Dev

.github/PULL_REQUEST_TEMPLATE.md

@@ -16,7 +16,7 @@ Learn more about contributing: [CONTRIBUTING.md](https://github.com/bigbio/quant
 - [ ] This comment contains a description of changes (with reason).
 - [ ] If you've fixed a bug or added code that should be tested, add tests!
 - [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](https://github.com/bigbio/quantms/tree/master/.github/CONTRIBUTING.md)
-- [ ] If necessary, also make a PR on the bigbio/quantms _branch_ on the [nf-core/test-datasets](https://github.com/nf-core/test-datasets) repository.
+- [ ] If necessary, also make a PR on the bigbio/quantms _branch_ on the [bigbio/quantms-test-datasets](https://github.com/bigbio/quantms-test-datasets) repository.
 - [ ] Make sure your code lints (`nf-core pipelines lint`).
 - [ ] Ensure the test suite passes (`nextflow run . -profile test,docker --outdir <OUTDIR>`).
 - [ ] Check for unexpected warnings in debug mode (`nextflow run . -profile debug,test,docker --outdir <OUTDIR>`).

conf/tests/test_full_dia.config

@@ -25,7 +25,7 @@ params {
     outdir = './results_dia_full'
 
     // Input data
-    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/quantms/testdata-aws/dia_full/PXD004684.sdrf.tsv'
+    input = 'https://raw.githubusercontent.com/bigbio/quantms-test-datasets/quantms/testdata-aws/dia_full/PXD004684.sdrf.tsv'
     database = 'https://raw.githubusercontent.com/bigbio/quantms-test-datasets/quantms/testdata/dia_ci/REF_EColi_K12_UPS1_combined.fasta'
     min_pr_mz = 450
     max_pr_mz = 1080

conf/tests/test_full_lfq.config

@@ -25,8 +25,8 @@ params {
     outdir = "./results_lfq_full"
 
     // Input data
-    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/quantms/testdata-aws/lfq_full/PXD001819.sdrf.tsv'
-    database = 'https://raw.githubusercontent.com/nf-core/test-datasets/quantms/testdata-aws/lfq_full/yeast_2021_04_reviewed.fasta'
+    input = 'https://raw.githubusercontent.com/bigbio/quantms-test-datasets/quantms/testdata-aws/lfq_full/PXD001819.sdrf.tsv'
+    database = 'https://raw.githubusercontent.com/bigbio/quantms-test-datasets/quantms/testdata-aws/lfq_full/yeast_2021_04_reviewed.fasta'
     search_engines = "msgf,comet"
     add_decoys = true
     protein_level_fdr_cutoff = 0.01

conf/tests/test_full_tmt.config

@@ -25,8 +25,8 @@ params {
     outdir = "./results_iso_full"
 
     // Input data for full size test
-    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/quantms/testdata-aws/tmt_full/PXD005486.sdrf.tsv'
-    database = 'https://raw.githubusercontent.com/nf-core/test-datasets/quantms/testdata-aws/tmt_full/uniprot_E_coli_13spiked_reviewed_2021_04.fasta'
+    input = 'https://raw.githubusercontent.com/bigbio/quantms-test-datasets/quantms/testdata-aws/tmt_full/PXD005486.sdrf.tsv'
+    database = 'https://raw.githubusercontent.com/bigbio/quantms-test-datasets/quantms/testdata-aws/tmt_full/uniprot_E_coli_13spiked_reviewed_2021_04.fasta'
     search_engines = "comet,msgf"
     protein_level_fdr_cutoff = 0.01
     psm_level_fdr_cutoff = 0.01

conf/tests/test_latest_dia.config

@@ -40,7 +40,7 @@ process {
     }
 
     withLabel: diann {
-        container = 'ghcr.io/bigbio/diann:2.1.0' // This docker container is private in for quantms
+        container = 'ghcr.io/bigbio/diann:2.1.0' // This docker container is in a private registry for bigbio
     }
 
