Add rgi/bwt

modules/nf-core/rgi/bwt/environment.yml

@@ -0,0 +1,7 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::rgi=6.0.5

modules/nf-core/rgi/bwt/main.nf

@@ -0,0 +1,81 @@
+process RGI_BWT {
+    tag "${meta.id}"
+    label 'process_medium'
+
+    conda "${moduleDir}/environment.yml"
+    container "${workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container
+        ? 'https://depot.galaxyproject.org/singularity/rgi:6.0.5--pyh05cac1d_0'
+        : 'biocontainers/rgi:6.0.5--pyh05cac1d_0'}"
+
+    input:
+    tuple val(meta), path(reads, arity: '1..2')
+    path card
+    path wildcard
+
+    output:
+    tuple val(meta), path("*.json"), emit: json
+    tuple val(meta), path("*.txt"), emit: tsv
+    tuple val(meta), path("temp/"), emit: tmp
+    tuple val("${task.process}"), val('rgi'), eval("rgi main --version"),  emit: versions_rgi, topic: versions
+    tuple val("${task.process}"), val('rgi-database'), eval("echo \$DB_VERSION"),  emit: versions_db , topic: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    // This customizes the command: rgi load
+    def args = task.ext.args ?: ''
+    // This customizes the command: rgi main
+    def args2 = task.ext.args2 ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def read_one = reads[0]
+    def read_two = reads.size() > 1 ? reads[1] : null
+    def load_wildcard = ""
+
+    if (wildcard) {
+        load_wildcard = """ \\
+            --wildcard_annotation ${wildcard}/wildcard_database_v\$DB_VERSION.fasta \\
+            --wildcard_annotation_all_models ${wildcard}/wildcard_database_v\$DB_VERSION\\_all.fasta \\
+            --wildcard_index ${wildcard}/wildcard/index-for-model-sequences.txt \\
+            --amr_kmers ${wildcard}/wildcard/all_amr_61mers.txt \\
+            --kmer_database ${wildcard}/wildcard/61_kmer_db.json \\
+            --kmer_size 61
+        """
+    }
+
+    """
+    DB_VERSION=\$(ls ${card}/card_database_*_all.fasta | sed "s/${card}\\/card_database_v\\([0-9].*[0-9]\\).*/\\1/")
+
+    rgi \\
+        load \\
+        ${args} \\
+        --local \\
+        --card_json ${card}/card.json \\
+        --debug \\
+        --card_annotation ${card}/card_database_v\$DB_VERSION.fasta \\
+        --card_annotation_all_models ${card}/card_database_v\$DB_VERSION\\_all.fasta \\
+        ${load_wildcard}
+
+    rgi \\
+        bwt \\
+        ${args2} \\
+        --local \\
+        --threads ${task.cpus} \\
+        --output_file ${prefix} \\
+        --read_one ${read_one} \\
+        ${ read_two ? "--read_two ${read_two}" : "" }
+
+    mkdir temp/
+    for FILE in *.xml *.fsa *.{nhr,nin,nsq} *.draft *.potentialGenes *{variant,rrna,protein,predictedGenes,overexpression,homolog}.json; do [[ -e \$FILE ]] && mv \$FILE temp/; done
+
+    """
+
+    stub:
+    """
+    mkdir -p temp
+    touch test.json
+    touch test.txt
+
+    DB_VERSION=stub_version
+    """
+}

