/main.nf

@@ -5,7 +5,7 @@ process CELLRANGER_MKGTF {
     if (params.enable_conda) {
         exit 1, "Conda environments cannot be used when using the Cell Ranger tool. Please use docker or singularity containers."
     }
-    container "nfcore/cellranger:6.0.2"
+    container "nfcore/cellranger:6.1.2"
 
     input:
     path gtf

modules/cellranger/mkref/main.nf

@@ -5,7 +5,7 @@ process CELLRANGER_MKREF {
     if (params.enable_conda) {
         exit 1, "Conda environments cannot be used when using the Cell Ranger tool. Please use docker or singularity containers."
     }
-    container "nfcore/cellranger:6.0.2"
+    container "nfcore/cellranger:6.1.2"
 
     input:
     path fasta

modules/deeparg/downloaddata/main.nf

@@ -0,0 +1,30 @@
+def VERSION='1.0.2'
+
+process DEEPARG_DOWNLOADDATA {
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::deeparg=1.0.2" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/deeparg:1.0.2--pyhdfd78af_1' :
+        'quay.io/biocontainers/deeparg:1.0.2--pyhdfd78af_1' }"
+
+    input:
+
+    output:
+    path "db/"          , emit: db
+    path "versions.yml" , emit: versions
+
+    script:
+    def args = task.ext.args ?: ''
+    """
+    deeparg \\
+        download_data \\
+        $args \\
+        -o db/
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        deeparg: $VERSION
+    END_VERSIONS
+    """
+}

modules/deeparg/downloaddata/meta.yml

@@ -0,0 +1,33 @@
+name: deeparg_downloaddata
+description: A deep learning based approach to predict Antibiotic Resistance Genes (ARGs) from metagenomes
+keywords:
+  - download
+  - database
+  - deeparg
+  - antimicrobial resistance genes
+  - deep learning
+  - prediction
+tools:
+  - deeparg:
+      description: A deep learning based approach to predict Antibiotic Resistance Genes (ARGs) from metagenomes
+      homepage: https://bench.cs.vt.edu/deeparg
+      documentation: https://bitbucket.org/gusphdproj/deeparg-ss/src/master/
+      tool_dev_url: https://bitbucket.org/gusphdproj/deeparg-ss/src/master/
+      doi: "10.1186/s40168-018-0401-z"
+      licence: ['MIT']
+
+input:
+  - none: There is no input. This module downloads a pre-built database for use with deepARG.
+
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - db:
+      type: directory
+      description: Directory containing database required for deepARG.
+      pattern: "db/"
+
+authors:
+  - "@jfy133"

modules/deeparg/predict/main.nf

@@ -0,0 +1,40 @@
+def VERSION="1.0.2"
+
+process DEEPARG_PREDICT {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::deeparg=1.0.2" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity//deeparg:1.0.2--pyhdfd78af_1' :
+        'quay.io/biocontainers/deeparg:1.0.2--pyhdfd78af_1' }"
+
+    input:
+    tuple val(meta), path(fasta), val(model)
+    path(db)
+
+    output:
+    tuple val(meta), path("*.align.daa")            , emit: daa
+    tuple val(meta), path("*.align.daa.tsv")        , emit: daa_tsv
+    tuple val(meta), path("*.mapping.ARG")          , emit: arg
+    tuple val(meta), path("*.mapping.potential.ARG"), emit: potential_arg
+    path "versions.yml"                             , emit: versions
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    deeparg \\
+        predict \\
+        $args \\
+        -i $fasta \\
+        -o ${prefix} \\
+        -d $db \\
+        --model $model
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        deeparg: $VERSION
+    END_VERSIONS
+    """
+}

