Merge pull request #95 from compomics/feature/modified-sequence-prop

Peptidoform: Add modified_sequence property

CHANGELOG.md

@@ -5,6 +5,13 @@ 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).
 
+## Unreleased
+
+### Added
+
+- `Peptidoform`: Add `modified_sequence` property to return the modified sequence in ProForma format, but without charge state.
+
+
 ## [1.0.1] - 2024-08-28
 
 ### Fixed

psm_utils/peptidoform.py

@@ -109,6 +109,23 @@ def sequence(self) -> str:
  """
  return "".join(pos[0] for pos in self.parsed_sequence)
 
+ @property
+ def modified_sequence(self) -> str:
+ """
+ Peptide sequence with modifications in ProForma format, but without charge state.
+
+ Includes all modifications, including labile, unlocalized, and terminal modifications.
+
+ Examples
+ --------
+ >>> Peptidoform("AC[U:4]DEK/2").modified_sequence
+ 'AC[U:4]DEK'
+
+ """
+ properties_without_charge = self.properties.copy()
+ properties_without_charge.pop("charge_state", None)
+ return proforma.to_proforma(self.parsed_sequence, **properties_without_charge)
+
  @property
  def precursor_charge(self) -> int | None:
  """

tests/test_peptidoform.py

@@ -59,6 +59,44 @@ def test__iter__(self):
  for mod in mods:
  assert isinstance(mod, proforma.TagBase)
 
+ def test_sequence(self):
+ test_cases = [
+ ("ACDEFGHIK", "ACDEFGHIK"),
+ ("[ac]-AC[cm]DEFGHIK", "ACDEFGHIK"),
+ ("[ac]-AC[Carbamidomethyl]DEFGHIK", "ACDEFGHIK"),
+ ("[Acetyl]-AC[cm]DEFGK", "ACDEFGK"),
+ ("<[cm]@C>[Acetyl]-ACDK", "ACDK"),
+ ("<[Carbamidomethyl]@C>[ac]-ACDEFGHIK", "ACDEFGHIK"),
+ ]
+
+ for test_case_in, expected_out in test_cases:
+ peptidoform = Peptidoform(test_case_in)
+ assert peptidoform.sequence == expected_out
+
+ def test_modified_sequence(self):
+ test_cases = [
+ ("ACDEFGHIK", "ACDEFGHIK"),
+ ("ACDEFGHIK/3", "ACDEFGHIK"),
+ ("[ac]-AC[cm]DEFGHIK", "[ac]-AC[cm]DEFGHIK"),
+ ("[ac]-AC[cm]DEFGHIK/3", "[ac]-AC[cm]DEFGHIK"),
+ ("<[cm]@C>[Acetyl]-ACDK/3", "<[cm]@C>[Acetyl]-ACDK"),
+ ]
+
+ for test_case_in, expected_out in test_cases:
+ peptidoform = Peptidoform(test_case_in)
+ assert peptidoform.modified_sequence == expected_out
+
+ def test_precursor_charge(self):
+ test_cases = [
+ ("ACDEFGHIK", None),
+ ("ACDEFGHIK/2", 2),
+ ("ACDEFGHIK/3", 3),
+ ]
+
+ for test_case_in, expected_out in test_cases:
+ peptidoform = Peptidoform(test_case_in)
+ assert peptidoform.precursor_charge == expected_out
+
  def test_rename_modifications(self):
  label_mapping = {
  "ac": "Acetyl",