Merge pull request #63 from drpatelh/master

Add docs and tests for all samtools commands

.github/workflows/samtools_flagstat.yml

@@ -0,0 +1,30 @@
+name: samtools_flagstat
+on:
+  push:
+    paths:
+      - software/samtools/flagstat/**
+      - .github/workflows/samtools_flagstat.yml
+      - tests
+  pull_request:
+    paths:
+      - software/samtools/flagstat/**
+      - .github/workflows/samtools_flagstat.yml
+      - tests
+
+jobs:
+  ci_test:
+    runs-on: ubuntu-latest
+    env:
+      NXF_ANSI_LOG: false
+    steps:
+
+    - uses: actions/checkout@v2
+
+    - name: Install Nextflow
+      run: |
+        export NXF_VER="20.07.1"
+        wget -qO- get.nextflow.io | bash
+        sudo mv nextflow /usr/local/bin/
+
+    # Test the module
+    - run: nextflow run ./software/samtools/flagstat/test/ -profile docker

.github/workflows/samtools_idxstats.yml

@@ -0,0 +1,30 @@
+name: samtools_idxstats
+on:
+  push:
+    paths:
+      - software/samtools/idxstats/**
+      - .github/workflows/samtools_idxstats.yml
+      - tests
+  pull_request:
+    paths:
+      - software/samtools/idxstats/**
+      - .github/workflows/samtools_idxstats.yml
+      - tests
+
+jobs:
+  ci_test:
+    runs-on: ubuntu-latest
+    env:
+      NXF_ANSI_LOG: false
+    steps:
+
+    - uses: actions/checkout@v2
+
+    - name: Install Nextflow
+      run: |
+        export NXF_VER="20.07.1"
+        wget -qO- get.nextflow.io | bash
+        sudo mv nextflow /usr/local/bin/
+
+    # Test the module
+    - run: nextflow run ./software/samtools/idxstats/test/ -profile docker

.github/workflows/samtools_index.yml

@@ -0,0 +1,30 @@
+name: samtools_index
+on:
+  push:
+    paths:
+      - software/samtools/index/**
+      - .github/workflows/samtools_index.yml
+      - tests
+  pull_request:
+    paths:
+      - software/samtools/index/**
+      - .github/workflows/samtools_index.yml
+      - tests
+
+jobs:
+  ci_test:
+    runs-on: ubuntu-latest
+    env:
+      NXF_ANSI_LOG: false
+    steps:
+
+    - uses: actions/checkout@v2
+
+    - name: Install Nextflow
+      run: |
+        export NXF_VER="20.07.1"
+        wget -qO- get.nextflow.io | bash
+        sudo mv nextflow /usr/local/bin/
+
+    # Test the module
+    - run: nextflow run ./software/samtools/index/test/ -profile docker

.github/workflows/samtools_sort.yml

@@ -0,0 +1,30 @@
+name: samtools_sort
+on:
+  push:
+    paths:
+      - software/samtools/sort/**
+      - .github/workflows/samtools_sort.yml
+      - tests
+  pull_request:
+    paths:
+      - software/samtools/sort/**
+      - .github/workflows/samtools_sort.yml
+      - tests
+
+jobs:
+  ci_test:
+    runs-on: ubuntu-latest
+    env:
+      NXF_ANSI_LOG: false
+    steps:
+
+    - uses: actions/checkout@v2
+
+    - name: Install Nextflow
+      run: |
+        export NXF_VER="20.07.1"
+        wget -qO- get.nextflow.io | bash
+        sudo mv nextflow /usr/local/bin/
+
+    # Test the module
+    - run: nextflow run ./software/samtools/sort/test/ -profile docker

.github/workflows/samtools_stats.yml

@@ -0,0 +1,30 @@
+name: samtools_stats
+on:
+  push:
+    paths:
+      - software/samtools/stats/**
+      - .github/workflows/samtools_stats.yml
+      - tests
+  pull_request:
+    paths:
+      - software/samtools/stats/**
+      - .github/workflows/samtools_stats.yml
+      - tests
+
+jobs:
+  ci_test:
+    runs-on: ubuntu-latest
+    env:
+      NXF_ANSI_LOG: false
+    steps:
+
+    - uses: actions/checkout@v2
+
+    - name: Install Nextflow
+      run: |
+        export NXF_VER="20.07.1"
+        wget -qO- get.nextflow.io | bash
+        sudo mv nextflow /usr/local/bin/
+
+    # Test the module
+    - run: nextflow run ./software/samtools/stats/test/ -profile docker