modules/deeparg/predict/meta.yml

@@ -0,0 +1,68 @@
+name: deeparg_predict
+description: A deep learning based approach to predict Antibiotic Resistance Genes (ARGs) from metagenomes
+keywords:
+  - deeparg
+  - antimicrobial resistance
+  - antimicrobial resistance genes
+  - arg
+  - deep learning
+  - prediction
+  - contigs
+  - metagenomes
+tools:
+  - deeparg:
+      description: A deep learning based approach to predict Antibiotic Resistance Genes (ARGs) from metagenomes
+      homepage: https://bench.cs.vt.edu/deeparg
+      documentation: https://bitbucket.org/gusphdproj/deeparg-ss/src/master/
+      tool_dev_url: https://bitbucket.org/gusphdproj/deeparg-ss/src/master/
+      doi: "10.1186/s40168-018-0401-z"
+      licence: ['MIT']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - fasta:
+      type: file
+      description: FASTA file containing gene-like sequences
+      pattern: "*.{fasta,fa,fna}"
+  - model:
+      type: string
+      description: Which model to use, depending on input data. Either 'LS' or 'SS' for long or short sequences respectively
+      pattern: "LS|LS"
+  - db:
+      type: directory
+      description: Path to a directory containing the deepARG pre-built models
+      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"
+  - daa:
+      type: file
+      description: Sequences of ARG-like sequences from DIAMOND alignment
+      pattern: "*.align.daa"
+  - daa_tsv:
+      type: file
+      description: Alignments scores against ARG-like sequences from DIAMOND alignment
+      pattern: "*.align.daa.tsv"
+  - arg:
+      type: file
+      description: Table containing sequences with an ARG-like probability of more than specified thresholds
+      pattern: "*.mapping.ARG"
+  - potential_arg:
+      type: file
+      description: Table containing sequences with an ARG-like probability of less than specified thresholds, and requires manual inspection
+      pattern: "*.mapping.potential.ARG"
+
+authors:
+  - "@jfy133"

modules/gatk4/mergebamalignment/main.nf

@@ -8,8 +8,7 @@ process GATK4_MERGEBAMALIGNMENT {
         'quay.io/biocontainers/gatk4:4.2.4.1--hdfd78af_0' }"
 
     input:
-    tuple val(meta), path(aligned)
-    path  unmapped
+    tuple val(meta), path(aligned), path(unmapped)
     path  fasta
     path  dict
 
@@ -28,10 +27,10 @@ process GATK4_MERGEBAMALIGNMENT {
     }
     """
     gatk --java-options "-Xmx${avail_mem}g" MergeBamAlignment \\
-        ALIGNED=$aligned \\
-        UNMAPPED=$unmapped \\
-        R=$fasta \\
-        O=${prefix}.bam \\
+        -ALIGNED $aligned \\
+        -UNMAPPED $unmapped \\
+        -R $fasta \\
+        -O ${prefix}.bam \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

modules/nextclade/datasetget/main.nf

@@ -2,10 +2,10 @@ process NEXTCLADE_DATASETGET {
     tag "$dataset"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::nextclade=1.9.0" : null)
+    conda (params.enable_conda ? "bioconda::nextclade=1.10.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/nextclade:1.9.0--h9ee0642_0' :
-        'quay.io/biocontainers/nextclade:1.9.0--h9ee0642_0' }"
+        'https://depot.galaxyproject.org/singularity/nextclade:1.10.1--h9ee0642_0' :
+        'quay.io/biocontainers/nextclade:1.10.1--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=1.9.0" : null)
+    conda (params.enable_conda ? "bioconda::nextclade=1.10.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/nextclade:1.9.0--h9ee0642_0' :
-        'quay.io/biocontainers/nextclade:1.9.0--h9ee0642_0' }"
+        'https://depot.galaxyproject.org/singularity/nextclade:1.10.1--h9ee0642_0' :
+        'quay.io/biocontainers/nextclade:1.10.1--h9ee0642_0' }"
 
     input:
     tuple val(meta), path(fasta)

