Adding met-excision as parameter to DIA and DDA workflows

CHANGELOG.md

@@ -3,12 +3,17 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [1.5.0dev] bigbio/quantms - [21/05/2025] - Zürich
+## [1.5.0] bigbio/quantms - [21/05/2025] - Zürich
+
+### `Added`
+
+- [#555](https://github.com/bigbio/quantms/pull/555) Added support for methionine excision to COMET and DIANN.
 
 ### `Changed`
 
+- [551](https://github.com/bigbio/quantms/pull/551) Standardization of names in meta.yml for all tools & Big refactoring for all modules to subfolders
 - [#547](https://github.com/bigbio/quantms/pull/547) Minor refinements with quantms code style, update msstats LFQ -> 4.14.0
-- [#539](https://github.com/bigbio/quantms/pull/539) quantms-utils 0.0.23 & sdrf-pipelines 0.0.32. This includes a fix for TMT labelled samples.
+- [#539](https://github.com/bigbio/quantms/pull/539) quantms-utils 0.0.23 & sdrf-pipelines 0.0.32. This includes a fix for TMT-labelled samples.
 - [#541](https://github.com/bigbio/quantms/pull/541) add mztab to results for pmultiqc
 
 ### `Fixed`

modules/local/diann/insilico_library_generation/main.nf

@@ -26,9 +26,10 @@ process INSILICO_LIBRARY_GENERATION {
     max_pr_mz = params.max_pr_mz ? "--max-pr-mz $params.max_pr_mz":""
     min_fr_mz = params.min_fr_mz ? "--min-fr-mz $params.min_fr_mz":""
     max_fr_mz = params.max_fr_mz ? "--max-fr-mz $params.max_fr_mz":""
+    met_excision = params.met_excision ? "--met-excision" : ""
 
     """
-    diann   `cat diann_config.cfg` \\
+    diann `cat diann_config.cfg` \\
             --fasta ${fasta} \\
             --fasta-search \\
             ${min_pr_mz} \\
@@ -45,6 +46,7 @@ process INSILICO_LIBRARY_GENERATION {
             --predictor \\
             --verbose $params.diann_debug \\
             --gen-spec-lib \\
+            ${met_excision} \\
             ${args}
 
     cp *lib.log.txt silicolibrarygeneration.log

modules/local/openms/comet/main.nf

@@ -79,6 +79,8 @@ process COMET {
 
     il_equiv = params.IL_equivalent ? "-PeptideIndexing:IL_equivalent" : ""
 
+    met_excision = params.met_excision ? "-clip_nterm_methionine true" : ""
+
     """
     CometAdapter \\
         -in ${mzml_file} \\
@@ -102,6 +104,7 @@ process COMET {
         -fragment_mass_tolerance ${bin_tol} \\
         -fragment_bin_offset ${bin_offset} \\
         -minimum_peaks $params.min_peaks \\
+        ${met_excision} \\
         ${il_equiv} \\
         -PeptideIndexing:unmatched_action ${params.unmatched_action} \\
         -debug $params.db_debug \\

nextflow.config

@@ -82,6 +82,7 @@ params {
 
     // shared search engine parameters
     enzyme                        = 'Trypsin'
+    met_excision                  = true // Met-excision is enabled by default
     num_enzyme_termini            = 'fully'
     allowed_missed_cleavages      = 2
     precursor_mass_tolerance      = 5

nextflow_schema.json

@@ -251,6 +251,13 @@
                     "fa_icon": "fas fa-list-ol",
                     "help_text": "Specify which enzymatic restriction should be applied, e.g. 'unspecific cleavage', 'Trypsin' (default), see OpenMS\n[enzymes](https://github.com/OpenMS/OpenMS/blob/develop/share/OpenMS/CHEMISTRY/Enzymes.xml). Note: MSGF does not support extended\ncutting rules, as used by default with `Trypsin`. I.e. if you specify `Trypsin` with MSGF, it will be automatically converted to\n`Trypsin/P`= 'Trypsin without proline rule'."
                 },
+                "met_excision": {
+                    "type": "boolean",
+                    "description": "Database searches accounted for N-terminal methionine excision, a common co-translational modification where the initial methionine is enzymatically removed from proteins.",
+                    "default": true,
+                    "fa_icon": "far fa-check-square",
+                    "help_text": "Warning: not supported by sage yet."
+                },
                 "num_enzyme_termini": {
                     "type": "string",
                     "description": "Specify the amount of termini matching the enzyme cutting rules for a peptide to be considered. Valid values are `fully` (default), `semi`, or `none`",