Add sylph sketch (nf-core#7078)

* Add sylph sketch * Update snap * Update snap * Remove sylph profile * Fix linting with version * Fix output format in meta.yama * Fix input formatting * Update meta * Fix input formatting * Fix output formatting * Add versions to output * Update snap * Update test * Fix lintinG * Test linting * Linting * Correct output names * Add quotes to output names * Linting * Fix align in input * Update modules/nf-core/sylph/sketch/tests/main.nf.test Co-authored-by: Sateesh_Peri <[email protected]> * Update snapshot * Add stub test --------- Co-authored-by: Sateesh_Peri <[email protected]>
LouisLeNezet · Dec 4, 2024 · 1212074 · 1212074
1 parent c83b675
commit 1212074
Show file tree

Hide file tree

Showing 5 changed files with 377 additions and 0 deletions.
diff --git a/modules/nf-core/sylph/sketch/environment.yml b/modules/nf-core/sylph/sketch/environment.yml
@@ -0,0 +1,5 @@
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - "bioconda::sylph=0.7.0"
diff --git a/modules/nf-core/sylph/sketch/main.nf b/modules/nf-core/sylph/sketch/main.nf
@@ -0,0 +1,51 @@
+process SYLPH_SKETCH {
+    tag "$meta.id"
+    label 'process_high'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/sylph:0.7.0--h919a2d8_0' :
+        'biocontainers/sylph:0.7.0--h919a2d8_0' }"
+
+    input:
+    tuple val(meta), path(reads)
+    path(reference)
+
+    output:
+    tuple val(meta), path('my_sketches/*.sylsp'), path('database.syldb'), emit: sketch_fastq_genome
+    path "versions.yml"                                                 , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def fastq = meta.single_end ? "-r ${reads[0]}" : "-1 ${reads[0]} -2 ${reads[1]}"
+    """
+    sylph sketch \\
+        $args \\
+        $fastq \\
+        -g $reference \\
+        -S $prefix \\
+        -d my_sketches
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        sylph: \$(sylph -V|awk '{print \$2}')
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    mkdir -p my_sketches
+    touch my_sketches/${prefix}.sylsp
+    touch database.syldb
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        sylph: \$(sylph -V|awk '{print \$2}')
+    END_VERSIONS
+    """
+}
diff --git a/modules/nf-core/sylph/sketch/meta.yml b/modules/nf-core/sylph/sketch/meta.yml
@@ -0,0 +1,60 @@
+name: "sylph_sketch"
+description: Sketching/indexing sequencing reads
+keywords:
+  - sketch
+  - metagenomics
+  - sylph
+  - indexing
+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: Input fastq files
+        pattern: "*.{fq,fastq,fq.gz,fastq.gz}"
+  - - reference:
+        type: file
+        description: Reference genome file in FASTA format
+output:
+  - sketch_fastq_genome:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+          pattern: "my_sketches/*.sylsp"
+      - my_sketches/*.sylsp:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+          pattern: "my_sketches/*.sylsp"
+      - database.syldb:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+          pattern: "my_sketches/*.sylsp"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+authors:
+  - "@jiahang1234"
+  - "@sofstam"
+maintainers:
+  - "@sofstam"
diff --git a/modules/nf-core/sylph/sketch/tests/main.nf.test b/modules/nf-core/sylph/sketch/tests/main.nf.test
@@ -0,0 +1,74 @@
+nextflow_process {
+
+    script "../main.nf"
+    process "SYLPH_SKETCH"
+    tag "modules"
+    tag "modules_nfcore"
+    tag "sylph"
+    tag "sylph/sketch"
+
+    test("sarscov2 illumina single-end [fastq_gz]") {
+        when {
+            process {
+                """
+                input[0] = [ [ id:'test', single_end:true ], // meta map
+                             [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true) ]
+                           ]
+                input[1] = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+    test("sarscov2 illumina paired-end [fastq_gz]") {
+        when {
+            process {
+                """
+                input[0] = [ [ id:'test', single_end:false ], // meta map
+                             [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+                               file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true) ]
+                           ]
+                input[1] = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+    test("sarscov2 illumina paired-end [fastq_gz]-stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = [ [ id:'test', single_end:false ], // meta map
