Update dsh-bio modules to version 2.0.4 (#482)

* Update dsh-bio modules to version 2.0.4

* update docker tag

* update md5 checksums

* Update software/dshbio/filtergff3/main.nf

* Update software/dshbio/splitgff3/main.nf

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

software/dshbio/filterbed/main.nf

@@ -4,18 +4,18 @@ include { initOptions; saveFiles; getSoftwareName } from './functions'
 params.options = [:]
 options        = initOptions(params.options)
 
-process DSH_FILTERBED {
+process DSHBIO_FILTERBED {
     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::dsh-bio=2.0.3" : null)
+    conda (params.enable_conda ? "bioconda::dsh-bio=2.0.4" : null)
     if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
-        container "https://depot.galaxyproject.org/singularity/dsh-bio:2.0.3--0"
+        container "https://depot.galaxyproject.org/singularity/dsh-bio:2.0.4--hdfd78af_0"
     } else {
-        container "quay.io/biocontainers/dsh-bio:2.0.3--0"
+        container "quay.io/biocontainers/dsh-bio:2.0.4--hdfd78af_0"
     }
 
     input:
@@ -29,7 +29,8 @@ process DSH_FILTERBED {
     def software = getSoftwareName(task.process)
     def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
     """
-    dsh-filter-bed \\
+    dsh-bio \\
+        filter-bed \\
         $options.args \\
         -i $bed \\
         -o ${prefix}.bed.gz

software/dshbio/filterbed/meta.yml

@@ -1,9 +1,9 @@
-name: dsh_filterbed
+name: dshbio_filterbed
 description: Filter features in gzipped BED format
 keywords:
     - bed
 tools:
-    - dsh:
+    - dshbio:
         description: |
             Reads, features, variants, assemblies, alignments, genomic range trees, pangenome
             graphs, and a bunch of random command line tools for bioinformatics. LGPL version 3

software/dshbio/filtergff3/main.nf

@@ -0,0 +1,40 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process DSHBIO_FILTERGFF3 {
+    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::dsh-bio=2.0.4" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/dsh-bio:2.0.4--hdfd78af_0"
+    } else {
+        container "quay.io/biocontainers/dsh-bio:2.0.4--hdfd78af_0"
+    }
+
+    input:
+    tuple val(meta), path(gff3)
+
+    output:
+    tuple val(meta), path("*.gff3.gz"), emit: gff3
+    path "*.version.txt"              , emit: version
+
+    script:
+    def software = getSoftwareName(task.process)
+    def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    """
+    dsh-bio \\
+        filter-gff3 \\
+        $options.args \\
+        -i $gff3 \\
+        -o ${prefix}.gff3.gz
+
+    echo \$(dsh-bio --version 2>&1) | grep -o 'dsh-bio-tools .*' | cut -f2 -d ' ' > ${software}.version.txt
+    """
+}

software/dshbio/filtergff3/meta.yml

@@ -0,0 +1,38 @@
+name: dshbio_filtergff3
+description: Filter features in gzipped GFF3 format
+keywords:
+    - gff3
+tools:
+    - dshbio:
+        description: |
+            Reads, features, variants, assemblies, alignments, genomic range trees, pangenome
+            graphs, and a bunch of random command line tools for bioinformatics. LGPL version 3
+            or later.
+        homepage: https://github.com/heuermh/dishevelled-bio
+        documentation: https://github.com/heuermh/dishevelled-bio
+input:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - gff3:
+        type: file
+        description: Features in gzipped GFF3 format
+        pattern: "*.{gff3.gz}"
+output:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - gff3:
+        type: file
+        description: Features in gzipped GFF3 format
+        pattern: "*.{gff3.gz}"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"
+authors:
+    - "@heuermh"

software/dshbio/splitbed/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/dshbio/splitbed/main.nf

@@ -4,18 +4,18 @@ include { initOptions; saveFiles; getSoftwareName } from './functions'
 params.options = [:]
 options        = initOptions(params.options)
 
-process DSH_SPLITBED {
+process DSHBIO_SPLITBED {
     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::dsh-bio=2.0.3" : null)
+    conda (params.enable_conda ? "bioconda::dsh-bio=2.0.4" : null)
     if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
-        container "https://depot.galaxyproject.org/singularity/dsh-bio:2.0.3--0"
+        container "https://depot.galaxyproject.org/singularity/dsh-bio:2.0.4--hdfd78af_0"
     } else {
-        container "quay.io/biocontainers/dsh-bio:2.0.3--0"
+        container "quay.io/biocontainers/dsh-bio:2.0.4--hdfd78af_0"
     }
 
     input:
@@ -29,7 +29,8 @@ process DSH_SPLITBED {
     def software = getSoftwareName(task.process)
     def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
     """
-    dsh-split-bed \\
+    dsh-bio \\
+        split-bed \\
         $options.args \\
         -p $prefix \\
         -s '.bed.gz' \\

software/dshbio/splitbed/meta.yml

@@ -1,9 +1,9 @@
-name: dsh_splitbed
+name: dshbio_splitbed
 description: Split features in gzipped BED format
 keywords:
     - bed
 tools:
-    - dsh:
+    - dshbio:
         description: |
             Reads, features, variants, assemblies, alignments, genomic range trees, pangenome
             graphs, and a bunch of random command line tools for bioinformatics. LGPL version 3

software/dshbio/splitgff3/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/dshbio/splitgff3/main.nf

