New module: spoligotyper

modules/nf-core/spoligotyper/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::spoligotyper=0.9.0

modules/nf-core/spoligotyper/main.nf

@@ -0,0 +1,42 @@
+process SPOLIGOTYPER {
+    tag "${meta.id}"
+    label 'process_low'
+
+    conda "${moduleDir}/environment.yml"
+    container "${workflow.containerEngine in ['singularity', 'apptainer'] && !task.ext.singularity_pull_docker_container
+        ? 'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/18/18627f630e2f90d14aa45effad5909fb77092cb48534b7d677f91f029c65d2de/data'
+        : 'community.wave.seqera.io/library/spoligotyper:0.9.0--679a58efe8efff70'}"
+
+    input:
+    tuple val(meta), path(reads)
+
+    output:
+    tuple val(meta), path("${prefix}_spoligotyping.txt")    , emit: tsv
+    tuple val(meta), path("${prefix}_spoligotyping.json")   , emit: json
+    tuple val(meta), path("${prefix}_spoligotyping.pdf")    , emit: pdf, optional: true
+    tuple val(meta), path("${prefix}_spoligotyping_mqc.json"), emit: multiqc
+    tuple val("${task.process}"), val('spoligotyper'), eval("spoligotyper --version | sed 's/spoligotyper //'"), emit: versions_spoligotyper, topic: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    prefix = task.ext.prefix ?: "${meta.id}"
+    // Reads (single-end or paired-end) or an assembly: spoligotyper detects the file type
+    def input = reads instanceof List && reads.size() == 2 ? "-r1 \"${reads[0]}\" -r2 \"${reads[1]}\"" : "-r1 \"${reads}\""
+    """
+    spoligotyper \\
+        $args \\
+        $input \\
+        --sample "${prefix}" \\
+        --output . \\
+        --threads $task.cpus
+    """
+
+    stub:
+    prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch "${prefix}_spoligotyping.txt" "${prefix}_spoligotyping.json" "${prefix}_spoligotyping.pdf" "${prefix}_spoligotyping_mqc.json"
+    """
+}