software/SOFTWARE/TOOL/meta.yml

@@ -4,74 +4,75 @@ name: software_tool
 ## TODO nf-core: Add a description and keywords
 description: Run FastQC on sequenced reads
 keywords:
-  - Quality Control
-  - QC
-  - Adapters
+    - quality control
+    - qc
+    - adapters
+    - fastq
 tools:
-  ## TODO nf-core: Change the name of "software_tool" below
-  - software_tool:
-      ## TODO nf-core: Add a description and other details for the tool below
-      description: |
-        FastQC gives general quality metrics about your reads.
-        It provides information about the quality score distribution
-        across your reads, the per base sequence content (%A/C/G/T).
-        You get information about adapter contamination and other
-        overrepresented sequences.
-      homepage: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/
-      documentation: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/
+    ## TODO nf-core: Change the name of "software" below
+    - software:
+        ## TODO nf-core: Add a description and other details for the software below
+        description: |
+            FastQC gives general quality metrics about your reads.
+            It provides information about the quality score distribution
+            across your reads, the per base sequence content (%A/C/G/T).
+            You get information about adapter contamination and other
+            overrepresented sequences.
+        homepage: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/
+        documentation: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/
 ## TODO nf-core: If you are using any additional "params" in the main.nf script of the module add them below
 params:
-  - outdir:
-      type: string
-      description: |
-        The pipeline's output directory. By default, the module will
-        output files into `$params.outdir/<SOFTWARE>`
-  - publish_dir_mode:
-      type: string
-      description: |
-        Value for the Nextflow `publishDir` mode parameter.
-        Available: symlink, rellink, link, copy, copyNoFollow, move.
-  - conda:
-      type: boolean
-      description: |
-        Run the module with Conda using the software specified
-        via the `conda` directive
+    - outdir:
+        type: string
+        description: |
+            The pipeline's output directory. By default, the module will
+            output files into `$params.outdir/<SOFTWARE>`
+    - publish_dir_mode:
+        type: string
+        description: |
+            Value for the Nextflow `publishDir` mode parameter.
+            Available: symlink, rellink, link, copy, copyNoFollow, move.
+    - conda:
+        type: boolean
+        description: |
+            Run the module with Conda using the software specified
+            via the `conda` directive
 ## TODO nf-core: Add a description of all of the variables used as input
 input:
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. [ id:'test', single_end:false ]
-  - reads:
-      type: file
-      description: |
-        List of input FastQ files of size 1 and 2 for single-end and paired-end data,
-        respectively.
-  - options:
-      type: map
-      description: |
-        Groovy Map containing module options for passing command-line arguments and
-        output file paths.
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - reads:
+        type: file
+        description: |
+            List of input FastQ files of size 1 and 2 for single-end and paired-end data,
+            respectively.
+    - options:
+        type: map
+        description: |
+            Groovy Map containing module options for passing command-line arguments and
+            output file paths.
 ## TODO nf-core: Add a description of all of the variables used as output
 output:
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. [ id:'test', single_end:false ]
-  - html:
-      type: file
-      description: FastQC report
-      pattern: "*_fastqc.html"
-  - zip:
-      type: file
-      description: FastQC report archive
-      pattern: "*_fastqc.zip"
-  - version:
-      type: file
-      description: File containing software version
-      pattern: "*.version.txt"
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - html:
+        type: file
+        description: FastQC report
+        pattern: "*_{fastqc.html}"
+    - zip:
+        type: file
+        description: FastQC report archive
+        pattern: "*_{fastqc.zip}"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"
 ## TODO nf-core: Add your GitHub username below
 authors:
-  - "@your_github_username"
+    - "@your_github_username"

software/SOFTWARE/TOOL/test/nextflow.config

@@ -1,20 +1,20 @@
 
 params {
-  outdir = "output/"
-  publish_dir_mode = "copy"
-  conda = false
+    outdir = "output/"
+    publish_dir_mode = "copy"
+    conda = false
 }
 
 profiles {
-  conda  {
-    params.conda = true
-  }
-  docker {
-    docker.enabled = true
-    docker.runOptions = '-u \$(id -u):\$(id -g)'
-  }
-  singularity {
-    singularity.enabled = true
-    singularity.autoMounts = true
-  }
+    conda  {
+        params.conda = true
+    }
+    docker {
+        docker.enabled = true
+        docker.runOptions = '-u \$(id -u):\$(id -g)'
+    }
+    singularity {
+        singularity.enabled = true
+        singularity.autoMounts = true
+    }
 }

software/bwa/index/meta.yml

@@ -1,52 +1,52 @@
 name: bwa_index
 description: Create BWA index for reference genome
 keywords:
-  - index
-  - fasta
-  - genome
+    - index
+    - fasta
+    - genome
+    - reference
 tools:
-  - bwa:
-      description: |
-        BWA is a software package for mapping DNA sequences against
-        a large reference genome, such as the human genome.
-      homepage: http://bio-bwa.sourceforge.net/
-      documentation: http://www.htslib.org/doc/samtools.html
-      arxiv: arXiv:1303.3997
+    - bwa:
+        description: |
+            BWA is a software package for mapping DNA sequences against
+            a large reference genome, such as the human genome.
+        homepage: http://bio-bwa.sourceforge.net/
+        documentation: http://www.htslib.org/doc/samtools.html
+        arxiv: arXiv:1303.3997
 params:
-  - outdir:
-      type: string
-      description: |
-        The pipeline's output directory. By default, the module will
-        output files into `$params.outdir/<SOFTWARE>`
-  - publish_dir_mode:
-      type: string
-      description: |
-        Value for the Nextflow `publishDir` mode parameter.
-        Available: symlink, rellink, link, copy, copyNoFollow, move.
-  - conda:
-      type: boolean
-      description: |
-        Run the module with Conda using the software specified
-        via the `conda` directive
+    - outdir:
+        type: string
+        description: |
+            The pipeline's output directory. By default, the module will
+            output files into `$params.outdir/<SOFTWARE>`
+    - publish_dir_mode:
+        type: string
+        description: |
+            Value for the Nextflow `publishDir` mode parameter.
+            Available: symlink, rellink, link, copy, copyNoFollow, move.
+    - conda:
+        type: boolean
+        description: |
+            Run the module with Conda using the software specified
+            via the `conda` directive
 input:
-  - fasta:
-      type: file
-      description: |
-        Input genome fasta file
-  - options:
-      type: map
-      description: |
-        Groovy Map containing module options for passing command-line arguments and
-        output file paths.
+    - fasta:
+        type: file
+        description: Input genome fasta file
+    - options:
+        type: map
+        description: |
+            Groovy Map containing module options for passing command-line arguments and
+            output file paths.
 output:
-  - index:
-      type: file
-      description: BWA genome index files
-      pattern: "*.{fasta}.{amb,ann,bwt,pac,sa}"
-  - version:
-      type: file
-      description: File containing software version
-      pattern: "*.version.txt"
+    - index:
+        type: file
+        description: BWA genome index files
+        pattern: "*.{amb,ann,bwt,pac,sa}"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"
 authors:
-  - "@drpatelh"
-  - "@maxulysse"
+    - "@drpatelh"
+    - "@maxulysse"

