Add new module Mapdamage2 (#975)

* Fitst attempt at mapdamage2

* Add new module mapdamage2

* Removed __pycache__/test_versions_yml.cpython-39-pytest-6.2.5.pyc

* Modify main.nf and meta.yml

* Modify main.nf and meta.yml

* Modify main.nf and meta.yml

* Modify meta.yml

* Update pytest_modules.yml

* Apply suggestions from code review

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

* edit the meta.yml and main.nf after reviews

* Update meta.yml

* Update meta.yml

Co-authored-by: AIbrahim <AIbrahim@apate.hki-jena.de>
Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

modules/mapdamage2/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+    // Do not publish versions.yml unless running from pytest workflow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/mapdamage2/main.nf

@@ -0,0 +1,58 @@
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process MAPDAMAGE2 {
+    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::mapdamage2=2.2.1" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/mapdamage2:2.2.1--pyr40_0"
+    } else {
+        container "quay.io/biocontainers/mapdamage2:2.2.1--pyr40_0"
+    }
+
+    input:
+    tuple val(meta), path(bam)
+    path(fasta)
+
+    output:
+    tuple val(meta), path("results_*/Runtime_log.txt")                                    ,emit: runtime_log
+    tuple val(meta), path("results_*/Fragmisincorporation_plot.pdf"), optional: true      ,emit: fragmisincorporation_plot
+    tuple val(meta), path("results_*/Length_plot.pdf"), optional: true                    ,emit: length_plot
+    tuple val(meta), path("results_*/misincorporation.txt"), optional: true               ,emit: misincorporation
+    tuple val(meta), path("results_*/lgdistribution.txt"), optional: true                 ,emit: lgdistribution
+    tuple val(meta), path("results_*/dnacomp.txt"), optional: true                        ,emit: dnacomp
+    tuple val(meta), path("results_*/Stats_out_MCMC_hist.pdf"), optional: true            ,emit: stats_out_mcmc_hist
+    tuple val(meta), path("results_*/Stats_out_MCMC_iter.csv"), optional: true            ,emit: stats_out_mcmc_iter
+    tuple val(meta), path("results_*/Stats_out_MCMC_trace.pdf"), optional: true           ,emit: stats_out_mcmc_trace
+    tuple val(meta), path("results_*/Stats_out_MCMC_iter_summ_stat.csv"), optional: true  ,emit: stats_out_mcmc_iter_summ_stat
+    tuple val(meta), path("results_*/Stats_out_MCMC_post_pred.pdf"), optional: true       ,emit: stats_out_mcmc_post_pred
+    tuple val(meta), path("results_*/Stats_out_MCMC_correct_prob.csv"), optional: true    ,emit: stats_out_mcmc_correct_prob
+    tuple val(meta), path("results_*/dnacomp_genome.csv"), optional: true                 ,emit: dnacomp_genome
+    tuple val(meta), path("results_*/rescaled.bam"), optional: true                       ,emit: rescaled
+    tuple val(meta), path("results_*/5pCtoT_freq.txt"), optional: true                    ,emit: pctot_freq
+    tuple val(meta), path("results_*/3pGtoA_freq.txt"), optional: true                    ,emit: pgtoa_freq
+    tuple val(meta), path("results_*/*.fasta"), optional: true                            ,emit: fasta
+    tuple val(meta), path("*/"), optional: true                                           ,emit: folder
+    path "versions.yml",emit: versions
+
+    script:
+    def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    """
+    mapDamage \\
+            $options.args \\
+            -i $bam \\
+            -r $fasta
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$(echo \$(mapDamage --version))
+    END_VERSIONS
+    """
+}

