sageproteomics/sage

modules/nf-core/sageproteomics/sage/environment.yml

@@ -0,0 +1,9 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+name: "sageproteomics_sage"
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - "bioconda::sage-proteomics=0.14.7"

modules/nf-core/sageproteomics/sage/main.nf

@@ -0,0 +1,60 @@
+process SAGEPROTEOMICS_SAGE {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/sage-proteomics:0.14.7--h031d066_0' :
+        'biocontainers/sage-proteomics:0.14.7--h031d066_0' }"
+
+    input:
+    tuple val(meta),  path("*.mzML")
+    tuple val(meta2), path(fasta_proteome)
+    tuple val(meta3), path(base_config)
+
+    output:
+    tuple val(meta), path("results.sage.tsv"),        emit: results_tsv
+    tuple val(meta), path("results.json"),            emit: results_json
+    tuple val(meta), path("results.sage.pin"),        emit: results_pin
+    path "versions.yml",                              emit: versions
+
+    //optional outs
+    tuple val(meta), path("tmt.tsv"), optional: true, emit: tmt_tsv
+    tuple val(meta), path("lfq.tsv"), optional: true, emit: lfq_tsv
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    export RAYON_NUM_THREADS=$task.cpus
+
+    sage $base_config \\
+        --disable-telemetry-i-dont-want-to-improve-sage \\
+        --fasta $fasta_proteome \\
+        --write-pin \\
+        *.mzML
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        sageproteomics: \$(sage --version |& sed '1!d ; s/sage //')
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch results.json
+    touch results.sage.tsv
+    touch results.sage.pin
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        sageproteomics: \$(sage --version |& sed '1!d ; s/sage //')
+    END_VERSIONS
+    """
+}

modules/nf-core/sageproteomics/sage/meta.yml

@@ -0,0 +1,81 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "sageproteomics_sage"
+description: sage is a search software for proteomics data
+keywords:
+  - proteomics
+  - sage
+  - mass spectrometry
+tools:
+  - "sageproteomics":
+      description: "Proteomics searching so fast it feels like magic."
+      homepage: "https://lazear.github.io/sage/"
+      documentation: "https://lazear.github.io/sage/"
+      tool_dev_url: "https://github.com/lazear/sage"
+      doi: "10.1021/acs.jproteome.3c00486"
+      licence: ["MIT"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1']`
+  - '"*.mzML"':
+      type: file
+      description: mzML open source mass spectrometry raw data format
+      pattern: "*.{mzML, mzML.gz}"
+  - meta2:
+      type: map
+      description: |
+        Groovy Map containing information about fasta_proteome
+        e.g. `[ id:'sample1']`
+  - fasta_proteome:
+      type: file
+      description: proteome database in fasta format
+      pattern: "*.{fasta, fasta.gz}"
+  - meta3:
+      type: map
+      description: |
+        Groovy Map containing information about base_config
+        e.g. `[ id:'sample1']`
+  - base_config:
+      type: file
+      description: sage configuration json
+      pattern: "*.{json}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1']`
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - results_tsv:
+      type: file
+      description: tsv output results
+      pattern: "results.sage.tsv"
+  - results_json:
+      type: file
+      description: json output results
+      pattern: "results.json"
+  - results_pin:
+      type: file
+      description: pin format output results
+      pattern: "results.sage.pin"
+  - tmt_tsv:
+      type: file
+      description: tandem mass tag quantification
+      pattern: "tmt.tsv"
+  - lfq_tsv:
+      type: file
+      description: label free quantification
+      pattern: "lfq.tsv"
+
+authors:
+  - "@dgemperline-lilly"
+maintainers:
+  - "@dgemperline-lilly"

modules/nf-core/sageproteomics/sage/tests/main.nf.test

@@ -0,0 +1,69 @@
+nextflow_process {
+
+    name "Test Process SAGEPROTEOMICS_SAGE"
+    script "../main.nf"
+    process "SAGEPROTEOMICS_SAGE"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "sageproteomics"
+    tag "sageproteomics/sage"
+
+    test("sageproteomics - mzML") {
+        when {
+            process {
+                """
+		input[0] = Channel.of([
+                    [ id:'test'], // meta map
+                    file(params.test_data['proteomics']['msspectra']['profile_spectra'], checkIfExists: true)
+	        ])
+		input[1] = Channel.of([
+		    [id:'test'], // meta2 map
+		    file(params.test_data['proteomics']['database']['yeast_ups'], checkIfExists: true)
+	        ])
+		input[2] = Channel.of([
+		    [id:'test'], // meta3 map
+		    file(params.test_data['proteomics']['parameter']['sage_base_config'], checkIfExists: true)
+	        ])
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.results_pin, process.out.results_tsv, process.out.versions).match() }
+            )
+        }
+
+    }
+    test("sageproteomics - mzML.gz - stub") {
+        options "-stub"
+        when {
+            process {
+                """
+		input[0] = Channel.of([
+                    [ id:'test'], // meta map
+                    file(params.test_data['proteomics']['msspectra']['profile_spectra'], checkIfExists: true)
+	        ])
+		input[1] = Channel.of([
+		    [id:'test'], // meta2 map
+		    file(params.test_data['proteomics']['database']['yeast_ups'], checkIfExists: true)
+	        ])
+		input[2] = Channel.of([
+		    [id:'test'], // meta3 map
+		   file(params.test_data['proteomics']['parameter']['sage_base_config'], checkIfExists: true)
+	        ])
+                """
+            }
+        }
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+}

modules/nf-core/sageproteomics/sage/tests/main.nf.test.snap

@@ -0,0 +1,107 @@
+{
+    "sageproteomics - mzML.gz - stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "results.sage.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "1": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "results.json:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "2": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "results.sage.pin:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "3": [
+                    "versions.yml:md5,78b0fbed713c6d678cc08a0835a3abf2"
+                ],
+                "4": [
+
+                ],
+                "5": [
+
+                ],
+                "lfq_tsv": [
+
+                ],
+                "results_json": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "results.json:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "results_pin": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "results.sage.pin:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "results_tsv": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "results.sage.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "tmt_tsv": [
+
+                ],
+                "versions": [
+                    "versions.yml:md5,78b0fbed713c6d678cc08a0835a3abf2"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-05-22T16:25:31.663053"
+    },
+    "sageproteomics - mzML": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "results.sage.pin:md5,c764acea503b516a59c21b94936c89eb"
+                ]
+            ],
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "results.sage.tsv:md5,175dbda915bff070c7129610b33436a6"
+                ]
+            ],
+            [
+                "versions.yml:md5,78b0fbed713c6d678cc08a0835a3abf2"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-05-22T17:21:17.741302"
+    }
+}

modules/nf-core/sageproteomics/sage/tests/tags.yml

@@ -0,0 +1,2 @@
+sageproteomics/sage:
+  - "modules/nf-core/sageproteomics/sage/**"