add nanolyse module (from nanoseq modules) (#471)

* add nanolyse modules

* add clean.fastq.gz path and md5sum

* fix errors

* remove unreproducible md5sum

* solve linting problem

* address PR suggestions

* GET_NANOLYSE_FASTA as a local module

* Update software/nanolyse/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Update software/nanolyse/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Update software/nanolyse/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Update software/nanolyse/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Update software/nanolyse/meta.yml

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Update software/nanolyse/meta.yml

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Update tests/software/nanolyse/test.yml

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Update tests/software/nanolyse/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Update tests/software/nanolyse/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* update to the version from nf-core/tools-dev

* input and output files cannot have the same names

* Update test.yml

* Update software/nanolyse/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Update tests/software/nanolyse/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Update test.yml

* revert

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

software/nanolyse/functions.nf

@@ -0,0 +1,70 @@
+/*
+ * -----------------------------------------------------
+ *  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"
+        }
+    }
+}

software/nanolyse/main.nf

@@ -0,0 +1,39 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+def options    = initOptions(params.options)
+
+process NANOLYSE {
+    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::nanolyse=1.2.0" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/nanolyse:1.2.0--py_0"
+    } else {
+        container "quay.io/biocontainers/nanolyse:1.2.0--py_0"
+    }
+
+    input:
+    tuple val(meta), path(fastq)
+    path fasta
+
+    output:
+    tuple val(meta), path("*.fastq.gz"), emit: fastq
+    path "*.log"                       , emit: log
+    path "*.version.txt"               , emit: version
+
+    script:
+    def software = getSoftwareName(task.process)
+    def prefix   = options.suffix ? "${meta.id}.${options.suffix}" : "${meta.id}"
+    """
+    gunzip -c $fastq | NanoLyse -r $fasta | gzip > ${prefix}.fastq.gz
+    mv NanoLyse.log ${prefix}.nanolyse.log
+
+    echo \$(NanoLyse --version 2>&1) | sed -e "s/NanoLyse //g" > ${software}.version.txt
+    """
+}

software/nanolyse/meta.yml

@@ -0,0 +1,46 @@
+name: nanolyse
+description: DNA contaminant removal using NanoLyse
+keywords:
+    - contaminant_removal
+tools:
+    - nanolyse:
+        description: |
+            DNA contaminant removal using NanoLyse
+        homepage: https://github.com/wdecoster/nanolyse
+        documentation: https://github.com/wdecoster/nanolyse#nanolyse
+input:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - fastq:
+        type: file
+        description: |
+            Basecalled reads in FASTQ.GZ format
+        pattern: "*.fastq.gz"
+    - fasta:
+        type: file
+        description: |
+            A reference fasta file against which to filter.
+        pattern: "*.fasta"
+output:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - fastq:
+        type: file
+        description: Reads with contaminants removed in FASTQ format
+        pattern: "*.fastq.gz"
+    - log:
+        type: file
+        description: Log of the Nanolyse run.
+        pattern: "*.log"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"
+authors:
+    - "@yuukiiwa"

tests/config/pytest_software.yml

@@ -403,6 +403,10 @@ multiqc:
   - software/multiqc/**
   - tests/software/multiqc/**
 
+nanolyse:
+  - software/nanolyse/**
+  - tests/software/nanolyse/**
+
 nanoplot:
   - software/nanoplot/**
   - tests/software/nanoplot/**

tests/software/nanolyse/main.nf

@@ -0,0 +1,24 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { NANOLYSE } from '../../../software/nanolyse/main.nf' addParams( options: [suffix: 'clean'] )
+
+process GET_NANOLYSE_FASTA {
+    output:
+    path "*fasta.gz", emit: fasta
+
+    script:
+    """
+    wget https://github.com/wdecoster/nanolyse/raw/master/reference/lambda.fasta.gz
+    """
+}
+
+workflow test_nanolyse {
+    input = [ [ id:'test' ], // meta map
+              [ file(params.test_data['sarscov2']['nanopore']['test_fastq_gz'], checkIfExists: true)]
+            ]
+
+    GET_NANOLYSE_FASTA()
+    NANOLYSE ( input, GET_NANOLYSE_FASTA.out.fasta )
+}

tests/software/nanolyse/test.yml

@@ -0,0 +1,6 @@
+- name: nanolyse
+  command: nextflow run ./tests/software/nanolyse -entry test_nanolyse -c tests/config/nextflow.config
+  tags:
+    - nanolyse
+  files:
+    - path: ./output/nanolyse/test.clean.fastq.gz