|
456
|
1 """
|
|
|
2 Utilities for generating and manipulating COBRA models and related metadata.
|
|
|
3
|
|
|
4 This module includes helpers to:
|
|
|
5 - extract rules, reactions, bounds, objective coefficients, and compartments
|
|
|
6 - build a COBRA model from a tabular file
|
|
|
7 - set objective and medium from dataframes
|
|
|
8 - validate a model and convert gene identifiers
|
|
|
9 - translate model GPRs using mapping tables
|
|
|
10 """
|
|
418
|
11 import os
|
|
|
12 import cobra
|
|
|
13 import pandas as pd
|
|
419
|
14 import re
|
|
426
|
15 import logging
|
|
419
|
16 from typing import Optional, Tuple, Union, List, Dict, Set
|
|
426
|
17 from collections import defaultdict
|
|
418
|
18 import utils.rule_parsing as rulesUtils
|
|
419
|
19 import utils.reaction_parsing as reactionUtils
|
|
|
20 from cobra import Model as cobraModel, Reaction, Metabolite
|
|
490
|
21 import sys
|
|
|
22
|
|
|
23
|
|
|
24 ############################ check_methods ####################################
|
|
|
25 def gene_type(l :str, name :str) -> str:
|
|
|
26 """
|
|
|
27 Determine the type of gene ID.
|
|
|
28
|
|
|
29 Args:
|
|
|
30 l (str): The gene identifier to check.
|
|
|
31 name (str): The name of the dataset, used in error messages.
|
|
|
32
|
|
|
33 Returns:
|
|
|
34 str: The type of gene ID ('hugo_id', 'ensembl_gene_id', 'symbol', or 'entrez_id').
|
|
|
35
|
|
|
36 Raises:
|
|
|
37 sys.exit: If the gene ID type is not supported, the execution is aborted.
|
|
|
38 """
|
|
|
39 if check_hgnc(l):
|
|
|
40 return 'hugo_id'
|
|
|
41 elif check_ensembl(l):
|
|
|
42 return 'ensembl_gene_id'
|
|
|
43 elif check_symbol(l):
|
|
|
44 return 'symbol'
|
|
|
45 elif check_entrez(l):
|
|
|
46 return 'entrez_id'
|
|
|
47 else:
|
|
|
48 sys.exit('Execution aborted:\n' +
|
|
|
49 'gene ID type in ' + name + ' not supported. Supported ID'+
|
|
|
50 'types are: HUGO ID, Ensemble ID, HUGO symbol, Entrez ID\n')
|
|
|
51
|
|
|
52 def check_hgnc(l :str) -> bool:
|
|
|
53 """
|
|
|
54 Check if a gene identifier follows the HGNC format.
|
|
|
55
|
|
|
56 Args:
|
|
|
57 l (str): The gene identifier to check.
|
|
|
58
|
|
|
59 Returns:
|
|
|
60 bool: True if the gene identifier follows the HGNC format, False otherwise.
|
|
|
61 """
|
|
|
62 if len(l) > 5:
|
|
|
63 if (l.upper()).startswith('HGNC:'):
|
|
|
64 return l[5:].isdigit()
|
|
|
65 else:
|
|
|
66 return False
|
|
|
67 else:
|
|
|
68 return False
|
|
|
69
|
|
|
70 def check_ensembl(l :str) -> bool:
|
|
|
71 """
|
|
|
72 Check if a gene identifier follows the Ensembl format.
|
|
|
73
|
|
|
74 Args:
|
|
|
75 l (str): The gene identifier to check.
|
|
|
76
|
|
|
77 Returns:
|
|
|
78 bool: True if the gene identifier follows the Ensembl format, False otherwise.
|
|
|
79 """
|
|
|
80 return l.upper().startswith('ENS')
|
|
|
81
|
|
|
82
|
|
|
83 def check_symbol(l :str) -> bool:
|
|
|
84 """
|
|
|
85 Check if a gene identifier follows the symbol format.
|
|
|
86
|
|
|
87 Args:
|
|
|
88 l (str): The gene identifier to check.
|
|
|
89
|
|
|
90 Returns:
|
|
|
91 bool: True if the gene identifier follows the symbol format, False otherwise.
|
|
|
92 """
|
|
|
93 if len(l) > 0:
|
|
|
94 if l[0].isalpha() and l[1:].isalnum():
|
|
|
95 return True
|
|
|
96 else:
|
|
|
97 return False
|
|
|
98 else:
|
|
|
99 return False
|
|
|
100
|
|
|
101 def check_entrez(l :str) -> bool:
|
|
|
102 """
|
|
|
103 Check if a gene identifier follows the Entrez ID format.
|
|
|
104
|
|
|
105 Args:
|
|
|
106 l (str): The gene identifier to check.
|
|
|
107
|
|
|
108 Returns:
|
|
|
109 bool: True if the gene identifier follows the Entrez ID format, False otherwise.
|
|
|
110 """
|
|
|
111 if len(l) > 0:
|
|
|
112 return l.isdigit()
|
|
|
113 else:
|
|
|
114 return False
|
|
418
|
115
|
|
|
116 ################################- DATA GENERATION -################################
|
|
|
117 ReactionId = str
|
|
419
|
118 def generate_rules(model: cobraModel, *, asParsed = True) -> Union[Dict[ReactionId, rulesUtils.OpList], Dict[ReactionId, str]]:
|
|
418
|
119 """
|
|
456
|
120 Generate a dictionary mapping reaction IDs to GPR rules from the model.
|
|
418
|
121
|
|
|
122 Args:
|
|
456
|
123 model: COBRA model to derive data from.
|
|
|
124 asParsed: If True, parse rules into a nested list structure; otherwise keep raw strings.
