Centrifuger quant

modules/nf-core/centrifuger/build/main.nf

@@ -5,7 +5,7 @@ process CENTRIFUGER_BUILD {
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
         'https://depot.galaxyproject.org/singularity/centrifuger:1.1.0--hf426362_0':
-        'biocontainers/centrifuger:1.1.0--hf426362_0' }"
+        'quay.io/biocontainers/centrifuger:1.1.0--hf426362_0' }"
 
     input:
     tuple val(meta), path(references, stageAs: 'genomes/*')

modules/nf-core/centrifuger/centrifuger/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::centrifuger=1.1.0"

modules/nf-core/centrifuger/centrifuger/main.nf

@@ -0,0 +1,88 @@
+process CENTRIFUGER_CENTRIFUGER {
+    tag "$meta.id"
+    label 'process_single'
+
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/centrifuger:1.1.0--hf426362_0':
+        'quay.io/biocontainers/centrifuger:1.1.0--hf426362_0' }"
+
+    input:
+    tuple val(meta), path(reads)
+    path db
+    val save_unclassified
+    val save_classified
+    path barcode
+    path umi
+
+
+    output:
+    tuple val(meta), path("${meta.id}.tsv"), emit: classification_file
+    tuple val(meta), path("${meta.id}.classified*"), optional: true, emit: fastq_classified
+    tuple val(meta), path("${meta.id}.unclassified*"), optional: true, emit: fastq_unclassified
+    tuple val("${task.process}"), val('centrifuger'), eval("centrifuger -v 2>&1 | head -n 1 | cut -d ' ' -f 2 | sed 's/^v//'"),emit: versions_centrifuger,  topic: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def paired = meta.single_end ? "-u ${reads}" : "-1 ${reads[0]} -2 ${reads[1]}"
+    // Optional outputs
+    def unclassified_arg = save_unclassified ? "--un ${prefix}.unclassified" : ""
+    def classified_arg = save_classified ? "--cl ${prefix}.classified" : ""
+    def barcode_arg = barcode ? "--barcode ${barcode}" : ""
+    def umi_arg = umi ? "--UMI ${umi}" : ""
+
+
+    """
+    db_name=`find -L ${db} -name "*.1.cfr" -not -name "._*"  | sed 's/\\.1.cfr\$//'`
+
+    centrifuger \\
+        -x \$db_name \\
+        ${paired} \\
+        ${unclassified_arg} \\
+        ${classified_arg} \\
+        ${barcode_arg} \\
+        ${umi_arg} \\
+        -t ${task.cpus} \\
+        ${args} > ${prefix}.tsv
+
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    echo ${args}
+    #main output
+    touch ${prefix}.tsv
+
+    #Optional outputs
+    if ${save_unclassified}; then
+        if ${meta.single_end}; then
+            echo "" | gzip >  ${prefix}.unclassified.fq.gz
+        else
+            echo "" | gzip > ${prefix}.unclassified_1.fq.gz
+            echo "" | gzip > ${prefix}.unclassified_2.fq.gz
+        fi
+    fi
+
+    if ${save_classified}; then
+        if ${meta.single_end}; then
+            echo "" | gzip  > ${prefix}.classified.fq.gz
+        else
+           echo "" | gzip > ${prefix}.classified_1.fq.gz
+           echo "" | gzip > ${prefix}.classified_2.fq.gz
+        fi
+    fi
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        centrifuger: \$(centrifuger -v 2>&1 | head -n 1 | cut -d ' ' -f 2)
+    END_VERSIONS
+    """
+}