@@ -0,0 +1,41 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process DSHBIO_SPLITGFF3 {
+    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::dsh-bio=2.0.4" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/dsh-bio:2.0.4--hdfd78af_0"
+    } else {
+        container "quay.io/biocontainers/dsh-bio:2.0.4--hdfd78af_0"
+    }
+
+    input:
+    tuple val(meta), path(gff3)
+
+    output:
+    tuple val(meta), path("*.gff3.gz"), emit: gff3
+    path "*.version.txt"              , emit: version
+
+    script:
+    def software = getSoftwareName(task.process)
+    def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    """
+    dsh-bio \\
+        split-gff3 \\
+        $options.args \\
+        -p $prefix \\
+        -s '.gff3.gz' \\
+        -i $gff3
+
+    echo \$(dsh-bio --version 2>&1) | grep -o 'dsh-bio-tools .*' | cut -f2 -d ' ' > ${software}.version.txt
+    """
+}

software/dshbio/splitgff3/meta.yml

@@ -0,0 +1,38 @@
+name: dshbio_splitgff3
+description: Split features in gzipped GFF3 format
+keywords:
+    - gff3
+tools:
+    - dshbio:
+        description: |
+            Reads, features, variants, assemblies, alignments, genomic range trees, pangenome
+            graphs, and a bunch of random command line tools for bioinformatics. LGPL version 3
+            or later.
+        homepage: https://github.com/heuermh/dishevelled-bio
+        documentation: https://github.com/heuermh/dishevelled-bio
+input:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - gff3:
+        type: file
+        description: Features in gzipped GFF3 format to split
+        pattern: "*.{gff3.gz}"
+output:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - gff3:
+        type: file
+        description: Features in split gzipped GFF3 formatted files
+        pattern: "*.{gff3.gz}"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"
+authors:
+    - "@heuermh"

tests/config/pytest_software.yml

@@ -190,13 +190,21 @@ deeptools/plotprofile:
   - software/deeptools/plotprofile/**
   - tests/software/deeptools/plotprofile/**
 
-dsh/filterbed:
+dshbio/filterbed:
-  - software/dsh/filterbed/**
+  - software/dshbio/filterbed/**
-  - tests/software/dsh/filterbed/**
+  - tests/software/dshbio/filterbed/**
 
-dsh/splitbed:
+dshbio/filtergff3:
-  - software/dsh/splitbed/**
+  - software/dshbio/filtergff3/**
-  - tests/software/dsh/splitbed/**
+  - tests/software/dshbio/filtergff3/**
+
+dshbio/splitbed:
+  - software/dshbio/splitbed/**
+  - tests/software/dshbio/splitbed/**
+
+dshbio/splitgff3:
+  - software/dshbio/splitgff3/**
+  - tests/software/dshbio/splitgff3/**
 
 fastp:
   - software/fastp/**

tests/software/dsh/filterbed/main.nf

@@ -1,13 +0,0 @@
-#!/usr/bin/env nextflow
-
-nextflow.enable.dsl = 2
-
-include { DSH_FILTERBED } from '../../../../software/dsh/filterbed/main.nf' addParams( options: [suffix: '.filtered', args: '--range chr1:0-1000'] )
-
-workflow test_dsh_filterbed {
-    input = [ [ id:'test' ], // meta map
-              [ file(params.test_data['sarscov2']['genome']['test_bed'], checkIfExists: true) ]
-            ]
-
-    DSH_FILTERBED ( input )
-}

tests/software/dsh/filterbed/test.yml

@@ -1,8 +0,0 @@
-- name: dsh filterbed
-  command: nextflow run ./tests/software/dsh/filterbed -entry test_dsh_filterbed -c tests/config/nextflow.config
-  tags:
-    - dsh
-    - dsh/filterbed
-  files:
-    - path: ./output/dsh/test.filtered.bed.gz
-      md5sum: 163be0a88c70ca629fd516dbaadad96a

tests/software/dsh/splitbed/test.yml

@@ -1,10 +0,0 @@
-- name: dsh splitbed
-  command: nextflow run ./tests/software/dsh/splitbed -entry test_dsh_splitbed -c tests/config/nextflow.config
-  tags:
-    - dsh
-    - dsh/splitbed
-  files:
-    - path: ./output/dsh/test.1.bed.gz
-      md5sum: 967ba338f361740eb015304003ababe7
-    - path: ./output/dsh/test.0.bed.gz
-      md5sum: 8b884d8cf5c57955f218f1c6dbf02d54