modules/nf-core/spoligotyper/meta.yml

@@ -0,0 +1,135 @@
+name: spoligotyper
+description: In silico spoligotyping, species check and lineage of Mycobacterium tuberculosis complex samples
+keywords:
+  - Mycobacterium tuberculosis
+  - Mycobacterium bovis
+  - spoligotyping
+  - genotyping
+  - lineage
+tools:
+  - spoligotyper:
+      description: |
+        In silico spoligotyping of Mycobacterium tuberculosis complex samples from reads or assemblies, with a
+        species check (regions of difference) and the lineage (SNP barcode), and a PDF report for quality assurance
+      homepage: https://github.com/duceppemo/spoligotyper
+      documentation: https://github.com/duceppemo/spoligotyper/wiki
+      tool_dev_url: https://github.com/duceppemo/spoligotyper
+      doi: "10.5281/zenodo.22926160"
+      licence:
+        - "MIT"
+      identifier: ""
+      args_id: "$args"
+
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'test', single_end:false ]
+    - reads:
+        type: file
+        description: Single-end or paired-end reads (fastq), or an assembly (fasta), gzipped or not
+        pattern: "*.{fastq,fq,fasta,fa,fna,fas}{,.gz}"
+        ontologies:
+          - edam: http://edamontology.org/format_1930 # FASTQ
+          - edam: http://edamontology.org/format_1929 # FASTA
+output:
+  tsv:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "${prefix}_spoligotyping.txt":
+          type: file
+          description: Tab-separated table with the spoligotype, species, lineage and warnings
+          pattern: "*_spoligotyping.txt"
+          ontologies:
+            - edam: http://edamontology.org/format_3475 # TSV
+  json:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "${prefix}_spoligotyping.json":
+          type: file
+          description: All the results and run information
+          pattern: "*_spoligotyping.json"
+          ontologies:
+            - edam: http://edamontology.org/format_3464 # JSON
+  pdf:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "${prefix}_spoligotyping.pdf":
+          type: file
+          description: Optional. PDF report for quality assurance (not written with --no-pdf)
+          pattern: "*_spoligotyping.pdf"
+          ontologies:
+            - edam: http://edamontology.org/format_3508 # PDF
+  multiqc:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "${prefix}_spoligotyping_mqc.json":
+          type: file
+          description: MultiQC custom content table
+          pattern: "*_spoligotyping_mqc.json"
+          ontologies:
+            - edam: http://edamontology.org/format_3464 # JSON
+  versions_spoligotyper:
+    - - ${task.process}:
+          type: string
+          description: The process the versions were collected from
+      - spoligotyper:
+          type: string
+          description: The tool name
+      - "spoligotyper --version | sed 's/spoligotyper //'":
+          type: eval
+          description: The version of the tool
+
+topics:
+  versions:
+    - - ${task.process}:
+          type: string
+          description: The process the versions were collected from
+      - spoligotyper:
+          type: string
+          description: The tool name
+      - "spoligotyper --version | sed 's/spoligotyper //'":
+          type: eval
+          description: The version of the tool
+
+authors:
+  - "@duceppemo"
+maintainers:
+  - "@duceppemo"
+containers:
+  docker:
+    linux/amd64:
+      name: community.wave.seqera.io/library/spoligotyper:0.9.0--679a58efe8efff70
+      build_id: bd-679a58efe8efff70_1
+      scan_id: sc-0c292160a28f85ac_1
+    linux/arm64:
+      name: community.wave.seqera.io/library/spoligotyper:0.9.0--872d67a3849f499b
+      build_id: bd-872d67a3849f499b_1
+      scan_id: sc-448dd396d71a4062_1
+  singularity:
+    linux/arm64:
+      name: oras://community.wave.seqera.io/library/spoligotyper:0.9.0--964817015cdc198a
+      build_id: bd-964817015cdc198a_1
+      https: https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/d7/d75cbca42d0b437d193d5f9e54428ca9302f3c9cfcf8f472b2bf972d08948433/data
+    linux/amd64:
+      name: oras://community.wave.seqera.io/library/spoligotyper:0.9.0--a133deb816fb42d2
+      build_id: bd-a133deb816fb42d2_1
+      https: https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/18/18627f630e2f90d14aa45effad5909fb77092cb48534b7d677f91f029c65d2de/data
+  conda:
+    linux/amd64:
+      lock_file: modules/nf-core/spoligotyper/.conda-lock/linux_amd64-bd-679a58efe8efff70_1.txt
+    linux/arm64:
+      lock_file: modules/nf-core/spoligotyper/.conda-lock/linux_arm64-bd-872d67a3849f499b_1.txt

modules/nf-core/spoligotyper/tests/main.nf.test

@@ -0,0 +1,81 @@
+nextflow_process {
+
+    name "Test Process SPOLIGOTYPER"
+    script "../main.nf"
+    process "SPOLIGOTYPER"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "spoligotyper"
+
+    // nf-core test data has no M. tuberculosis complex genome: these tests check that the module runs and
+    // writes its outputs ("MTBC not detected" is the expected result).
+    test("sarscov2 - fasta") {
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:true ],
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
+                ]
+                """
+            }
+        }
+        then {
+            assertAll(
+                { assert process.success },
+                // Stable checks for the unstable channels: json and pdf embed run timestamps
+                { assert path(process.out.tsv[0][1]).text.contains('MTBC not detected') },
+                { assert path(process.out.json[0][1]).text.contains('MTBC not detected') },
+                { assert file(process.out.pdf[0][1]).length() > 0 },
+                { assert snapshot(sanitizeOutput(process.out, unstableKeys: ["json", "pdf"])).match() }
+            )
+        }
+    }
+
+    test("sarscov2 - paired-end fastq") {
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ],
+                    [
+                        file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true),
+                        file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_2.fastq.gz', checkIfExists: true)
+                    ]
+                ]
+                """
+            }
+        }
+        then {
+            assertAll(
+                { assert process.success },
+                // Stable checks for the unstable channels: json and pdf embed run timestamps
+                { assert path(process.out.tsv[0][1]).text.contains('fastq') },
+                { assert path(process.out.json[0][1]).text.contains('fastq') },
+                { assert file(process.out.pdf[0][1]).length() > 0 },
+                { assert snapshot(sanitizeOutput(process.out, unstableKeys: ["json", "pdf"])).match() }
+            )
+        }
+    }
+
+    test("sarscov2 - fasta - stub") {
+        options "-stub"
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:true ],
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
+                ]
+                """
+            }
+        }
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(sanitizeOutput(process.out)).match() }
+            )
+        }
+    }
+}