Add new module: cmseq/polymut (#918)

* add pydamage module

* remove TODOs

* split module by subcommands

* update version parsing

* remove forgotten TODOs

* update module names

* remove old holistic module

* Update modules/pydamage/analyze/main.nf

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

* add keywords

* update resource requirement

* Update modules/pydamage/filter/main.nf

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

* Update modules/pydamage/filter/meta.yml

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

* merge from upstream

* update pydamage from upstream

* add freebayes

* update pydamage test from upstream

* fix meta.yml

* update functions.nf

* update test.yml

* update version parsing

* update version parsing

* fix indentation

* Update modules/freebayes/main.nf

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

* Update modules/freebayes/main.nf

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

* Update modules/freebayes/main.nf

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

* add optional inputs

* Update modules/freebayes/main.nf

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

* add bed test

* add metabat2 module

* only freebayes

* remove metabat2

* update md5sum because of vcf including date of the day

* add keyword

* rescue conflicted files

* attempt to fix ECLint

* add pytest workflow for metabat

* remove -

* Update modules/metabat2/jgisummarizebamcontigdepths/meta.yml

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

* Update modules/metabat2/metabat2/meta.yml

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

* Update modules/metabat2/metabat2/meta.yml

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

* Update modules/metabat2/jgisummarizebamcontigdepths/meta.yml

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

* add optional inputs/outpus

* remove trailing whitespace

* first cmseq commit

* compressing and removing not reproducible md5sums

* save intermediate work

* follow symlinks while decompressing

* add cmseq/polymut

* add polymut

* add extra test with optional input file

* remove metabat2

* Update modules/cmseq/polymut/main.nf

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

* Update modules/cmseq/polymut/meta.yml

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

* Update modules/cmseq/polymut/meta.yml

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

* fix file extension

* Update modules/cmseq/polymut/meta.yml

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

* add test without bam index

* split tests in workflows

* answer PR review

* report version from variable

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>
Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

modules/cmseq/polymut/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/cmseq/polymut/main.nf

@@ -0,0 +1,46 @@
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+def VERSION = '1.0.4'
+
+process CMSEQ_POLYMUT {
+    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::cmseq=1.0.4" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/cmseq:1.0.4--pyhb7b1952_0"
+    } else {
+        container "quay.io/biocontainers/cmseq:1.0.4--pyhb7b1952_0"
+    }
+
+    input:
+    tuple val(meta), path(bam), path(bai), path(gff), path(fasta)
+
+    output:
+    tuple val(meta), path("*.txt"), emit: polymut
+    path "versions.yml"                   , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    def fasta_refid = fasta ? "-c $fasta" : ""
+    def sortindex = bai ? "" : "--sortindex"
+    """
+    polymut.py \\
+        $options.args \\
+        $sortindex \\
+        $fasta_refid \\
+        --gff_file $gff \\
+        $bam > ${prefix}.txt
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$( echo $VERSION )
+    END_VERSIONS
+    """
+}

modules/cmseq/polymut/meta.yml

@@ -0,0 +1,61 @@
+name: cmseq_polymut
+description: Calculates polymorphic site rates over protein coding genes
+keywords:
+  - polymut
+  - polymorphic
+  - mags
+  - assembly
+  - polymorphic sites
+  - estimation
+  - protein coding genes
+  - cmseq
+  - bam
+  - coverage
+tools:
+  - cmseq:
+      description: Set of utilities on sequences and BAM files
+      homepage: https://github.com/SegataLab/cmseq
+      documentation: https://github.com/SegataLab/cmseq
+      tool_dev_url: https://github.com/SegataLab/cmseq
+      licence: ['MIT License']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: BAM file
+      pattern: "*.bam"
+  - bai:
+      type: file
+      description: BAM index file
+      pattern: "*.bai"
+  - gff:
+      type: file
+      description: GFF file used to extract protein-coding genes
+      pattern: "*.gff"
+  - fasta:
+      type: file
+      description: Optional fasta file to run on a subset of references in the BAM file.
+      pattern: .{fa,fasta,fas,fna}
+
+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"
+  - polymut:
+      type: file
+      description: Polymut report in `.txt` format.
+      pattern: "*.txt"
+
+authors:
+  - "@maxibor"

tests/config/pytest_modules.yml

@@ -274,6 +274,10 @@ chromap/index:
   - modules/chromap/index/**
   - tests/modules/chromap/index/**
 
+cmseq/polymut:
+  - modules/cmseq/polymut/**
+  - tests/modules/cmseq/polymut/**
+
 cnvkit:
   - modules/cnvkit/**
   - tests/modules/cnvkit/**

tests/modules/cmseq/polymut/main.nf

@@ -0,0 +1,38 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CMSEQ_POLYMUT } from '../../../../modules/cmseq/polymut/main.nf' addParams( options: [:] )
+
+workflow test_cmseq_polymut_1 {
+
+    input_1 = [ [ id:'test', single_end:false ], // meta map
+              file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+              [],
+              file(params.test_data['sarscov2']['genome']['genome_gff3'], checkIfExists: true),
+              [] ]
+
+    CMSEQ_POLYMUT( input_1 )
+    
+}
+
+workflow test_cmseq_polymut_2 {
+    input_2 = [ [ id:'test', single_end:false ], // meta map
+              file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+              file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true),
+              file(params.test_data['sarscov2']['genome']['genome_gff3'], checkIfExists: true),
+              [] ]
+
+    CMSEQ_POLYMUT( input_2 )
+}
+
+workflow test_cmseq_polymut_3 {
+    input_3 = [ [ id:'test', single_end:false ], // meta map
+              file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+              file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true),
+              file(params.test_data['sarscov2']['genome']['genome_gff3'], checkIfExists: true),
+              file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true), ]
+
+    CMSEQ_POLYMUT( input_3 )
+}
+    

tests/modules/cmseq/polymut/test.yml

@@ -0,0 +1,26 @@
+- name: cmseq polymut test_cmseq_polymut_1
+  command: nextflow run tests/modules/cmseq/polymut -entry test_cmseq_polymut_1 -c tests/config/nextflow.config
+  tags:
+    - cmseq/polymut
+    - cmseq
+  files:
+    - path: output/cmseq/test.txt
+      md5sum: fd325c1724ee23d132a9115c64494efc
+
+- name: cmseq polymut test_cmseq_polymut_2
+  command: nextflow run tests/modules/cmseq/polymut -entry test_cmseq_polymut_2 -c tests/config/nextflow.config
+  tags:
+    - cmseq/polymut
+    - cmseq
+  files:
+    - path: output/cmseq/test.txt
+      md5sum: fd325c1724ee23d132a9115c64494efc
+
+- name: cmseq polymut test_cmseq_polymut_3
+  command: nextflow run tests/modules/cmseq/polymut -entry test_cmseq_polymut_3 -c tests/config/nextflow.config
+  tags:
+    - cmseq/polymut
+    - cmseq
+  files:
+    - path: output/cmseq/test.txt
+      md5sum: fd325c1724ee23d132a9115c64494efc