Merge pull request #121 from KevinMenden/master

Adding test for STAR
2024-09-20 23:32:05 +00:00 · 2021-01-26 13:01:27 +00:00 · 2021-01-26 13:01:27 +00:00 · 3ef16b7cfd
commit 3ef16b7cfd
parent daa25b9329 84355f674d
9 changed files with 76885 additions and 13 deletions
--- a/.github/workflows/star_align.yml
+++ b/.github/workflows/star_align.yml
@ -0,0 +1,40 @@
+name: star_genomegenerate
+on:
+  push:
+    paths:
+      - software/star/align/**
+      - .github/workflows/star_align.yml
+      - tests/software/star/**
+  pull_request:
+    paths:
+      - software/star/align/**
+      - .github/workflows/star_align.yml
+      - tests/software/star/**
+
+jobs:
+  ci_test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        nxf_version: [20.11.0-edge]
+    env:
+      NXF_ANSI_LOG: false
+    steps:
+      - uses: actions/checkout@v2
+
+      - name: Install Nextflow
+        env:
+          NXF_VER: ${{ matrix.nxf_version }}
+        run: |
+          wget -qO- get.nextflow.io | bash
+          sudo mv nextflow /usr/local/bin/
+
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: "3.x"
+      - name: Install dependencies
+        run: python -m pip install --upgrade pip pytest-workflow
+
+      # Test the module
+      - run: pytest --tag star_align --symlink --wt 2
--- a/.github/workflows/star_genomegenerate.yml
+++ b/.github/workflows/star_genomegenerate.yml
@ -0,0 +1,40 @@
+name: star_genomegenerate
+on:
+  push:
+    paths:
+      - software/star/genomegenerate/**
+      - .github/workflows/star_genomegenerate.yml
+      - tests/software/star/**
+  pull_request:
+    paths:
+      - software/star/genomegenerate/**
+      - .github/workflows/star_genomegenerate.yml
+      - tests/software/star/**
+
+jobs:
+  ci_test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        nxf_version: [20.11.0-edge]
+    env:
+      NXF_ANSI_LOG: false
+    steps:
+      - uses: actions/checkout@v2
+
+      - name: Install Nextflow
+        env:
+          NXF_VER: ${{ matrix.nxf_version }}
+        run: |
+          wget -qO- get.nextflow.io | bash
+          sudo mv nextflow /usr/local/bin/
+
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: "3.x"
+      - name: Install dependencies
+        run: python -m pip install --upgrade pip pytest-workflow
+
+      # Test the module
+      - run: pytest --tag star_genomegenerate --symlink --wt 2
--- a/software/star/align/main.nf
+++ b/software/star/align/main.nf
@ -12,46 +12,51 @@ process STAR_ALIGN {
        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:meta.id) }

    // Note: 2.7X indices incompatible with AWS iGenomes.
-    conda (params.enable_conda ? "bioconda::star=2.6.1d" : null)
+    conda (params.enable_conda ? 'bioconda::star=2.6.1d' : null)
    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
-        container "https://depot.galaxyproject.org/singularity/star:2.6.1d--0"
+        container 'https://depot.galaxyproject.org/singularity/star:2.6.1d--0'
    } else {
-        container "quay.io/biocontainers/star:2.6.1d--0"
+        container 'quay.io/biocontainers/star:2.6.1d--0'
    }

-
    input:
    tuple val(meta), path(reads)
    path  index
    path  gtf

    output:
-    tuple val(meta), path("*Aligned.out.bam") , emit: bam
-    tuple val(meta), path("*Log.final.out")   , emit: log_final
-    tuple val(meta), path("*Log.out")         , emit: log_out
-    tuple val(meta), path("*Log.progress.out"), emit: log_progress
-    path  "*.version.txt"                     , emit: version
+    tuple val(meta), path('*d.out.bam')       , emit: bam
+    tuple val(meta), path('*Log.final.out')   , emit: log_final
+    tuple val(meta), path('*Log.out')         , emit: log_out
+    tuple val(meta), path('*Log.progress.out'), emit: log_progress
+    path  '*.version.txt'                     , emit: version

