Add module: sylph/query

modules/nf-core/sylph/query/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::sylph=0.9.0

modules/nf-core/sylph/query/main.nf

@@ -0,0 +1,39 @@
+process SYLPH_QUERY {
+    tag "${meta.id}"
+    label 'process_high'
+
+    conda "${moduleDir}/environment.yml"
+    container "${workflow.containerEngine in ['singularity', 'apptainer'] && !task.ext.singularity_pull_docker_container
+        ? 'https://depot.galaxyproject.org/singularity/sylph:0.9.0--ha6fb395_0'
+        : 'quay.io/biocontainers/sylph:0.9.0--ha6fb395_0'}"
+
+    input:
+    tuple val(meta), path(reads)
+    path database
+
+    output:
+    tuple val(meta), path('*.tsv'), emit: query_out
+    tuple val("${task.process}"), val('sylph'), eval('sylph -V | sed "s/sylph //g"'), topic: versions, emit: versions_sylph
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def input = meta.single_end ? "-r ${reads}" : "-1 ${reads[0]} -2 ${reads[1]}"
+    """
+    sylph query \\
+        -t ${task.cpus} \\
+        ${args} \\
+        ${database} \\
+        ${input} \\
+        --output-file ${prefix}.tsv
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.tsv
+    """
+}

modules/nf-core/sylph/query/meta.yml

@@ -0,0 +1,77 @@
+name: "sylph_query"
+description: Sylph query command for querying genome databases against reads/metagenomes
+keywords:
+  - query
+  - metagenomics
+  - sylph
+  - containment
+  - genome
+tools:
+  - sylph:
+      description: Sylph quickly enables querying of genomes against even low-coverage
+        shotgun metagenomes to find nearest neighbour ANI.
+      homepage: https://github.com/bluenote-1577/sylph
+      documentation: https://sylph-docs.github.io/
+      tool_dev_url: https://github.com/bluenote-1577/sylph
+      doi: 10.1038/s41587-024-02412-y
+      licence:
+        - "MIT"
+      identifier: biotools:sylph
+
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'test', single_end:false ]`
+    - reads:
+        type: file
+        description: |
+          List of input FastQ/FASTA files of size 1 and 2 for single-end and paired-end data,
+          respectively. They are automatically sketched to .sylsp/.syldb
+        pattern: "*.{fasta,fastq,fna,fa,fq,fas}{,.gz}"
+        ontologies:
+          - edam: http://edamontology.org/format_1929 # FASTA
+          - edam: http://edamontology.org/format_1930 # FASTQ
+  - database:
+      type: file
+      description: Pre-sketched *.syldb/*.sylsp files. Raw single-end fastq/fasta are
+        allowed and will be automatically sketched to .sylsp/.syldb.
+      pattern: "*.{syldb,sylsp}"
+output:
+  query_out:
+    - - meta:
+          type: map
+          description: Groovy Map containing sample information
+      - "*.tsv":
+          type: file
+          description: Output TSV file of containment ANI query results.
+          pattern: "*.tsv"
+          ontologies:
+            - edam: http://edamontology.org/format_3475 # TSV
+  versions_sylph:
+    - - ${task.process}:
+          type: string
+          description: The process the versions were collected from
+      - sylph:
+          type: string
+          description: The tool name
+      - sylph -V | sed "s/sylph //g":
+          type: eval
+          description: The expression to obtain the version of the tool
+topics:
+  versions:
+    - - ${task.process}:
+          type: string
+          description: The process the versions were collected from
+      - sylph:
+          type: string
+          description: The tool name
+      - sylph -V | sed "s/sylph //g":
+          type: eval
+          description: The expression to obtain the version of the tool
+authors:
+  - "@ZunairKhm"
+  - "@nghiaagent"
+maintainers:
+  - "@nghiaagent"

modules/nf-core/sylph/query/tests/main.nf.test

@@ -0,0 +1,87 @@
+nextflow_process {
+
+    name "Test Process SYLPH_QUERY"
+    script "../main.nf"
+    process "SYLPH_QUERY"
+    tag "modules"
+    tag "modules_nfcore"
+    tag "sylph"
+    tag "sylph/query"
+
+    test("sarscov2 illumina single-end [fastq_gz]") {
+        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] = file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    process.out.findAll { key, val -> key.startsWith("versions") },
+                    file(process.out.query_out[0][1]).readLines()[0]
+                ).match() }
+            )
+        }
+    }
+
+    test("sarscov2 illumina paired-end [fastq_gz]") {
+        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] = file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    process.out.findAll { key, val -> key.startsWith("versions") },
+                    file(process.out.query_out[0][1]).readLines()[0]
+                ).match() }
+            )
+        }
+    }
+
+    test("sarscov2 illumina paired-end [fastq_gz]-stub") {
+        options "-stub"
+
+        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] = file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+}

modules/nf-core/sylph/query/tests/main.nf.test.snap

@@ -0,0 +1,83 @@
+{
+    "sarscov2 illumina paired-end [fastq_gz]": {
+        "content": [
+            {
+                "versions_sylph": [
+                    [
+                        "SYLPH_QUERY",
+                        "sylph",
+                        "0.9.0"
+                    ]
+                ]
+            },
+            "Sample_file\tGenome_file\tAdjusted_ANI\tEff_cov\tANI_5-95_percentile\tEff_lambda\tLambda_5-95_percentile\tMedian_cov\tMean_cov_geq1\tContainment_ind\tNaive_ANI\tContig_name"
+        ],
+        "timestamp": "2026-07-22T17:40:58.29668",
+        "meta": {
+            "nf-test": "0.9.5",
+            "nextflow": "26.04.4"
+        }
+    },
+    "sarscov2 illumina single-end [fastq_gz]": {
+        "content": [
+            {
+                "versions_sylph": [
+                    [
+                        "SYLPH_QUERY",
+                        "sylph",
+                        "0.9.0"
+                    ]
+                ]
+            },
+            "Sample_file\tGenome_file\tAdjusted_ANI\tEff_cov\tANI_5-95_percentile\tEff_lambda\tLambda_5-95_percentile\tMedian_cov\tMean_cov_geq1\tContainment_ind\tNaive_ANI\tContig_name"
+        ],
+        "timestamp": "2026-07-22T17:40:51.150032",
+        "meta": {
+            "nf-test": "0.9.5",
+            "nextflow": "26.04.4"
+        }
+    },
+    "sarscov2 illumina paired-end [fastq_gz]-stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "1": [
+                    [
+                        "SYLPH_QUERY",
+                        "sylph",
+                        "0.9.0"
+                    ]
+                ],
+                "query_out": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "versions_sylph": [
+                    [
+                        "SYLPH_QUERY",
+                        "sylph",
+                        "0.9.0"
+                    ]
+                ]
+            }
+        ],
+        "timestamp": "2026-07-22T17:41:07.524879",
+        "meta": {
+            "nf-test": "0.9.5",
+            "nextflow": "26.04.4"
+        }
+    }
+}