Merge pull request #34 from CCBR/nf-modules

docs: link to CCBR/nf-modules & include example

README.md

@@ -55,6 +55,8 @@ See the website for detailed information, documentation, and examples:
    - dependencies
    - project URLs
 1. Write your nextflow workflow.
+   - Where possible, reuse existing modules and subworklows from [CCBR/nf-modules](https://github.com/CCBR/nf-modules)[^3].
+     Also consider contributing new modules & subworkflows to that repository!
 1. Write your documentation in `docs/` and enable GitHub Pages.
    - In settings, go to General > Pages and select the `gh-pages` branch.
      mkdocs will build your site under the `gh-pages` branch, and GitHub Pages will make it available at `https://OWNER.github.io/TOOL_NAME`.
@@ -119,3 +121,4 @@ If you plan to contribute your pipeline to nf-core, don't use this template -- i
 
 [^1]: nektool https://github.com/beardymcjohnface/nektool
 [^2]: instructions for nf-core pipelines https://nf-co.re/docs/contributing/tutorials/creating_with_nf_core
+[^3]: See also our reusable modules and subworkflows for CCBR nextflow pipelines: <https://github.com/CCBR/nf-modules>

main.nf

@@ -17,6 +17,7 @@ input        : ${params.input}
 .stripIndent()
 
 include { FASTQC } from "./modules/local/qc.nf"
+include { BWA_MEM } from './modules/CCBR/bwa/mem'
 
 workflow.onComplete {
     if (!workflow.stubRun && !workflow.commandLine.contains('-preview')) {

modules.json

@@ -0,0 +1,17 @@
+{
+    "name": "CCBR/TOOL_NAME",
+    "homePage": "https://github.com/CCBR/TOOL_NAME",
+    "repos": {
+        "https://github.com/CCBR/nf-modules": {
+            "modules": {
+                "CCBR": {
+                    "bwa/mem": {
+                        "branch": "main",
+                        "git_sha": "490e4454c81e3fb852f7f964356f9981b6f1c439",
+                        "installed_by": ["modules"]
+                    }
+                }
+            }
+        }
+    }
+}

modules/CCBR/bwa/mem/main.nf

@@ -0,0 +1,53 @@
+process BWA_MEM {
+    tag { meta.id }
+    label 'process_high'
+
+    container 'nciccbr/ccbr_ubuntu_base_20.04:v5'
+
+    input:
+        tuple val(meta), path(fastq)
+        tuple val(meta_idx), path(index_files)
+
+    output:
+        tuple val(meta), path("*.bam"), path("*.bai"), emit: bam
+        path  "versions.yml"                         , emit: versions
+
+    when:
+        task.ext.when == null || task.ext.when
+
+    script:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    # current working directory is a tmpdir when 'scratch' is set
+    TMP=tmp/
+    mkdir \$TMP
+    trap 'rm -rf "\$TMP"' EXIT
+
+    INDEX=`find -L ./ -name "*.amb" | sed 's/\\.amb\$//'`
+
+    bwa mem \\
+      -t ${task.cpus} \\
+      -o \$TMP/align.bam \\
+      \$INDEX \\
+      ${fastq}
+
+    samtools sort \\
+      -@ ${task.cpus} \\
+      -m 2G \\
+      -T \$TMP \\
+      --write-index \\
+      -o ${prefix}.bam##idx##${prefix}.bam.bai \\
+      \$TMP/align.bam
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bwa: \$(echo \$(bwa 2>&1) | sed 's/^.*Version: //; s/Contact:.*\$//')
+        samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+    END_VERSIONS
+    """
+
+    stub:
+    """
+    touch ${meta.id}.bam ${meta.id}.bam.bai versions.yml
+    """
+}

modules/CCBR/bwa/mem/meta.yml

@@ -0,0 +1,51 @@
+name: bwa_mem
+description: Performs fastq alignment to a fasta reference using BWA. Adapted from the nf-core bwa-mem module.
+keywords:
+  - 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
+      licence: ["GPL-3.0-or-later"]
+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: "Directory containing BWA index *.{amb,ann,bwt,pac,sa}"
+output:
+  - bam:
+      type: file
+      description: Output BAM file containing read alignments
+      pattern: "*.{bam}"
+  - bai:
+      type: file
+      description: Output BAI index file
+      pattern: "*.{bai}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@kelly-sovacool"
+maintainers:
+  - "@kelly-sovacool"