Add module get_chrom_sizes (#1063)

* hifiasm copied from fastqc

* hifiasm tests init from fastqc

* meta.yml init; test.yml and main.nf for printing version

* Add hifiasm version printing

* Removed spaced on an empty line

* Reverted hifiasm from main

* init getchromsizes

* add tests for getchromsizes

* Included meta.yml

* removed whitespace

* Moved getchromsizes to custom folder

* Update modules/custom/getchromsizes/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

Co-authored-by: Sviatoslav Sidorov <sviatoslav.sidorov@crick.ac.uk>
Co-authored-by: Svyatoslav Sidorov <svet.sidorov@gmail.com>
Co-authored-by: Chris Cheshire <chris.j.cheshire@gmail.com>
Co-authored-by: Tamara Hodgetts <hodgett@crick.ac.uk>
Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

modules/custom/getchromsizes/functions.nf

@@ -0,0 +1,78 @@
+//
+//  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()
+}
+
+//
+// Extract name of module from process name using $task.process
+//
+def getProcessName(task_process) {
+    return task_process.tokenize(':')[-1]
+}
+
+//
+// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+//
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+//
+// Tidy up and join elements of a list to return a path string
+//
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+//
+// Function to save/publish module results
+//
+def saveFiles(Map args) {
+    def ioptions  = initOptions(args.options)
+    def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+
+    // Do not publish versions.yml unless running from pytest workflow
+    if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) {
+        return null
+    }
+    if (ioptions.publish_by_meta) {
+        def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+        for (key in key_list) {
+            if (args.meta && key instanceof String) {
+                def path = key
+                if (args.meta.containsKey(key)) {
+                    path = args.meta[key] instanceof Boolean ? "${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/custom/getchromsizes/main.nf

@@ -0,0 +1,39 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process CUSTOM_GETCHROMSIZES {
+    tag "$fasta"
+    label 'process_low'
+    publishDir "${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::samtools=1.14" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/samtools:1.14--hb421002_0"
+    } else {
+        container "quay.io/biocontainers/samtools:1.14--hb421002_0"
+    }
+
+    input:
+    path fasta
+
+    output:
+    path '*.sizes'      , emit: sizes
+    path '*.fai'        , emit: fai
+    path  "versions.yml", emit: versions
+
+    script:
+    """
+    samtools faidx $fasta
+    cut -f 1,2 ${fasta}.fai > ${fasta}.sizes
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+    END_VERSIONS
+    """
+}

modules/custom/getchromsizes/meta.yml

@@ -0,0 +1,39 @@
+name: custom_getchromsizes
+description: Generates a FASTA file of chromosome sizes and a fasta index file
+keywords:
+  - fasta
+  - chromosome
+  - indexing
+tools:
+  - samtools:
+      description: Tools for dealing with SAM, BAM and CRAM files
+      homepage: http://www.htslib.org/
+      documentation: http://www.htslib.org/doc/samtools.html
+      tool_dev_url: https://github.com/samtools/samtools
+      doi: 10.1093/bioinformatics/btp352
+      licence: ['MIT']
+
+input:
+  - fasta:
+      type: file
+      description: FASTA file
+      pattern: "*.{fasta}"
+
+output:
+  - sizes:
+      type: file
+      description: File containing chromosome lengths
+      pattern: "*.{sizes}"
+  - fai:
+      type: file
+      description: FASTA index file
+      pattern: "*.{fai}"
+  - versions:
+      type: file
+      description: File containing software version
+      pattern: "versions.yml"
+
+
+authors:
+  - "@tamara-hodgetts"
+  - "@chris-cheshire"

tests/config/pytest_modules.yml

@@ -318,6 +318,10 @@ custom/dumpsoftwareversions:
   - modules/custom/dumpsoftwareversions/**
   - tests/modules/custom/dumpsoftwareversions/**
 
+custom/getchromsizes:
+  - modules/custom/getchromsizes/**
+  - tests/modules/custom/getchromsizes/**
+
 cutadapt:
   - modules/cutadapt/**
   - tests/modules/cutadapt/**

tests/modules/custom/getchromsizes/main.nf

@@ -0,0 +1,12 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CUSTOM_GETCHROMSIZES } from '../../../../modules/custom/getchromsizes/main.nf' addParams( options: [:] )
+
+workflow test_custom_getchromsizes {
+    
+    input = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) 
+
+    CUSTOM_GETCHROMSIZES ( input )
+}

tests/modules/custom/getchromsizes/test.yml

@@ -0,0 +1,10 @@
+- name: custom getchromsizes
+  command: nextflow run ./tests/modules/custom/getchromsizes -entry test_custom_getchromsizes -c tests/config/nextflow.config
+  tags:
+    - custom
+    - custom/getchromsizes
+  files:
+    - path: output/custom/genome.fasta.fai
+      md5sum: 9da2a56e2853dc8c0b86a9e7229c9fe5
+    - path: output/custom/genome.fasta.sizes
+      md5sum: a57c401f27ae5133823fb09fb21c8a3c