Add openmsthirdparty/cometadapter (#6627)

* Setup cometadapter module

* cometadapter draft

* finalize tests

* remove defaults

* enclosing input as channel

* replace collect with map

* add channel of again

* fix input channles by joining them

* update correct snapshot

* fix lint

* fix snapshots, comet writes timestamps in output file

* prettier

* Update environment.yml

* strip out suffix version tag, which differs between container and conda

* move to version content check instead of hash

* align conda version and container version tag

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
+    """
+}

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

@@ -0,0 +1,55 @@
+name: "openmsthirdparty_cometadapter"
+description: Annotates MS/MS spectra using Comet.
+keywords:
+  - search engine
+  - fasta
+  - mzml
+  - 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/nmeth.3959"
+      licence: ["BSD"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1', single_end:false ]`
+  - mzml:
+      type: file
+      description: File containing mass spectra in mzML format
+      pattern: "*.{mzML}"
+  - fasta:
+      type: file
+      description: Protein sequence database containing targets and decoys
+      pattern: "*.{fasta}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1', single_end:false ]`
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - idxml:
+      type: file
+      description: File containing target and decoy hits in idXML format
+      pattern: "*.{idXML}"
+  - pin:
+      type: file
+      description: TSV file tailored as Percolator input (pin) file
+      pattern: "*.{tsv}"
+
+authors:
+  - "@jonasscheid"
+maintainers:
+  - "@jonasscheid"

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

@@ -0,0 +1,86 @@
+nextflow_process {
+
+    name "Test Process OPENMSTHIRDPARTY_COMETADAPTER"
+    script "../main.nf"
+    process "OPENMSTHIRDPARTY_COMETADAPTER"
+    config "./nextflow.config"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "openms"
+    tag "openmsthirdparty"
+    tag "openmsthirdparty/cometadapter"
+    tag "thermorawfileparser"
+    tag "openms/decoydatabase"
+
+    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)
+                ])
+                """
+            }
+        }
+    }
+
+    test("proteomics - comet") {
+
+        when {
+            process {
+                """
+                input[0] =
+                    THERMORAWFILEPARSER.out.spectra.join(
+                    OPENMS_DECOYDATABASE.out.decoy_fasta
+                    )
+                """
+            }
+        }
+        // Comet stores timestamp in output file, so we cannot compare checksums
+        then {
+            assert process.success
+            // Assert the search metadata
+            assert snapshot(file(process.out.idxml[0][1]).readLines()[0..30]).match()
+            // Make sure the file is not empty
+            assert file(process.out.idxml[0][1]).readLines().any { it.contains('ProteinHit') }
+            assert file(process.out.idxml[0][1]).readLines().any { it.contains('PeptideHit') }
+            assert snapshot(path(process.out.versions.get(0)).yaml).match("versions")
+        }
+    }
+
+    test("proteomics - comet - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] =
+                    THERMORAWFILEPARSER.out.spectra.join(
+                    OPENMS_DECOYDATABASE.out.decoy_fasta
+                    )
+                """
+            }
+        }
+
+        then {
+            assert process.success
+        }
+    }
+
+}

