Add module openms/idmassaccuracy

modules/nf-core/openms/idmassaccuracy/environment.yml

@@ -0,0 +1,5 @@
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - "bioconda::openms=3.1.0"

modules/nf-core/openms/idmassaccuracy/main.nf

@@ -0,0 +1,52 @@
+process OPENMS_IDMASSACCURACY {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/openms:3.1.0--h191ead1_4' :
+        'biocontainers/openms:3.1.0--h191ead1_4' }"
+
+    input:
+    tuple val(meta), path(mzmls), path(idxmls)
+
+    output:
+    tuple val(meta), path("*frag_mass_err.tsv") , emit: frag_err
+    tuple val(meta), path("*prec_mass_err.tsv") , emit: prec_err, optional: true
+    path "versions.yml"                         , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    IDMassAccuracy \\
+        -in $mzmls \\
+        -id_in $idxmls \\
+        -out_fragment ${prefix}_frag_mass_err.tsv \\
+        -threads $task.cpus \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        OpenMS: \$(FileInfo 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g' | cut -d ' ' -f 1 | cut -d '-' -f 1)
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    touch ${prefix}_frag_mass_err.tsv
+    touch ${prefix}_prec_mass_err.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        OpenMS: \$(FileInfo 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g' | cut -d ' ' -f 1 | cut -d '-' -f 1)
+    END_VERSIONS
+    """
+}

modules/nf-core/openms/idmassaccuracy/meta.yml

@@ -0,0 +1,55 @@
+name: "openms_idmassaccuracy"
+description: Calculates a distribution of the mass error from given mass spectra and IDs.
+keywords:
+  - mass_error
+  - openms
+  - proteomics
+tools:
+  - "openms":
+      description: "OpenMS is an open-source software C++ library for LC-MS data management and analyses"
+      homepage: "https://openms.de"
+      documentation: "https://openms.readthedocs.io/en/latest/index.html"
+      tool_dev_url: "https://github.com/OpenMS/OpenMS"
+      doi: "10.1038/s41592-024-02197-7"
+      licence: ["BSD"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'test' ]`
+  - mzmls:
+      type: file
+      description: |
+        List containing one or more mzML files
+        e.g. `[ 'file1.mzML', 'file2.mzML' ]`
+      pattern: "*.{mzML}"
+  - idxmls:
+      type: file
+      description: |
+        List containing one or more idXML files
+        e.g. `[ 'file1.idXML', 'file2.idXML' ]`
+      pattern: "*.{idXML}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'test' ]`
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - frag_err:
+      type: file
+      description: TSV file containing the fragment mass errors
+      pattern: "*frag_mass_err.{tsv}"
+  - prec_err:
+      type: file
+      description: Optional TSV file containing the precursor mass errors
+      pattern: "*prec_mass_err.{tsv}"
+
+authors:
+  - "@jonasscheid"

modules/nf-core/openms/idmassaccuracy/tests/main.nf.test

@@ -0,0 +1,81 @@
+nextflow_process {
+
+    name "Test Process OPENMS_IDMASSACCURACY"
+    script "../main.nf"
+    process "OPENMS_IDMASSACCURACY"
+    config "./nextflow.config"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "openms"
+    tag "openms/idmassaccuracy"
+    tag "thermorawfileparser"
+    tag "openms/decoydatabase"
+    tag "openmsthirdparty/cometadapter"
+
+    setup {
+        run("THERMORAWFILEPARSER") {
+            script "../../../thermorawfileparser/main.nf"
+            process {
+                """
+                input[0] = Channel.of([
+                    [ id:'test'],
+                    file(params.modules_testdata_base_path + 'proteomics/msspectra/PXD012083_e005640_II.raw', checkIfExists: true)
+                ])
+                """
+            }
+        }
+        run("OPENMS_DECOYDATABASE") {
+            script "../../../openms/decoydatabase/main.nf"
+            process {
+                """
+                input[0] = Channel.of([
+                    [ id:'test'],
+                    file(params.modules_testdata_base_path + 'proteomics/database/UP000005640_9606.fasta', checkIfExists: true)
+                ])
+                """
+            }
+        }
+        run("OPENMSTHIRDPARTY_COMETADAPTER") {
+            script "../../../openmsthirdparty/cometadapter/main.nf"
+            process {
+                """
+                input[0] = THERMORAWFILEPARSER.out.spectra.join(OPENMS_DECOYDATABASE.out.decoy_fasta)
+                """
+            }
+        }
+    }
+
+    test("proteomics - openms - mass_error") {
+        when {
+            process {
+                """
+                input[0] = THERMORAWFILEPARSER.out.spectra.join(OPENMSTHIRDPARTY_COMETADAPTER.out.idxml)
+                """
+            }
+        }
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+    test("proteomics - openms - mass_error - stub") {
+        options "-stub"
+        when {
+            process {
+                """
+                input[0] = THERMORAWFILEPARSER.out.spectra.join(OPENMSTHIRDPARTY_COMETADAPTER.out.idxml)
+                """
+            }
+        }
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+}