software/bwa/index/test/nextflow.config

@@ -1,20 +1,20 @@
 
 params {
-  outdir = "output/"
-  publish_dir_mode = "copy"
-  conda = false
+    outdir = "output/"
+    publish_dir_mode = "copy"
+    conda = false
 }
 
 profiles {
-  conda  {
-    params.conda = true
-  }
-  docker {
-    docker.enabled = true
-    docker.runOptions = '-u \$(id -u):\$(id -g)'
-  }
-  singularity {
-    singularity.enabled = true
-    singularity.autoMounts = true
-  }
+    conda  {
+        params.conda = true
+    }
+    docker {
+        docker.enabled = true
+        docker.runOptions = '-u \$(id -u):\$(id -g)'
+    }
+    singularity {
+        singularity.enabled = true
+        singularity.autoMounts = true
+    }
 }

software/bwa/mem/meta.yml

@@ -1,68 +1,69 @@
 name: bwa_mem
 description: Performs fastq alignment to a fasta reference using BWA
 keywords:
-  - mem
-  - bwa
-  - alignment
-  - map
+    - mem
+    - bwa
+    - alignment
+    - map
+    - fastq
+    - bam
+    - sam
 tools:
-  - bwa:
-      description: |
-        BWA is a software package for mapping DNA sequences against
-        a large reference genome, such as the human genome.
-      homepage: http://bio-bwa.sourceforge.net/
-      documentation: http://www.htslib.org/doc/samtools.html
-      arxiv: arXiv:1303.3997
+    - bwa:
+        description: |
+            BWA is a software package for mapping DNA sequences against
+            a large reference genome, such as the human genome.
+        homepage: http://bio-bwa.sourceforge.net/
+        documentation: http://www.htslib.org/doc/samtools.html
+        arxiv: arXiv:1303.3997
 params:
-  - outdir:
-      type: string
-      description: |
-        The pipeline's output directory. By default, the module will
-        output files into `$params.outdir/<SOFTWARE>`
-  - publish_dir_mode:
-      type: string
-      description: |
-        Value for the Nextflow `publishDir` mode parameter.
-        Available: symlink, rellink, link, copy, copyNoFollow, move.
-  - conda:
-      type: boolean
-      description: |
-        Run the module with Conda using the software specified
-        via the `conda` directive
+    - outdir:
+        type: string
+        description: |
+            The pipeline's output directory. By default, the module will
+            output files into `$params.outdir/<SOFTWARE>`
+    - publish_dir_mode:
+        type: string
+        description: |
+            Value for the Nextflow `publishDir` mode parameter.
+            Available: symlink, rellink, link, copy, copyNoFollow, move.
+    - conda:
+        type: boolean
+        description: |
+            Run the module with Conda using the software specified
+            via the `conda` directive
 input:
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. [ id:'test', single_end:false ]
-  - reads:
-      type: file
-      description: |
-        List of input FastQ files of size 1 and 2 for single-end and paired-end data,
-        respectively.
-  - index:
-      type: file
-      description: |
-        BWA genome index files
-      pattern: "*.{amb,ann,bwt,pac,sa}"
-  - fasta:
-      type: file
-      description: |
-        Input genome fasta file
-  - options:
-      type: map
-      description: |
-        Groovy Map containing module options for passing command-line arguments and
-        output file paths.
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - reads:
+        type: file
+        description: |
+            List of input FastQ files of size 1 and 2 for single-end and paired-end data,
+            respectively.
+    - index:
+        type: file
+        description: BWA genome index files
+        pattern: "*.{amb,ann,bwt,pac,sa}"
+    - fasta:
+        type: file
+        description: Input genome fasta file
+    - options:
+        type: map
+        description: |
+            Groovy Map containing module options for passing command-line arguments and
+            output file paths.
 output:
-  - bam:
-      type: file
-      description: Output BAM file containing read alignments
-      pattern: "*.bam"
-  - version:
-      type: file
-      description: File containing software version
-      pattern: "*.version.txt"
+    - bam:
+        type: file
+        description: Output BAM file containing read alignments
+        pattern: "*.{bam}"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"
 authors:
-  - "@drpatelh"
-  - "@jeremy1805"
+    - "@drpatelh"
+    - "@jeremy1805"

software/bwa/mem/test/nextflow.config

@@ -1,20 +1,20 @@
 
 params {
-  outdir = "output/"
-  publish_dir_mode = "copy"
-  conda = false
+    outdir = "output/"
+    publish_dir_mode = "copy"
+    conda = false
 }
 
 profiles {
-  conda  {
-    params.conda = true
-  }
-  docker {
-    docker.enabled = true
-    docker.runOptions = '-u \$(id -u):\$(id -g)'
-  }
-  singularity {
-    singularity.enabled = true
-    singularity.autoMounts = true
-  }
+    conda  {
+        params.conda = true
+    }
+    docker {
+        docker.enabled = true
+        docker.runOptions = '-u \$(id -u):\$(id -g)'
+    }
+    singularity {
+        singularity.enabled = true
+        singularity.autoMounts = true
+    }
 }

