Add ThermoRawFileParser support to DIA proteomics subworkflow

Adds automatic conversion of Thermo RAW files to mzML format before analysis:
- Branch input files to detect .raw extensions
- Convert RAW files using ThermoRawFileParser module
- Reconstruct input channel with converted mzML files
- Configure THERMORAWFILEPARSER to output mzML format (--format=1)
- Update meta.yml to document RAW file support

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <[email protected]>

Author: pinin4fjords

subworkflows/nf-core/dia_proteomics_analysis/main.nf

@@ -7,6 +7,7 @@
 include { QUANTMSUTILS_DIANNCFG          } from '../../../modules/nf-core/quantmsutils/dianncfg/main'
 include { QUANTMSUTILS_MZMLSTATISTICS    } from '../../../modules/nf-core/quantmsutils/mzmlstatistics/main'
 include { QUANTMSUTILS_DIANN2MZTAB       } from '../../../modules/nf-core/quantmsutils/diann2mztab/main'
+include { THERMORAWFILEPARSER            } from '../../../modules/nf-core/thermorawfileparser/main'
 
 include { DIANN as DIANN_INSILICOLIBRARYGENERATION } from '../../../modules/nf-core/diann/main'
 include { DIANN as DIANN_PRELIMINARYANALYSIS } from '../../../modules/nf-core/diann/main'
@@ -152,6 +153,33 @@ workflow DIA_PROTEOMICS_ANALYSIS {
     ch_versions = Channel.empty()
     (random_preanalysis, random_preanalysis_n, random_preanalysis_seed) = random_preanalysis ?: [false, null, null]
 
+    //
+    // MODULE: Convert RAW files to mzML if needed
+    //
+    ch_input
+        .branch {
+            raw: it[1].toString().toLowerCase().endsWith('.raw')
+            other: true
+        }
+        .set { ch_input_branched }
+
+    THERMORAWFILEPARSER(ch_input_branched.raw.map { meta, ms_file, enzyme, fixed_mods, variable_mods, precursor_tolerance, fragment_tolerance, precursor_tolerance_unit, fragment_tolerance_unit ->
+        [meta, ms_file]
+    })
+    ch_versions = ch_versions.mix(THERMORAWFILEPARSER.out.versions)
+
+    // Reconstruct the input channel with converted files
+    ch_input_converted = THERMORAWFILEPARSER.out.spectra
+        .join(ch_input_branched.raw.map { meta, ms_file, enzyme, fixed_mods, variable_mods, precursor_tolerance, fragment_tolerance, precursor_tolerance_unit, fragment_tolerance_unit ->
+            [meta, enzyme, fixed_mods, variable_mods, precursor_tolerance, fragment_tolerance, precursor_tolerance_unit, fragment_tolerance_unit]
+        })
+        .map { meta, mzml, enzyme, fixed_mods, variable_mods, precursor_tolerance, fragment_tolerance, precursor_tolerance_unit, fragment_tolerance_unit ->
+            [meta, mzml, enzyme, fixed_mods, variable_mods, precursor_tolerance, fragment_tolerance, precursor_tolerance_unit, fragment_tolerance_unit]
+        }
+
+    // Combine converted and non-RAW files
+    ch_input = ch_input_branched.other.mix(ch_input_converted)
+
     //
     // Generate all combinations of inputs and create channel views with appropriate metadata
     // This multiMap creates all necessary entity combinations up-front:

subworkflows/nf-core/dia_proteomics_analysis/meta.yml

@@ -36,6 +36,7 @@ components:
   - quantmsutils/dianncfg
   - quantmsutils/mzmlstatistics
   - quantmsutils/diann2mztab
+  - thermorawfileparser
 input:
   - ch_input:
       type: channel
@@ -45,7 +46,8 @@ input:
         fragment_tolerance, precursor_tolerance_unit, fragment_tolerance_unit]
         e.g. `[[id:'sample1'], file('sample1.mzML'), 'Trypsin', 'Carbamidomethyl (C)',
         'Oxidation (M)', 10, 20, 'ppm', 'ppm']`
-      pattern: "*.{mzML,mzml}"
+        Supports mzML and Thermo RAW files. RAW files are automatically converted to mzML using ThermoRawFileParser.
+      pattern: "*.{mzML,mzml,raw,RAW}"
   - ch_searchdb:
       type: channel
       description: |

subworkflows/nf-core/dia_proteomics_analysis/nextflow.config

@@ -12,6 +12,11 @@
 
 process {
 
+    // THERMORAWFILEPARSER - Convert RAW files to mzML
+    withName: 'THERMORAWFILEPARSER' {
+        ext.args = '--format=1'  // Output format 1 = mzML
+    }
+
     // QUANTMSUTILS_GENERATECFG - Configuration generation
     withName: 'QUANTMSUTILS_DIANNCFG' {
         ext.args = ''

subworkflows/nf-core/dia_proteomics_analysis/tests/main.nf.test

@@ -12,6 +12,7 @@ nextflow_process {
     tag "quantmsutils/dianncfg"
     tag "quantmsutils/mzmlstatistics"
     tag "quantmsutils/diann2mztab"
+    tag "thermorawfileparser"
     tag "proteomics"
     tag "dia_proteomics_analysis"
     tag "untar"