modules/prodigal/main.nf

@@ -2,10 +2,10 @@ process PRODIGAL {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::prodigal=2.6.3" : null)
+    conda (params.enable_conda ? "prodigal=2.6.3 pigz=2.6" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/prodigal:2.6.3--h516909a_2' :
-        'quay.io/biocontainers/prodigal:2.6.3--h516909a_2' }"
+        'https://depot.galaxyproject.org/singularity/mulled-v2-2e442ba7b07bfa102b9cf8fac6221263cd746ab8:57f05cfa73f769d6ed6d54144cb3aa2a6a6b17e0-0' :
+        'quay.io/biocontainers/mulled-v2-2e442ba7b07bfa102b9cf8fac6221263cd746ab8:57f05cfa73f769d6ed6d54144cb3aa2a6a6b17e0-0' }"
 
     input:
     tuple val(meta), path(genome)
@@ -16,13 +16,13 @@ process PRODIGAL {
     tuple val(meta), path("${prefix}.fna"),                 emit: nucleotide_fasta
     tuple val(meta), path("${prefix}.faa"),                 emit: amino_acid_fasta
     tuple val(meta), path("${prefix}_all.txt"),             emit: all_gene_annotations
-    path "versions.yml"           , emit: versions
+    path "versions.yml",                                    emit: versions
 
     script:
     def args = task.ext.args   ?: ''
     prefix   = task.ext.prefix ?: "${meta.id}"
     """
-    prodigal -i "${genome}" \\
+    pigz -cdf ${genome} | prodigal \\
         $args \\
         -f $output_format \\
         -d "${prefix}.fna" \\
@@ -33,6 +33,7 @@ process PRODIGAL {
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
         prodigal: \$(prodigal -v 2>&1 | sed -n 's/Prodigal V\\(.*\\):.*/\\1/p')
+        pigz: \$(pigz -V 2>&1 | sed 's/pigz //g')
     END_VERSIONS
     """
 }

modules/prodigal/meta.yml

@@ -5,10 +5,10 @@ keywords:
 tools:
   - prodigal:
       description: Prodigal (Prokaryotic Dynamic Programming Genefinding Algorithm) is a microbial (bacterial and archaeal) gene finding program
-      homepage: {}
-      documentation: {}
+      homepage: {https://github.com/hyattpd/Prodigal}
+      documentation: {https://github.com/hyattpd/prodigal/wiki}
       tool_dev_url: {}
-      doi: ""
+      doi: "10.1186/1471-2105-11-119"
       licence: ["GPL v3"]
 
 input:
@@ -17,10 +17,12 @@ input:
       description: |
         Groovy Map containing sample information
         e.g. [ id:'test', single_end:false ]
-  - bam:
+  - genome:
       type: file
-      description: BAM/CRAM/SAM file
-      pattern: "*.{bam,cram,sam}"
+      description: fasta/fasta.gz file
+  - output_format:
+      type: string
+      description: Output format ("gbk"/"gff"/"sqn"/"sco")
 
 output:
   - meta:
@@ -32,10 +34,22 @@ output:
       type: file
       description: File containing software versions
       pattern: "versions.yml"
-  - bam:
+  - nucleotide_fasta:
       type: file
-      description: Sorted BAM/CRAM/SAM file
-      pattern: "*.{bam,cram,sam}"
+      description: nucleotide sequences file
+      pattern: "*.{fna}"
+  - amino_acid_fasta:
+      type: file
+      description: protein translations file
+      pattern: "*.{faa}"
+  - all_gene_annotations:
+      type: file
+      description: complete starts file
+      pattern: "*.{_all.txt}"
+  - gene_annotations:
+      type: file
+      description: gene annotations in output_format given as input
+      pattern: "*.{output_format}"
 
 authors:
   - "@grst"

tests/config/pytest_modules.yml

@@ -46,6 +46,10 @@ bamaligncleaner:
   - modules/bamaligncleaner/**
   - tests/modules/bamaligncleaner/**
 
+bamtools/convert:
+  - modules/bamtools/convert/**
+  - tests/modules/bamtools/convert/**
+
 bamtools/split:
   - modules/bamtools/split/**
   - tests/modules/bamtools/split/**
@@ -380,6 +384,14 @@ dedup:
   - modules/dedup/**
   - tests/modules/dedup/**
 