modules/nf-core/openms/idmassaccuracy/tests/main.nf.test.snap

@@ -0,0 +1,90 @@
+{
+    "proteomics - openms - mass_error - stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test_frag_mass_err.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "1": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test_prec_mass_err.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "2": [
+                    "versions.yml:md5,84212cbbf016bbcae0eb1bb0fcc30db7"
+                ],
+                "frag_err": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test_frag_mass_err.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "prec_err": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test_prec_mass_err.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,84212cbbf016bbcae0eb1bb0fcc30db7"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-09-16T05:12:06.655389198"
+    },
+    "proteomics - openms - mass_error": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test_frag_mass_err.tsv:md5,c659254bc1305edde65eca890a6cf36f"
+                    ]
+                ],
+                "1": [
+
+                ],
+                "2": [
+                    "versions.yml:md5,84212cbbf016bbcae0eb1bb0fcc30db7"
+                ],
+                "frag_err": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test_frag_mass_err.tsv:md5,c659254bc1305edde65eca890a6cf36f"
+                    ]
+                ],
+                "prec_err": [
+
+                ],
+                "versions": [
+                    "versions.yml:md5,84212cbbf016bbcae0eb1bb0fcc30db7"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-09-16T05:11:55.087464408"
+    }
+}

modules/nf-core/openms/idmassaccuracy/tests/nextflow.config

@@ -0,0 +1,27 @@
+process {
+
+    withName:OPENMSTHIRDPARTY_COMETADAPTER {
+        ext.args    = [
+            "-instrument low_res",
+            "-fragment_bin_offset 0.4",
+            "-precursor_mass_tolerance 5",
+            "-precursor_error_units 'ppm'",
+            "-fragment_mass_tolerance 0.50025",
+            "-digest_mass_range '800:5000'",
+            "-max_variable_mods_in_peptide 1",
+            "-precursor_charge '2:5'",
+            "-activation_method 'CID'",
+            "-variable_modifications 'Oxidation (M)'",
+            "-enzyme 'unspecific cleavage'",
+            "-spectrum_batch_size 0"
+        ].join(' ').trim()
+    }
+
+        withName:OPENMS_IDMASSACCURACY {
+        ext.args    = [
+            "-precursor_error_ppm",
+            "-fragment_mass_tolerance 0.50025"
+        ].join(' ').trim()
+    }
+
+}

modules/nf-core/openmsthirdparty/cometadapter/environment.yml

@@ -0,0 +1,5 @@
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - "bioconda::openms-thirdparty=3.1.0"

modules/nf-core/openmsthirdparty/cometadapter/main.nf

@@ -0,0 +1,55 @@
+process OPENMSTHIRDPARTY_COMETADAPTER {
+    tag "$meta.id"
+    label 'process_high'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/openms-thirdparty:3.1.0--h9ee0642_4' :
+        'biocontainers/openms-thirdparty:3.1.0--h9ee0642_4' }"
+
+    input:
+    tuple val(meta), path(mzml), path(fasta)
+
+    output:
+    tuple val(meta), path("*.idXML"), emit: idxml
+    tuple val(meta), path("*.tsv")  , emit: pin, optional: true
+    path "versions.yml"             , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    CometAdapter \\
+        -in $mzml \\
+        -database $fasta \\
+        -out ${prefix}.idXML \\
+        -threads $task.cpus \\
+        $args
+
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        CometAdapter: \$(CometAdapter 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g' | cut -d ' ' -f 1 | cut -d '-' -f 1)
+        Comet: \$(comet 2>&1 | grep -E "Comet version.*" | sed 's/Comet version //g' | sed 's/"//g')
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    touch ${prefix}.idXML
+    touch ${prefix}_pin.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        CometAdapter: \$(CometAdapter 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g' | cut -d ' ' -f 1 | cut -d '-' -f 1)
+        Comet: \$(comet 2>&1 | grep -E "Comet version.*" | sed 's/Comet version //g' | sed 's/"//g')
+    END_VERSIONS
+    """
+}