New module: checkm/lineagewf (#899)

* 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

* Added but test failing due to null on output channel

* fix prefix variable

* Complete checkm_lineagewf

* Remove TODOs

* Add description of fasta_ext parameter

* Improve meta map for this context

* Update meta.yml

* Update modules/checkm/lineagewf/meta.yml

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

* Update main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>
Co-authored-by: Maxime Borry <maxibor@users.noreply.github.com>
Co-authored-by: Daniel Lundin <erik.rikard.daniel@gmail.com>

modules/checkm/lineagewf/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/checkm/lineagewf/main.nf

@@ -0,0 +1,49 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process CHECKM_LINEAGEWF {
+    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::checkm-genome=1.1.3" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/checkm-genome:1.1.3--py_1"
+    } else {
+        container "quay.io/biocontainers/checkm-genome:1.1.3--py_1"
+    }
+
+    input:
+    tuple val(meta), path(fasta)
+    val fasta_ext
+
+    output:
+    tuple val(meta), path("${prefix}")    , emit: checkm_output
+    tuple val(meta), path("${prefix}.tsv"), emit: checkm_tsv
+    path "versions.yml"                   , emit: versions
+
+    script:
+    prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    """
+    checkm \\
+        lineage_wf \\
+        -t $task.cpus \\
+        -f ${prefix}.tsv \\
+        --tab_table \\
+        --pplacer_threads $task.cpus \\
+        -x $fasta_ext \\
+        $options.args \\
+        . \\
+        $prefix
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$( checkm 2>&1 | grep '...:::' | sed 's/.*CheckM v//;s/ .*//' )
+    END_VERSIONS
+    """
+}

modules/checkm/lineagewf/meta.yml

@@ -0,0 +1,58 @@
+name: checkm_lineagewf
+description: CheckM provides a set of tools for assessing the quality of genomes recovered from isolates, single cells, or metagenomes.
+keywords:
+  - checkm
+  - mag
+  - metagenome
+  - quality
+  - isolates
+  - microbes
+  - single cells
+  - completeness
+  - contamination
+  - bins
+  - genome bins
+tools:
+  - checkm:
+      description: Assess the quality of microbial genomes recovered from isolates, single cells, and metagenomes.
+      homepage: https://ecogenomics.github.io/CheckM/
+      documentation: https://github.com/Ecogenomics/CheckM/wiki
+      tool_dev_url: https://github.com/Ecogenomics/CheckM
+      doi: "10.1101/gr.186072.114"
+      licence: ['GPL v3']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - fasta:
+      type: file
+      description: One or a list of multiple FASTA files of each bin, with extension defined with the fasta_ext value
+      pattern: "*.{$fasta_ext}"
+  - fasta_ext:
+      type: value
+      description: The file-type extension suffix of the input FASTA files (e.g., fasta, fna, fa, fas)
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'sample', bin:'1' ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - checkm_output:
+      type: directory
+      description: CheckM output directory
+      pattern: "*/"
+  - checkm_tsv:
+      type: file
+      description: CheckM summary completeness statistics table
+      pattern: "*.tsv"
+
+authors:
+  - "@jfy133"

tests/config/pytest_modules.yml

@@ -254,6 +254,10 @@ cat/fastq:
   - modules/cat/fastq/**
   - tests/modules/cat/fastq/**
 
+checkm/lineagewf:
+  - modules/checkm/lineagewf/**
+  - tests/modules/checkm/lineagewf/**
+
 chromap/chromap:
   - modules/chromap/chromap/**
   - tests/modules/chromap/chromap/**
@@ -1106,7 +1110,7 @@ ucsc/bigwigaverageoverbed:
 ucsc/liftover:
   - modules/ucsc/liftover/**
   - tests/modules/ucsc/liftover/**
-  
+
 ucsc/wigtobigwig:
   - modules/ucsc/wigtobigwig/**
   - tests/modules/ucsc/wigtobigwig/**

tests/modules/checkm/lineagewf/main.nf

@@ -0,0 +1,24 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CHECKM_LINEAGEWF } from '../../../../modules/checkm/lineagewf/main.nf' addParams( options: [:] )
+
+workflow test_checkm_lineagewf {
+
+    input = [ [ id:'test', single_end:false ], // meta map
+              file(params.test_data['sarscov2']['illumina']['contigs_fasta'], checkIfExists: true) ]
+    fasta_ext = 'fasta'
+
+    CHECKM_LINEAGEWF ( input, fasta_ext )
+}
+
+workflow test_checkm_lineagewf_multi {
+
+    input = [ [ id:'test', single_end:false ], // meta map
+              [ file(params.test_data['sarscov2']['illumina']['contigs_fasta'], checkIfExists: true),
+                file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)] ]
+    fasta_ext = 'fasta'
+
+    CHECKM_LINEAGEWF ( input, fasta_ext )
+}

tests/modules/checkm/lineagewf/test.yml

@@ -0,0 +1,35 @@
+- name: checkm lineagewf
+  command: nextflow run ./tests/modules/checkm/lineagewf -entry test_checkm_lineagewf -c tests/config/nextflow.config
+  tags:
+    - checkm
+    - checkm/lineagewf
+  files:
+    - path: output/checkm/test.tsv
+      md5sum: d5559764f563c4b55223e4e4a3dc1ec9
+    - path: output/checkm/test/checkm.log
+      contains:
+        - "INFO: Parsing HMM hits to marker genes:"
+    - path: output/checkm/test/lineage.ms
+      contains:
+        - "# [Lineage Marker File]"
+        - "contigs"
+        - "UID1"
+
+- name: checkm lineagewf_multi
+  command: nextflow run ./tests/modules/checkm/lineagewf -entry test_checkm_lineagewf_multi -c tests/config/nextflow.config
+  tags:
+    - checkm
+    - checkm/lineagewf
+  files:
+    - path: output/checkm/test.tsv
+      md5sum: 7e0fa177dcf151b84b7751813fbde3d1
+    - path: output/checkm/test/checkm.log
+      contains:
+        - "INFO: Parsing HMM hits to marker genes:"
+    - path: output/checkm/test/lineage.ms
+      contains:
+        - "# [Lineage Marker File]"
+        - "contigs"
+        - "UID1"
+        - "genome"
+