|
|
418
|
125
|
|
|
126 Returns:
|
|
456
|
127 Dict[ReactionId, rulesUtils.OpList]: Parsed rules by reaction ID.
|
|
|
128 Dict[ReactionId, str]: Raw rules by reaction ID.
|
|
418
|
129 """
|
|
|
130 _ruleGetter = lambda reaction : reaction.gene_reaction_rule
|
|
|
131 ruleExtractor = (lambda reaction :
|
|
|
132 rulesUtils.parseRuleToNestedList(_ruleGetter(reaction))) if asParsed else _ruleGetter
|
|
|
133
|
|
|
134 return {
|
|
|
135 reaction.id : ruleExtractor(reaction)
|
|
|
136 for reaction in model.reactions
|
|
|
137 if reaction.gene_reaction_rule }
|
|
|
138
|
|
419
|
139 def generate_reactions(model :cobraModel, *, asParsed = True) -> Dict[ReactionId, str]:
|
|
418
|
140 """
|
|
456
|
141 Generate a dictionary mapping reaction IDs to reaction formulas from the model.
|
|
418
|
142
|
|
|
143 Args:
|
|
456
|
144 model: COBRA model to derive data from.
|
|
|
145 asParsed: If True, convert formulas into a parsed representation; otherwise keep raw strings.
|
|
418
|
146
|
|
|
147 Returns:
|
|
456
|
148 Dict[ReactionId, str]: Reactions by reaction ID (parsed if requested).
|
|
418
|
149 """
|
|
|
150
|
|
|
151 unparsedReactions = {
|
|
|
152 reaction.id : reaction.reaction
|
|
|
153 for reaction in model.reactions
|
|
|
154 if reaction.reaction
|
|
|
155 }
|
|
|
156
|
|
|
157 if not asParsed: return unparsedReactions
|
|
|
158
|
|
|
159 return reactionUtils.create_reaction_dict(unparsedReactions)
|
|
|
160
|
|
419
|
161 def get_medium(model:cobraModel) -> pd.DataFrame:
|
|
456
|
162 """
|
|
|
163 Extract the uptake reactions representing the model medium.
|
|
|
164
|
|
|
165 Returns a DataFrame with a single column 'reaction' listing exchange reactions
|
|
|
166 with negative lower bound and no positive stoichiometric coefficients (uptake only).
|
|
|
167 """
|
|
418
|
168 trueMedium=[]
|
|
|
169 for r in model.reactions:
|
|
|
170 positiveCoeff=0
|
|
|
171 for m in r.metabolites:
|
|
|
172 if r.get_coefficient(m.id)>0:
|
|
|
173 positiveCoeff=1;
|
|
|
174 if (positiveCoeff==0 and r.lower_bound<0):
|
|
|
175 trueMedium.append(r.id)
|
|
|
176
|
|
|
177 df_medium = pd.DataFrame()
|
|
|
178 df_medium["reaction"] = trueMedium
|
|
|
179 return df_medium
|
|
|
180
|
|
426
|
181 def extract_objective_coefficients(model: cobraModel) -> pd.DataFrame:
|
|
|
182 """
|
|
456
|
183 Extract objective coefficients for each reaction.
|
|
|
184
|
|
426
|
185 Args:
|
|
456
|
186 model: COBRA model
|
|
|
187
|
|
426
|
188 Returns:
|
|
456
|
189 pd.DataFrame with columns: ReactionID, ObjectiveCoefficient
|
|
426
|
190 """
|
|
|
191 coeffs = []
|
|
456
|
192 # model.objective.expression is a linear expression
|
|
426
|
193 objective_expr = model.objective.expression.as_coefficients_dict()
|
|
|
194
|
|
|
195 for reaction in model.reactions:
|
|
|
196 coeff = objective_expr.get(reaction.forward_variable, 0.0)
|
|
|
197 coeffs.append({
|
|
|
198 "ReactionID": reaction.id,
|
|
|
199 "ObjectiveCoefficient": coeff
|
|
|
200 })
|
|
|
201
|
|
|
202 return pd.DataFrame(coeffs)
|
|
|
203
|
|
419
|
204 def generate_bounds(model:cobraModel) -> pd.DataFrame:
|
|
456
|
205 """
|
|
|
206 Build a DataFrame of lower/upper bounds for all reactions.
|
|
|
207
|
|
|
208 Returns:
|
|
|
209 pd.DataFrame indexed by reaction IDs with columns ['lower_bound', 'upper_bound'].
|
|
|
210 """
|
|
418
|
211
|
|
|
212 rxns = []
|
|
|
213 for reaction in model.reactions:
|
|
|
214 rxns.append(reaction.id)
|
|
|
215
|
|
|
216 bounds = pd.DataFrame(columns = ["lower_bound", "upper_bound"], index=rxns)
|
|
|
217
|
|
|
218 for reaction in model.reactions:
|
|
|
219 bounds.loc[reaction.id] = [reaction.lower_bound, reaction.upper_bound]
|
|
|
220 return bounds
|
|
|
221
|
|
|
222
|
|
|
223
|
|
419
|
224 def generate_compartments(model: cobraModel) -> pd.DataFrame:
|
|
418
|
225 """
|
|
|
226 Generates a DataFrame containing compartment information for each reaction.
|
|
|
227 Creates columns for each compartment position (Compartment_1, Compartment_2, etc.)
|
|
|
228
|
|
|
229 Args:
|
|
|
230 model: the COBRA model to extract compartment data from.
|
|
|
231
|
|
|
232 Returns:
|
|
|
233 pd.DataFrame: DataFrame with ReactionID and compartment columns
|
|
|
234 """
|
|
|
235 pathway_data = []
|
|
|
236
|
|
|
237 # First pass: determine the maximum number of pathways any reaction has
|
|
|
238 max_pathways = 0
|
|
|
239 reaction_pathways = {}
|
|
|
240
|
|
|
241 for reaction in model.reactions:
|
|
|
242 # Get unique pathways from all metabolites in the reaction
|
|
|
243 if type(reaction.annotation['pathways']) == list:
|
|
|
244 reaction_pathways[reaction.id] = reaction.annotation['pathways']
|
|
|
245 max_pathways = max(max_pathways, len(reaction.annotation['pathways']))
|
|
|
246 else:
|
|
|
247 reaction_pathways[reaction.id] = [reaction.annotation['pathways']]
|
|
|
248
|
|
|
249 # Create column names for pathways
|
|
|
250 pathway_columns = [f"Pathway_{i+1}" for i in range(max_pathways)]
|
|
|
251
|
|
|
252 # Second pass: create the data
|
|
|
253 for reaction_id, pathways in reaction_pathways.items():
|
|
|
254 row = {"ReactionID": reaction_id}
|
|
|
255
|
|
|
256 # Fill pathway columns
|
|
|
257 for i in range(max_pathways):
|
|
|
258 col_name = pathway_columns[i]
|
|
|
259 if i < len(pathways):
|
|
|
260 row[col_name] = pathways[i]
|
|
|
261 else:
|
|
|
262 row[col_name] = None # or "" if you prefer empty strings
|
|
|
263
|
|
|
264 pathway_data.append(row)
|
|
|
265
|
|
419
|
266 return pd.DataFrame(pathway_data)
|
|
|
267
|
|
|
268
|
|
|
269
|
|
|
270 def build_cobra_model_from_csv(csv_path: str, model_id: str = "new_model") -> cobraModel:
|
|
|
271 """
|
|
456
|
272 Build a COBRApy model from a tabular file with reaction data.
|
|
|
273
|
|
419
|
274 Args:
|
|
456
|
275 csv_path: Path to the tab-separated file.
