add defaults to psm_reader.yaml

alphabase/constants/const_files/psm_reader.yaml

@@ -221,7 +221,7 @@ spectronaut_report:
     'proteins': ['PG.ProteinNames','PG.ProteinGroups']
     'genes': 'PG.Genes'
     'uniprot_ids': 'PG.UniProtIds'
-    'charge': 'charge'
+    'charge': ['charge']
   mod_seq_columns:
     - 'ModifiedSequence'
   precursor_id_columns:
@@ -233,14 +233,14 @@ spectronaut:
   rt_unit: irt
   fixed_C57: False
   column_mapping:
-    'raw_name': 'ReferenceRun'
+    'raw_name': ['ReferenceRun', 'R.Label']
     'sequence': ['StrippedPeptide','PeptideSequence']
-    'charge': 'PrecursorCharge'
+    'charge': ['PrecursorCharge', 'FG.Charge']
     'rt': ['RT','iRT','Tr_recalibrated','RetentionTime','NormalizedRetentionTime']
     'ccs': 'CCS'
     'precursor_mz': 'PrecursorMz'
     'mobility': ['Mobility','IonMobility','PrecursorIonMobility']
-    'proteins': ['Protein Name','ProteinId','ProteinID','ProteinName','ProteinGroup','ProteinGroups']
+    'proteins': ['Protein Name','ProteinId','ProteinID','ProteinName','ProteinGroup','ProteinGroups','PG.ProteinGroups']
     'uniprot_ids': ['UniProtIds','UniProtID','UniprotId']
     'genes': ['Genes','Gene','GeneName','GeneNames']
   mod_seq_columns:
@@ -249,7 +249,7 @@ spectronaut:
     - 'FullUniModPeptideName'
     - 'ModifiedPeptideSequence'
     - 'LabeledSequence'
-    - 'FullUniModPeptideName'
+    - "EG.ModifiedSequence"
   precursor_id_columns:
     - "EG.PrecursorId"
   modification_mapping_type: 'maxquant'

alphabase/psm_reader/dia_psm_reader.py

@@ -1,13 +1,16 @@
 """Readers for Spectronaut's output library and reports, Swath data and DIANN data."""
 
+from pathlib import Path
 from typing import List, Optional
 
 import numpy as np
 import pandas as pd
 
+from alphabase.constants._const import CONST_FILE_FOLDER, PSM_READER_YAML_FILE_NAME
 from alphabase.psm_reader.keys import PsmDfCols
 from alphabase.psm_reader.maxquant_reader import ModifiedSequenceReader
 from alphabase.psm_reader.psm_reader import psm_reader_provider
+from alphabase.yaml_utils import load_yaml
 
 
 class SpectronautReader(ModifiedSequenceReader):
@@ -19,12 +22,26 @@ class SpectronautReader(ModifiedSequenceReader):
 
     def _pre_process(self, df: pd.DataFrame) -> pd.DataFrame:
         """Spectronaut-specific preprocessing of output data."""
+        # Obtain matching charge columns from the psm_reader.yaml
+        available_charge_columns = load_yaml(
+            Path(CONST_FILE_FOLDER) / PSM_READER_YAML_FILE_NAME
+        )[self._reader_type]["column_mapping"]["charge"]
+
+        self.precursor_charge_column = "PrecursorCharge"
+        for charge_col in available_charge_columns:
+            if charge_col in df.columns:
+                self.precursor_charge_column = charge_col
+                break
+
         if "ReferenceRun" in df.columns:
             df.drop_duplicates(
-                ["ReferenceRun", self.mod_seq_column, "PrecursorCharge"], inplace=True
+                ["ReferenceRun", self.mod_seq_column, self.precursor_charge_column],
+                inplace=True,
             )
         else:
-            df.drop_duplicates([self.mod_seq_column, "PrecursorCharge"], inplace=True)
+            df.drop_duplicates(
+                [self.mod_seq_column, self.precursor_charge_column], inplace=True
+            )
         df.reset_index(drop=True, inplace=True)
 
         return df