+deeparg/downloaddata:
+  - modules/deeparg/downloaddata/**
+  - tests/modules/deeparg/downloaddata/**
+
+deeparg/predict:
+  - modules/deeparg/predict/**
+  - tests/modules/deeparg/predict/**
+
 deeptools/computematrix:
   - modules/deeptools/computematrix/**
   - tests/modules/deeptools/computematrix/**

tests/modules/bamtools/convert/main.nf

@@ -0,0 +1,104 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { BAMTOOLS_CONVERT as BAMTOOLS_CONVERT_EXT_ERROR }   from '../../../../modules/bamtools/convert/main.nf'
+include { BAMTOOLS_CONVERT as BAMTOOLS_CONVERT_NOEXT_ERROR } from '../../../../modules/bamtools/convert/main.nf'
+include { BAMTOOLS_CONVERT as BAMTOOLS_CONVERT_BED }         from '../../../../modules/bamtools/convert/main.nf'
+include { BAMTOOLS_CONVERT as BAMTOOLS_CONVERT_FASTA }       from '../../../../modules/bamtools/convert/main.nf'
+include { BAMTOOLS_CONVERT as BAMTOOLS_CONVERT_FASTQ }       from '../../../../modules/bamtools/convert/main.nf'
+include { BAMTOOLS_CONVERT as BAMTOOLS_CONVERT_JSON }        from '../../../../modules/bamtools/convert/main.nf'
+include { BAMTOOLS_CONVERT as BAMTOOLS_CONVERT_PILEUP }      from '../../../../modules/bamtools/convert/main.nf'
+include { BAMTOOLS_CONVERT as BAMTOOLS_CONVERT_SAM }         from '../../../../modules/bamtools/convert/main.nf'
+include { BAMTOOLS_CONVERT as BAMTOOLS_CONVERT_YAML }        from '../../../../modules/bamtools/convert/main.nf'
+
+workflow test_bamtools_convert_ext_error {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true)
+    ]
+
+    BAMTOOLS_CONVERT_EXT_ERROR ( input )
+}
+
+workflow test_bamtools_convert_noext_error {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true)
+    ]
+
+    BAMTOOLS_CONVERT_NOEXT_ERROR ( input )
+}
+
+workflow test_bamtools_convert_bed {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true)
+    ]
+
+    BAMTOOLS_CONVERT_BED ( input )
+}
+
+workflow test_bamtools_convert_fasta {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true)
+    ]
+
+    BAMTOOLS_CONVERT_FASTA ( input )
+}
+
+workflow test_bamtools_convert_fastq {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true)
+    ]
+
+    BAMTOOLS_CONVERT_FASTQ ( input )
+}
+
+workflow test_bamtools_convert_json {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true)
+    ]
+
+    BAMTOOLS_CONVERT_JSON ( input )
+}
+
+workflow test_bamtools_convert_pileup {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true)
+    ]
+
+    BAMTOOLS_CONVERT_PILEUP ( input )
+}
+
+workflow test_bamtools_convert_sam {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true)
+    ]
+
+    BAMTOOLS_CONVERT_SAM ( input )
+}
+
+workflow test_bamtools_convert_yaml {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true)
+    ]
+
+    BAMTOOLS_CONVERT_YAML ( input )
+}
+

tests/modules/bamtools/convert/nextflow.config

@@ -0,0 +1,41 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName: BAMTOOLS_CONVERT_EXT_ERROR {
+        ext.args = "-format vcf"
+    }
+
+    withName: BAMTOOLS_CONVERT_NOEXT_ERROR {
+        ext.args = ""
+    }
+
+    withName: BAMTOOLS_CONVERT_BED {
+        ext.args = "-format bed"
+    }
+
+    withName: BAMTOOLS_CONVERT_FASTA {
+        ext.args = "-format fasta"
+    }
+
+    withName: BAMTOOLS_CONVERT_FASTQ {
+        ext.args = "-format fastq"
+    }
+
+    withName: BAMTOOLS_CONVERT_JSON {
+        ext.args = "-format json"
+    }
+
+    withName: BAMTOOLS_CONVERT_PILEUP {
+        ext.args = "-format pileup"
+    }
+
+    withName: BAMTOOLS_CONVERT_SAM {
+        ext.args = "-format sam"
+    }
+
+    withName: BAMTOOLS_CONVERT_YAML {
+        ext.args = "-format yaml"
+    }
+
+}