modules/nf-core/openmsthirdparty/cometadapter/tests/main.nf.test.snap

@@ -0,0 +1,59 @@
+{
+    "proteomics - comet": {
+        "content": [
+            [
+                "<?xml version=\"1.0\" encoding=\"UTF-8\"?>",
+                "<?xml-stylesheet type=\"text/xsl\" href=\"https://www.openms.de/xml-stylesheet/IdXML.xsl\" ?>",
+                "<IdXML version=\"1.5\" xsi:noNamespaceSchemaLocation=\"https://www.openms.de/xml-schema/IdXML_1_5.xsd\" xmlns:xsi=\"http://www.w3.org/2001/XMLSchema-instance\">",
+                "\t<SearchParameters id=\"SP_0\" db=\"UP000005640_9606_decoy.fasta\" db_version=\"\" taxonomy=\"\" mass_type=\"monoisotopic\" charges=\"2:5\" enzyme=\"unspecific cleavage\" missed_cleavages=\"1\" precursor_peak_tolerance=\"5\" precursor_peak_tolerance_ppm=\"true\" peak_mass_tolerance=\"0.50025\" peak_mass_tolerance_ppm=\"false\" >",
+                "\t\t<FixedModification name=\"Carbamidomethyl (C)\" />",
+                "\t\t<VariableModification name=\"Oxidation (M)\" />",
+                "\t\t\t\t<UserParam type=\"string\" name=\"CometAdapter:1:in\" value=\"test.mzML\"/>",
+                "\t\t\t\t<UserParam type=\"string\" name=\"CometAdapter:1:out\" value=\"test.idXML\"/>",
+                "\t\t\t\t<UserParam type=\"string\" name=\"CometAdapter:1:database\" value=\"UP000005640_9606_decoy.fasta\"/>",
+                "\t\t\t\t<UserParam type=\"string\" name=\"CometAdapter:1:comet_executable\" value=\"comet.exe\"/>",
+                "\t\t\t\t<UserParam type=\"string\" name=\"CometAdapter:1:pin_out\" value=\"\"/>",
+                "\t\t\t\t<UserParam type=\"string\" name=\"CometAdapter:1:default_params_file\" value=\"\"/>",
+                "\t\t\t\t<UserParam type=\"float\" name=\"CometAdapter:1:precursor_mass_tolerance\" value=\"5.0\"/>",
+                "\t\t\t\t<UserParam type=\"string\" name=\"CometAdapter:1:precursor_error_units\" value=\"ppm\"/>",
+                "\t\t\t\t<UserParam type=\"string\" name=\"CometAdapter:1:isotope_error\" value=\"off\"/>",
+                "\t\t\t\t<UserParam type=\"float\" name=\"CometAdapter:1:fragment_mass_tolerance\" value=\"0.50025\"/>",
+                "\t\t\t\t<UserParam type=\"string\" name=\"CometAdapter:1:fragment_error_units\" value=\"Da\"/>",
+                "\t\t\t\t<UserParam type=\"float\" name=\"CometAdapter:1:fragment_bin_offset\" value=\"0.4\"/>",
+                "\t\t\t\t<UserParam type=\"string\" name=\"CometAdapter:1:instrument\" value=\"low_res\"/>",
+                "\t\t\t\t<UserParam type=\"string\" name=\"CometAdapter:1:use_A_ions\" value=\"false\"/>",
+                "\t\t\t\t<UserParam type=\"string\" name=\"CometAdapter:1:use_B_ions\" value=\"true\"/>",
+                "\t\t\t\t<UserParam type=\"string\" name=\"CometAdapter:1:use_C_ions\" value=\"false\"/>",
+                "\t\t\t\t<UserParam type=\"string\" name=\"CometAdapter:1:use_X_ions\" value=\"false\"/>",
+                "\t\t\t\t<UserParam type=\"string\" name=\"CometAdapter:1:use_Y_ions\" value=\"true\"/>",
+                "\t\t\t\t<UserParam type=\"string\" name=\"CometAdapter:1:use_Z_ions\" value=\"false\"/>",
+                "\t\t\t\t<UserParam type=\"string\" name=\"CometAdapter:1:use_NL_ions\" value=\"false\"/>",
+                "\t\t\t\t<UserParam type=\"string\" name=\"CometAdapter:1:enzyme\" value=\"unspecific cleavage\"/>",
+                "\t\t\t\t<UserParam type=\"string\" name=\"CometAdapter:1:second_enzyme\" value=\"\"/>",
+                "\t\t\t\t<UserParam type=\"string\" name=\"CometAdapter:1:num_enzyme_termini\" value=\"fully\"/>",
+                "\t\t\t\t<UserParam type=\"int\" name=\"CometAdapter:1:missed_cleavages\" value=\"1\"/>",
+                "\t\t\t\t<UserParam type=\"int\" name=\"CometAdapter:1:min_peptide_length\" value=\"5\"/>"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-09-13T13:57:34.932657501"
+    },
+    "versions": {
+        "content": [
+            {
+                "OPENMSTHIRDPARTY_COMETADAPTER": {
+                    "CometAdapter": "3.1.0",
+                    "Comet": "2023.01 rev. 2"
+                }
+            }
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-09-13T13:57:35.577894316"
+    }
+}

modules/nf-core/openmsthirdparty/cometadapter/tests/nextflow.config

@@ -0,0 +1,20 @@
+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()
+    }
+
+}

modules/nf-core/openmsthirdparty/cometadapter/tests/tags.yml

@@ -0,0 +1,2 @@
+openmsthirdparty/cometadapter:
+  - "modules/nf-core/openmsthirdparty/cometadapter/**"

tests/config/test_data.config

@@ -769,6 +769,7 @@ params {
             }
             'database' {
                 yeast_ups                       = "${params.test_data_base}/data/proteomics/database/yeast_UPS.fasta"
+                swissprot                       = "${params.test_data_base}/data/proteomics/database/UP000005640_9606.fasta"
             }
             'maxquant' {
                 mq_contrasts                    = "${params.test_data_base}/data/proteomics/maxquant/MaxQuant_contrasts.csv"