Merge pull request #62 from drpatelh/master

Add docs and test data for BWA mem

.github/workflows/bwa_mem.yml

@@ -0,0 +1,30 @@
+name: bwa_mem
+on:
+  push:
+    paths:
+      - software/bwa/mem/**
+      - .github/workflows/bwa_mem.yml
+      - tests
+  pull_request:
+    paths:
+      - software/bwa/mem/**
+      - .github/workflows/bwa_mem.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/bwa/mem/test/ -profile docker

software/bwa/mem/meta.yml

@@ -1,42 +1,68 @@
-name: bwa mem
-description: Performs fastq alignment to a fasta reference using the burrows-wheeler aligner
+name: bwa_mem
+description: Performs fastq alignment to a fasta reference using BWA
 keywords:
-    - mem
-    - bwa
-    - alignment
+  - mem
+  - bwa
+  - alignment
+  - map
 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
 input:
-    -
-        - id:
-            type: val
-            description: read/read pair id
-        - reads:
-            type: file
-            description: Input fastq file
-            pattern: "*.{fastq,fq}"
-        - index:
-            type: file
-            description: bwa indexes file
-            pattern: "*.{amb,ann,bwt,pac,sa}"
-        - prefix:
-            type: val
-            description: bwa index prefix, equivalent to index file names without extensions. Usually the reference genome file name unless otherwise specified.
+  - 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
-            pattern: "*.bam"
-        - bamindex:
-            type: file
-            description: Output bam index file
-            pattern: "*.bai"
-
+  - bam:
+      type: file
+      description: Output BAM file containing read alignments
+      pattern: "*.bam"
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.version.txt"
 authors:
-    - "@jeremy1805"
+  - "@drpatelh"
+  - "@jeremy1805"

software/bwa/mem/test/input/Ecoli_DNA_R1.fastq.gz

@@ -0,0 +1 @@
+../../../../../tests/data/fastq/dna/Ecoli_DNA_R1.fastq.gz

software/bwa/mem/test/input/Ecoli_DNA_R2.fastq.gz

@@ -0,0 +1 @@
+../../../../../tests/data/fastq/dna/Ecoli_DNA_R2.fastq.gz

software/bwa/mem/test/input/NC_010473.fa

@@ -0,0 +1 @@
+../../../../../tests/data/fasta/E_coli/NC_010473.fa

software/bwa/mem/test/input/index

@@ -0,0 +1 @@
+../../../../../tests/data/index/E_coli/bwa/

software/bwa/mem/test/main.nf

@@ -1,13 +1,45 @@
 #!/usr/bin/env nextflow
-nextflow.preview.dsl = 2
-include '../../../../tests/functions/check_process_outputs.nf' params(params)
-include '../main.nf' params(params)
 
-reads = '../../../../test-datasets/tools/bwa/mem/reads/*_R{1,2}_001.fastq.gz'
-index = '../../../../test-datasets/tools/bwa/mem/index/H3N2.{amb,ann,bwt,pac,sa}'
-prefix = 'H3N2'
+nextflow.enable.dsl = 2
+
+include { BWA_MEM } from '../main.nf'
+
+/*
+ * Test with single-end data
+ */
+workflow test_single_end {
+
+    def input = []
+    input = [ [ id:'test', single_end:true ], // meta map
+              [ file("${baseDir}/input/Ecoli_DNA_R1.fastq.gz", checkIfExists: true) ] ]
+
+    BWA_MEM (
+        input,
+        file("${baseDir}/input/index/NC_010473.fa.{amb,ann,bwt,pac,sa}", checkIfExists: true),
+        file("${baseDir}/input/NC_010473.fa", checkIfExists: true),
+        [ publish_dir:'test_single_end' ]
+    )
+}
+
+/*
+ * Test with paired-end data
+ */
+workflow test_paired_end {
+
+    def input = []
+    input = [ [ id:'test', single_end:false ], // meta map
+              [ file("${baseDir}/input/Ecoli_DNA_R1.fastq.gz", checkIfExists: true),
+                file("${baseDir}/input/Ecoli_DNA_R2.fastq.gz", checkIfExists: true) ] ]
+
+    BWA_MEM (
+        input,
+        file("${baseDir}/input/index/NC_010473.fa.{amb,ann,bwt,pac,sa}", checkIfExists: true),
+        file("${baseDir}/input/NC_010473.fa", checkIfExists: true),
+        [ publish_dir:'test_paired_end' ]
+    )
+}
 
 workflow {
-  read_input=Channel.fromFilePairs(reads)
-  bwa_mem(read_input,file(index),prefix)
+    test_single_end()
+    test_paired_end()
 }

software/bwa/mem/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
+  }
+}

tests/data/index/E_coli/bwa/NC_010473.fa.amb

@@ -0,0 +1,3 @@
+4686137 1 2
+20895 1 Y
+142347 1 R

tests/data/index/E_coli/bwa/NC_010473.fa.ann

@@ -0,0 +1,3 @@
+4686137 1 11
+0 gi|170079663|ref|NC_010473.1| Escherichia coli str. K-12 substr. DH10B, complete genome
+0 4686137 2