tests/software/dshbio/filterbed/main.nf

@@ -0,0 +1,13 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { DSHBIO_FILTERBED } from '../../../../software/dshbio/filterbed/main.nf' addParams( options: [suffix: '.filtered', args: '--range chr1:0-1000'] )
+
+workflow test_dshbio_filterbed {
+    input = [ [ id:'test' ], // meta map
+              [ file(params.test_data['sarscov2']['genome']['test_bed'], checkIfExists: true) ]
+            ]
+
+    DSHBIO_FILTERBED ( input )
+}

tests/software/dshbio/filterbed/test.yml

@@ -0,0 +1,8 @@
+- name: dshbio filterbed
+  command: nextflow run ./tests/software/dshbio/filterbed -entry test_dshbio_filterbed -c tests/config/nextflow.config
+  tags:
+    - dshbio
+    - dshbio/filterbed
+  files:
+    - path: ./output/dshbio/test.filtered.bed.gz
+      md5sum: 163be0a88c70ca629fd516dbaadad96a

tests/software/dshbio/filtergff3/main.nf

@@ -0,0 +1,13 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { DSHBIO_FILTERGFF3 } from '../../../../software/dshbio/filtergff3/main.nf' addParams( options: [suffix: '.filtered', args: '--range MT192765.1:0-1000'] )
+
+workflow test_dshbio_filtergff3 {
+    input = [ [ id:'test' ], // meta map
+              [ file(params.test_data['sarscov2']['genome']['genome_gff3_gz'], checkIfExists: true) ]
+            ]
+
+    DSHBIO_FILTERGFF3 ( input )
+}

tests/software/dshbio/filtergff3/test.yml

@@ -0,0 +1,8 @@
+- name: dshbio filtergff3
+  command: nextflow run ./tests/software/dshbio/filtergff3 -entry test_dshbio_filtergff3 -c tests/config/nextflow.config
+  tags:
+    - dshbio
+    - dshbio/filtergff3
+  files:
+    - path: ./output/dshbio/test.filtered.gff3.gz
+      md5sum: 89d320cf91c0ca8fd200cfa9688954e3

tests/software/dshbio/splitbed/main.nf

@@ -2,12 +2,12 @@
 
 nextflow.enable.dsl = 2
 
-include { DSH_SPLITBED } from '../../../../software/dsh/splitbed/main.nf' addParams( options: [suffix: '.', args: '--records 2'] )
+include { DSHBIO_SPLITBED } from '../../../../software/dshbio/splitbed/main.nf' addParams( options: [suffix: '.', args: '--records 2'] )
 
-workflow test_dsh_splitbed {
+workflow test_dshbio_splitbed {
     input = [ [ id:'test' ], // meta map
               [ file(params.test_data['sarscov2']['genome']['test_bed'], checkIfExists: true) ]
             ]
 
-    DSH_SPLITBED ( input )
+    DSHBIO_SPLITBED ( input )
 }

tests/software/dshbio/splitbed/test.yml

@@ -0,0 +1,10 @@
+- name: dshbio splitbed
+  command: nextflow run ./tests/software/dshbio/splitbed -entry test_dshbio_splitbed -c tests/config/nextflow.config
+  tags:
+    - dshbio
+    - dshbio/splitbed
+  files:
+    - path: ./output/dshbio/test.1.bed.gz
+      md5sum: 967ba338f361740eb015304003ababe7
+    - path: ./output/dshbio/test.0.bed.gz
+      md5sum: 8b884d8cf5c57955f218f1c6dbf02d54

tests/software/dshbio/splitgff3/main.nf

@@ -0,0 +1,13 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { DSHBIO_SPLITGFF3 } from '../../../../software/dshbio/splitgff3/main.nf' addParams( options: [suffix: '.', args: '--records 15'] )
+
+workflow test_dshbio_splitgff3 {
+    input = [ [ id:'test' ], // meta map
+              [ file(params.test_data['sarscov2']['genome']['genome_gff3_gz'], checkIfExists: true) ]
+            ]
+
+    DSHBIO_SPLITGFF3 ( input )
+}

tests/software/dshbio/splitgff3/test.yml

@@ -0,0 +1,10 @@
+- name: dshbio splitgff3
+  command: nextflow run ./tests/software/dshbio/splitgff3 -entry test_dshbio_splitgff3 -c tests/config/nextflow.config
+  tags:
+    - dshbio
+    - dshbio/splitgff3
+  files:
+    - path: ./output/dshbio/test.1.gff3.gz
+      md5sum: 0742895e81fe080c01f43f9dd616baae
+    - path: ./output/dshbio/test.0.gff3.gz
+      md5sum: 9aed611b89093f5e0db4e63cb56d8416