New module: gunc run (+ gunc downloaddb) (#880)

* Specify more guidelines on input channels

* Linting

* Updates based on code review

* Update README.md

* Fix broken sentence

* feat: add megahit module, currently decompressed output

* Update main.nf

* Update tests/modules/megahit/test.yml

Co-authored-by: Maxime Borry <maxibor@users.noreply.github.com>

* Apply suggestions from code review

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

* feat: compress all outputs, remove md5sums due to gz stochasicity

* fix: wrong conda channel for pigz

* fix: broken singleend tests and update meta.yml

* Missed one

* Apply suggestions from code review

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

* fix: pigz formatting

* Apply suggestions from code review

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

* Apply suggestions from code review

* Add GUNC download_db and run commands

* Bump with version without zgrep

* Apply suggestions from code review

Co-authored-by: Robert A. Petit III <robbie.petit@gmail.com>

* Harshil formatting

* Apply suggestions from code review

Co-authored-by: Robert A. Petit III <robbie.petit@gmail.com>

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>
Co-authored-by: Maxime Borry <maxibor@users.noreply.github.com>
Co-authored-by: Robert A. Petit III <robbie.petit@gmail.com>

modules/gunc/downloaddb/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/gunc/downloaddb/main.nf

@@ -0,0 +1,37 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process GUNC_DOWNLOADDB {
+    tag '$db_name'
+    label 'process_low'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:[:], publish_by_meta:[]) }
+
+    conda (params.enable_conda ? "bioconda::gunc=1.0.5" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/gunc:1.0.5--pyhdfd78af_0"
+    } else {
+        container "quay.io/biocontainers/gunc:1.0.5--pyhdfd78af_0"
+    }
+
+    input:
+    val db_name
+
+    output:
+    path "*.dmnd"       , emit: db
+    path "versions.yml" , emit: versions
+
+    script:
+    """
+    gunc download_db . -db $db_name $options.args
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$( gunc --version )
+    END_VERSIONS
+    """
+}

modules/gunc/downloaddb/meta.yml

@@ -0,0 +1,36 @@
+name: gunc_downloaddb
+description: Download database for GUNC detection of Chimerism and Contamination in Prokaryotic Genomes
+keywords:
+  - download
+  - prokaryote
+  - assembly
+  - genome
+  - quality control
+  - chimeras
+tools:
+  - gunc:
+      description: Python package for detection of chimerism and contamination in prokaryotic genomes.
+      homepage: https://grp-bork.embl-community.io/gunc/
+      documentation: https://grp-bork.embl-community.io/gunc/
+      tool_dev_url: https://github.com/grp-bork/gunc
+      doi: "10.1186/s13059-021-02393-0"
+      licence: ['GNU General Public v3 or later (GPL v3+)']
+
+input:
+  - db_name:
+      type: string
+      description: "Which database to download. Options: progenomes or gtdb"
+      pattern: "progenomes|gtdb"
+
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - db:
+      type: file
+      description: GUNC database file
+      pattern: "*.dmnd"
+
+authors:
+  - "@jfy133"

modules/gunc/run/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/gunc/run/main.nf

@@ -0,0 +1,45 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process GUNC_RUN {
+    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::gunc=1.0.5" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/gunc:1.0.5--pyhdfd78af_0"
+    } else {
+        container "quay.io/biocontainers/gunc:1.0.5--pyhdfd78af_0"
+    }
+
+    input:
+    tuple val(meta), path(fasta)
+    path(db)
+
+    output:
+    tuple val(meta), path("*maxCSS_level.tsv")                  , emit: maxcss_level_tsv
+    tuple val(meta), path("*all_levels.tsv")    , optional: true, emit: all_levels_tsv
+    path "versions.yml"                                         , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    """
+    gunc \\
+        run \\
+        --input_fasta $fasta \\
+        --db_file $db \\
+        --threads $task.cpus \\
+        $options.args
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$( gunc --version )
+    END_VERSIONS
+    """
+}

modules/gunc/run/meta.yml

@@ -0,0 +1,53 @@
+name: gunc_run
+description: Detection of Chimerism and Contamination in Prokaryotic Genomes
+keywords:
+  - prokaryote
+  - assembly
+  - genome
+  - quality control
+  - chimeras
+tools:
+  - gunc:
+      description: Python package for detection of chimerism and contamination in prokaryotic genomes.
+      homepage: https://grp-bork.embl-community.io/gunc/
+      documentation: https://grp-bork.embl-community.io/gunc/
+      tool_dev_url: https://github.com/grp-bork/gunc
+      doi: "10.1186/s13059-021-02393-0"
+      licence: ['GNU General Public v3 or later (GPL v3+)']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - fasta:
+      type: file
+      description: FASTA file containing contig (bins)
+      pattern: "*.fa"
+  - db:
+      type: file
+      description: GUNC database file
+      pattern: "*.dmnd"
+
+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"
+  - maxcss_levels_tsv:
+      type: file
+      description: Output file with scores for a taxonomic level with the highest CSS score
+      pattern: "*.tsv"
+  - all_levels_tsv:
+      type: file
+      description: Optional output file with results for each taxonomic level
+      pattern: "*.tsv"
+
+authors:
+  - "@jfy133"

tests/config/pytest_modules.yml

@@ -546,6 +546,14 @@ gubbins:
   - modules/gubbins/**
   - tests/modules/gubbins/**
 
+gunc/downloaddb:
+  - modules/gunc/downloaddb/**
+  - tests/modules/gunc/downloaddb/**
+
+gunc/run:
+  - modules/gunc/run/**
+  - tests/modules/gunc/run/**
+
 gunzip:
   - modules/gunzip/**
   - tests/modules/gunzip/**

tests/modules/gunc/downloaddb/main.nf

@@ -0,0 +1,12 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GUNC_DOWNLOADDB } from '../../../../modules/gunc/downloaddb/main.nf' addParams( options: [:] )
+
+workflow test_gunc_downloaddb {
+
+    input = 'progenomes'
+
+    GUNC_DOWNLOADDB ( input )
+}

tests/modules/gunc/downloaddb/test.yml

@@ -0,0 +1,8 @@
+- name: gunc downloaddb
+  command: nextflow run ./tests/modules/gunc/downloaddb -entry test_gunc_downloaddb -c tests/config/nextflow.config
+  tags:
+    - gunc
+    - gunc/downloaddb
+  files:
+    - path: output/gunc/gunc_db_progenomes2.1.dmnd
+      md5sum: 447c9330056b02f29f30fe81fe4af4eb

tests/modules/gunc/run/main.nf

@@ -0,0 +1,17 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GUNC_RUN        } from '../../../../modules/gunc/run/main.nf' addParams( options: [:] )
+include { GUNC_DOWNLOADDB } from '../../../../modules/gunc/downloaddb/main.nf' addParams( options: [:] )
+
+
+workflow test_gunc_run {
+
+    input = [ [ id:'test', single_end:false ], // meta map
+              file(params.test_data['sarscov2']['illumina']['contigs_fasta'], checkIfExists: true) ]
+
+    GUNC_DOWNLOADDB('progenomes')
+
+    GUNC_RUN ( input, GUNC_DOWNLOADDB.out.db )
+}

tests/modules/gunc/run/test.yml

@@ -0,0 +1,8 @@
+- name: gunc run
+  command: nextflow run ./tests/modules/gunc/run -entry test_gunc_run -c tests/config/nextflow.config
+  tags:
+    - gunc
+    - gunc/run
+  files:
+    - path: output/gunc/GUNC.progenomes_2.1.maxCSS_level.tsv
+      md5sum: 0420c1a9f2c50fefaee9fab5d80a551a