-    tuple val(meta), path("*sortedByCoord.out.bam")  , optional:true, emit: bam_sorted
-    tuple val(meta), path("*toTranscriptome.out.bam"), optional:true, emit: bam_transcript
-    tuple val(meta), path("*fastq.gz")               , optional:true, emit: fastq
-    tuple val(meta), path("*.tab")                   , optional:true, emit: tab
+    tuple val(meta), path('*sortedByCoord.out.bam')  , optional:true, emit: bam_sorted
+    tuple val(meta), path('*toTranscriptome.out.bam'), optional:true, emit: bam_transcript
+    tuple val(meta), path('*Aligned.unsort.out.bam') , optional:true, emit: bam_unsorted
+    tuple val(meta), path('*fastq.gz')               , optional:true, emit: fastq
+    tuple val(meta), path('*.tab')                   , optional:true, emit: tab

    script:
    def software   = getSoftwareName(task.process)
    def prefix     = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
    def ignore_gtf = params.star_ignore_sjdbgtf ? '' : "--sjdbGTFfile $gtf"
    def seq_center = params.seq_center ? "--outSAMattrRGline ID:$prefix 'CN:$params.seq_center' 'SM:$prefix'" : "--outSAMattrRGline ID:$prefix 'SM:$prefix'"
+    def out_sam_type = (options.args.contains('--outSAMtype')) ? '' : '--outSAMtype BAM Unsorted'
+    def mv_unsorted_bam = (options.args.contains('--outSAMtype BAM Unsorted SortedByCoordinate')) ? "mv ${prefix}.Aligned.out.bam ${prefix}.Aligned.unsort.out.bam" : ''
    """
    STAR \\
        --genomeDir $index \\
        --readFilesIn $reads  \\
        --runThreadN $task.cpus \\
        --outFileNamePrefix $prefix. \\
+        $out_sam_type \\
        $ignore_gtf \\
        $seq_center \\
        $options.args

