Mercurial > repos > bimib > cobraxy

comparison COBRAxy/utils/model_utils.py @ 508:ca98c149ec61 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author francesco_lapi
date Wed, 01 Oct 2025 14:21:26 +0000
parents ffc234ec80db
children fd53d42348bd
comparison
equal deleted inserted replaced
507:20e135a73cad 508:ca98c149ec61
1153 added += 1 1153 added += 1
1154 1154
1155 logger.info(f"Model genes updated: removed {removed}, added {added}") 1155 logger.info(f"Model genes updated: removed {removed}, added {added}")
1156 1156
1157 1157
1158 def export_model_to_tabular(model: cobraModel,
1159 output_path: str,
1160 translation_issues: Dict = None,
1161 include_objective: bool = True,
1162 save_function = None) -> pd.DataFrame:
1163 """
1164 Export a COBRA model to tabular format with optional components.
1165
1166 Args:
1167 model: COBRA model to export
1168 output_path: Path where to save the tabular file
1169 translation_issues: Optional dict of {reaction_id: issues} from gene translation
1170 include_objective: Whether to include objective coefficient column
1171 save_function: Optional custom save function, if None uses pd.DataFrame.to_csv
1172
1173 Returns:
1174 pd.DataFrame: The merged tabular data
1175 """
1176 # Generate model data
1177 rules = generate_rules(model, asParsed=False)
1178
1179 reactions = generate_reactions(model, asParsed=False)
1180 bounds = generate_bounds(model)
1181 medium = get_medium(model)
1182 compartments = generate_compartments(model)
1183
1184 # Create base DataFrames
1185 df_rules = pd.DataFrame(list(rules.items()), columns=["ReactionID", "GPR"])
1186 df_reactions = pd.DataFrame(list(reactions.items()), columns=["ReactionID", "Formula"])
1187 df_bounds = bounds.reset_index().rename(columns={"index": "ReactionID"})
1188 df_medium = medium.rename(columns={"reaction": "ReactionID"})
1189 df_medium["InMedium"] = True
1190
1191 # Start merging
1192 merged = df_reactions.merge(df_rules, on="ReactionID", how="outer")
1193 merged = merged.merge(df_bounds, on="ReactionID", how="outer")
1194
1195 # Add objective coefficients if requested
1196 if include_objective:
1197 objective_function = extract_objective_coefficients(model)
1198 merged = merged.merge(objective_function, on="ReactionID", how="outer")
1199
1200 # Add compartments/pathways if they exist
1201 if compartments is not None:
1202 merged = merged.merge(compartments, on="ReactionID", how="outer")
1203
1204 # Add medium information
1205 merged = merged.merge(df_medium, on="ReactionID", how="left")
1206
1207 # Add translation issues if provided
1208 if translation_issues:
1209 df_translation_issues = pd.DataFrame([
1210 {"ReactionID": rxn_id, "TranslationIssues": issues}
1211 for rxn_id, issues in translation_issues.items()
1212 ])
1213 if not df_translation_issues.empty:
1214 merged = merged.merge(df_translation_issues, on="ReactionID", how="left")
1215 merged["TranslationIssues"] = merged["TranslationIssues"].fillna("")
1216
1217 # Final processing
1218 merged["InMedium"] = merged["InMedium"].fillna(False)
1219 merged = merged.sort_values(by="InMedium", ascending=False)
1220
1221 # Save the file
1222 if save_function:
1223 save_function(merged, output_path)
1224 else:
1225 merged.to_csv(output_path, sep="\t", index=False)
1226
1227 return merged
1228
1229
1158 def _log_translation_statistics(stats: Dict[str, int], 1230 def _log_translation_statistics(stats: Dict[str, int],
1159 unmapped_genes: List[str], 1231 unmapped_genes: List[str],
1160 multi_mapping_genes: List[Tuple[str, List[str]]], 1232 multi_mapping_genes: List[Tuple[str, List[str]]],
1161 original_genes: Set[str], 1233 original_genes: Set[str],
1162 final_genes, 1234 final_genes,