|
|
|
276 model_id: ID for the newly created model.
|
|
|
277
|
|
419
|
278 Returns:
|
|
456
|
279 cobra.Model: The constructed COBRApy model.
|
|
419
|
280 """
|
|
|
281
|
|
|
282 df = pd.read_csv(csv_path, sep='\t')
|
|
|
283
|
|
|
284 model = cobraModel(model_id)
|
|
|
285
|
|
|
286 metabolites_dict = {}
|
|
|
287 compartments_dict = {}
|
|
|
288
|
|
456
|
289 print(f"Building model from {len(df)} reactions...")
|
|
419
|
290
|
|
|
291 for idx, row in df.iterrows():
|
|
448
|
292 reaction_formula = str(row['Formula']).strip()
|
|
419
|
293 if not reaction_formula or reaction_formula == 'nan':
|
|
|
294 continue
|
|
|
295
|
|
|
296 metabolites = extract_metabolites_from_reaction(reaction_formula)
|
|
|
297
|
|
|
298 for met_id in metabolites:
|
|
|
299 compartment = extract_compartment_from_metabolite(met_id)
|
|
|
300
|
|
|
301 if compartment not in compartments_dict:
|
|
|
302 compartments_dict[compartment] = compartment
|
|
|
303
|
|
|
304 if met_id not in metabolites_dict:
|
|
|
305 metabolites_dict[met_id] = Metabolite(
|
|
|
306 id=met_id,
|
|
|
307 compartment=compartment,
|
|
|
308 name=met_id.replace(f"_{compartment}", "").replace("__", "_")
|
|
|
309 )
|
|
|
310
|
|
|
311 model.compartments = compartments_dict
|
|
|
312
|
|
|
313 model.add_metabolites(list(metabolites_dict.values()))
|
|
|
314
|
|
456
|
315 print(f"Added {len(metabolites_dict)} metabolites and {len(compartments_dict)} compartments")
|
|
419
|
316
|
|
|
317 reactions_added = 0
|
|
|
318 reactions_skipped = 0
|
|
|
319
|
|
|
320 for idx, row in df.iterrows():
|
|
|
321
|
|
|
322 reaction_id = str(row['ReactionID']).strip()
|
|
427
|
323 reaction_formula = str(row['Formula']).strip()
|
|
419
|
324
|
|
|
325 if not reaction_formula or reaction_formula == 'nan':
|
|
456
|
326 raise ValueError(f"Missing reaction formula for {reaction_id}")
|
|
419
|
327
|
|
|
328 reaction = Reaction(reaction_id)
|
|
|
329 reaction.name = reaction_id
|
|
|
330
|
|
|
331 reaction.lower_bound = float(row['lower_bound']) if pd.notna(row['lower_bound']) else -1000.0
|
|
|
332 reaction.upper_bound = float(row['upper_bound']) if pd.notna(row['upper_bound']) else 1000.0
|
|
|
333
|
|
427
|
334 if pd.notna(row['GPR']) and str(row['GPR']).strip():
|
|
|
335 reaction.gene_reaction_rule = str(row['GPR']).strip()
|
|
419
|
336
|
|
|
337 try:
|
|
|
338 parse_reaction_formula(reaction, reaction_formula, metabolites_dict)
|
|
|
339 except Exception as e:
|
|
456
|
340 print(f"Error parsing reaction {reaction_id}: {e}")
|
|
419
|
341 reactions_skipped += 1
|
|
|
342 continue
|
|
|
343
|
|
|
344 model.add_reactions([reaction])
|
|
|
345 reactions_added += 1
|
|
|
346
|
|
|
347
|
|
456
|
348 print(f"Added {reactions_added} reactions, skipped {reactions_skipped} reactions")
|
|
419
|
349
|
|
430
|
350 # set objective function
|
|
|
351 set_objective_from_csv(model, df, obj_col="ObjectiveCoefficient")
|
|
|
352
|
|
419
|
353 set_medium_from_data(model, df)
|
|
|
354
|
|
456
|
355 print(f"Model completed: {len(model.reactions)} reactions, {len(model.metabolites)} metabolites")
|
|
419
|
356
|
|
|
357 return model
|
|
|
358
|
|
|
359
|
|
|
360 # Estrae tutti gli ID metaboliti nella formula (gestisce prefissi numerici + underscore)
|
|
499
|
361 #def extract_metabolites_from_reaction(reaction_formula: str) -> Set[str]:
|
|
|
362 # """
|
|
|
363 # Extract metabolite IDs from a reaction formula.
|
|
|
364 # Robust pattern: tokens ending with _<compartment> (e.g., _c, _m, _e),
|
|
|
365 # allowing leading digits/underscores.
