Adding plink/vcf module (#656)

* adding plink module using nf-core tool [ci skip]

* Restructures the project for plink/vcf (#1)

* Add version string for plink
* Create a plink/vcf module

* small tweaks on main.nf and started to test [ci skip]

* small changes on test args, local test with docker passed!

* Update plink/vcf module listing

* Update tag

* fix tags as per linting guidelines

* revert to the original state of tags

* adding --threads to `main.nf` and `meta.yml` information

Co-authored-by: Abhinav Sharma <abhi18av@users.noreply.github.com>

modules/plink/vcf/functions.nf

@@ -0,0 +1,68 @@
+//
+//  Utility functions used in nf-core DSL2 module files
+//
+
+//
+// Extract name of software tool from process name using $task.process
+//
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+//
+// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+//
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+//
+// Tidy up and join elements of a list to return a path string
+//
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+//
+// Function to save/publish module results
+//
+def saveFiles(Map args) {
+    if (!args.filename.endsWith('.version.txt')) {
+        def ioptions  = initOptions(args.options)
+        def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+        if (ioptions.publish_by_meta) {
+            def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+            for (key in key_list) {
+                if (args.meta && key instanceof String) {
+                    def path = key
+                    if (args.meta.containsKey(key)) {
+                        path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key]
+                    }
+                    path = path instanceof String ? path : ''
+                    path_list.add(path)
+                }
+            }
+        }
+        if (ioptions.publish_files instanceof Map) {
+            for (ext in ioptions.publish_files) {
+                if (args.filename.endsWith(ext.key)) {
+                    def ext_list = path_list.collect()
+                    ext_list.add(ext.value)
+                    return "${getPathFromList(ext_list)}/$args.filename"
+                }
+            }
+        } else if (ioptions.publish_files == null) {
+            return "${getPathFromList(path_list)}/$args.filename"
+        }
+    }
+}

modules/plink/vcf/main.nf

@@ -0,0 +1,44 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process PLINK_VCF {
+    tag "$meta.id"
+    label 'process_medium'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) }
+
+    conda (params.enable_conda ? "bioconda::plink=1.90b6.21" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/plink:1.90b6.21--h779adbc_1"
+    } else {
+        container "quay.io/biocontainers/plink:1.90b6.21--h779adbc_1"
+    }
+
+    input:
+    tuple val(meta), path(vcf)
+
+    output:
+    tuple val(meta), path("*.bed"), emit: bed, optional: true
+    tuple val(meta), path("*.bim"), emit: bim, optional: true
+    tuple val(meta), path("*.fam"), emit: fam, optional: true
+
+    path "*.version.txt", emit: version
+
+    script:
+    def software = getSoftwareName(task.process)
+    def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+
+    """
+    plink \\
+        --vcf ${vcf} \\
+        $options.args \\
+        --threads $task.cpus \\
+        --out ${prefix}
+
+    echo \$(plink --version 2>&1) | sed 's/^PLINK //' | sed 's/..-bit.*//'> ${software}.version.txt
+    """
+}

modules/plink/vcf/meta.yml

@@ -0,0 +1,53 @@
+name: plink_vcf
+description: Analyses variant calling files using plink
+keywords:
+  - plink
+  - vcf
+tools:
+  - plink:
+      description: |
+        Whole genome association analysis toolset, designed to perform a range
+        of basic, large-scale analyses in a computationally efficient manner
+      homepage: "https://www.cog-genomics.org/plink"
+      documentation: None
+      tool_dev_url: "https://www.cog-genomics.org/plink/1.9/dev"
+      doi: ""
+      licence: ['GPL']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - vcf:
+      type: file
+      description: Variant calling file (vcf)
+      pattern: "*.{vcf}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.{version.txt}"
+  - bed:
+      type: file
+      description: PLINK binary biallelic genotype table
+      pattern: "*.{bed}"
+  - bim:
+      type: file
+      description: PLINK extended MAP file
+      pattern: "*.{bim}"
+  - fam:
+      type: file
+      description: PLINK sample information file
+      pattern: "*.{fam}"
+
+authors:
+  - "@Mxrcon"
+  - "@abhi18av"

tests/config/pytest_modules.yml

@@ -659,6 +659,10 @@ plasmidid:
   - modules/plasmidid/**
   - tests/modules/plasmidid/**
 
+plink/vcf:
+  - modules/plink/vcf/**
+  - tests/modules/plink/vcf/**
+
 preseq/lcextrap:
   - modules/preseq/lcextrap/**
   - tests/modules/preseq/lcextrap/**

tests/modules/plink/vcf/main.nf

@@ -0,0 +1,13 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { PLINK_VCF } from '../../../../modules/plink/vcf/main.nf' addParams( options: ['args':" --make-bed --biallelic-only strict --vcf-half-call missing --double-id --recode ped --id-delim \'=\' --allow-extra-chr"])
+
+workflow test_plink_vcf {
+
+    input = [ [ id:'test', single_end:false ], // meta map
+              file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true) ]
+
+    PLINK_VCF ( input )
+}

tests/modules/plink/vcf/test.yml

@@ -0,0 +1,12 @@
+- name: plink vcf test_plink_vcf
+  command: nextflow run tests/modules/plink/vcf -entry test_plink_vcf -c tests/config/nextflow.config
+  tags:
+    - plink
+    - plink/vcf
+  files:
+    - path: output/plink/test.bed
+      md5sum: 55c3ab2636212911b5f952ef6f5d855c
+    - path: output/plink/test.bim
+      md5sum: 54164b6f103e152de05712c6bb317db8
+    - path: output/plink/test.fam
+      md5sum: 22d32d7daa3ae6b819a24895e82b2a70