add paraclu (#909)

* add paraclu

* remove TODOs

* add min_cluster as input parameter, remove option parameters

* add tool_dev_url

modules/paraclu/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+    // Do not publish versions.yml unless running from pytest workflow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/paraclu/main.nf

@@ -0,0 +1,45 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process PARACLU {
+    tag "$meta.id"
+    label 'process_low'
+    publishDir "${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::paraclu=10" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/paraclu%3A10--h9a82719_1"
+    } else {
+        container "quay.io/biocontainers/paraclu:10--h9a82719_1"
+    }
+
+    input:
+    tuple val(meta), path(bed)
+    val(min_cluster)
+
+    output:
+    tuple val(meta), path("*.bed"), emit: bed
+    path "versions.yml"           , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    def VERSION=10
+    """
+
+    awk -F "\t" '{print\$1"\t"\$6"\t"\$2"\t"\$5}' < $bed > ${bed}_4P
+    sort -k1,1 -k3n ${bed}_4P > ${bed}_4Ps
+    paraclu $min_cluster ${bed}_4Ps > ${prefix}.clustered
+    paraclu-cut  ${prefix}.clustered >  ${prefix}.clustered.simplified
+    awk -F '\t' '{print \$1"\t"\$3"\t"\$4"\t"\$1":"\$3".."\$4","\$2"\t"\$6"\t"\$2}' ${prefix}.clustered.simplified >  ${prefix}.clustered.simplified.bed
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: $VERSION
+    END_VERSIONS
+    """
+}

modules/paraclu/meta.yml

@@ -0,0 +1,45 @@
+name: paraclu
+description: Paraclu finds clusters in data attached to sequences.
+keywords:
+  - sort
+tools:
+  - paraclu:
+      description: Paraclu finds clusters in data attached to sequences.
+      homepage: https://gitlab.com/mcfrith/paraclu
+      documentation: https://gitlab.com/mcfrith/paraclu
+      tool_dev_url: https://gitlab.com/mcfrith/paraclu
+      doi: ""
+      licence: ['GPL v3-or-later']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bed:
+      type: file
+      description: BED file
+      pattern: "*.bed"
+  - min_cluster:
+      type: integer
+      description: Minimum size of cluster
+      pattern: "*.bed"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - bed:
+      type: file
+      description: clustered BED file
+      pattern: "*.bed"
+
+authors:
+  - "@mashehu"

tests/config/pytest_modules.yml

@@ -791,6 +791,10 @@ pangolin:
   - modules/pangolin/**
   - tests/modules/pangolin/**
 
+paraclu:
+  - modules/paraclu/**
+  - tests/modules/paraclu/**
+
 pbbam/pbmerge:
   - modules/pbbam/pbmerge/**
   - tests/modules/pbbam/pbmerge/**

tests/modules/paraclu/main.nf

@@ -0,0 +1,15 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { PARACLU } from '../../../modules/paraclu/main.nf' addParams( options: [:] )
+
+workflow test_paraclu {
+
+    input = [[  id:'test' ], // meta map
+                file(params.test_data['sarscov2']['genome']['test_bed'], checkIfExists: true)
+                ]
+    min_cluster = 30
+
+    PARACLU ( input, min_cluster )
+}

tests/modules/paraclu/test.yml

@@ -0,0 +1,7 @@
+- name: paraclu test_paraclu
+  command: nextflow run tests/modules/paraclu -entry test_paraclu -c tests/config/nextflow.config
+  tags:
+    - paraclu
+  files:
+    - path: output/paraclu/test.clustered.simplified.bed
+      md5sum: d41d8cd98f00b204e9800998ecf8427e