|
|
|
366 # """
|
|
|
367 # metabolites = set()
|
|
|
368 # # optional coefficient followed by a token ending with _<letters>
|
|
|
369 # if reaction_formula[-1] == ']' and reaction_formula[-3] == '[':
|
|
|
370 # pattern = r'(?:\d+(?:\.\d+)?\s+)?([A-Za-z0-9_]+[[A-Za-z0-9]]+)'
|
|
|
371 # else:
|
|
|
372 # pattern = r'(?:\d+(?:\.\d+)?\s+)?([A-Za-z0-9_]+_[A-Za-z0-9]+)'
|
|
|
373 # matches = re.findall(pattern, reaction_formula)
|
|
|
374 # metabolites.update(matches)
|
|
|
375 # return metabolites
|
|
|
376
|
|
|
377
|
|
419
|
378 def extract_metabolites_from_reaction(reaction_formula: str) -> Set[str]:
|
|
|
379 """
|
|
500
|
380 Extract metabolite IDs from a reaction formula.
|
|
|
381
|
|
|
382 Handles:
|
|
|
383 - optional stoichiometric coefficients (integers or decimals)
|
|
|
384 - compartment tags at the end of the metabolite, either [c] or _c
|
|
|
385
|
|
|
386 Returns the IDs including the compartment suffix exactly as written.
|
|
419
|
387 """
|
|
499
|
388 pattern = re.compile(
|
|
500
|
389 r'(?:^|(?<=\s)|(?<=\+)|(?<=,)|(?<==)|(?<=:))' # left boundary (start, space, +, comma, =, :)
|
|
|
390 r'(?:\d+(?:\.\d+)?\s*)?' # optional coefficient
|
|
|
391 r'([A-Za-z0-9_]+(?:\[[A-Za-z0-9]+\]|_[A-Za-z0-9]+))' # metabolite + compartment
|
|
499
|
392 )
|
|
|
393 return {m.group(1) for m in pattern.finditer(reaction_formula)}
|
|
419
|
394
|
|
|
395
|
|
500
|
396
|
|
419
|
397 def extract_compartment_from_metabolite(metabolite_id: str) -> str:
|
|
456
|
398 """Extract the compartment from a metabolite ID."""
|
|
500
|
399 if '_' == metabolite_id[-2]:
|
|
419
|
400 return metabolite_id.split('_')[-1]
|
|
493
|
401 if metabolite_id[-1] == ']' and metabolite_id[-3] == '[':
|
|
|
402 return metabolite_id[-2]
|
|
419
|
403 return 'c' # default cytoplasm
|
|
|
404
|
|
|
405
|
|
|
406 def parse_reaction_formula(reaction: Reaction, formula: str, metabolites_dict: Dict[str, Metabolite]):
|
|
456
|
407 """Parse a reaction formula and set metabolites with their coefficients."""
|
|
419
|
408
|
|
|
409 if '<=>' in formula:
|
|
|
410 left, right = formula.split('<=>')
|
|
|
411 reversible = True
|
|
|
412 elif '<--' in formula:
|
|
|
413 left, right = formula.split('<--')
|
|
|
414 reversible = False
|
|
|
415 elif '-->' in formula:
|
|
|
416 left, right = formula.split('-->')
|
|
|
417 reversible = False
|
|
|
418 elif '<-' in formula:
|
|
|
419 left, right = formula.split('<-')
|
|
|
420 reversible = False
|
|
|
421 else:
|
|
456
|
422 raise ValueError(f"Unrecognized reaction format: {formula}")
|
|
419
|
423
|
|
|
424 reactants = parse_metabolites_side(left.strip())
|
|
|
425 products = parse_metabolites_side(right.strip())
|
|
|
426
|
|
|
427 metabolites_to_add = {}
|
|
|
428
|
|
|
429 for met_id, coeff in reactants.items():
|
|
|
430 if met_id in metabolites_dict:
|
|
|
431 metabolites_to_add[metabolites_dict[met_id]] = -coeff
|
|
|
432
|
|
|
433 for met_id, coeff in products.items():
|
|
|
434 if met_id in metabolites_dict:
|
|
|
435 metabolites_to_add[metabolites_dict[met_id]] = coeff
|
|
|
436
|
|
|
437 reaction.add_metabolites(metabolites_to_add)
|
|
|
438
|
|
|
439
|
|
|
440 def parse_metabolites_side(side_str: str) -> Dict[str, float]:
|
|
456
|
441 """Parse one side of a reaction and extract metabolites with coefficients."""
|
|
419
|
442 metabolites = {}
|
|
|
443 if not side_str or side_str.strip() == '':
|
|
|
444 return metabolites
|
|
|
445
|
|
|
446 terms = side_str.split('+')
|
|
|
447 for term in terms:
|
|
|
448 term = term.strip()
|
|
|
449 if not term:
|
|
|
450 continue
|
|
|
451
|
|
456
|
452 # optional coefficient + id ending with _<compartment>
|
|
419
|
453 match = re.match(r'(?:(\d+\.?\d*)\s+)?([A-Za-z0-9_]+_[a-z]+)', term)
|
|
|
454 if match:
|
|
|
455 coeff_str, met_id = match.groups()
|
|
|
456 coeff = float(coeff_str) if coeff_str else 1.0
|
|
|
457 metabolites[met_id] = coeff
|
|
|
458
|
|
|
459 return metabolites
|
|
|
460
|
|
|
461
|
|
|
462
|
|
430
|
463 def set_objective_from_csv(model: cobra.Model, df: pd.DataFrame, obj_col: str = "ObjectiveCoefficient"):
|
|
419
|
464 """
|
|
430
|
465 Sets the model's objective function based on a column of coefficients in the CSV.
|
|
|
466 Can be any reaction(s), not necessarily biomass.
|
|
419
|
467 """
|
|
430
|
468 obj_dict = {}
|
|
419
|
469
|
|
430
|
470 for idx, row in df.iterrows():
|
|
|
471 reaction_id = str(row['ReactionID']).strip()
|
|
|
472 coeff = float(row[obj_col]) if pd.notna(row[obj_col]) else 0.0
|
|
|
473 if coeff != 0:
|
|
|
474 if reaction_id in model.reactions:
|
|
|
475 obj_dict[model.reactions.get_by_id(reaction_id)] = coeff
|
|
|
476 else:
|
|
|
477 print(f"Warning: reaction {reaction_id} not found in model, skipping for objective.")
|
|
|
478
|
|
|
479 if not obj_dict:
|
|
|
480 raise ValueError("No reactions found with non-zero objective coefficient.")
|
|
|
481
|
|
|
482 model.objective = obj_dict
|
|
|
483 print(f"Objective set with {len(obj_dict)} reactions.")
|
|
|
484
|
|
|
485
|
|
419
|
486
|
|
|
487
|
|
|
488 def set_medium_from_data(model: cobraModel, df: pd.DataFrame):
|
|
456
|
489 """Set the medium based on the 'InMedium' column in the dataframe."""