tests/modules/bamtools/convert/test.yml

@@ -0,0 +1,90 @@
+- name: bamtools convert test_bamtools_convert_ext_error
+  command: nextflow run tests/modules/bamtools/convert -entry test_bamtools_convert_ext_error -c tests/config/nextflow.config
+  tags:
+    - bamtools
+    - bamtools/convert
+  exit_code: 1
+
+- name: bamtools convert test_bamtools_convert_noext_error
+  command: nextflow run tests/modules/bamtools/convert -entry test_bamtools_convert_noext_error -c tests/config/nextflow.config
+  tags:
+    - bamtools
+    - bamtools/convert
+  exit_code: 1
+
+- name: bamtools convert test_bamtools_convert_bed
+  command: nextflow run tests/modules/bamtools/convert -entry test_bamtools_convert_bed -c tests/config/nextflow.config
+  tags:
+    - bamtools
+    - bamtools/convert
+  files:
+    - path: output/bamtools/test.bed
+      md5sum: 4e34cc15bf31e700f5f3a9f8fffb6c81
+    - path: output/bamtools/versions.yml
+      md5sum: eb7a144b8a97965d3482f6f96b8a8243
+
+- name: bamtools convert test_bamtools_convert_fasta
+  command: nextflow run tests/modules/bamtools/convert -entry test_bamtools_convert_fasta -c tests/config/nextflow.config
+  tags:
+    - bamtools
+    - bamtools/convert
+  files:
+    - path: output/bamtools/test.fasta
+      md5sum: 52aeacf78571862b7e97c7d44ac8f827
+    - path: output/bamtools/versions.yml
+      md5sum: 42d19a2b2b07f05edb82b34369dfd754
+
+- name: bamtools convert test_bamtools_convert_fastq
+  command: nextflow run tests/modules/bamtools/convert -entry test_bamtools_convert_fastq -c tests/config/nextflow.config
+  tags:
+    - bamtools
+    - bamtools/convert
+  files:
+    - path: output/bamtools/test.fastq
+      md5sum: e591c48daad2c56638e5d6f21f1f71c5
+    - path: output/bamtools/versions.yml
+      md5sum: 13f0bf8a3e1f8f527f96dabaa5c8051e
+
+- name: bamtools convert test_bamtools_convert_json
+  command: nextflow run tests/modules/bamtools/convert -entry test_bamtools_convert_json -c tests/config/nextflow.config
+  tags:
+    - bamtools
+    - bamtools/convert
+  files:
+    - path: output/bamtools/test.json
+      md5sum: 04afed696f9f14da85a460353645d1f5
+    - path: output/bamtools/versions.yml
+      md5sum: 33d633dbd6209cb93c9b071f8c0ed3b3
+
+- name: bamtools convert test_bamtools_convert_pileup
+  command: nextflow run tests/modules/bamtools/convert -entry test_bamtools_convert_pileup -c tests/config/nextflow.config
+  tags:
+    - bamtools
+    - bamtools/convert
+  files:
+    - path: output/bamtools/test.pileup
+      md5sum: e5a3cb4a3e1bf980a575fafce6a2826f
+    - path: output/bamtools/versions.yml
+      md5sum: fd3ad0edd1e085b1a002e0593d1d5814
+
+- name: bamtools convert test_bamtools_convert_sam
+  command: nextflow run tests/modules/bamtools/convert -entry test_bamtools_convert_sam -c tests/config/nextflow.config
+  tags:
+    - bamtools
+    - bamtools/convert
+  files:
+    - path: output/bamtools/test.sam
+      md5sum: 61ab3d0de16a9da8b651f9c692e19d5e
+    - path: output/bamtools/versions.yml
+      md5sum: 4be470ce3cc0143ae5ae415b612a4965
+
+- name: bamtools convert test_bamtools_convert_yaml
+  command: nextflow run tests/modules/bamtools/convert -entry test_bamtools_convert_yaml -c tests/config/nextflow.config
+  tags:
+    - bamtools
+    - bamtools/convert
+  files:
+    - path: output/bamtools/test.yaml
+      md5sum: 68b56f198da036fef33e150eb773dc3b
+    - path: output/bamtools/versions.yml
+      md5sum: 1116abc088c5edf11bee393961c18b3e