modules/nf-core/rgi/bwt/meta.yml

@@ -0,0 +1,126 @@
+name: rgi_bwt
+description: Predict antibiotic resistance from protein or nucleotide data
+keywords:
+  - bacteria
+  - fasta
+  - antibiotic resistance
+tools:
+  - rgi:
+      description: This tool provides a preliminary annotation of your DNA
+        sequence(s) based upon the data available in The Comprehensive Antibiotic
+        Resistance Database (CARD). Hits to genes tagged with Antibiotic
+        Resistance ontology terms will be highlighted. As CARD expands to include
+        more pathogens, genomes, plasmids, and ontology terms this tool will grow
+        increasingly powerful in providing first-pass detection of antibiotic
+        resistance associated genes. See license at CARD website.
+      homepage: https://card.mcmaster.ca
+      documentation: https://github.com/arpcard/rgi
+      tool_dev_url: https://github.com/arpcard/rgi
+      doi: "10.1093/nar/gkz935"
+      licence: ["https://card.mcmaster.ca/about"]
+      identifier: ""
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'test', single_end:false ]
+    - reads:
+        type: file
+        description: Single-end or paired-end nucleotide sequences in FASTQ or FASTA format
+        pattern: "*.{fastq,fastq.gz,fq,fq.gz,fasta,fasta.gz,fa,fa.gz,fna,fna.gz,faa,faa.gz}"
+        ontologies:
+          - edam: http://edamontology.org/format_1930 # FASTQ
+  - card:
+      type: directory
+      description: Directory containing the CARD database. This is expected to be
+        the unarchived but otherwise unaltered download folder (see RGI
+        documentation for download instructions).
+      pattern: "*/"
+  - wildcard:
+      type: directory
+      description: Directory containing the WildCARD database (optional). This is
+        expected to be the unarchived but otherwise unaltered download folder (see
+        RGI documentation for download instructions).
+      pattern: "*/"
+output:
+  json:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "*.json":
+          type: file
+          description: JSON formatted file with RGI results
+          pattern: "*.{json}"
+          ontologies:
+            - edam: http://edamontology.org/format_3464 # JSON
+  tsv:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "*.txt":
+          type: file
+          description: Tab-delimited file with RGI results
+          pattern: "*.{txt}"
+          ontologies: []
+  tmp:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - temp/:
+          type: directory
+          description: Directory containing various intermediate files
+          pattern: "temp/"
+  versions_rgi:
+    - - ${task.process}:
+          type: string
+          description: The process the versions were collected from
+      - rgi:
+          type: string
+          description: The tool name
+      - rgi main --version:
+          type: string
+          description: The version string returned by the command
+  versions_db:
+    - - ${task.process}:
+          type: string
+          description: The process the versions were collected from
+      - rgi-database:
+          type: string
+          description: The tool name
+      - echo \$DB_VERSION:
+          type: string
+          description: The CARD database version string
+
+topics:
+  versions:
+    - - ${task.process}:
+          type: string
+          description: The process the versions were collected from
+      - rgi:
+          type: string
+          description: The tool name
+      - rgi main --version:
+          type: string
+          description: Command used to collect the version
+    - - ${task.process}:
+          type: string
+          description: The process the versions were collected from
+      - rgi-database:
+          type: string
+          description: The tool name
+      - echo \$DB_VERSION:
+          type: string
+          description: Command used to collect the version
+
+authors:
+  - "@vinisalazar"
+maintainers:
+  - "@nickp60"
+  - "@vinisalazar"

modules/nf-core/rgi/bwt/tests/main.nf.test

@@ -0,0 +1,95 @@
+nextflow_process {
+
+    name "Test Process RGI_BWT"
+    script "../main.nf"
+    process "RGI_BWT"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "rgi"
+    tag "rgi/bwt"
+    tag "rgi/cardannotation"
+    tag "untar"
+
+    setup {
+        run("UNTAR") {
+            script "modules/nf-core/untar/main.nf"
+            process {
+            """
+            file('https://card.mcmaster.ca/latest/data', checkIfExists: true).copyTo('card-data.tar.bz2')
+
+            input[0] = [
+                [ ],
+                file("card-data.tar.bz2")
+            ]
+            """
+            }
+        }
+
+        run("RGI_CARDANNOTATION") {
+            script "modules/nf-core/rgi/cardannotation"
+            process {
+                """
+                input[0] = UNTAR.out.untar.map{ it[1] }
+                """
+            }
+        }
+    }
+
+    test("rgi/bwt - homo_sapiens - test_fastq_gz") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+                    [
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/fastq/test_1.fastq.gz', checkIfExists: true),
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/fastq/test_2.fastq.gz', checkIfExists: true),
+                    ]
+                ]
+                input[1] = RGI_CARDANNOTATION.out.db
+                input[2] = []
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    process.out.findAll { key, val -> key.startsWith("versions") },
+                    file(process.out.tmp.get(0).get(1)).list().sort(),
+                    ).match() }
+            )
+        }
+    }
+
+    test("rgi/bwt - homo_sapiens - test_fastq_gz - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+                    [
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/fastq/test_1.fastq.gz', checkIfExists: true),
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/fastq/test_2.fastq.gz', checkIfExists: true),
+                    ]
+                ]
+                input[1] = RGI_CARDANNOTATION.out.db
+                input[2] = []
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+}