|
|
419
|
490 medium_reactions = df[df['InMedium'] == True]['ReactionID'].tolist()
|
|
|
491
|
|
|
492 medium_dict = {}
|
|
|
493 for rxn_id in medium_reactions:
|
|
|
494 if rxn_id in [r.id for r in model.reactions]:
|
|
|
495 reaction = model.reactions.get_by_id(rxn_id)
|
|
|
496 if reaction.lower_bound < 0: # Solo reazioni di uptake
|
|
|
497 medium_dict[rxn_id] = abs(reaction.lower_bound)
|
|
|
498
|
|
|
499 if medium_dict:
|
|
|
500 model.medium = medium_dict
|
|
456
|
501 print(f"Medium set with {len(medium_dict)} components")
|
|
419
|
502
|
|
|
503
|
|
|
504 def validate_model(model: cobraModel) -> Dict[str, any]:
|
|
456
|
505 """Validate the model and return basic statistics."""
|
|
419
|
506 validation = {
|
|
|
507 'num_reactions': len(model.reactions),
|
|
|
508 'num_metabolites': len(model.metabolites),
|
|
|
509 'num_genes': len(model.genes),
|
|
|
510 'num_compartments': len(model.compartments),
|
|
|
511 'objective': str(model.objective),
|
|
|
512 'medium_size': len(model.medium),
|
|
|
513 'reversible_reactions': len([r for r in model.reactions if r.reversibility]),
|
|
|
514 'exchange_reactions': len([r for r in model.reactions if r.id.startswith('EX_')]),
|
|
|
515 }
|
|
|
516
|
|
|
517 try:
|
|
456
|
518 # Growth test
|
|
419
|
519 solution = model.optimize()
|
|
|
520 validation['growth_rate'] = solution.objective_value
|
|
|
521 validation['status'] = solution.status
|
|
|
522 except Exception as e:
|
|
|
523 validation['growth_rate'] = None
|
|
|
524 validation['status'] = f"Error: {e}"
|
|
|
525
|
|
|
526 return validation
|
|
|
527
|
|
456
|
528 def convert_genes(model, annotation):
|
|
|
529 """Rename genes using a selected annotation key in gene.notes; returns a model copy."""
|
|
419
|
530 from cobra.manipulation import rename_genes
|
|
|
531 model2=model.copy()
|
|
|
532 try:
|
|
|
533 dict_genes={gene.id:gene.notes[annotation] for gene in model2.genes}
|
|
|
534 except:
|
|
|
535 print("No annotation in gene dict!")
|
|
|
536 return -1
|
|
|
537 rename_genes(model2,dict_genes)
|
|
|
538
|
|
426
|
539 return model2
|
|
|
540
|
|
|
541 # ---------- Utility helpers ----------
|
|
|
542 def _normalize_colname(col: str) -> str:
|
|
|
543 return col.strip().lower().replace(' ', '_')
|
|
|
544
|
|
|
545 def _choose_columns(mapping_df: 'pd.DataFrame') -> Dict[str, str]:
|
|
|
546 """
|
|
456
|
547 Find useful columns and return a dict {ensg: colname1, hgnc_id: colname2, ...}.
|
|
|
548 Raise ValueError if no suitable mapping is found.
|
|
426
|
549 """
|
|
|
550 cols = { _normalize_colname(c): c for c in mapping_df.columns }
|
|
|
551 chosen = {}
|
|
456
|
552 # candidate names for each category
|
|
426
|
553 candidates = {
|
|
|
554 'ensg': ['ensg', 'ensembl_gene_id', 'ensembl'],
|
|
|
555 'hgnc_id': ['hgnc_id', 'hgnc', 'hgnc:'],
|
|
444
|
556 'hgnc_symbol': ['hgnc_symbol', 'hgnc symbol', 'symbol'],
|
|
455
|
557 'entrez_id': ['entrez', 'entrez_id', 'entrezgene'],
|
|
|
558 'gene_number': ['gene_number']
|
|
426
|
559 }
|
|
|
560 for key, names in candidates.items():
|
|
|
561 for n in names:
|
|
|
562 if n in cols:
|
|
|
563 chosen[key] = cols[n]
|
|
|
564 break
|
|
|
565 return chosen
|
|
|
566
|
|
|
567 def _validate_target_uniqueness(mapping_df: 'pd.DataFrame',
|
|
|
568 source_col: str,
|
|
|
569 target_col: str,
|
|
|
570 model_source_genes: Optional[Set[str]] = None,
|
|
|
571 logger: Optional[logging.Logger] = None) -> None:
|
|
|
572 """
|
|
456
|
573 Check that, within the filtered mapping_df, each target maps to at most one source.
|
|
|
574 Log examples if duplicates are found.
|
|
426
|
575 """
|
|
|
576 if logger is None:
|
|
|
577 logger = logging.getLogger(__name__)
|
|
|
578
|
|
|
579 if mapping_df.empty:
|
|
|
580 logger.warning("Mapping dataframe is empty for the requested source genes; skipping uniqueness validation.")
|
|
|
581 return
|
|
|
582
|
|
456
|
583 # normalize temporary columns for grouping (without altering the original df)
|
|
426
|
584 tmp = mapping_df[[source_col, target_col]].copy()
|
|
|
585 tmp['_src_norm'] = tmp[source_col].astype(str).map(_normalize_gene_id)
|
|
|
586 tmp['_tgt_norm'] = tmp[target_col].astype(str).str.strip()
|
|
|
587
|
|
456
|
588 # optionally filter to the set of model source genes
|
|
426
|
589 if model_source_genes is not None:
|
|
|
590 tmp = tmp[tmp['_src_norm'].isin(model_source_genes)]
|
|
|
591
|
|
|
592 if tmp.empty:
|
|
|
593 logger.warning("After filtering to model source genes, mapping table is empty — nothing to validate.")
