enabled changing the enzyme identification to a manual input via Conf…

…ig() object

Scripts/pam_generation_uniprot_id.py

@@ -439,8 +439,6 @@ def filter_sublists(nested_list, target_string):
     # ecoli_pam.objective = ecoli_pam.BIOMASS_REACTION
     ecoli_pam.change_reaction_bounds('EX_glc__D_e', -10, 0)
     ecoli_pam.optimize()
-    print(ecoli_pam.objective.value)
-    print(ecoli_pam.reactions.query('ACONT'))
     # import pickle
     #
     # with open('path_to_your_pickle_file.pkl', 'wb') as file:

src/PAModelpy/CatalyticEvent.py

@@ -282,6 +282,8 @@ def add_catalytic_reaction_to_enzyme_constraint(self, catalytic_reaction:Reactio
         if self.rxn_id in enzyme.rxn2kcat.keys():
             del enzyme.rxn2kcat[self.rxn_id]
         enzyme.rxn2kcat[catalytic_reaction.id] = kcat_dict
+        #also add catalytic reaction to the ActiveEnzymeSector
+        self._model.sectors.ActiveEnzymeSector.rxn2protein[catalytic_reaction.id] = {enzyme.id: kcat_dict}
 
 
     def remove_enzymes(self, enzyme_list: list):
@@ -395,10 +397,9 @@ def change_kcat_values(self, enzyme_kcat_dict : dict):
                 self._model._change_kcat_in_enzyme_constraint(ce_reaction, enzyme, direction, kcat)
 
     @staticmethod
-    def _extract_reaction_id_from_catalytic_reaction_id(input_str: str) -> str:
-        # Define the regex pattern for protein IDs, obtained from UniProtKB, 2024-08-07
-        # https://www.uniprot.org/help/accession_numbers
-        protein_id_pattern = r'(?:[OPQ][0-9][A-Z0-9]{3}[0-9]|[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2})'
+    def _extract_reaction_id_from_catalytic_reaction_id(input_str: str,
+                                                        protein_id_pattern:str = r'(?:[OPQ][0-9][A-Z0-9]{3}[0-9]|[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2})'
+                                                        ) -> str:
 
         # Remove the 'CE_' prefix if it exists
         if input_str.startswith('CE_'):

src/PAModelpy/Enzyme.py

@@ -70,6 +70,7 @@ def __init__(
         self.enzyme_variable = None
         self.create_enzyme_variable()
 
+        self.enzyme_id_regex = r'(?:[OPQ][0-9][A-Z0-9]{3}[0-9]|[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2})'
         self.catalytic_event_id = (
             "CE_" + "{0}"
         )  # generic template for the catalytic events IDs
@@ -132,6 +133,7 @@ def model(self):
     @model.setter
     def model(self, model):
         self._model = model
+        self.enzyme_id_regex = model.ENZYME_ID_REGEX
 
     def set_forward_concentration(self, conc):
         self.enzyme_variable.set_forward_concentration(conc)
@@ -249,7 +251,7 @@ def change_kcat_values(self, rxn2kcat: Dict):
             if 'CE_' not in rxn_id:
                 catalytic_event_id = self.catalytic_event_id.format(rxn_id)
             else:
-                catalytic_event_id = f"CE_{CatalyticEvent._extract_reaction_id_from_catalytic_reaction_id(rxn_id)}"
+                catalytic_event_id = f"CE_{CatalyticEvent._extract_reaction_id_from_catalytic_reaction_id(rxn_id, self.enzyme_id_regex)}"
 
             # change rxn2kcat dictionary
             self.rxn2kcat[rxn_id] = kcats

src/PAModelpy/EnzymeSectors.py

@@ -221,6 +221,10 @@ def add(self, model):
                                     )
 
