io.flashlfq: Fix Peptide Monoisotopic Mass and Protein Accession column names (#97)

Author: RalfG

CHANGELOG.md

@@ -5,6 +5,12 @@ All notable changes to this project will be documented in this file.
 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).
 
+## [1.1.1] - 2024-09-06
+
+### Fixed
+
+- `io.flashlfq`: Fix column names `Peptide Monoisotopic Mass` and `Protein Accession`.
+
 ## [1.1.0] - 2024-09-05
 
 ### Added

psm_utils/__init__.py

@@ -1,6 +1,6 @@
 """Common utilities for parsing and handling PSMs, and search engine results."""
 
-__version__ = "1.1.0"
+__version__ = "1.1.1"
 __all__ = ["Peptidoform", "PSM", "PSMList"]
 
 from warnings import filterwarnings

psm_utils/io/flashlfq.py

@@ -62,20 +62,20 @@ def _parse_entry(self, entry: dict, spectrum_id) -> PSM:
             spectrum_id=spectrum_id,
             run=entry.get("File Name"),
             retention_time=entry.get("Scan Retention Time"),
-            protein_list=self._parse_protein_list(entry.get("Protein Accessions")),
+            protein_list=self._parse_protein_list(entry.get("Protein Accession")),
         )
 
     @staticmethod
-    def _parse_protein_list(protein_accessions: Optional[str]) -> list[str]:
+    def _parse_protein_list(protein_accession: Optional[str]) -> list[str]:
         """Parse protein list string to list of protein accessions."""
-        if not protein_accessions:
+        if not protein_accession:
             return []
-        elif ";" in protein_accessions:  # Docs define separator as semicolon
-            return protein_accessions.split(";")
-        elif "|" in protein_accessions:  # Example file uses pipe
-            return protein_accessions.split("|")
+        elif ";" in protein_accession:  # Docs define separator as semicolon
+            return protein_accession.split(";")
+        elif "|" in protein_accession:  # Example file uses pipe
+            return protein_accession.split("|")
         else:
-            return [protein_accessions]  # Single protein
+            return [protein_accession]  # Single protein
 
 
 class FlashLFQWriter(WriterBase):
@@ -125,10 +125,10 @@ def __enter__(self) -> FlashLFQWriter:
                 "File Name",
                 "Base Sequence",
                 "Full Sequence",
-                "Peptide Monoisotope Mass",
+                "Peptide Monoisotopic Mass",
                 "Scan Retention Time",
                 "Precursor Charge",
-                "Protein Accessions",
+                "Protein Accession",
             ]
             mode = "wt"
 
@@ -221,8 +221,8 @@ def _psm_to_entry(psm: PSM) -> dict:
             "File Name": psm.run,
             "Base Sequence": psm.peptidoform.sequence,
             "Full Sequence": psm.peptidoform.modified_sequence,
-            "Peptide Monoisotope Mass": psm.peptidoform.theoretical_mass,
+            "Peptide Monoisotopic Mass": f"{psm.peptidoform.theoretical_mass:.6f}",
             "Scan Retention Time": psm.retention_time,
             "Precursor Charge": psm.peptidoform.precursor_charge,
-            "Protein Accessions": ";".join(psm.protein_list),
+            "Protein Accession": ";".join(psm.protein_list),
         }

tests/test_io/test_flashlfq.py

@@ -8,7 +8,7 @@
 from psm_utils.psm_list import PSMList
 
 # Sample data for testing
-sample_tsv_data = """File Name\tBase Sequence\tFull Sequence\tPeptide Monoisotope Mass\tScan Retention Time\tPrecursor Charge\tProtein Accessions
+sample_tsv_data = """File Name\tBase Sequence\tFull Sequence\tPeptide Monoisotopic Mass\tScan Retention Time\tPrecursor Charge\tProtein Accession
 sample1.raw\tPEPTIDE\tPEPTIDE\t1000.0\t5.0\t2\tP12345;P67890
 sample2.raw\tPEPTIDE\tPEPTIDE\t1000.0\t10.0\t2\tP23456|P78901
 """
@@ -32,7 +32,7 @@ def invalid_psm_entry():
         "Precursor Charge": "2",
         "File Name": "sample1.raw",
         "Scan Retention Time": "5.0",
-        "Protein Accessions": None,
+        "Protein Accession": None,
     }
 
 
@@ -43,7 +43,7 @@ def test_flashlfqreader_parse_entry(valid_psm):
         "Precursor Charge": "2",
         "File Name": "sample1.raw",
         "Scan Retention Time": "5.0",
-        "Protein Accessions": "P12345;P67890",
+        "Protein Accession": "P12345;P67890",
     }
     psm = reader._parse_entry(entry, spectrum_id="0")
     assert psm == valid_psm
@@ -59,7 +59,7 @@ def test_flashlfqreader_iterate_over_file():
 
 
 def test_flashlfqreader_invalid_entry_handling():
-    invalid_data = """File Name\tBase Sequence\tPeptide Monoisotope Mass\tScan Retention Time\tPrecursor Charge\tProtein Accessions
+    invalid_data = """File Name\tBase Sequence\tPeptide Monoisotopic Mass\tScan Retention Time\tPrecursor Charge\tProtein Accession
 sample1.raw\tPEPTIDE\t1000.0\t5.0
 sample2.raw\tPEPTIDE\t1000.0\t10.0
 sample3.raw\tPEPTIDE\t1000.0\t15.0
@@ -95,10 +95,10 @@ def test_flashlfqwriter_existing_file():
                 "File Name",
                 "Base Sequence",
                 "Full Sequence",
-                "Peptide Monoisotope Mass",
+                "Peptide Monoisotopic Mass",
                 "Scan Retention Time",
                 "Precursor Charge",
-                "Protein Accessions",
+                "Protein Accession",
             ]