+    $mv_unsorted_bam
+
    if [ -f ${prefix}.Unmapped.out.mate1 ]; then
        mv ${prefix}.Unmapped.out.mate1 ${prefix}.unmapped_1.fastq
        gzip ${prefix}.unmapped_1.fastq
--- a/software/star/align/meta.yml
+++ b/software/star/align/meta.yml
@ -0,0 +1,97 @@
+name: star_align
+description: Align reads to a reference genome using STAR
+keywords:
+  - align
+  - fasta
+  - genome
+  - reference
+tools:
+  - star:
+      description: |
+        STAR is a software package for mapping DNA sequences against
+        a large reference genome, such as the human genome.
+      homepage: https://github.com/alexdobin/STAR
+      manual: https://github.com/alexdobin/STAR/blob/master/doc/STARmanual.pdf
+      doi: 10.1093/bioinformatics/bts635
+params:
+  - outdir:
+      type: string
+      description: |
+        The pipeline's output directory. By default, the module will
+        output files into `$params.outdir/<SOFTWARE>`
+  - publish_dir_mode:
+      type: string
+      description: |
+        Value for the Nextflow `publishDir` mode parameter.
+        Available: symlink, rellink, link, copy, copyNoFollow, move.
+  - enable_conda:
+      type: boolean
+      description: |
+        Run the module with Conda using the software specified
+        via the `conda` directive
+  - singularity_pull_docker_container:
+      type: boolean
+      description: |
+        Instead of directly downloading Singularity images for use with Singularity,
+        force the workflow to pull and convert Docker containers instead.
+
+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: directory
+      description: STAR genome index
+      pattern: "star"
+output:
+  - bam:
+      type: file
+      description: Output BAM file containing read alignments
+      pattern: "*.{bam}"
+  - log_final:
+      type: file
+      description: STAR final log file
+      pattern: "*Log.final.out"
+  - log_out:
+      type: file
+      description: STAR lot out file
+      pattern: "*Log.out"
+  - log_progress:
+      type: file
+      description: STAR log progress file
+      pattern: "*Log.progress.out"
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.{version.txt}"
+  - bam_sorted:
+      type: file
+      description: Sorted BAM file of read alignments (optional)
+      pattern: "*sortedByCoord.out.bam"
+  - bam_transcript:
+      type: file
+      description: Output BAM file of transcriptome alignment (optional)
+      pattern: "*toTranscriptome.out.bam"
+  - bam_unsorted:
+      type: file
+      description: Unsorted BAM file of read alignments (optional)
+      pattern: "*Aligned.unsort.out.bam"
+  - fastq:
+      type: file
+      description: Unmapped FastQ files (optional)
+      pattern: "*fastq.gz"
+  - tab:
+      type: file
+      description: STAR output tab file(s) (optional)
+      pattern: "*.tab"
+
+authors:
+  - "@kevinmenden"
+  - "@drpatelh"
--- a/software/star/genomegenerate/meta.yml
+++ b/software/star/genomegenerate/meta.yml
@ -0,0 +1,58 @@
+name: star_genomegenerate
+description: Create index for STAR
+keywords:
+  - index
+  - fasta
+  - genome
+  - reference
+tools:
+  - star:
+      description: |
+        STAR is a software package for mapping DNA sequences against
+        a large reference genome, such as the human genome.
+      homepage: https://github.com/alexdobin/STAR
+      manual: https://github.com/alexdobin/STAR/blob/master/doc/STARmanual.pdf
+      doi: 10.1093/bioinformatics/bts635
+params:
+  - outdir:
+      type: string
+      description: |
+        The pipeline's output directory. By default, the module will
+        output files into `$params.outdir/<SOFTWARE>`
+  - publish_dir_mode:
+      type: string
+      description: |
+        Value for the Nextflow `publishDir` mode parameter.
+        Available: symlink, rellink, link, copy, copyNoFollow, move.
+  - enable_conda:
+      type: boolean
+      description: |
+        Run the module with Conda using the software specified
+        via the `conda` directive
+  - singularity_pull_docker_container:
+      type: boolean
+      description: |
+        Instead of directly downloading Singularity images for use with Singularity,
+        force the workflow to pull and convert Docker containers instead.
+
+input:
+  - fasta:
+      type: file
+      description: Fasta file of the reference genome
+  - gtf:
+      type: file
+      description: GTF file of the reference genome
+
+output:
+  - index:
+      type: directory
+      description: Folder containing the star index files
+      pattern: "star"
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.{version.txt}"
+
+authors:
+  - "@kevinmenden"
+  - "@drpatelh"
--- a/tests/data/fasta/E_coli/GCF_000019425.1_ASM1942v1_genomic.fna
+++ b/tests/data/fasta/E_coli/GCF_000019425.1_ASM1942v1_genomic.fna
--- a/tests/data/gff/GCF_000019425.1_ASM1942v1_genomic.gtf
+++ b/tests/data/gff/GCF_000019425.1_ASM1942v1_genomic.gtf
--- a/tests/software/star/main.nf
+++ b/tests/software/star/main.nf
@ -0,0 +1,36 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+def options_align = [args: '--readFilesCommand zcat']
+def options_gg = [args: '--genomeSAindexNbases 9']
+include { STAR_ALIGN } from '../../../software/star/align/main.nf' addParams( options: options_align )
+include { STAR_GENOMEGENERATE } from '../../../software/star/genomegenerate/main.nf'  addParams( options: options_gg )
+
+workflow test_star_genomegenerate {
+    fasta = file("${launchDir}/tests/data/fasta/E_coli/GCF_000019425.1_ASM1942v1_genomic.fna", checkIfExists: true)
+    gtf = file("${launchDir}/tests/data/gff/GCF_000019425.1_ASM1942v1_genomic.gtf", checkIfExists: true)
+    STAR_GENOMEGENERATE ( fasta, gtf )
+}
+
+workflow test_star_alignment_single_end {