software/fastqc/meta.yml

@@ -1,71 +1,72 @@
 name: fastqc
 description: Run FastQC on sequenced reads
 keywords:
-  - quality control
-  - qc
-  - adapters
+    - quality control
+    - qc
+    - adapters
+    - fastq
 tools:
-  - fastqc:
-      description: |
-        FastQC gives general quality metrics about your reads.
-        It provides information about the quality score distribution
-        across your reads, the per base sequence content (%A/C/G/T).
-        You get information about adapter contamination and other
-        overrepresented sequences.
-      homepage: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/
-      documentation: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/
+    - fastqc:
+        description: |
+            FastQC gives general quality metrics about your reads.
+            It provides information about the quality score distribution
+            across your reads, the per base sequence content (%A/C/G/T).
+            You get information about adapter contamination and other
+            overrepresented sequences.
+        homepage: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/
+        documentation: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/
 params:
-  - outdir:
-      type: string
-      description: |
-        The pipeline's output directory. By default, the module will
-        output files into `$params.outdir/<SOFTWARE>`
-  - publish_dir_mode:
-      type: string
-      description: |
-        Value for the Nextflow `publishDir` mode parameter.
-        Available: symlink, rellink, link, copy, copyNoFollow, move.
-  - conda:
-      type: boolean
-      description: |
-        Run the module with Conda using the software specified
-        via the `conda` directive
+    - outdir:
+        type: string
+        description: |
+            The pipeline's output directory. By default, the module will
+            output files into `$params.outdir/<SOFTWARE>`
+    - publish_dir_mode:
+        type: string
+        description: |
+            Value for the Nextflow `publishDir` mode parameter.
+            Available: symlink, rellink, link, copy, copyNoFollow, move.
+    - conda:
+        type: boolean
+        description: |
+            Run the module with Conda using the software specified
+            via the `conda` directive
 input:
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. [ id:'test', single_end:false ]
-  - reads:
-      type: file
-      description: |
-        List of input FastQ files of size 1 and 2 for single-end and paired-end data,
-        respectively.
-  - options:
-      type: map
-      description: |
-        Groovy Map containing module options for passing command-line arguments and
-        output file paths.
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - reads:
+        type: file
+        description: |
+            List of input FastQ files of size 1 and 2 for single-end and paired-end data,
+            respectively.
+    - options:
+        type: map
+        description: |
+            Groovy Map containing module options for passing command-line arguments and
+            output file paths.
 output:
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. [ id:'test', single_end:false ]
-  - html:
-      type: file
-      description: FastQC report
-      pattern: "*_fastqc.html"
-  - zip:
-      type: file
-      description: FastQC report archive
-      pattern: "*_fastqc.zip"
-  - version:
-      type: file
-      description: File containing software version
-      pattern: "*.version.txt"
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - html:
+        type: file
+        description: FastQC report
+        pattern: "*_{fastqc.html}"
+    - zip:
+        type: file
+        description: FastQC report archive
+        pattern: "*_{fastqc.zip}"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"
 authors:
-  - "@drpatelh"
-  - "@grst"
-  - "@ewels"
-  - "@FelixKrueger"
+    - "@drpatelh"
+    - "@grst"
+    - "@ewels"
+    - "@FelixKrueger"

software/fastqc/test/nextflow.config

@@ -1,20 +1,20 @@
 
 params {
-  outdir = "output/"
-  publish_dir_mode = "copy"
-  conda = false
+    outdir = "output/"
+    publish_dir_mode = "copy"
+    conda = false
 }
 
 profiles {
-  conda  {
-    params.conda = true
-  }
-  docker {
-    docker.enabled = true
-    docker.runOptions = '-u \$(id -u):\$(id -g)'
-  }
-  singularity {
-    singularity.enabled = true
-    singularity.autoMounts = true
-  }
+    conda  {
+        params.conda = true
+    }
+    docker {
+        docker.enabled = true
+        docker.runOptions = '-u \$(id -u):\$(id -g)'
+    }
+    singularity {
+        singularity.enabled = true
+        singularity.autoMounts = true
+    }
 }

software/samtools/flagstat/meta.yml

@@ -0,0 +1,69 @@
+name: samtools_flagstat
+description: Counts the number of alignments in a BAM/CRAM/SAM file for each FLAG type
+keywords:
+    - stats
+    - mapping
+    - counts
+    - bam
+    - sam
+    - cram
+tools:
+    - samtools:
+        description: |
+            SAMtools is a set of utilities for interacting with and post-processing
+            short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li.
+            These files are generated as output by short read aligners like BWA.
+        homepage: http://www.htslib.org/
+        documentation: hhttp://www.htslib.org/doc/samtools.html
+        doi: 10.1093/bioinformatics/btp352
+params:
+    - outdir:
+        type: string
+        description: |
+            The pipeline's output directory. By default, the module will
+            output files into `$params.outdir/<SOFTWARE>`
+    - publish_dir_mode:
+        type: string
+        description: |
+            Value for the Nextflow `publishDir` mode parameter.
+            Available: symlink, rellink, link, copy, copyNoFollow, move.
+    - conda:
+        type: boolean
+        description: |
+            Run the module with Conda using the software specified
+            via the `conda` directive
+input:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - bam:
+        type: file
+        description: BAM/CRAM/SAM file
+        pattern: "*.{bam,cram,sam}"
+    - bai:
+        type: file
+        description: Index for BAM/CRAM/SAM file
+        pattern: "*.{bai,crai,sai}"
+    - options:
+        type: map
+        description: |
+            Groovy Map containing module options for passing command-line arguments and
+            output file paths.
+output:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - flagstat:
+        type: file
+        description: File containing samtools flagstat output
+        pattern: "*.{flagstat}"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"
+authors:
+    - "@drpatelh"