+                             [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+                               file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true) ]
+                           ]
+                input[1] = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+}
diff --git a/modules/nf-core/sylph/sketch/tests/main.nf.test.snap b/modules/nf-core/sylph/sketch/tests/main.nf.test.snap
@@ -0,0 +1,187 @@
+{
+    "SYLPH_SKETCH: Should run without failures with single-end data": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": true
+                        },
+                        "test.sylsp:md5,4f9ba8a3613e74e0fd4213330abae522",
+                        "database.syldb:md5,c60e5450276385d81557a3f2b224762f"
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,f78c271e0133ef3d93db094bdab7cf3c"
+                ],
+                "sketch_fastq_genome": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": true
+                        },
+                        "test.sylsp:md5,4f9ba8a3613e74e0fd4213330abae522",
+                        "database.syldb:md5,c60e5450276385d81557a3f2b224762f"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,f78c271e0133ef3d93db094bdab7cf3c"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.1"
+        },
+        "timestamp": "2024-11-27T11:14:52.331315"
+    },
+    "sarscov2 illumina paired-end [fastq_gz]": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.paired.sylsp:md5,8ac5d34be025f7491c13ab6407e946fd",
+                        "database.syldb:md5,c60e5450276385d81557a3f2b224762f"
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,f78c271e0133ef3d93db094bdab7cf3c"
+                ],
+                "sketch_fastq_genome": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.paired.sylsp:md5,8ac5d34be025f7491c13ab6407e946fd",
+                        "database.syldb:md5,c60e5450276385d81557a3f2b224762f"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,f78c271e0133ef3d93db094bdab7cf3c"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.1"
+        },
+        "timestamp": "2024-11-28T10:12:17.710653"
+    },
+    "SYLPH_SKETCH: Should run without failures with paired-end data": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.paired.sylsp:md5,8ac5d34be025f7491c13ab6407e946fd",
+                        "database.syldb:md5,c60e5450276385d81557a3f2b224762f"
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,f78c271e0133ef3d93db094bdab7cf3c"
+                ],
+                "sketch_fastq_genome": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.paired.sylsp:md5,8ac5d34be025f7491c13ab6407e946fd",
+                        "database.syldb:md5,c60e5450276385d81557a3f2b224762f"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,f78c271e0133ef3d93db094bdab7cf3c"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.1"
+        },
+        "timestamp": "2024-11-27T11:15:00.053288"
+    },
+    "sarscov2 illumina single-end [fastq_gz]": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": true
+                        },
+                        "test.sylsp:md5,4f9ba8a3613e74e0fd4213330abae522",
+                        "database.syldb:md5,c60e5450276385d81557a3f2b224762f"
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,f78c271e0133ef3d93db094bdab7cf3c"
+                ],
+                "sketch_fastq_genome": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": true
+                        },
+                        "test.sylsp:md5,4f9ba8a3613e74e0fd4213330abae522",
+                        "database.syldb:md5,c60e5450276385d81557a3f2b224762f"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,f78c271e0133ef3d93db094bdab7cf3c"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.1"
+        },
+        "timestamp": "2024-11-27T17:04:41.72956"
+    },
+    "sarscov2 illumina paired-end [fastq_gz]-stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.sylsp:md5,d41d8cd98f00b204e9800998ecf8427e",
+                        "database.syldb:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,f78c271e0133ef3d93db094bdab7cf3c"
+                ],
+                "sketch_fastq_genome": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.sylsp:md5,d41d8cd98f00b204e9800998ecf8427e",
+                        "database.syldb:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,f78c271e0133ef3d93db094bdab7cf3c"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.1"
+        },
+        "timestamp": "2024-11-28T11:24:25.020343"
+    }
+}