tests/modules/cellranger/count/test.yml

@@ -8,12 +8,12 @@
     - path: output/cellranger/sample-123/outs/metrics_summary.csv
       md5sum: 707df0f101d479d93f412ca74f9c4131
     - path: output/cellranger/sample-123/outs/molecule_info.h5
-      md5sum: cf03b2b3ca776a1c37aa3518e91268ba
+      md5sum: 0e56836ef0725f2ab05f56ca5a71e55b
     - path: output/cellranger/sample-123/outs/possorted_genome_bam.bam
       md5sum: 15441da9cfceea0bb48c8b66b1b860df
     - path: output/cellranger/sample-123/outs/possorted_genome_bam.bam.bai
       md5sum: 7c3d49c77016a09535aff61a027f750c
     - path: output/cellranger/sample-123/outs/raw_feature_bc_matrix
     - path: output/cellranger/sample-123/outs/raw_feature_bc_matrix.h5
-      md5sum: 40c8df814eb8723b7317b234dc8222e9
+      md5sum: cdad1cd7b215d7137cf92515e81a8525
     - path: output/cellranger/sample-123/outs/web_summary.html

tests/modules/cellranger/mkfastq/nextflow.config

@@ -2,4 +2,8 @@ process {
 
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
 
+    withName: CELLRANGER_MKFASTQ {
+        ext.args = "--tiles 1101"
+    }
+
 }

tests/modules/cellranger/mkfastq/test.yml

@@ -1,13 +1,16 @@
 - name: cellranger mkfastq test_cellranger_mkfastq_simple
-  command: nextflow run tests/modules/cellranger/mkfastq -entry test_cellranger_mkfastq_simple -c tests/config/nextflow.config -c ./tests/modules/cellranger/mkfastq/nextflow.config
+  command: nextflow run tests/modules/cellranger/mkfastq -entry test_cellranger_mkfastq_simple -c tests/config/nextflow.config -c ./tests/modules/cellranger/mkfastq/nextflow.config -stub-run
   tags:
     - cellranger
     - cellranger/mkfastq
-  # files:
-  #   - path: output/cellranger/genome.filtered.gtf
-  #     md5sum: a8b8a7b5039e05d3a9cf9151ea138b5b
+  files:
+    - path: output/cellranger/cellranger-tiny-bcl-1/outs/fastq_path/fake_file.fastq.gz
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
 - name: cellranger mkfastq test_cellranger_mkfastq_illumina
-  command: nextflow run tests/modules/cellranger/mkfastq -entry test_cellranger_mkfastq_illumina -c tests/config/nextflow.config -c ./tests/modules/cellranger/mkfastq/nextflow.config
+  command: nextflow run tests/modules/cellranger/mkfastq -entry test_cellranger_mkfastq_illumina -c tests/config/nextflow.config -c ./tests/modules/cellranger/mkfastq/nextflow.config -stub-run
   tags:
     - cellranger
     - cellranger/mkfastq
+  files:
+    - path: output/cellranger/cellranger-tiny-bcl-1/outs/fastq_path/fake_file.fastq.gz
+      md5sum: d41d8cd98f00b204e9800998ecf8427e