software/samtools/flagstat/test/input/test.paired_end.sorted.bam

@@ -0,0 +1 @@
+../../../../../tests/data/bam/test.paired_end.sorted.bam

software/samtools/flagstat/test/input/test.paired_end.sorted.bam.bai

@@ -0,0 +1 @@
+../../../../../tests/data/bam/test.paired_end.sorted.bam.bai

software/samtools/flagstat/test/main.nf

@@ -0,0 +1,19 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SAMTOOLS_FLAGSTAT } from '../main.nf'
+
+workflow test {
+
+    def input = []
+    input = [ [ id:'test', single_end:false ], // meta map
+              file("${baseDir}/input/test.paired_end.sorted.bam", checkIfExists: true),
+              file("${baseDir}/input/test.paired_end.sorted.bam.bai", checkIfExists: true) ]
+
+    SAMTOOLS_FLAGSTAT ( input, [:] )
+}
+
+workflow {
+    test()
+}

software/samtools/flagstat/test/nextflow.config

@@ -0,0 +1,20 @@
+
+params {
+    outdir = "output/"
+    publish_dir_mode = "copy"
+    conda = false
+}
+
+profiles {
+    conda  {
+        params.conda = true
+    }
+    docker {
+        docker.enabled = true
+        docker.runOptions = '-u \$(id -u):\$(id -g)'
+    }
+    singularity {
+        singularity.enabled = true
+        singularity.autoMounts = true
+    }
+}

software/samtools/flagstat/test/output/samtools/test.paired_end.sorted.bam.flagstat

@@ -0,0 +1,13 @@
+20000 + 0 in total (QC-passed reads + QC-failed reads)
+0 + 0 secondary
+0 + 0 supplementary
+0 + 0 duplicates
+20000 + 0 mapped (100.00% : N/A)
+20000 + 0 paired in sequencing
+10000 + 0 read1
+10000 + 0 read2
+20000 + 0 properly paired (100.00% : N/A)
+20000 + 0 with itself and mate mapped
+0 + 0 singletons (0.00% : N/A)
+0 + 0 with mate mapped to a different chr
+0 + 0 with mate mapped to a different chr (mapQ>=5)

software/samtools/idxstats/meta.yml

@@ -0,0 +1,70 @@
+name: samtools_idxstats
+description: Reports alignment summary statistics for a BAM/CRAM/SAM file
+keywords:
+    - stats
+    - mapping
+    - counts
+    - chromosome
+    - bam
+    - sam
+    - cram
+tools:
+    - samtools:
+        description: |
+            SAMtools is a set of utilities for interacting with and post-processing
+            short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li.
+            These files are generated as output by short read aligners like BWA.
+        homepage: http://www.htslib.org/
+        documentation: hhttp://www.htslib.org/doc/samtools.html
+        doi: 10.1093/bioinformatics/btp352
+params:
+    - outdir:
+        type: string
+        description: |
+            The pipeline's output directory. By default, the module will
+            output files into `$params.outdir/<SOFTWARE>`
+    - publish_dir_mode:
+        type: string
+        description: |
+            Value for the Nextflow `publishDir` mode parameter.
+            Available: symlink, rellink, link, copy, copyNoFollow, move.
+    - conda:
+        type: boolean
+        description: |
+            Run the module with Conda using the software specified
+            via the `conda` directive
+input:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - bam:
+        type: file
+        description: BAM/CRAM/SAM file
+        pattern: "*.{bam,cram,sam}"
+    - bai:
+        type: file
+        description: Index for BAM/CRAM/SAM file
+        pattern: "*.{bai,crai,sai}"
+    - options:
+        type: map
+        description: |
+            Groovy Map containing module options for passing command-line arguments and
+            output file paths.
+output:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - idxstats:
+        type: file
+        description: File containing samtools idxstats output
+        pattern: "*.{idxstats}"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"
+authors:
+    - "@drpatelh"

software/samtools/idxstats/test/input/test.paired_end.sorted.bam

@@ -0,0 +1 @@
+../../../../../tests/data/bam/test.paired_end.sorted.bam

software/samtools/idxstats/test/input/test.paired_end.sorted.bam.bai

@@ -0,0 +1 @@
+../../../../../tests/data/bam/test.paired_end.sorted.bam.bai

software/samtools/idxstats/test/main.nf

@@ -0,0 +1,19 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SAMTOOLS_IDXSTATS } from '../main.nf'
+
+workflow test {
+
+    def input = []
+    input = [ [ id:'test', single_end:false ], // meta map
+              file("${baseDir}/input/test.paired_end.sorted.bam", checkIfExists: true),
+              file("${baseDir}/input/test.paired_end.sorted.bam.bai", checkIfExists: true) ]
+
+    SAMTOOLS_IDXSTATS ( input, [:] )
+}
+
+workflow {
+    test()
+}

software/samtools/idxstats/test/nextflow.config

@@ -0,0 +1,20 @@
+
+params {
+    outdir = "output/"
+    publish_dir_mode = "copy"
+    conda = false
+}
+
+profiles {
+    conda  {
+        params.conda = true
+    }
+    docker {
+        docker.enabled = true
+        docker.runOptions = '-u \$(id -u):\$(id -g)'
+    }
+    singularity {
+        singularity.enabled = true
+        singularity.autoMounts = true
+    }
+}

software/samtools/idxstats/test/output/samtools/test.paired_end.sorted.bam.idxstats