+    fasta = file("${launchDir}/tests/data/fasta/E_coli/GCF_000019425.1_ASM1942v1_genomic.fna", checkIfExists: true)
+    gtf = file("${launchDir}/tests/data/gff/GCF_000019425.1_ASM1942v1_genomic.gtf", checkIfExists: true)
+    STAR_GENOMEGENERATE ( fasta, gtf )
+
+    input = [ [ id:'test', single_end:true ], // meta map
+              [ file("${launchDir}/tests/data/fastq/rna/test_single_end.fastq.gz", checkIfExists: true) ] ]
+
+    STAR_ALIGN( input, STAR_GENOMEGENERATE.out.index, gtf)
+}
+
+workflow test_star_alignment_paired_end {
+    fasta = file("${launchDir}/tests/data/fasta/E_coli/GCF_000019425.1_ASM1942v1_genomic.fna", checkIfExists: true)
+    gtf = file("${launchDir}/tests/data/gff/GCF_000019425.1_ASM1942v1_genomic.gtf", checkIfExists: true)
+    STAR_GENOMEGENERATE ( fasta, gtf )
+
+    input = [ [ id:'test', single_end:false ], // meta map
+               [ file("${launchDir}/tests/data/fastq/rna/test_R1.fastq.gz", checkIfExists: true),
+                 file("${launchDir}/tests/data/fastq/rna/test_R2.fastq.gz", checkIfExists: true) ] ]
+
+    STAR_ALIGN( input, STAR_GENOMEGENERATE.out.index, gtf)
+}
--- a/tests/software/star/test.yml
+++ b/tests/software/star/test.yml
@ -0,0 +1,108 @@
+- name: Run star genomegenerate
+  command: nextflow run ./tests/software/star -profile docker -entry test_star_genomegenerate -c tests/config/nextflow.config
+  tags:
+    - star
+    - star_genomegenerate
+  files:
+    - path: output/star/star/Genome
+      md5sum: 323c992bac354f93073ce0fc43f222f8
+    - path: output/star/star/SA
+      md5sum: 3e70e4fc6d031e1915bb510727f2c559
+    - path: output/star/star/SAindex
+      md5sum: a94198b95a245d4f64af2a7133b6ec7b
+    - path: output/star/star/chrLength.txt
+      md5sum: f2bea3725fe1c01420c57fb73bdeb31a
+    - path: output/star/star/chrNameLength.txt
+      md5sum: c7ceb0a8827b2ea91c386933bee48742
+    - path: output/star/star/chrStart.txt
+      md5sum: faf5c55020c99eceeef3e34188ac0d2f
+    - path: output/star/star/exonGeTrInfo.tab
+      md5sum: aec6e7a1ae3fc8c638ce5a9ce9c886b6
+    - path: output/star/star/exonInfo.tab
+      md5sum: 42eca6ebc2dc72d9d6e6b3acd3714343
+    - path: output/star/star/genomeParameters.txt
+      md5sum: ed47b8b034cae2fefcdb39321aea47cd
+    - path: output/star/star/sjdbInfo.txt
+      md5sum: 1082ab459363b3f2f7aabcef0979c1ed
+    - path: output/star/star/sjdbList.fromGTF.out.tab
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/star/star/sjdbList.out.tab
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/star/star/transcriptInfo.tab
+      md5sum: 8fbe69abbbef4f89da3854873984dbac
+
+- name: Run star single-end alignment
+  command: nextflow run ./tests/software/star -profile docker -entry test_star_alignment_single_end -c tests/config/nextflow.config
+  tags:
+    - star
+    - star_align
+    - star_alignment_single_end
+  files:
+    - path: output/star/star/Genome
+      md5sum: 323c992bac354f93073ce0fc43f222f8
+    - path: output/star/star/SA
+      md5sum: 3e70e4fc6d031e1915bb510727f2c559
+    - path: output/star/star/SAindex
+      md5sum: a94198b95a245d4f64af2a7133b6ec7b
+    - path: output/star/star/chrLength.txt
+      md5sum: f2bea3725fe1c01420c57fb73bdeb31a
+    - path: output/star/star/chrNameLength.txt
+      md5sum: c7ceb0a8827b2ea91c386933bee48742
+    - path: output/star/star/chrStart.txt
+      md5sum: faf5c55020c99eceeef3e34188ac0d2f
+    - path: output/star/star/exonGeTrInfo.tab
+      md5sum: aec6e7a1ae3fc8c638ce5a9ce9c886b6
+    - path: output/star/star/exonInfo.tab
+      md5sum: 42eca6ebc2dc72d9d6e6b3acd3714343
+    - path: output/star/star/genomeParameters.txt
+      md5sum: ed47b8b034cae2fefcdb39321aea47cd
+    - path: output/star/star/sjdbInfo.txt
+      md5sum: 1082ab459363b3f2f7aabcef0979c1ed
+    - path: output/star/star/sjdbList.fromGTF.out.tab
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/star/star/sjdbList.out.tab
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/star/star/transcriptInfo.tab
+      md5sum: 8fbe69abbbef4f89da3854873984dbac
+    - path: output/star/test.Aligned.out.bam
+      md5sum: d7f59c1728482e76a18e3f6eb9c66c25
+    - path: output/star/test.SJ.out.tab
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+
+- name: Run star paired-end alignment
+  command: nextflow run ./tests/software/star -profile docker -entry test_star_alignment_paired_end -c tests/config/nextflow.config
+  tags:
+    - star
+    - star_align
+    - star_alignment_paired_end
+  files:
+    - path: output/star/star/Genome
+      md5sum: 323c992bac354f93073ce0fc43f222f8
+    - path: output/star/star/SA
+      md5sum: 3e70e4fc6d031e1915bb510727f2c559
+    - path: output/star/star/SAindex
+      md5sum: a94198b95a245d4f64af2a7133b6ec7b
+    - path: output/star/star/chrLength.txt
+      md5sum: f2bea3725fe1c01420c57fb73bdeb31a
+    - path: output/star/star/chrNameLength.txt
+      md5sum: c7ceb0a8827b2ea91c386933bee48742
+    - path: output/star/star/chrStart.txt
+      md5sum: faf5c55020c99eceeef3e34188ac0d2f
+    - path: output/star/star/exonGeTrInfo.tab
+      md5sum: aec6e7a1ae3fc8c638ce5a9ce9c886b6
+    - path: output/star/star/exonInfo.tab
+      md5sum: 42eca6ebc2dc72d9d6e6b3acd3714343
+    - path: output/star/star/genomeParameters.txt
+      md5sum: ed47b8b034cae2fefcdb39321aea47cd
+    - path: output/star/star/sjdbInfo.txt
+      md5sum: 1082ab459363b3f2f7aabcef0979c1ed
+    - path: output/star/star/sjdbList.fromGTF.out.tab
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/star/star/sjdbList.out.tab
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/star/star/transcriptInfo.tab
+      md5sum: 8fbe69abbbef4f89da3854873984dbac
+    - path: output/star/test.Aligned.out.bam
+      md5sum: 5c52bcaa15e86914ad6b895638235166
+    - path: output/star/test.SJ.out.tab
+      md5sum: d41d8cd98f00b204e9800998ecf8427e