|
|
|
594 return
|
|
|
595
|
|
456
|
596 # build reverse mapping: target -> set(sources)
|
|
426
|
597 grouped = tmp.groupby('_tgt_norm')['_src_norm'].agg(lambda s: set(s.dropna()))
|
|
456
|
598 # find targets with more than one source
|
|
426
|
599 problematic = {t: sorted(list(s)) for t, s in grouped.items() if len(s) > 1}
|
|
|
600
|
|
|
601 if problematic:
|
|
456
|
602 # prepare warning message with examples (limited subset)
|
|
455
|
603 sample_items = list(problematic.items())
|
|
426
|
604 msg_lines = ["Mapping validation failed: some target IDs are associated with multiple source IDs."]
|
|
|
605 for tgt, sources in sample_items:
|
|
|
606 msg_lines.append(f" - target '{tgt}' <- sources: {', '.join(sources)}")
|
|
|
607 full_msg = "\n".join(msg_lines)
|
|
456
|
608 # log warning
|
|
455
|
609 logger.warning(full_msg)
|
|
426
|
610
|
|
456
|
611 # if everything is fine
|
|
426
|
612 logger.info("Mapping validation passed: no target ID is associated with multiple source IDs (within filtered set).")
|
|
|
613
|
|
|
614
|
|
|
615 def _normalize_gene_id(g: str) -> str:
|
|
456
|
616 """Normalize a gene ID for use as a key (removes prefixes like 'HGNC:' and strips)."""
|
|
426
|
617 if g is None:
|
|
|
618 return ""
|
|
|
619 g = str(g).strip()
|
|
|
620 # remove common prefixes
|
|
|
621 g = re.sub(r'^(HGNC:)', '', g, flags=re.IGNORECASE)
|
|
|
622 g = re.sub(r'^(ENSG:)', '', g, flags=re.IGNORECASE)
|
|
|
623 return g
|
|
|
624
|
|
493
|
625 def _is_or_only_expression(expr: str) -> bool:
|
|
|
626 """
|
|
|
627 Check if a GPR expression contains only OR operators (no AND operators).
|
|
|
628
|
|
|
629 Args:
|
|
|
630 expr: GPR expression string
|
|
|
631
|
|
|
632 Returns:
|
|
|
633 bool: True if expression contains only OR (and parentheses) and has multiple genes, False otherwise
|
|
|
634 """
|
|
|
635 if not expr or not expr.strip():
|
|
|
636 return False
|
|
|
637
|
|
|
638 # Normalize the expression
|
|
|
639 normalized = expr.replace(' AND ', ' and ').replace(' OR ', ' or ')
|
|
|
640
|
|
|
641 # Check if it contains any AND operators
|
|
|
642 has_and = ' and ' in normalized.lower()
|
|
|
643
|
|
|
644 # Check if it contains OR operators
|
|
|
645 has_or = ' or ' in normalized.lower()
|
|
|
646
|
|
|
647 # Must have OR operators and no AND operators
|
|
|
648 return has_or and not has_and
|
|
|
649
|
|
|
650
|
|
|
651 def _flatten_or_only_gpr(expr: str) -> str:
|
|
|
652 """
|
|
|
653 Flatten a GPR expression that contains only OR operators by:
|
|
|
654 1. Removing all parentheses
|
|
|
655 2. Extracting unique gene names
|
|
|
656 3. Joining them with ' or '
|
|
|
657
|
|
|
658 Args:
|
|
|
659 expr: GPR expression string with only OR operators
|
|
|
660
|
|
|
661 Returns:
|
|
|
662 str: Flattened GPR expression
|
|
|
663 """
|
|
|
664 if not expr or not expr.strip():
|
|
|
665 return expr
|
|
|
666
|
|
|
667 # Extract all gene tokens (exclude logical operators and parentheses)
|
|
|
668 gene_pattern = r'\b[A-Za-z0-9:_.-]+\b'
|
|
|
669 logical = {'and', 'or', 'AND', 'OR', '(', ')'}
|
|
|
670
|
|
|
671 tokens = re.findall(gene_pattern, expr)
|
|
|
672 genes = [t for t in tokens if t not in logical]
|
|
|
673
|
|
|
674 # Create set to remove duplicates, then convert back to list to maintain some order
|
|
|
675 unique_genes = list(dict.fromkeys(genes)) # Preserves insertion order
|
|
|
676
|
|
|
677 if len(unique_genes) == 0:
|
|
|
678 return expr
|
|
|
679 elif len(unique_genes) == 1:
|
|
|
680 return unique_genes[0]
|
|
|
681 else:
|
|
|
682 return ' or '.join(unique_genes)
|
|
|
683
|
|
|
684
|
|
455
|
685 def _simplify_boolean_expression(expr: str) -> str:
|
|
|
686 """
|
|
490
|
687 Simplify a boolean expression by removing duplicates while strictly preserving semantics.
|
|
|
688 This function handles simple duplicates within parentheses while being conservative about
|
|
|
689 complex expressions that could change semantics.
|
|
455
|
690 """
|
|
|
691 if not expr or not expr.strip():
|
|
|
692 return expr
|
|
|
693
|
|
490
|
694 # Normalize operators and whitespace
|
|
455
|
695 expr = expr.replace(' AND ', ' and ').replace(' OR ', ' or ')
|
|
490
|
696 expr = ' '.join(expr.split()) # Normalize whitespace
|
|
455
|
697
|
|
490
|
698 def simplify_parentheses_content(match_obj):
|
|
|
699 """Helper function to simplify content within parentheses."""
