Add PyDamage filter (#713)

* 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>

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

modules/pydamage/filter/functions.nf

@@ -0,0 +1,68 @@
+//
+//  Utility functions used in nf-core DSL2 module files
+//
+
+//
+// Extract name of software tool from process name using $task.process
+//
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+//
+// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+//
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+//
+// Tidy up and join elements of a list to return a path string
+//
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+//
+// Function to save/publish module results
+//
+def saveFiles(Map args) {
+    if (!args.filename.endsWith('.version.txt')) {
+        def ioptions  = initOptions(args.options)
+        def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+        if (ioptions.publish_by_meta) {
+            def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+            for (key in key_list) {
+                if (args.meta && key instanceof String) {
+                    def path = key
+                    if (args.meta.containsKey(key)) {
+                        path = args.meta[key] instanceof Boolean ? "${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/pydamage/filter/main.nf

@@ -0,0 +1,40 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process PYDAMAGE_FILTER {
+    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::pydamage=0.62" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/pydamage:0.62--pyhdfd78af_0"
+    } else {
+        container "quay.io/biocontainers/pydamage:0.62--pyhdfd78af_0"
+    }
+
+    input:
+    tuple val(meta), path(csv)
+
+    output:
+    tuple val(meta), path("pydamage_results/pydamage_filtered_results.csv"), emit: csv
+    path "*.version.txt"          , emit: version
+
+    script:
+    def software = getSoftwareName(task.process)
+    def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    """
+
+    pydamage \\
+        filter \\
+        $options.args \\
+        $csv
+
+    echo \$(pydamage --version 2>&1)  | sed -e 's/pydamage, version //g' > ${software}.version.txt
+    """
+}

modules/pydamage/filter/meta.yml

@@ -0,0 +1,51 @@
+name: pydamage_filter
+description: Damage parameter estimation for ancient DNA
+keywords:
+  - ancient DNA
+  - aDNA
+  - de novo assembly
+  - filtering
+  - damage
+  - deamination
+  - miscoding lesions
+  - C to T
+  - palaeogenomics
+  - archaeogenomics
+  - palaeogenetics
+  - archaeogenetics
+tools:
+  - pydamage:
+      description: Damage parameter estimation for ancient DNA
+      homepage: https://github.com/maxibor/pydamage
+      documentation: https://pydamage.readthedocs.io/
+      tool_dev_url: https://github.com/maxibor/pydamage
+      licence: ['GPL v3']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - csv:
+      type: file
+      description: csv file from pydamage analyze
+      pattern: "*.csv"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.{version.txt}"
+  - csv:
+      type: file
+      description: PyDamage filtered results as csv file
+      pattern: "*.csv"
+
+authors:
+  - "@maxibor"

tests/config/pytest_modules.yml

@@ -707,6 +707,10 @@ pydamage/analyze:
   - modules/pydamage/analyze/**
   - tests/modules/pydamage/analyze/**
 
+pydamage/filter:
+  - modules/pydamage/filter/**
+  - tests/modules/pydamage/filter/**
+
 qcat:
   - modules/qcat/**
   - tests/modules/qcat/**

tests/modules/pydamage/filter/main.nf

@@ -0,0 +1,16 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { PYDAMAGE_ANALYZE } from '../../../../modules/pydamage/analyze/main.nf' addParams( options: [:] )
+include { PYDAMAGE_FILTER } from '../../../../modules/pydamage/filter/main.nf' addParams( options: [:] )
+
+workflow test_pydamage {
+
+    input = [ [ id:'test', single_end:false ], // meta map
+              file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+              file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true) ]
+
+    PYDAMAGE_ANALYZE ( input )
+    PYDAMAGE_FILTER (PYDAMAGE_ANALYZE.out.csv)
+}

tests/modules/pydamage/filter/test.yml

@@ -0,0 +1,10 @@
+- name: test_pydamage_filter
+  command: nextflow run tests/modules/pydamage/filter -entry test_pydamage -c tests/config/nextflow.config
+  tags:
+    - pydamage
+    - pydamage/filter
+  files:
+    - path: output/pydamage/pydamage_results/pydamage_filtered_results.csv
+      md5sum: 9f297233cf4932d7d7e52cc72d4727dc
+    - path: output/pydamage/pydamage_results/pydamage_results.csv
+      md5sum: 6847e0d5aa6dba85bbd2dd509772b7a0