modules/nf-core/centrifuger/centrifuger/meta.yml

@@ -0,0 +1,114 @@
+name: "centrifuger_centrifuger"
+description: Classification of sequencing reads using the Centrifuger tool.
+keywords:
+  - metagenomics
+  - classification
+  - centrifuger
+tools:
+  - "centrifuger":
+      description: "Lossless compression of microbial genomes for efficient and accurate
+        metagenomic sequence classification."
+      homepage: "https://github.com/mourisl/centrifuger"
+      documentation: "https://github.com/mourisl/centrifuger"
+      tool_dev_url: "https://github.com/mourisl/centrifuger"
+      doi: "10.1186/s13059-024-03244-4"
+      licence:
+        - "MIT"
+      identifier: biotools:centrifuger
+input:
+  - - meta:
+        type: map
+        description: Groovy Map containing sample information. e.g. `[
+          id:'sample1', single_end:false ]`
+    - reads:
+        type: file
+        description: |
+          List of input FastQ files of size 1 and 2 for single-end and paired-end, respectively.
+        pattern: "*.{fastq,fq,fastq.gz,fq.gz}"
+        ontologies:
+          - edam: http://edamontology.org/format_1930 #FASTQ
+  - db:
+      type: directory
+      description: Path to directory containing Centrifuger database files.
+  - save_unclassified:
+      type: boolean
+      description: |
+        Optional - if true, output unclassified reads.
+  - save_classified:
+      type: boolean
+      description: |
+        Optional - if true, output classified reads.
+  - barcode:
+      type: file
+      description: |
+        Optional barcode file.
+  - umi:
+      type: file
+      description: |
+        Optional UMI file.
+output:
+  classification_file:
+    - - meta:
+          type: map
+          description: Groovy Map containing sample information. e.g. `[
+            id:'sample1', single_end:false ]`
+      - ${meta.id}.tsv:
+          type: file
+          description: |
+            File contαining classification results
+          pattern: "${prefix}.tsv"
+          ontologies:
+            - edam: http://edamontology.org/format_3475 #TSV
+
+  fastq_classified:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - ${meta.id}.classified*:
+          type: file
+          description: FASTQ file(s) containing classified reads
+          pattern: "*.{fastq,fq,fastq.gz,fq.gz}"
+          ontologies:
+            - edam: http://edamontology.org/format_1930
+
+  fastq_unclassified:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - ${meta.id}.unclassified*:
+          type: file
+          description: FASTQ file(s) containing unclassified reads
+          pattern: "*.{fastq,fq,fastq.gz,fq.gz}"
+          ontologies:
+            - edam: http://edamontology.org/format_1930
+  versions_centrifuger:
+    - - ${task.process}:
+          type: string
+          description: The name of the process
+      - centrifuger:
+          type: string
+          description: The name of the tool
+      - centrifuger -v 2>&1 | head -n 1 | cut -d ' ' -f 2 | sed 's/^v//':
+          type: eval
+          description: The expression to obtain the version of the tool
+topics:
+  versions:
+    - - ${task.process}:
+          type: string
+          description: The name of the process
+      - centrifuger:
+          type: string
+          description: The name of the tool
+      - centrifuger -v 2>&1 | head -n 1 | cut -d ' ' -f 2 | sed 's/^v//':
+          type: eval
+          description: The expression to obtain the version of the tool
+authors:
+  - "@haris18s"
+maintainers:
+  - "@haris18s"
+  - "@sofstam"
+  - "@jfy133"

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

@@ -0,0 +1,114 @@
+nextflow_process {
+
+    name "Test Process CENTRIFUGER_CENTRIFUGER"
+    script "../main.nf"
+    process "CENTRIFUGER_CENTRIFUGER"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "centrifuger"
+    tag "centrifuger/centrifuger"
+    tag "untar"
+
+    setup {
+        run("UNTAR") {
+            script "../../../untar/main.nf"
+            process {
+                """
+                input[0] = [ [], file('https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/cfr_files_short.tar.gz', checkIfExists: true) ]
+                """
+            }
+        }
+    }
+
+    test("sarscov2 - fastq_single_end") {
+        when {
+            process {
+                """
+                input[0] = [[ id:'test', single_end: true ],
+                file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true)
+                ]
+                input[1] = UNTAR.out.untar.map{ it[1] }
+                input[2] = true
+                input[3] = true
+                    input[4] = []
+                input[5] = []
+                """
+            }
+        }
+        then {
+            assertAll(
+                {assert process.success },
+                { assert snapshot(
+                    file(process.out.classification_file[0][1]).name,
+                    file(process.out.fastq_classified[0][1]).name,
+                    file(process.out.fastq_unclassified[0][1]).name,
+                    process.out.findAll { key, val -> key.startsWith('versions') }
+                ).match() }
+            )
+        }
+    }
+    test("sarscov2 - fastq_paired_end") {
+        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)
+                    ]
+                ]
+                input[1] = UNTAR.out.untar.map{ it[1] }
+                input[2] = true
+                input[3] = true
+                input[4] = []
+                input[5] = []
+                """
+            }
+        }
+        then {
+            assertAll(
+                {assert process.success },
+                { assert snapshot(
+                    file(process.out.classification_file[0][1]).name,
+                    process.out.fastq_classified[0][1].collect { file(it).name },
+                    process.out.fastq_unclassified[0][1].collect {file (it).name },
+                    process.out.findAll { key, val -> key.startsWith('versions') }
+                ).match() }
+            )
+        }
+
+    }
+    test("sarscov2 - fastq_single_end_stub") {
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = [[ id:'test', single_end: true ],
+                file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true)
+                ]
+                input[1] = UNTAR.out.untar.map{ it[1] }
+                input[2] = true
+                input[3] = true
+                input[4] = []
+                input[5] = []
+                """
+            }
+        }
+        then {
+            assertAll(
+                {assert process.success },
+                { assert snapshot(
+                    file(process.out.classification_file[0][1]).name,
+                    file(process.out.fastq_classified[0][1]).name,
+                    file(process.out.fastq_unclassified[0][1]).name,
+                    process.out.findAll { key, val -> key.startsWith('versions') }
+                ).match() }
+            )
+        }
+
+    }
+
+}