tests/modules/cellranger/mkref/test.yml

@@ -11,7 +11,7 @@
     - path: output/cellranger/homo_sapiens_chr22_reference/genes/genes.gtf.gz
       md5sum: 6d9b5f409bfea95022bc25b9590e194e
     - path: output/cellranger/homo_sapiens_chr22_reference/reference.json
-      md5sum: a4e2b9bbf016c55b0d4d7bc1fa53896f
+      md5sum: 5d8d1669cd251433505f183e1c9ed6bc
     - path: output/cellranger/homo_sapiens_chr22_reference/star/Genome
       md5sum: 22102926fadf5890e905ca71b2da3f35
     - path: output/cellranger/homo_sapiens_chr22_reference/star/SA

tests/modules/deeparg/downloaddata/main.nf

@@ -0,0 +1,9 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { DEEPARG_DOWNLOADDATA } from '../../../../modules/deeparg/downloaddata/main.nf'
+
+workflow test_deeparg_downloaddata {
+    DEEPARG_DOWNLOADDATA ()
+}

tests/modules/deeparg/downloaddata/nextflow.config

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

tests/modules/deeparg/downloaddata/test.yml

@@ -0,0 +1,9 @@
+- name: deeparg downloaddata test_deeparg_downloaddata
+  command: nextflow run tests/modules/deeparg/downloaddata -entry test_deeparg_downloaddata -c tests/config/nextflow.config
+  tags:
+    - deeparg
+    - deeparg/downloaddata
+  files:
+    - path: output/deeparg/db/
+    - path: output/deeparg/db/data/gg13/dataset.rev.2.bt2
+      md5sum: 99d90f132fc2795d5a527ce31f1c4d30

tests/modules/deeparg/predict/main.nf

@@ -0,0 +1,19 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { DEEPARG_DOWNLOADDATA } from '../../../../modules/deeparg/downloaddata/main.nf'
+include { DEEPARG_PREDICT      } from '../../../../modules/deeparg/predict/main.nf'
+
+workflow test_deeparg_predict {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['bacteroides_fragilis']['genome']['genome_fna_gz'], checkIfExists: true),
+        'LS'
+    ]
+
+    DEEPARG_DOWNLOADDATA()
+    DEEPARG_PREDICT ( input, DEEPARG_DOWNLOADDATA.out.db )
+
+}

tests/modules/deeparg/predict/nextflow.config

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

tests/modules/deeparg/predict/test.yml

@@ -0,0 +1,17 @@
+- name: deeparg predict test_deeparg_predict
+  command: nextflow run tests/modules/deeparg/predict -entry test_deeparg_predict -c tests/config/nextflow.config
+  tags:
+    - deeparg/predict
+    - deeparg
+  files:
+    - path: output/deeparg/test.align.daa
+      md5sum: c52d0af8362244f214da25bc45f2bf42
+    - path: output/deeparg/test.align.daa.tsv
+      md5sum: a4aa1da2db98274ede2b927fa8227e5a
+    - path: output/deeparg/test.mapping.ARG
+      md5sum: 0e049e99eab4c55666062df21707d5b9
+    - path: output/deeparg/test.mapping.potential.ARG
+      contains:
+        - "#ARG"
+    - path: output/deeparg/versions.yml
+      md5sum: e848ddab324e8c6fd18eaa6b2656f195

tests/modules/gatk4/mergebamalignment/main.nf

@@ -6,11 +6,11 @@ include { GATK4_MERGEBAMALIGNMENT } from '../../../../modules/gatk4/mergebamalig
 
 workflow test_gatk4_mergebamalignment {
     input    = [ [ id:'test' ], // meta map
-                 file(params.test_data['sarscov2']['illumina']['test_single_end_bam'], checkIfExists: true)
+                 file(params.test_data['sarscov2']['illumina']['test_single_end_bam'], checkIfExists: true),
+                 file(params.test_data['sarscov2']['illumina']['test_unaligned_bam'], checkIfExists: true)
                ]
-    unmapped = file(params.test_data['sarscov2']['illumina']['test_unaligned_bam'], checkIfExists: true)
     fasta    = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
     dict     = file(params.test_data['sarscov2']['genome']['genome_dict'], checkIfExists: true)
 