     resourceLimits = [

modules.json

@@ -12,8 +12,9 @@
                     },
                     "thermorawfileparser": {
                         "branch": "main",
-                        "git_sha": "a1a4a11ff508b2b5c23c9fb21c51c3327b748d4d",
-                        "installed_by": ["modules"]
+                        "git_sha": "53f2d78652a7040e3d44610286471642b1e1b55b",
+                        "installed_by": ["modules"],
+                        "patch": "modules/bigbio/thermorawfileparser/thermorawfileparser.diff"
                     }
                 }
             }

modules/bigbio/thermorawfileparser/environment.yml

@@ -1,4 +1,3 @@
-name: thermorawfileparser
 channels:
   - conda-forge
   - bioconda

modules/bigbio/thermorawfileparser/main.nf

@@ -1,62 +1,67 @@
 process THERMORAWFILEPARSER {
-    tag "$meta.mzml_id"
+    tag "${meta.mzml_id}"
     label 'process_low'
     label 'process_single'
     label 'error_retry'
 
     conda "${moduleDir}/environment.yml"
-    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/thermorawfileparser:1.4.5--h05cac1d_1' :
-        'biocontainers/thermorawfileparser:1.4.5--h05cac1d_1' }"
+    container "${workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container
+        ? 'https://depot.galaxyproject.org/singularity/thermorawfileparser:1.4.5--h05cac1d_1'
+        : 'biocontainers/thermorawfileparser:1.4.5--h05cac1d_1'}"
 
-    stageInMode {
-        if (task.attempt == 1) {
-            if (task.executor == "awsbatch") {
-                'symlink'
-            } else {
-                'link'
-            }
-        } else if (task.attempt == 2) {
-            if (task.executor == "awsbatch") {
-                'copy'
-            } else {
-                'symlink'
-            }
-        } else {
-            'copy'
-        }
-    }
     input:
-    tuple val(meta), path(rawfile)
+    tuple val(meta), path(raw)
 
     output:
-    tuple val(meta), path("*.{mzML,mgf,parquet}"), emit: convert_files
-    path "versions.yml",   emit: versions
-    path "*.log",   emit: log
+    tuple val(meta), path("*.{mzML,mzML.gz,mgf,mgf.gz,parquet,parquet.gz}"), emit: spectra
+    tuple val("${task.process}"), val('thermorawfileparser'), eval("ThermoRawFileParser.sh --version"), emit: versions_thermorawfileparser, topic: versions
+    path "*.log", emit: log
+
+    when:
+    task.ext.when == null || task.ext.when
 
     script:
     def args = task.ext.args ?: ''
+    // Detect existing format options in any supported syntax: -f=2, -f 2, --format=2,
+    // or --format 2.
+    def hasFormatArg = (args =~ /(^|\s)(-f(=|\s)\d+|--format(=|\s)\d+)/).find()
     // Default to indexed mzML format (-f=2) if not specified in args
-    def formatArg = args.contains('-f=') ? '' : '-f=2'
+    def formatArg = hasFormatArg ? '' : '-f=2'
+    def prefix = task.ext.prefix ?: "${meta.mzml_id}"
+    def suffix = args.contains("--format 0") || args.contains("-f 0")
+        ? "mgf"
+        : args.contains("--format 1") || args.contains("-f 1")
+            ? "mzML"
+            : args.contains("--format 2") || args.contains("-f 2")
+                ? "mzML"
+                : args.contains("--format 3") || args.contains("-f 3")
+                    ? "parquet"
+                    : "mzML"
+    suffix = args.contains("--gzip") ? "${suffix}.gz" : "${suffix}"
 