@@ -0,0 +1,2 @@
+gi|170079663|ref|NC_010473.1|	4686137	20000	0
+*	0	0	0

software/samtools/index/meta.yml

@@ -1,7 +1,10 @@
-name: samtools index
-description: index a BAM or CRAM file
+name: samtools_index
+description: Index SAM/BAM/CRAM file
 keywords:
     - index
+    - bam
+    - sam
+    - cram
 tools:
     - samtools:
         description: |
@@ -11,17 +14,51 @@ tools:
         homepage: http://www.htslib.org/
         documentation: hhttp://www.htslib.org/doc/samtools.html
         doi: 10.1093/bioinformatics/btp352
+params:
+    - outdir:
+        type: string
+        description: |
+            The pipeline's output directory. By default, the module will
+            output files into `$params.outdir/<SOFTWARE>`
+    - publish_dir_mode:
+        type: string
+        description: |
+            Value for the Nextflow `publishDir` mode parameter.
+            Available: symlink, rellink, link, copy, copyNoFollow, move.
+    - conda:
+        type: boolean
+        description: |
+            Run the module with Conda using the software specified
+            via the `conda` directive
 input:
-    -
-        - input:
-            type: file
-            description: Input BAM or CRAM file
-            pattern: "*.{bam,cram}"
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - bam:
+        type: file
+        description: BAM/CRAM/SAM file
+        pattern: "*.{bam,cram,sam}"
+    - options:
+        type: map
+        description: |
+            Groovy Map containing module options for passing command-line arguments and
+            output file paths.
 output:
-    -
-        - index:
-            type: file
-            description: BAM or CRAM index file
-            pattern: "*.{bai}"
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - bai:
+        type: file
+        description: BAM/CRAM/SAM index file
+        pattern: "*.{bai,crai,sai}"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"
 authors:
+    - "@drpatelh"
     - "@ewels"

software/samtools/index/test/input/test.paired_end.sorted.bam

@@ -0,0 +1 @@
+../../../../../tests/data/bam/test.paired_end.sorted.bam

software/samtools/index/test/main.nf

@@ -1,13 +1,18 @@
 #!/usr/bin/env nextflow
-echo true
 
-cheers = Channel.from 'Bonjour', 'Ciao', 'Hello', 'Hola'
+nextflow.enable.dsl = 2
 
-process sayHello {
-  input:
-    val x from cheers
-  script:
-    """
-    echo '$x world!'
-    """
+include { SAMTOOLS_INDEX } from '../main.nf'
+
+workflow test {
+
+    def input = []
+    input = [ [ id:'test', single_end:false ], // meta map
+              file("${baseDir}/input/test.paired_end.sorted.bam", checkIfExists: true) ]
+
+    SAMTOOLS_INDEX ( input, [:] )
+}
+
+workflow {
+    test()
 }

software/samtools/index/test/nextflow.config

@@ -1,2 +1,20 @@
-docker.enabled = true
-params.outdir = './results'
+
+params {
+    outdir = "output/"
+    publish_dir_mode = "copy"
+    conda = false
+}
+
+profiles {
+    conda  {
+        params.conda = true
+    }
+    docker {
+        docker.enabled = true
+        docker.runOptions = '-u \$(id -u):\$(id -g)'
+    }
+    singularity {
+        singularity.enabled = true
+        singularity.autoMounts = true
+    }
+}

software/samtools/sort/meta.yml

@@ -1,7 +1,10 @@
-name: samtools sort
-description: Sort a BAM or CRAM file
+name: samtools_sort
+description: Sort SAM/BAM/CRAM file
 keywords:
     - sort
+    - bam
+    - sam
+    - cram
 tools:
     - samtools:
         description: |
@@ -11,17 +14,51 @@ tools:
         homepage: http://www.htslib.org/
         documentation: hhttp://www.htslib.org/doc/samtools.html
         doi: 10.1093/bioinformatics/btp352
+params:
+    - outdir:
+        type: string
+        description: |
+            The pipeline's output directory. By default, the module will
+            output files into `$params.outdir/<SOFTWARE>`
+    - publish_dir_mode:
+        type: string
+        description: |
+            Value for the Nextflow `publishDir` mode parameter.
+            Available: symlink, rellink, link, copy, copyNoFollow, move.
+    - conda:
+        type: boolean
+        description: |
+            Run the module with Conda using the software specified
+            via the `conda` directive
 input:
-    -
-        - input:
-            type: file
-            description: Input BAM or CRAM file
-            pattern: "*.{bam,cram}"
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - bam:
+        type: file
+        description: BAM/CRAM/SAM file
+        pattern: "*.{bam,cram,sam}"
+    - options:
+        type: map
+        description: |
+            Groovy Map containing module options for passing command-line arguments and
+            output file paths.
 output:
-    -
-        - sorted_file:
-            type: file
-            description: Sorted BAM or CRAM file
-            pattern: "*.{bam,cram}"
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - bam:
+        type: file
+        description: Sorted BAM/CRAM/SAM file
+        pattern: "*.{bam,cram,sam}"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"
 authors:
+    - "@drpatelh"
     - "@ewels"

software/samtools/sort/test/input/test.paired_end.name.sorted.bam

@@ -0,0 +1 @@
+../../../../../tests/data/bam/test.paired_end.name.sorted.bam

software/samtools/sort/test/main.nf

@@ -1,13 +1,18 @@
 #!/usr/bin/env nextflow
-echo true
 
-cheers = Channel.from 'Bonjour', 'Ciao', 'Hello', 'Hola'
+nextflow.enable.dsl = 2
 
