New module: metabat2 (#875)

* 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

* compressing and removing not reproducible md5sums

* follow symlinks while decompressing

* Update tests/modules/metabat2/metabat2/main.nf

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

* Update tests/modules/metabat2/metabat2/main.nf

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

* split tests

* export env variable

* Update modules/metabat2/jgisummarizebamcontigdepths/main.nf

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>

* Update modules/metabat2/metabat2/main.nf

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>

* answer PR comments and switch to bgzip

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>
Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>
Co-authored-by: Gregor Sturm <mail@gregor-sturm.de>

modules/metabat2/jgisummarizebamcontigdepths/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/metabat2/jgisummarizebamcontigdepths/main.nf

@@ -0,0 +1,44 @@
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process METABAT2_JGISUMMARIZEBAMCONTIGDEPTHS {
+    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::metabat2=2.15" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/metabat2:2.15--h986a166_1"
+    } else {
+        container "quay.io/biocontainers/metabat2:2.15--h986a166_1"
+    }
+
+    input:
+    tuple val(meta), path(bam), path(bai)
+
+    output:
+    tuple val(meta), path("*.txt.gz"), emit: depth
+    path "versions.yml"                    , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    """
+    export OMP_NUM_THREADS=$task.cpus
+
+    jgi_summarize_bam_contig_depths \\
+        --outputDepth ${prefix}.txt \\
+        $options.args \\
+        $bam
+
+    bgzip --threads $task.cpus ${prefix}.txt
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$( metabat2 --help 2>&1 | head -n 2 | tail -n 1| sed 's/.*\\:\\([0-9]*\\.[0-9]*\\).*/\\1/' )
+    END_VERSIONS
+    """
+}

modules/metabat2/jgisummarizebamcontigdepths/meta.yml

@@ -0,0 +1,50 @@
+name: metabat2_jgisummarizebamcontigdepths
+description: Depth computation per contig step of metabat2
+keywords:
+  - sort
+  - binning
+  - depth
+  - bam
+  - coverage
+  - de novo assembly
+tools:
+  - metabat2:
+      description: Metagenome binning
+      homepage: https://bitbucket.org/berkeleylab/metabat/src/master/
+      documentation: https://bitbucket.org/berkeleylab/metabat/src/master/
+      tool_dev_url: https://bitbucket.org/berkeleylab/metabat/src/master/
+      doi: "10.7717/peerj.7359"
+      licence: ['BSD-3-clause-LBNL']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: Sorted BAM file of reads aligned on the assembled contigs
+      pattern: "*.bam"
+  - bai:
+      type: file
+      description: BAM index file
+      pattern: "*.bam.bai"
+
+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"
+  - depth:
+      type: file
+      description: Text file listing the coverage per contig
+      pattern: ".txt.gz"
+
+authors:
+  - "@maxibor"

modules/metabat2/metabat2/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/metabat2/metabat2/main.nf

@@ -0,0 +1,53 @@
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process METABAT2_METABAT2 {
+    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::metabat2=2.15" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/metabat2:2.15--h986a166_1"
+    } else {
+        container "quay.io/biocontainers/metabat2:2.15--h986a166_1"
+    }
+
+    input:
+    tuple val(meta), path(fasta), path(depth)
+
+    output:
+    tuple val(meta), path("bins/*.fa.gz")       , optional:true , emit: fasta
+    tuple val(meta), path("*.tsv.gz"), optional:true , emit: membership
+    path "versions.yml"                                         , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    def decompress_depth = depth ? "gzip -d -f $depth" : ""
+    def depth_file = depth ? "-a ${depth.baseName}" : ""
+    """
+    $decompress_depth
+
+    metabat2 \\
+        $options.args \\
+        -i $fasta \\
+        $depth_file \\
+        -t $task.cpus \\
+        --saveCls \\
+        -o metabat2/${prefix}
+
+    mv metabat2/${prefix} ${prefix}.tsv
+    mv metabat2 bins
+    bgzip --threads $task.cpus ${prefix}.tsv
+    bgzip --threads $task.cpus bins/*.fa
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$( metabat2 --help 2>&1 | head -n 2 | tail -n 1| sed 's/.*\\:\\([0-9]*\\.[0-9]*\\).*/\\1/' )
+    END_VERSIONS
+    """
+}

modules/metabat2/metabat2/meta.yml

@@ -0,0 +1,56 @@
+name: metabat2_metabat2
+keywords:
+  - sort
+  - binning
+  - depth
+  - bam
+  - coverage
+  - de novo assembly
+tools:
+  - metabat2:
+      description: Metagenome binning
+      homepage: https://bitbucket.org/berkeleylab/metabat/src/master/
+      documentation: https://bitbucket.org/berkeleylab/metabat/src/master/
+      tool_dev_url: https://bitbucket.org/berkeleylab/metabat/src/master/
+      doi: "10.7717/peerj.7359"
+      licence: ['BSD-3-clause-LBNL']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - fasta:
+      type: file
+      description: Fasta file of the assembled contigs
+      pattern: "*.{fa,fas,fasta,fna,fa.gz,fas.gz,fasta.gz,fna.gz}"
+  - depth:
+      type: file
+      description: |
+          Optional text file listing the coverage per contig pre-generated
+          by metabat2_jgisummarizebamcontigdepths
+      pattern: "*.txt"
+
+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"
+  - fasta:
+      type: file
+      description: Bins created from assembled contigs in fasta file
+      pattern: "*.fa.gz"
+  - membership:
+      type: file
+      description: cluster memberships as a matrix format.
+      pattern: "*.tsv.gz"
+
+
+authors:
+  - "@maxibor"

tests/config/pytest_modules.yml

@@ -774,10 +774,19 @@ megahit:
   - modules/megahit/**
   - tests/modules/megahit/**
 
