Cooler digest (#517)

* add software/cooler

* fix the wrong files uploaded.

* create a branch for cooler/digest

Co-authored-by: Jose Espinosa-Carrasco <kadomu@gmail.com>

software/cooler/digest/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"
+        }
+    }
+}

software/cooler/digest/main.nf

@@ -0,0 +1,42 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process COOLER_DIGEST {
+    tag '$fasta'
+    label 'process_medium'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:[:], publish_by_meta:[]) }
+
+    conda (params.enable_conda ? "bioconda::cooler=0.8.11" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/cooler:0.8.11--pyh3252c3a_0"
+    } else {
+        container "quay.io/biocontainers/cooler:0.8.11--pyh3252c3a_0"
+    }
+
+    input:
+    path fasta
+    path chromsizes
+    val  enzyme
+
+    output:
+    path "*.bed"                  , emit: bed
+    path "*.version.txt"          , emit: version
+
+    script:
+    def software = getSoftwareName(task.process)
+    """
+    cooler digest \\
+        $options.args \\
+        -o "${fasta.baseName}_${enzyme.replaceAll(/[^0-9a-zA-Z]+/, "_")}.bed" \\
+        $chromsizes \\
+        $fasta \\
+        $enzyme
+
+    echo \$(cooler --version 2>&1) | sed 's/cooler, version //' > ${software}.version.txt
+    """
+}

software/cooler/digest/meta.yml

@@ -0,0 +1,39 @@
+name: cooler_digest
+description: Generate fragment-delimited genomic bins
+keywords:
+  - digest
+  - enzyme
+tools:
+  - cooler:
+      description: Sparse binary format for genomic interaction matrices
+      homepage: https://cooler.readthedocs.io/en/latest/index.html
+      documentation: https://cooler.readthedocs.io/en/latest/index.html
+      tool_dev_url: https://github.com/open2c/cooler
+      doi: "10.1093/bioinformatics/btz540"
+      licence: ['BSD-3-clause']
+
+input:
+  - fasta:
+      type: file
+      description: Genome assembly FASTA file or folder containing FASTA files (uncompressed).
+      pattern: "*.{fasta,fa}"
+  - chromsizes:
+      type: file
+      description: Path to a chromsizes file.
+  - enzyme:
+      type: String
+      description: Name of restriction enzyme. e.g. CviQI.
+      documentation: http://biopython.org/DIST/docs/cookbook/Restriction.html
+
+output:
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.{version.txt}"
+  - bed:
+      type: file
+      description: A genome segmentation of restriction fragments as a BED file.
+      pattern: "*.{bed}"
+
+authors:
+  - "@jianhong"

tests/config/pytest_software.yml

@@ -178,6 +178,10 @@ cnvkit:
   - software/cnvkit/**
   - tests/software/cnvkit/**
 
+cooler/digest:
+  - software/cooler/digest/**
+  - tests/software/cooler/digest/**
+
 cooler/dump:
   - software/cooler/dump/**
   - tests/software/cooler/dump/**

tests/software/cooler/digest/main.nf

@@ -0,0 +1,14 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { COOLER_DIGEST } from '../../../../software/cooler/digest/main.nf' addParams( options: [:] )
+
+workflow test_cooler_digest {
+
+    input = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    sizes = file(params.test_data['sarscov2']['genome']['genome_sizes'], checkIfExists: true)
+    enzyme = "CviQI"
+
+    COOLER_DIGEST ( input, sizes, enzyme )
+}

tests/software/cooler/digest/test.yml

@@ -0,0 +1,8 @@
+- name: cooler digest test_cooler_digest
+  command: nextflow run tests/software/cooler/digest -entry test_cooler_digest -c tests/config/nextflow.config
+  tags:
+    - cooler/digest
+    - cooler
+  files:
+    - path: output/cooler/genome_CviQI.bed
+      md5sum: f02d3cfaf642b27d4cc197209845e096