-process sayHello {
-  input:
-    val x from cheers
-  script:
-    """
-    echo '$x world!'
-    """
+include { SAMTOOLS_SORT } from '../main.nf'
+
+workflow test {
+
+    def input = []
+    input = [ [ id:'test', single_end:false ], // meta map
+              file("${baseDir}/input/test.paired_end.name.sorted.bam", checkIfExists: true) ]
+
+    SAMTOOLS_SORT ( input, [:] )
+}
+
+workflow {
+    test()
 }

software/samtools/sort/test/nextflow.config

@@ -1,2 +1,20 @@
-docker.enabled = true
-params.outdir = './results'
+
+params {
+    outdir = "output/"
+    publish_dir_mode = "copy"
+    conda = false
+}
+
+profiles {
+    conda  {
+        params.conda = true
+    }
+    docker {
+        docker.enabled = true
+        docker.runOptions = '-u \$(id -u):\$(id -g)'
+    }
+    singularity {
+        singularity.enabled = true
+        singularity.autoMounts = true
+    }
+}

software/samtools/stats/meta.yml

@@ -0,0 +1,68 @@
+name: samtools_stats
+description: Produces comprehensive statistics from SAM/BAM/CRAM file
+keywords:
+    - statistics
+    - counts
+    - bam
+    - sam
+    - cram
+tools:
+    - samtools:
+        description: |
+            SAMtools is a set of utilities for interacting with and post-processing
+            short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li.
+            These files are generated as output by short read aligners like BWA.
+        homepage: http://www.htslib.org/
+        documentation: hhttp://www.htslib.org/doc/samtools.html
+        doi: 10.1093/bioinformatics/btp352
+params:
+    - outdir:
+        type: string
+        description: |
+            The pipeline's output directory. By default, the module will
+            output files into `$params.outdir/<SOFTWARE>`
+    - publish_dir_mode:
+        type: string
+        description: |
+            Value for the Nextflow `publishDir` mode parameter.
+            Available: symlink, rellink, link, copy, copyNoFollow, move.
+    - conda:
+        type: boolean
+        description: |
+            Run the module with Conda using the software specified
+            via the `conda` directive
+input:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - bam:
+        type: file
+        description: BAM/CRAM/SAM file
+        pattern: "*.{bam,cram,sam}"
+    - bai:
+        type: file
+        description: Index for BAM/CRAM/SAM file
+        pattern: "*.{bai,crai,sai}"
+    - options:
+        type: map
+        description: |
+            Groovy Map containing module options for passing command-line arguments and
+            output file paths.
+output:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - stats:
+        type: file
+        description: File containing samtools stats output
+        pattern: "*.{stats}"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"
+authors:
+    - "@drpatelh"

software/samtools/stats/test/input/test.paired_end.sorted.bam

@@ -0,0 +1 @@
+../../../../../tests/data/bam/test.paired_end.sorted.bam

software/samtools/stats/test/input/test.paired_end.sorted.bam.bai

@@ -0,0 +1 @@
+../../../../../tests/data/bam/test.paired_end.sorted.bam.bai

software/samtools/stats/test/main.nf

@@ -0,0 +1,19 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SAMTOOLS_STATS } from '../main.nf'
+
+workflow test {
+
+    def input = []
+    input = [ [ id:'test', single_end:false ], // meta map
+              file("${baseDir}/input/test.paired_end.sorted.bam", checkIfExists: true),
+              file("${baseDir}/input/test.paired_end.sorted.bam.bai", checkIfExists: true) ]
+
+    SAMTOOLS_STATS ( input, [:] )
+}
+
+workflow {
+    test()
+}

software/samtools/stats/test/nextflow.config

@@ -0,0 +1,20 @@
+
+params {
+    outdir = "output/"
+    publish_dir_mode = "copy"
+    conda = false
+}
+
+profiles {
+    conda  {
+        params.conda = true
+    }
+    docker {
+        docker.enabled = true
+        docker.runOptions = '-u \$(id -u):\$(id -g)'
+    }
+    singularity {
+        singularity.enabled = true
+        singularity.autoMounts = true
+    }
+}