modules/mapdamage2/meta.yml

@@ -0,0 +1,114 @@
+name: mapdamage2
+
+description: Computational framework for tracking and quantifying DNA damage patterns among ancient DNA sequencing reads generated by Next-Generation Sequencing platforms.
+keywords:
+  - ancient DNA
+  - DNA damage
+  - NGS
+  - damage patterns
+  - bam
+tools:
+  - mapdamage2:
+      description: Tracking and quantifying damage patterns in ancient DNA sequences
+      homepage: http://ginolhac.github.io/mapDamage/
+      documentation: https://ginolhac.github.io/mapDamage/
+      tool_dev_url: https://github.com/ginolhac/mapDamage
+      doi: "10.1093/bioinformatics/btt193"
+      licence: ['MIT']
+
+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}"
+  - fasta:
+      type: file
+      description: Fasta file, the reference the input BAM was mapped against
+      pattern: "*.{fasta}"
+
+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"
+    - runtime_log:
+      type: file
+      description: Log file with a summary of command lines used and timestamps.
+      pattern: "Runtime_log.txt"
+    - fragmisincorporation_plot:
+      type: file
+      description: A pdf file that displays both fragmentation and misincorporation patterns.
+      pattern: "Fragmisincorporation_plot.pdf"
+    - length_plot:
+      type: file
+      description: A pdf file that displays length distribution of singleton reads per strand and cumulative frequencies of C->T at 5'-end and G->A at 3'-end are also displayed per strand.
+      pattern: "Length_plot.pdf"
+    - misincorporation:
+      type: file
+      description: Contains a table with occurrences for each type of mutations and relative positions from the reads ends.
+      pattern: "misincorporation.txt"
+    - pctot_freq:
+      type: file
+      description: Contains frequencies of Cytosine to Thymine mutations per position from the 5'-ends.
+      pattern: "5pCtoT_freq.txt"
+    - pgtoa_freq:
+      type: file
+      description: Contains frequencies of Guanine to Adenine mutations per position from the 3'-ends.
+      pattern: "3pGtoA_freq.txt"
+    - dnacomp:
+      type: file
+      description:  Contains a table of the reference genome base composition per position, inside reads and adjacent regions.
+      pattern: "dnacomp.txt"
+    - lgdistribution:
+      type: file
+      description: Contains a table with read length distributions per strand.
+      pattern: "lgdistribution.txt"
+    - stats_out_mcmc_hist:
+      type: file
+      description: A MCMC histogram for the damage parameters and log likelihood.
+      pattern: "Stats_out_MCMC_hist.pdf"
+    - stats_out_mcmc_iter:
+      type: file
+      description: Values for the damage parameters and log likelihood in each MCMC iteration.
+      pattern: "Stats_out_MCMC_iter.csv"
+    - stats_out_mcmc_trace:
+      type: file
+      description: A MCMC trace plot for the damage parameters and log likelihood.
+      pattern: "Stats_out_MCMC_trace.pdf"
+    - stats_out_mcmc_iter_summ_stat:
+      type: file
+      description: Summary statistics for the damage parameters estimated posterior distributions.
+      pattern: "Stats_out_MCMC_iter_summ_stat.csv"
+    - stats_out_mcmc_post_pred:
+      type: file
+      description: Empirical misincorporation frequency and posterior predictive intervals from the fitted model.
+      pattern: "Stats_out_MCMC_post_pred.pdf"
+    - stats_out_mcmc_correct_prob:
+      type: file
+      description: Position specific probability of a C->T and G->A misincorporation is due to damage.
+      pattern: "Stats_out_MCMC_correct_prob.csv"
+    - dnacomp_genome:
+      type: file
+      description: Contains the global reference genome base composition (computed by seqtk).
+      pattern: "dnacomp_genome.csv"
+    - rescaled:
+      type: file
+      description: Rescaled BAM file, where likely post-mortem damaged bases have downscaled quality scores.
+      pattern: "*.{bam}"
+    - fasta:
+      type: file
+      description: Allignments in a FASTA file, only if flagged by -d.
+      pattern: "*.{fasta}"
+    - folder:
+      type: folder
+      description: Folder created when --plot-only, --rescale and --stats-only flags are passed.
+      pattern: "*/"
+
+authors:
+- "@darcy220606"

tests/config/pytest_modules.yml

@@ -758,6 +758,10 @@ manta/tumoronly:
   - modules/manta/tumoronly/**
   - tests/modules/manta/tumoronly/**
 
+mapdamage2:
+  - modules/mapdamage2/**
+  - tests/modules/mapdamage2/**
+
 mash/sketch:
   - modules/mash/sketch/**
   - tests/modules/mash/sketch/**

tests/modules/mapdamage2/main.nf

@@ -0,0 +1,15 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { MAPDAMAGE2 } from '../../../modules/mapdamage2/main.nf' addParams( options: [:] )
+
+workflow test_mapdamage2 {
+    
+    input = [ [ id:'test', single_end:false ], // meta map
+              file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true) 
+            ]                            
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    
+    MAPDAMAGE2 ( input, fasta )
+}

tests/modules/mapdamage2/test.yml

@@ -0,0 +1,25 @@
+- name: mapdamage2 test_mapdamage2
+  command: nextflow run tests/modules/mapdamage2 -entry test_mapdamage2 -c tests/config/nextflow.config
+  tags:
+    - mapdamage2
+  files:
+    - path: output/mapdamage2/results_test.paired_end.sorted/3pGtoA_freq.txt
+      md5sum: 3b300b8d2842441675cb2b56740801f0
+    - path: output/mapdamage2/results_test.paired_end.sorted/5pCtoT_freq.txt
+      md5sum: 4c27465cd02e1fb8bf6fb2b01e98446d
+    - path: output/mapdamage2/results_test.paired_end.sorted/Fragmisincorporation_plot.pdf
+    - path: output/mapdamage2/results_test.paired_end.sorted/Runtime_log.txt
+    - path: output/mapdamage2/results_test.paired_end.sorted/Stats_out_MCMC_correct_prob.csv
+    - path: output/mapdamage2/results_test.paired_end.sorted/Stats_out_MCMC_hist.pdf
+    - path: output/mapdamage2/results_test.paired_end.sorted/Stats_out_MCMC_iter.csv
+    - path: output/mapdamage2/results_test.paired_end.sorted/Stats_out_MCMC_iter_summ_stat.csv
+    - path: output/mapdamage2/results_test.paired_end.sorted/Stats_out_MCMC_post_pred.pdf
+    - path: output/mapdamage2/results_test.paired_end.sorted/Stats_out_MCMC_trace.pdf
+    - path: output/mapdamage2/results_test.paired_end.sorted/dnacomp.txt
+      md5sum: 4244d9fa554bbfeebbcea8eba3ad6466
+    - path: output/mapdamage2/results_test.paired_end.sorted/dnacomp_genome.csv
+      md5sum: ea91a3d205717d3c6b3e0b77bb840945
+    - path: output/mapdamage2/results_test.paired_end.sorted/lgdistribution.txt
+      md5sum: f86dfc04b1fff4337cc91add6356e3a0
+    - path: output/mapdamage2/results_test.paired_end.sorted/misincorporation.txt
+      md5sum: 1c89b4c96d1f8996c3d0879cad5129a5