+metabat2/jgisummarizebamcontigdepths:
+  - modules/metabat2/jgisummarizebamcontigdepths/**
+  - tests/modules/metabat2/jgisummarizebamcontigdepths/**
+
+metabat2/metabat2:
+  - modules/metabat2/metabat2/**
+  - tests/modules/metabat2/metabat2/**
+
 meningotype:
   - modules/meningotype/**
   - tests/modules/meningotype/**
 
+
 metaphlan3:
   - modules/metaphlan3/**
   - tests/modules/metaphlan3/**

tests/modules/metabat2/jgisummarizebamcontigdepths/main.nf

@@ -0,0 +1,14 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { METABAT2_JGISUMMARIZEBAMCONTIGDEPTHS } from '../../../../modules/metabat2/jgisummarizebamcontigdepths/main.nf' addParams( options: [:] )
+
+workflow test_metabat2_jgisummarizebamcontigdepths {
+    
+    input = [ [ id:'test' ], // 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) ]
+
+    METABAT2_JGISUMMARIZEBAMCONTIGDEPTHS ( input )
+}

tests/modules/metabat2/jgisummarizebamcontigdepths/test.yml

@@ -0,0 +1,8 @@
+- name: metabat2 jgisummarizebamcontigdepths test_metabat2_jgisummarizebamcontigdepths
+  command: nextflow run tests/modules/metabat2/jgisummarizebamcontigdepths -entry test_metabat2_jgisummarizebamcontigdepths -c tests/config/nextflow.config
+  tags:
+    - metabat2/jgisummarizebamcontigdepths
+    - metabat2
+  files:
+    - path: output/metabat2/test.txt.gz
+      md5sum: 8f735aa408d6c90e5a0310e06ace7a9a

tests/modules/metabat2/metabat2/main.nf

@@ -0,0 +1,35 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { METABAT2_METABAT2 } from '../../../../modules/metabat2/metabat2/main.nf' addParams( options: [args: '--minContig 1500 --minCV 0.1 --minCVSum 0.1 --minClsSize 10 --minS 2'] )
+include { METABAT2_JGISUMMARIZEBAMCONTIGDEPTHS } from '../../../../modules/metabat2/jgisummarizebamcontigdepths/main.nf' addParams( options: [:] )
+
+workflow test_metabat2_no_depth {
+
+    input_depth = [ [ 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) ]
+
+    Channel.fromPath(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+        .map { it -> [[ id:'test', single_end:false ], it, []] }
+        .set { input_metabat2 }
+    
+    METABAT2_METABAT2 ( input_metabat2 )
+}
+
+workflow test_metabat2_depth {
+
+    input_depth = [ [ 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) ]
+
+    METABAT2_JGISUMMARIZEBAMCONTIGDEPTHS ( input_depth )
+
+    Channel.fromPath(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+        .map { it -> [[ id:'test', single_end:false ], it] }
+        .join(METABAT2_JGISUMMARIZEBAMCONTIGDEPTHS.out.depth)
+        .set { input_metabat2 }
+
+        METABAT2_METABAT2 ( input_metabat2 )
+}

tests/modules/metabat2/metabat2/test.yml

@@ -0,0 +1,23 @@
+- name: metabat2 metabat2 test_metabat2_no_depth
+  command: nextflow run tests/modules/metabat2/metabat2 -entry test_metabat2_no_depth -c tests/config/nextflow.config
+  tags:
+    - metabat2/metabat2
+    - metabat2
+  files:
+    - path: output/metabat2/bins/test.1.fa.gz
+      md5sum: 0e9bce5b5a0033fd4411a21dec881170
+    - path: output/metabat2/test.tsv.gz
+      md5sum: ea77e8c4426d2337419905b57f1ec335
+
+- name: metabat2 metabat2 test_metabat2_depth
+  command: nextflow run tests/modules/metabat2/metabat2 -entry test_metabat2_depth -c tests/config/nextflow.config
+  tags:
+    - metabat2/metabat2
+    - metabat2
+  files:
+    - path: output/metabat2/bins/test.1.fa.gz
+      md5sum: 0e9bce5b5a0033fd4411a21dec881170
+    - path: output/metabat2/test.tsv.gz
+      md5sum: ea77e8c4426d2337419905b57f1ec335
+    - path: output/metabat2/test.txt.gz
+      md5sum: 8f735aa408d6c90e5a0310e06ace7a9a