|
|
|
700 content = match_obj.group(1) # Content inside parentheses
|
|
455
|
701
|
|
490
|
702 # Only simplify if it's a pure OR or pure AND chain
|
|
|
703 if ' or ' in content and ' and ' not in content:
|
|
|
704 # Pure OR chain - safe to deduplicate
|
|
|
705 parts = [p.strip() for p in content.split(' or ') if p.strip()]
|
|
|
706 unique_parts = []
|
|
|
707 seen = set()
|
|
|
708 for part in parts:
|
|
|
709 if part not in seen:
|
|
|
710 unique_parts.append(part)
|
|
|
711 seen.add(part)
|
|
455
|
712
|
|
490
|
713 if len(unique_parts) == 1:
|
|
|
714 return unique_parts[0] # Remove unnecessary parentheses for single items
|
|
|
715 else:
|
|
|
716 return '(' + ' or '.join(unique_parts) + ')'
|
|
|
717
|
|
|
718 elif ' and ' in content and ' or ' not in content:
|
|
|
719 # Pure AND chain - safe to deduplicate
|
|
|
720 parts = [p.strip() for p in content.split(' and ') if p.strip()]
|
|
|
721 unique_parts = []
|
|
|
722 seen = set()
|
|
|
723 for part in parts:
|
|
|
724 if part not in seen:
|
|
|
725 unique_parts.append(part)
|
|
|
726 seen.add(part)
|
|
455
|
727
|
|
490
|
728 if len(unique_parts) == 1:
|
|
|
729 return unique_parts[0] # Remove unnecessary parentheses for single items
|
|
|
730 else:
|
|
|
731 return '(' + ' and '.join(unique_parts) + ')'
|
|
|
732 else:
|
|
|
733 # Mixed operators or single item - return with parentheses as-is
|
|
|
734 return '(' + content + ')'
|
|
|
735
|
|
|
736 def remove_duplicates_simple(parts_str: str, separator: str) -> str:
|
|
|
737 """Remove duplicates from a simple chain of operations."""
|
|
|
738 parts = [p.strip() for p in parts_str.split(separator) if p.strip()]
|
|
455
|
739
|
|
490
|
740 # Remove duplicates while preserving order
|
|
|
741 unique_parts = []
|
|
|
742 seen = set()
|
|
|
743 for part in parts:
|
|
|
744 if part not in seen:
|
|
|
745 unique_parts.append(part)
|
|
|
746 seen.add(part)
|
|
455
|
747
|
|
490
|
748 if len(unique_parts) == 1:
|
|
|
749 return unique_parts[0]
|
|
455
|
750 else:
|
|
490
|
751 return f' {separator} '.join(unique_parts)
|
|
455
|
752
|
|
|
753 try:
|
|
490
|
754 import re
|
|
|
755
|
|
|
756 # First, simplify content within parentheses
|
|
|
757 # This handles cases like (A or A) -> A and (B and B) -> B
|
|
|
758 expr_simplified = re.sub(r'\(([^()]+)\)', simplify_parentheses_content, expr)
|
|
|
759
|
|
|
760 # Check if the resulting expression has mixed operators
|
|
|
761 has_and = ' and ' in expr_simplified
|
|
|
762 has_or = ' or ' in expr_simplified
|
|
|
763
|
|
|
764 # Only simplify top-level if it's pure AND or pure OR
|
|
|
765 if has_and and not has_or and '(' not in expr_simplified:
|
|
|
766 # Pure AND chain at top level - safe to deduplicate
|
|
|
767 return remove_duplicates_simple(expr_simplified, 'and')
|
|
|
768 elif has_or and not has_and and '(' not in expr_simplified:
|
|
|
769 # Pure OR chain at top level - safe to deduplicate
|
|
|
770 return remove_duplicates_simple(expr_simplified, 'or')
|
|
|
771 else:
|
|
|
772 # Mixed operators or has parentheses - return the simplified version (with parentheses content cleaned)
|
|
|
773 return expr_simplified
|
|
|
774
|
|
455
|
775 except Exception:
|
|
490
|
776 # If anything goes wrong, return the original expression
|
|
455
|
777 return expr
|
|
|
778
|
|
492
|
779
|
|
426
|
780 def translate_model_genes(model: 'cobra.Model',
|
|
|
781 mapping_df: 'pd.DataFrame',
|
|
|
782 target_nomenclature: str,
|
|
|
783 source_nomenclature: str = 'hgnc_id',
|
|
455
|
784 allow_many_to_one: bool = False,
|
|
490
|
785 logger: Optional[logging.Logger] = None) -> Tuple['cobra.Model', Dict[str, str]]:
|
|
426
|
786 """
|
|
456
|
787 Translate model genes from source_nomenclature to target_nomenclature using a mapping table.
|
|
|
788 mapping_df should contain columns enabling mapping (e.g., ensg, hgnc_id, hgnc_symbol, entrez).
|
|
|
789
|
|
455
|
790 Args:
|
|
456
|
791 model: COBRA model to translate.
|
|
|
792 mapping_df: DataFrame containing the mapping information.
|
|
|
793 target_nomenclature: Desired target key (e.g., 'hgnc_symbol').
|
|
|
794 source_nomenclature: Current source key in the model (default 'hgnc_id').
|
|
|
795 allow_many_to_one: If True, allow many-to-one mappings and handle duplicates in GPRs.
|
|
|
796 logger: Optional logger.
|
|
490
|
797
|
|
|
798 Returns:
|
|
|
799 Tuple containing:
|
|
|
800 - Translated COBRA model
|
|
|
801 - Dictionary mapping reaction IDs to translation issue descriptions
|
|
426
|
802 """
|
|
|
803 if logger is None:
|
|
|
804 logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
|
|
|
805 logger = logging.getLogger(__name__)
|
|
|
806
|
|
|
807 logger.info(f"Translating genes from '{source_nomenclature}' to '{target_nomenclature}'")
|
|
|
808
|
|
|
809 # normalize column names and choose relevant columns
|
|
|
810 chosen = _choose_columns(mapping_df)
|
|
|
811 if not chosen:
|
|
|
812 raise ValueError("Could not detect useful columns in mapping_df. Expected at least one of: ensg, hgnc_id, hgnc_symbol, entrez.")
|
|
|
813
|
|
|
814 # map source/target to actual dataframe column names (allow user-specified source/target keys)
|
|
|
815 # normalize input args
|
|
|
816 src_key = source_nomenclature.strip().lower()
|
|
|
817 tgt_key = target_nomenclature.strip().lower()
|
|
|
818
|
|
|
819 # try to find the actual column names for requested keys
|
|
|
820 col_for_src = None
|
|
|
821 col_for_tgt = None
|
|
|
822 # first, try exact match
|
|
|
823 for k, actual in chosen.items():
|
|
|
824 if k == src_key:
|
|
|
825 col_for_src = actual
|
|
|
826 if k == tgt_key:
|
|
|
827 col_for_tgt = actual
|
|
|
828
|
|
|
829 # if not found, try mapping common names
|
|
|
830 if col_for_src is None:
|
|
|
831 possible_src_names = {k: v for k, v in chosen.items()}
|
|
|
832 # try to match by contained substring
|
|
|
833 for k, actual in possible_src_names.items():
|
|
|
834 if src_key in k:
|
|
|
835 col_for_src = actual
|
|
|
836 break
|
|
|
837
|
|
|
838 if col_for_tgt is None:
|
|
|
839 for k, actual in chosen.items():
|
|
|
840 if tgt_key in k:
|
|
|
841 col_for_tgt = actual
|
|
|
842 break
|
|
|
843
|
|
|
844 if col_for_src is None:
|
|
|
845 raise ValueError(f"Source column for '{source_nomenclature}' not found in mapping dataframe.")