     """
-    ThermoRawFileParser.sh -i='${rawfile}' ${formatArg} ${args} -o=./ 2>&1 | tee '${rawfile.baseName}_conversion.log'
-
-    cat <<-END_VERSIONS > versions.yml
-    "${task.process}":
-        ThermoRawFileParser: \$(ThermoRawFileParser.sh --version)
-    END_VERSIONS
+    ThermoRawFileParser.sh \\
+        -i='${raw}' \\
+        ${formatArg} ${args} \\
+        -o=./ 2>&1 | tee '${prefix}_conversion.log'
     """
 
     stub:
-    def prefix = task.ext.prefix ?: "${meta.mzml_id}"
     def args = task.ext.args ?: ''
-    // Determine output format from args, default to mzML
-    // Format 0 = MGF, formats 1-2 = mzML, format 3 = Parquet, format 4 = None
-    def outputExt = (args =~ /-f=0\b/).find() ? 'mgf' : 'mzML'
+    def prefix = task.ext.prefix ?: "${meta.mzml_id}"
+    def suffix = args.contains("--format 0") || args.contains("-f 0")
+        ? "mgf"
+        : args.contains("--format 1") || args.contains("-f 1")
+            ? "mzML"
+            : args.contains("--format 2") || args.contains("-f 2")
+                ? "mzML"
+                : args.contains("--format 3") || args.contains("-f 3")
+                    ? "parquet"
+                    : "mzML"
+    suffix = args.contains("--gzip") ? "${suffix}.gz" : "${suffix}"
 
     """
-    touch '${prefix}.${outputExt}'
+    touch '${prefix}.${suffix}'
     touch '${prefix}_conversion.log'
 
     cat <<-END_VERSIONS > versions.yml

modules/bigbio/thermorawfileparser/meta.yml

@@ -1,10 +1,12 @@
 name: thermorawfileparser
-description: Convert RAW file to mzML or MGF files
+description: Convert RAW file to mzML or MGF files format
 keywords:
   - raw
-  - mzML
-  - MGF
-  - OpenMS
+  - mzml
+  - mgf
+  - parquet
+  - parser
+  - proteomics
 tools:
   - thermorawfileparser:
       description: |
@@ -14,36 +16,66 @@ tools:
         - `-L` or `--msLevel=VALUE` to select MS levels (e.g., `-L=1,2` or `--msLevel=1-3`)
       homepage: https://github.com/compomics/ThermoRawFileParser
       documentation: https://github.com/compomics/ThermoRawFileParser
+      tool_dev_url: https://github.com/compomics/ThermoRawFileParser
+      doi: "10.1021/acs.jproteome.9b00328"
+      licence:
+        - "Apache Software"
+      identifier: biotools:ThermoRawFileParser
 input:
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-  - rawfile:
-      type: file
-      description: |
-        Thermo RAW file
-      pattern: "*.{raw,RAW}"
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1', single_end:false ]`
+    - raw:
+        type: file
+        description: Thermo RAW file
+        pattern: "*.{raw,RAW}"
+        ontologies: []
 output:
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. [ id:'sample1', mzml_id:'UPS1_50amol_R3' ]
-  - convert_files:
-      type: file
-      description: |
-        Converted files in mzML or MGF format depending on the format parameter (-f).
-        Format options: 0 for MGF, 1 for mzML, 2 for indexed mzML (default), 3 for Parquet, 4 for None.
-      pattern: "*.{mzML,mgf,parquet}"
-  - log:
-      type: file
-      description: log file
-      pattern: "*.log"
-  - versions:
-      type: file
-      description: File containing software version
-      pattern: "versions.yml"
+  spectra:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', single_end:false ]`
+      - "*.{mzML,mzML.gz,mgf,mgf.gz,parquet,parquet.gz}":
+          type: file
+          description: Mass spectra in open format
+          pattern: "*.{mzML,mzML.gz,mgf,mgf.gz,parquet,parquet.gz}"
+          ontologies: []
+  versions_thermorawfileparser:
+    - - ${task.process}:
+          type: string
+          description: The process the versions were collected from
+      - thermorawfileparser:
+          type: string
+          description: The name of the tool
+      - ThermoRawFileParser.sh --version:
+          type: eval
+          description: The expression to obtain the version of the tool
+  log:
+    - "*.log":
+        type: file
+        description: Log file from the conversion process
+        pattern: "*.log"
+        ontologies: []
+topics:
+  versions:
+    - - ${task.process}:
+          type: string
+          description: The process the versions were collected from
+      - thermorawfileparser:
+          type: string
+          description: The name of the tool
+      - ThermoRawFileParser.sh --version:
+          type: eval
+          description: The expression to obtain the version of the tool
 authors:
+  - "@jonasscheid"
+  - "@daichengxin"
+  - "@ypriverol"
+maintainers:
+  - "@jonasscheid"
   - "@daichengxin"
   - "@ypriverol"

