add graphmap index and align modules (from nanoseq modules) (#468)

* add graphmap index module

* add graphmap2/index

* add graohmap2 align module

* remove graphmap2 align md5sum

software/graphmap2/align/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/graphmap2/align/main.nf

@@ -0,0 +1,35 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+def options    = initOptions(params.options)
+
+process GRAPHMAP2_ALIGN {
+    tag "$meta.id"
+    publishDir "${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::graphmap=0.6.3" : null)
+    container "quay.io/biocontainers/graphmap:0.6.3--he513fc3_0"
+
+    input:
+    tuple val(meta), path(fastq)
+    path(fasta)
+    path(index)
+
+    output:
+    tuple val(meta), path("*.sam"), emit: align_sam
+
+    script:
+    """
+    graphmap2 \\
+        align \\
+        -t $task.cpus \\
+        -r $fasta \\
+        -i $index \\
+        -d $fastq \\
+        -o ${meta.id}.sam \\
+        --extcigar
+    """
+}

software/graphmap2/align/meta.yml

@@ -0,0 +1,49 @@
+name: graphmap2_align
+description: A versatile pairwise aligner for genomic and spliced nucleotide sequences
+keywords:
+    - align
+    - fasta
+    - fastq
+    - genome
+    - reference
+tools:
+    - graphmap2:
+        description: |
+            A versatile pairwise aligner for genomic and spliced nucleotide sequences.
+        homepage: https://github.com/lh3/minimap2
+        documentation: https://github.com/lh3/minimap2#uguide
+input:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - fastq:
+        type: file
+        description: |
+            List of input FASTQ files
+            and paired-end data, respectively.
+    - fasta:
+        type: file
+        description: |
+            Reference database in FASTA format.
+    - index:
+        type: file
+        description: |
+            FASTA index in gmidx.
+output:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - sam:
+        type: file
+        description: Alignment in SAM format
+        pattern: "*.sam"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"
+authors:
+    - "@yuukiiwa"

software/graphmap2/index/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/graphmap2/index/main.nf

@@ -0,0 +1,31 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+def options    = initOptions(params.options)
+
+process GRAPHMAP2_INDEX {
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:'') }
+
+    conda     (params.enable_conda ? "bioconda::graphmap=0.6.3" : null)
+    container "quay.io/biocontainers/graphmap:0.6.3--he513fc3_0"
+
+    input:
+    path(fasta)
+
+    output:
+    path("*.gmidx")       ,emit: index
+    path "*.version.txt"  ,emit: version
+
+    script:
+    """
+    graphmap2 \\
+        align \\
+        -t $task.cpus \\
+        -I \\
+        -r $fasta
+    echo \$(graphmap2 2>&1) > graphmap2.version.txt
+    """
+}

software/graphmap2/index/meta.yml

@@ -0,0 +1,28 @@
+name: graphmap2_index
+description: A versatile pairwise aligner for genomic and spliced nucleotide sequences
+keywords:
+    - index
+    - fasta
+    - reference
+tools:
+    - graphmap2:
+        description: |
+            A versatile pairwise aligner for genomic and spliced nucleotide sequences.
+        homepage: https://github.com/lbcb-sci/graphmap2
+        documentation: https://github.com/lbcb-sci/graphmap2#graphmap2---a-highly-sensitive-and-accurate-mapper-for-long-error-prone-reads
+input:
+    - fasta:
+        type: file
+        description: |
+            Reference database in FASTA format.
+output:
+    - gmidx:
+        type: file
+        description: Graphmap2 fasta index in gmidx format
+        pattern: "*.gmidx"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"
+authors:
+    - "@yuukiiwa"

tests/config/pytest_software.yml

@@ -274,6 +274,14 @@ gffread:
   - software/gffread/**
   - tests/software/gffread/**
 
+graphmap2/align:
+  - software/graphmap2/align/**
+  - tests/software/graphmap2/align/**
+
+graphmap2/index:
+  - software/graphmap2/index/**
+  - tests/software/graphmap2/index/**
+
 gubbins:
   - software/gubbins/**
   - tests/software/gubbins/**

tests/software/graphmap2/align/main.nf

@@ -0,0 +1,17 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GRAPHMAP2_INDEX } from '../../../../software/graphmap2/index/main.nf' addParams( options: [:] )
+include { GRAPHMAP2_ALIGN } from '../../../../software/graphmap2/align/main.nf' addParams( options: [:] )
+
+workflow test_graphmap2_align {
+
+    input = [ [ id:'test' ], // meta map
+              [ file(params.test_data['sarscov2']['nanopore']['test_fastq_gz'], checkIfExists: true) ]
+            ]
+    fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+
+    GRAPHMAP2_INDEX ( fasta )
+    GRAPHMAP2_ALIGN ( input, fasta, GRAPHMAP2_INDEX.out.index )
+}

tests/software/graphmap2/align/test.yml

@@ -0,0 +1,7 @@
+- name: graphmap2 align
+  command: nextflow run ./tests/software/graphmap2/align -entry test_graphmap2_align -c tests/config/nextflow.config
+  tags:
+    - graphmap2
+    - graphmap2/align
+  files:
+    - path: ./output/graphmap2/test.sam

tests/software/graphmap2/index/main.nf

@@ -0,0 +1,12 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GRAPHMAP2_INDEX } from '../../../../software/graphmap2/index/main.nf' addParams( options: [:] )
+
+workflow test_graphmap2_index {
+
+    fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+
+    GRAPHMAP2_INDEX ( fasta )
+}

tests/software/graphmap2/index/test.yml

@@ -0,0 +1,8 @@
+- name: graphmap2 index
+  command: nextflow run ./tests/software/graphmap2/index -entry test_graphmap2_index -c tests/config/nextflow.config
+  tags:
+    - graphmap2
+    - graphmap2/index
+  files:
+    - path: ./output/graphmap2/genome.fasta.gmidx
+      md5sum: 2973f9b7fa52c78899c73908f8afc6be