Add sylph/profile module

.github/actions/get-shards/action.yml

@@ -17,7 +17,6 @@ outputs:
   total_shards:
     description: "Total number of shards"
     value: ${{ steps.shards.outputs.total_shards }}
-
 runs:
   using: "composite"
   steps:
@@ -26,22 +25,24 @@ runs:
       with:
         version: ${{ env.NFT_VER }}
         install-pdiff: true
-
     - name: Get number of shards
       id: shards
       shell: bash
       run: |
-
         # Prepare tag parameter if tags are provided
         TAGS=$([ -n "${{ inputs.tags }}" ] && echo "--tag ${{ inputs.tags }}" || echo "")
-        # Run nf-test with dynamic tag parameter
+
+        # Run nf-test with dynamic parameter
         nftest_output=$(nf-test test \
           --dry-run \
           --profile docker \
           ${TAGS} \
           --filter process,workflow \
-          ${{ inputs.paths }})
-
+          ${{ inputs.paths }}) || {
+            echo "nf-test command failed with exit code $?"
+            echo "Full output: $nftest_output"
+            exit 1
+        }
         echo "nf-test dry-run output: $nftest_output"
 
         # Default values for shard and total_shards

modules/nf-core/sylph/profile/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=0.7.0"

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

@@ -0,0 +1,49 @@
+process SYLPH_PROFILE {
+    tag "$meta.id"
+    label 'process_high'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/sylph:0.7.0--h919a2d8_0' :
+        'biocontainers/sylph:0.7.0--h919a2d8_0' }"
+
+    input:
+    tuple val(meta), path(reads)
+    path(database)
+
+    output:
+    tuple val(meta), path('*.tsv'), emit: profile_out
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    sylph profile \\
+        -t $task.cpus \\
+        $args \\
+        $reads \\
+        $database\\
+        -o ${prefix}.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        sylph: \$(sylph -V | awk '{print \$2}')
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.tsv
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        sylph: \$(sylph -V | awk '{print \$2}')
+    END_VERSIONS
+    """
+
+}

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

@@ -0,0 +1,51 @@
+name: "sylph_profile"
+description: Sylph profile command for taxonoming profiling
+keywords:
+  - profile
+  - metagenomics
+  - sylph
+  - classification
+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://github.com/bluenote-1577/sylph
+      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
+  - - 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,fasta,fastq}"
+output:
+  - profile_out:
+      - meta:
+          type: map
+          description: Groovy Map containing sample information
+      - "*.tsv":
+          type: file
+          description: Output file of species-level taxonomic profiling with abundances and ANIs.
+          pattern: "*tsv"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+authors:
+  - "@jiahang1234"
+  - "@sofstam"
+maintainers:
+  - "@sofstam"

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

@@ -0,0 +1,80 @@
+nextflow_process {
+
+    name "Test Process SYLPH_PROFILE"
+    script "../main.nf"
+    process "SYLPH_PROFILE"
+    tag "modules"
+    tag "modules_nfcore"
+    tag "sylph"
+    tag "sylph/profile"
+
+    test("sarscov2 illumina single-end [fastq_gz]") {
+        when {
+            process {
+                """
+                input[0] = [ [ id:'test' ], // meta map
+                            [
+                        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 {
+            assert process.success
+            assert snapshot(
+                process.out.versions,
+                file(process.out.profile_out[0][1]).readLines()[0]
+            ).match()
+        }
+    }
+
+    test("sarscov2 illumina paired-end [fastq_gz]") {
+        when {
+            process {
+                """
+                input[0] = [ [ id:'test' ], // meta map
+                            [
+                        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 {
+            assert process.success
+            assert snapshot(
+                process.out.versions,
+                file(process.out.profile_out[0][1]).readLines()[0]
+            ).match()
+        }
+    }
+
+    test("sarscov2 illumina paired-end [fastq_gz]-stub") {
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = [ [ id:'test' ], // meta map
+                            [
+                        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 {
+            assert process.success
+            assert snapshot(process.out).match()
+        }
+    }
+}

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

@@ -0,0 +1,61 @@
+{
+    "sarscov2 illumina paired-end [fastq_gz]": {
+        "content": [
+            [
+                "versions.yml:md5,7b5a545483277cc0ff9189f8891e737f"
+            ],
+            "Sample_file\tGenome_file\tTaxonomic_abundance\tSequence_abundance\tAdjusted_ANI\tEff_cov\tANI_5-95_percentile\tEff_lambda\tLambda_5-95_percentile\tMedian_cov\tMean_cov_geq1\tContainment_ind\tNaive_ANI\tkmers_reassigned\tContig_name"
+        ],
+        "meta": {
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.4"
+        },
+        "timestamp": "2025-01-27T15:47:59.374481624"
+    },
+    "sarscov2 illumina single-end [fastq_gz]": {
+        "content": [
+            [
+                "versions.yml:md5,7b5a545483277cc0ff9189f8891e737f"
+            ],
+            "Sample_file\tGenome_file\tTaxonomic_abundance\tSequence_abundance\tAdjusted_ANI\tEff_cov\tANI_5-95_percentile\tEff_lambda\tLambda_5-95_percentile\tMedian_cov\tMean_cov_geq1\tContainment_ind\tNaive_ANI\tkmers_reassigned\tContig_name"
+        ],
+        "meta": {
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.4"
+        },
+        "timestamp": "2025-01-27T15:47:53.556942841"
+    },
+    "sarscov2 illumina paired-end [fastq_gz]-stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,7b5a545483277cc0ff9189f8891e737f"
+                ],
+                "profile_out": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,7b5a545483277cc0ff9189f8891e737f"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.4"
+        },
+        "timestamp": "2025-01-27T15:48:04.991824868"
+    }
+}

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

@@ -34,8 +34,7 @@ output:
           type: map
           description: |
             Groovy Map containing sample information
-            e.g. [ id:'test', single_end:false ]
-          pattern: "my_sketches/*.sylsp"
+            e.g. [ id:'test']
       - my_sketches/*.sylsp:
           type: map
           description: |