                                     model.add_enzymes([enzyme])
+                                    #add relation to rxn2protein dictionary
+
+                                    self.rxn2protein[rxn_id] = {**self.rxn2protein[rxn_id],
+                                                                **{enzyme_complex_id:kcat}}
                                     self.constraints += [enzyme]
                                     self.variables.append(enzyme.enzyme_variable)
                                 else:

src/PAModelpy/PAModel.py

@@ -69,6 +69,7 @@ class PAModel(Model):
     CO2_EXHANGE_RXNID = Config.CO2_EXHANGE_RXNID
     GLUCOSE_EXCHANGE_RXNID = Config.GLUCOSE_EXCHANGE_RXNID
     BIOMASS_REACTION = Config.BIOMASS_REACTION
+    ENZYME_ID_REGEX = Config.ENZYME_ID_REGEX
 
     def __init__(self, id_or_model: Union[str, "Model", None] = None,
                  name: Optional[str] = None,
@@ -78,13 +79,14 @@ def __init__(self, id_or_model: Union[str, "Model", None] = None,
                  translational_sector: Optional[TransEnzymeSector]=None,
                  unused_sector: Optional[UnusedEnzymeSector]=None,
                  custom_sectors: Optional[CustomSector] =[None],
-                 configuration = Config):
+                 configuration = Config()):
         """Constants"""
         self.TOTAL_PROTEIN_CONSTRAINT_ID = configuration.TOTAL_PROTEIN_CONSTRAINT_ID
         self.P_TOT_DEFAULT = configuration.P_TOT_DEFAULT  # g_protein/g_cdw
         self.CO2_EXHANGE_RXNID = configuration.CO2_EXHANGE_RXNID
         self.GLUCOSE_EXCHANGE_RXNID = configuration.GLUCOSE_EXCHANGE_RXNID
         self.BIOMASS_REACTION = configuration.BIOMASS_REACTION
+        self.ENZYME_ID_REGEX = configuration.ENZYME_ID_REGEX
 
         self.configuration = configuration
         """Initialize the Model."""
@@ -1377,7 +1379,8 @@ def change_kcat_value(self, enzyme_id:str, kcats:dict):
             for rxn, kcat_f_b in kcats.items():
                 # if a catalytic reaction is given, then extract the actual reaction id from it using the protein id convention from uniprot
                 if 'CE' in rxn:
-                    rxn = CatalyticEvent._extract_reaction_id_from_catalytic_reaction_id(rxn)
+                    rxn = CatalyticEvent._extract_reaction_id_from_catalytic_reaction_id(rxn,
+                                                                                         self.ENZYME_ID_REGEX)
                 active_enzyme.rxn2protein[rxn][enzyme_id] = kcat_f_b
         else:
             warnings.warn(f'The enzyme {enzyme_id} does not exist in the model. The kcat can thus not be changed.')

src/PAModelpy/configuration.py

@@ -10,6 +10,7 @@ class Config:
     - ACETATE_EXCRETION_RXNID: str, `EX_ac_e`
     - PHYS_RXN_IDS: List of str,  `[BIOMASS_REACTION, GLUCOSE_EXCHANGE_RXNID, ACETATE_EXCRETION_RXNID, CO2_EXHANGE_RXNID, OXYGEN_UPTAKE_RXNID,
                         'PGI', 'G6PDH2r', 'EDA', 'CS', 'ICL', 'PPC', 'ME1', 'ME2']`
+    - ENZYME_ID_REGEX: r-str: r'(?:[OPQ][0-9][A-Z0-9]{3}[0-9]|[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2})'
 
     Defaults are configured for the iML1515 E.coli model
     """
@@ -37,6 +38,10 @@ class Config:
         "ME2",
     ]
 
+    # Define the regex pattern for protein IDs, obtained from UniProtKB, 2024-08-07
+    # https://www.uniprot.org/help/accession_numbers
+    ENZYME_ID_REGEX = r'(?:[OPQ][0-9][A-Z0-9]{3}[0-9]|[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2})'
+
     def reset(self):
         """
         Reset the config object to the standard settings for E.coli iML1515.
@@ -64,3 +69,4 @@ def reset(self):
             "ME1",
             "ME2",
         ]
+        self.ENZYME_ID_REGEX = r'(?:[OPQ][0-9][A-Z0-9]{3}[0-9]|[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2})'