modules/bigbio/thermorawfileparser/tests/main.nf.test

@@ -22,8 +22,8 @@ nextflow_process {
 
         then {
             assert process.success
-            assert snapshot(process.out.versions).match("versions")
-            assert new File(process.out.convert_files[0][1]).name == 'TMT_Erwinia_1uLSike_Top10HCD_isol2_45stepped_60min_01.mzML'
+            assert snapshot(process.out.versions_thermorawfileparser).match("versions")
+            assert new File(process.out.spectra[0][1]).name == 'TMT_Erwinia_1uLSike_Top10HCD_isol2_45stepped_60min_01.mzML'
             assert process.out.log.size() == 1
         }
     }
@@ -36,7 +36,7 @@ nextflow_process {
             process {
                 """
                 input[0] = [
-                    [ id: 'test', mzml_id: 'test_sample' ],
+                    [ id: 'test_sample', mzml_id: 'test_sample' ],
                     file(params.test_data['proteomics']['msspectra']['ups1_50amol_r3'], checkIfExists: false)
                 ]
                 """
@@ -45,8 +45,9 @@ nextflow_process {
 
         then {
             assert process.success
-            assert snapshot(process.out.versions).match("versions_stub")
-            assert new File(process.out.convert_files[0][1]).name == 'test_sample.mzML'
+            assert snapshot(process.out.versions_thermorawfileparser).match("versions_stub")
+            assert new File(process.out.spectra[0][1]).name == 'test_sample.mzML'
+            assert snapshot(process.out).match()
             assert process.out.log.size() == 1
         }
     }

modules/bigbio/thermorawfileparser/tests/main.nf.test.snap

@@ -1,26 +1,34 @@
 {
-  "versions": {
-    "content": [
-      [
-        "versions.yml:md5,dc9625538c025d615109ef8cac3a86ab"
-      ]
-    ],
-    "meta": {
-      "nf-test": "0.9.3",
-      "nextflow": "25.04.8"
+    "versions_stub": {
+        "content": [
+            [
+                [
+                    "THERMORAWFILEPARSER",
+                    "thermorawfileparser",
+                    "1.4.5"
+                ]
+            ]
+        ],
+        "timestamp": "2026-03-20T12:41:22.8183",
+        "meta": {
+            "nf-test": "0.9.4",
+            "nextflow": "25.10.4"
+        }
     },
-    "timestamp": "2025-12-11T06:27:00.000000"
-  },
-  "versions_stub": {
-    "content": [
-      [
-        "versions.yml:md5,dc9625538c025d615109ef8cac3a86ab"
-      ]
-    ],
-    "meta": {
-      "nf-test": "0.9.3",
-      "nextflow": "25.04.8"
-    },
-    "timestamp": "2025-12-11T06:27:00.000000"
-  }
-}
+    "versions": {
+        "content": [
+            [
+                [
+                    "THERMORAWFILEPARSER",
+                    "thermorawfileparser",
+                    "1.4.5"
+                ]
+            ]
+        ],
+        "timestamp": "2026-03-20T12:36:30.88531",
+        "meta": {
+            "nf-test": "0.9.4",
+            "nextflow": "25.10.4"
+        }
+    }
+}