-    GATK4_MERGEBAMALIGNMENT ( input, unmapped, fasta, dict )
+    GATK4_MERGEBAMALIGNMENT ( input, fasta, dict )
 }

tests/modules/nextclade/datasetget/main.nf

@@ -8,7 +8,8 @@ workflow test_nextclade_datasetget {
 
     dataset = 'sars-cov-2'
     reference = 'MN908947'
-    tag = '2022-01-05T19:54:31Z'
+    tag = '2022-01-18T12:00:00Z'
 
     NEXTCLADE_DATASETGET ( dataset, reference, tag )
+
 }

tests/modules/nextclade/datasetget/test.yml

@@ -9,12 +9,14 @@
     - path: output/nextclade/sars-cov-2/primers.csv
       md5sum: 5990c3483bf66ce607aeb90a44e7ef2e
     - path: output/nextclade/sars-cov-2/qc.json
-      md5sum: 018fa0c0b0d2e824954e37e01495d549
+      md5sum: c512f51fda0212b21ffff05779180963
     - path: output/nextclade/sars-cov-2/reference.fasta
       md5sum: c7ce05f28e4ec0322c96f24e064ef55c
     - path: output/nextclade/sars-cov-2/sequences.fasta
       md5sum: 41129d255b99e0e92bdf20e866b99a1b
     - path: output/nextclade/sars-cov-2/tag.json
-      md5sum: 2f6d8e806d9064571ee4188ef1304c9c
+      md5sum: 402ac2b87e2a6a64a3fbf5ad16497af3
     - path: output/nextclade/sars-cov-2/tree.json
-      md5sum: f8fb33ed62b59142ac20998eb599df6c
+      md5sum: b8f32f547ff9e2131d6fc66b68fc54b1
+    - path: output/nextclade/sars-cov-2/virus_properties.json
+      md5sum: 5f2de3949e07cb633f3d9e4a7654dc81

tests/modules/nextclade/run/main.nf

@@ -9,7 +9,7 @@ workflow test_nextclade_run {
 
     dataset = 'sars-cov-2'
     reference = 'MN908947'
-    tag = '2022-01-05T19:54:31Z'
+    tag = '2022-01-18T12:00:00Z'
 
     NEXTCLADE_DATASETGET ( dataset, reference, tag )
 
@@ -20,3 +20,4 @@ workflow test_nextclade_run {
 
     NEXTCLADE_RUN ( input, NEXTCLADE_DATASETGET.out.dataset )
 }
+

tests/modules/nextclade/run/test.yml

@@ -6,8 +6,8 @@
   files:
     - path: output/nextclade/test.json
     - path: output/nextclade/test.csv
-      md5sum: 3b87a4da190ba2e1fdc8418dc3a7ffdb
+      md5sum: 570c1aa2d5fd25c23d0042c1b06108e1
     - path: output/nextclade/test.tsv
-      md5sum: 449393288e8734a02def139c550a8d9b
+      md5sum: dd76e1a4c760785489be4e4a860b4d00
     - path: output/nextclade/test.tree.json
-      md5sum: 9c6e33cb7ff860bee6194847bd2c855c
+      md5sum: 3591b4dc1542995a7ffcffcb1f52b524

tests/test_versions_yml.py

@@ -16,6 +16,9 @@ def _get_workflow_names():
         # test_config = yaml.safe_load(f.read_text())
         test_config = yaml.load(f.read_text(), Loader=yaml.BaseLoader)
         for workflow in test_config:
+            # https://github.com/nf-core/modules/pull/1242 - added to cover tests 
+            # that expect an error and therefore will not generate a versions.yml
+            if 'exit_code' not in workflow: 
                 yield workflow["name"]