software/trimgalore/meta.yml

@@ -1,97 +1,98 @@
 name: trimgalore
 description: Trim FastQ files using Trim Galore!
 keywords:
-  - trimming
-  - adapters
-  - sequencing adapters
+    - trimming
+    - adapters
+    - sequencing adapters
+    - fastq
 tools:
-  - trimgalore:
-      description: |
-        A wrapper tool around Cutadapt and FastQC to consistently apply quality
-        and adapter trimming to FastQ files, with some extra functionality for
-        MspI-digested RRBS-type (Reduced Representation Bisufite-Seq) libraries.
-      homepage: https://www.bioinformatics.babraham.ac.uk/projects/trim_galore/
-      documentation: https://github.com/FelixKrueger/TrimGalore/blob/master/Docs/Trim_Galore_User_Guide.md
+    - trimgalore:
+        description: |
+            A wrapper tool around Cutadapt and FastQC to consistently apply quality
+            and adapter trimming to FastQ files, with some extra functionality for
+            MspI-digested RRBS-type (Reduced Representation Bisufite-Seq) libraries.
+        homepage: https://www.bioinformatics.babraham.ac.uk/projects/trim_galore/
+        documentation: https://github.com/FelixKrueger/TrimGalore/blob/master/Docs/Trim_Galore_User_Guide.md
 params:
-  - outdir:
-      type: string
-      description: |
-        The pipeline's output directory. By default, the module will
-        output files into `$params.outdir/<SOFTWARE>`
-  - publish_dir_mode:
-      type: string
-      description: |
-        Value for the Nextflow `publishDir` mode parameter.
-        Available: symlink, rellink, link, copy, copyNoFollow, move.
-  - conda:
-      type: boolean
-      description: |
-        Run the module with Conda using the software specified
-        via the `conda` directive
-  - clip_r1:
-      type: integer
-      description: |
-        Instructs Trim Galore to remove bp from the 5' end of read 1
-        (or single-end reads)
-  - clip_r2:
-      type: integer
-      description: |
-        Instructs Trim Galore to remove bp from the 5' end of read 2
-        (paired-end reads only)
-  - three_prime_clip_r1:
-      type: integer
-      description: |
-        Instructs Trim Galore to remove bp from the 3' end of read 1
-        AFTER adapter/quality trimming has been performed
-  - three_prime_clip_r2:
-      type: integer
-      description: |
-        Instructs Trim Galore to re move bp from the 3' end of read 2
-        AFTER adapter/quality trimming has been performed
+    - outdir:
+        type: string
+        description: |
+            The pipeline's output directory. By default, the module will
+            output files into `$params.outdir/<SOFTWARE>`
+    - publish_dir_mode:
+        type: string
+        description: |
+            Value for the Nextflow `publishDir` mode parameter.
+            Available: symlink, rellink, link, copy, copyNoFollow, move.
+    - conda:
+        type: boolean
+        description: |
+            Run the module with Conda using the software specified
+            via the `conda` directive
+    - clip_r1:
+        type: integer
+        description: |
+            Instructs Trim Galore to remove bp from the 5' end of read 1
+            (or single-end reads)
+    - clip_r2:
+        type: integer
+        description: |
+            Instructs Trim Galore to remove bp from the 5' end of read 2
+            (paired-end reads only)
+    - three_prime_clip_r1:
+        type: integer
+        description: |
+            Instructs Trim Galore to remove bp from the 3' end of read 1
+            AFTER adapter/quality trimming has been performed
+    - three_prime_clip_r2:
+        type: integer
+        description: |
+            Instructs Trim Galore to re move bp from the 3' end of read 2
+            AFTER adapter/quality trimming has been performed
 input:
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. [ id:'test', single_end:false ]
-  - reads:
-      type: file
-      description: |
-        List of input FastQ files of size 1 and 2 for single-end and paired-end data,
-        respectively.
-  - options:
-      type: map
-      description: |
-        Groovy Map containing module options for passing command-line arguments and
-        output file paths.
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - reads:
+        type: file
+        description: |
+            List of input FastQ files of size 1 and 2 for single-end and paired-end data,
+            respectively.
+    - options:
+        type: map
+        description: |
+            Groovy Map containing module options for passing command-line arguments and
+            output file paths.
 output:
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. [ id:'test', single_end:false ]
-  - reads:
-      type: file
-      description: |
-        List of input adapter trimmed FastQ files of size 1 and 2 for
-        single-end and paired-end data, respectively.
-      pattern: "*.fq.gz"
-  - html:
-      type: file
-      description: FastQC report (optional)
-      pattern: "*_fastqc.html"
-  - zip:
-      type: file
-      description: FastQC report archive (optional)
-      pattern: "*_fastqc.zip"
-  - log:
-      type: file
-      description: Trim Galore! trimming report
-      pattern: "*report.txt"
-  - version:
-      type: file
-      description: File containing software version
-      pattern: "*.version.txt"
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - reads:
+        type: file
+        description: |
+            List of input adapter trimmed FastQ files of size 1 and 2 for
+            single-end and paired-end data, respectively.
+        pattern: "*.{fq.gz}"
+    - html:
+        type: file
+        description: FastQC report (optional)
+        pattern: "*_{fastqc.html}"
+    - zip:
+        type: file
+        description: FastQC report archive (optional)
+        pattern: "*_{fastqc.zip}"
+    - log:
+        type: file
+        description: Trim Galore! trimming report
+        pattern: "*_{report.txt}"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"
 authors:
     - "@drpatelh"
     - "@ewels"

software/trimgalore/test/nextflow.config

@@ -1,25 +1,25 @@
 
 params {
-  outdir = "output/"
-  publish_dir_mode = "copy"
-  conda = false
+    outdir = "output/"
+    publish_dir_mode = "copy"
+    conda = false
 
-  clip_r1 = 0
-  clip_r2 = 0
-  three_prime_clip_r1 = 0
-  three_prime_clip_r2 = 0
+    clip_r1 = 0
+    clip_r2 = 0
+    three_prime_clip_r1 = 0
+    three_prime_clip_r2 = 0
 }
 
 profiles {
-  conda  {
-    params.conda = true
-  }
-  docker {
-    docker.enabled = true
-    docker.runOptions = '-u \$(id -u):\$(id -g)'
-  }
-  singularity {
-    singularity.enabled = true
-    singularity.autoMounts = true
-  }
+    conda  {
+        params.conda = true
+    }
+    docker {
+        docker.enabled = true
+        docker.runOptions = '-u \$(id -u):\$(id -g)'
+    }
+    singularity {
+        singularity.enabled = true
+        singularity.autoMounts = true
+    }
 }

tests/functions/check_process_outputs.nf

@@ -1,14 +0,0 @@
-#!/usr/bin/env nextflow
-nextflow.preview.dsl = 2
-
-cheers = Channel.from 'Bonjour', 'Ciao', 'Hello', 'Hola'
-
-process check_output {
-    input:
-    val x from cheers
-
-    script:
-    """
-    echo '$x world!'
-    """
-}