|
|
|
846 if col_for_tgt is None:
|
|
|
847 raise ValueError(f"Target column for '{target_nomenclature}' not found in mapping dataframe.")
|
|
|
848
|
|
|
849 model_source_genes = { _normalize_gene_id(g.id) for g in model.genes }
|
|
|
850 logger.info(f"Filtering mapping to {len(model_source_genes)} source genes present in model (normalized).")
|
|
|
851
|
|
|
852 tmp_map = mapping_df[[col_for_src, col_for_tgt]].dropna().copy()
|
|
|
853 tmp_map[col_for_src + "_norm"] = tmp_map[col_for_src].astype(str).map(_normalize_gene_id)
|
|
|
854
|
|
|
855 filtered_map = tmp_map[tmp_map[col_for_src + "_norm"].isin(model_source_genes)].copy()
|
|
|
856
|
|
|
857 if filtered_map.empty:
|
|
|
858 logger.warning("No mapping rows correspond to source genes present in the model after filtering. Proceeding with empty mapping (no translation will occur).")
|
|
|
859
|
|
455
|
860 if not allow_many_to_one:
|
|
|
861 _validate_target_uniqueness(filtered_map, col_for_src, col_for_tgt, model_source_genes=model_source_genes, logger=logger)
|
|
426
|
862
|
|
455
|
863 # Crea il mapping
|
|
426
|
864 gene_mapping = _create_gene_mapping(filtered_map, col_for_src, col_for_tgt, logger)
|
|
|
865
|
|
|
866 # copy model
|
|
|
867 model_copy = model.copy()
|
|
|
868
|
|
|
869 # statistics
|
|
493
|
870 stats = {'translated': 0, 'one_to_one': 0, 'one_to_many': 0, 'not_found': 0, 'simplified_gprs': 0, 'flattened_or_gprs': 0}
|
|
426
|
871 unmapped = []
|
|
|
872 multi = []
|
|
490
|
873
|
|
|
874 # Dictionary to store translation issues per reaction
|
|
|
875 reaction_translation_issues = {}
|
|
426
|
876
|
|
|
877 original_genes = {g.id for g in model_copy.genes}
|
|
|
878 logger.info(f"Original genes count: {len(original_genes)}")
|
|
|
879
|
|
|
880 # translate GPRs
|
|
|
881 for rxn in model_copy.reactions:
|
|
|
882 gpr = rxn.gene_reaction_rule
|
|
|
883 if gpr and gpr.strip():
|
|
490
|
884 new_gpr, rxn_issues = _translate_gpr(gpr, gene_mapping, stats, unmapped, multi, logger, track_issues=True)
|
|
|
885 if rxn_issues:
|
|
|
886 reaction_translation_issues[rxn.id] = rxn_issues
|
|
|
887
|
|
426
|
888 if new_gpr != gpr:
|
|
493
|
889 # Check if this GPR has translation issues and contains only OR operators
|
|
|
890 if rxn_issues and _is_or_only_expression(new_gpr):
|
|
|
891 # Flatten the GPR: remove parentheses and create set of unique genes
|
|
|
892 flattened_gpr = _flatten_or_only_gpr(new_gpr)
|
|
|
893 if flattened_gpr != new_gpr:
|
|
|
894 stats['flattened_or_gprs'] += 1
|
|
|
895 logger.debug(f"Flattened OR-only GPR with issues for {rxn.id}: '{new_gpr}' -> '{flattened_gpr}'")
|
|
|
896 new_gpr = flattened_gpr
|
|
|
897
|
|
455
|
898 simplified_gpr = _simplify_boolean_expression(new_gpr)
|
|
|
899 if simplified_gpr != new_gpr:
|
|
|
900 stats['simplified_gprs'] += 1
|
|
|
901 logger.debug(f"Simplified GPR for {rxn.id}: '{new_gpr}' -> '{simplified_gpr}'")
|
|
|
902 rxn.gene_reaction_rule = simplified_gpr
|
|
|
903 logger.debug(f"Reaction {rxn.id}: '{gpr}' -> '{simplified_gpr}'")
|
|
426
|
904
|
|
|
905 # update model genes based on new GPRs
|
|
|
906 _update_model_genes(model_copy, logger)
|
|
|
907
|
|
|
908 # final logging
|
|
|
909 _log_translation_statistics(stats, unmapped, multi, original_genes, model_copy.genes, logger)
|
|
|
910
|
|
|
911 logger.info("Translation finished")
|
|
490
|
912 return model_copy, reaction_translation_issues
|
|
426
|
913
|
|
|
914
|
|
|
915 # ---------- helper functions ----------
|
|
|
916 def _create_gene_mapping(mapping_df, source_col: str, target_col: str, logger: logging.Logger) -> Dict[str, List[str]]:
|
|
|
917 """
|
|
|
918 Build mapping dict: source_id -> list of target_ids
|
|
|
919 Normalizes IDs (removes prefixes like 'HGNC:' etc).
|
|
|
920 """
|
|
|
921 df = mapping_df[[source_col, target_col]].dropna().copy()
|
|
|
922 # normalize to string
|
|
|
923 df[source_col] = df[source_col].astype(str).map(_normalize_gene_id)
|
|
|
924 df[target_col] = df[target_col].astype(str).str.strip()
|
|
|
925
|
|
|
926 df = df.drop_duplicates()
|
|
|
927
|
|
|
928 logger.info(f"Creating mapping from {len(df)} rows")
|
|
|
929
|
|
|
930 mapping = defaultdict(list)
|
|
|
931 for _, row in df.iterrows():
|
|
|
932 s = row[source_col]
|
|
|
933 t = row[target_col]
|
|
|
934 if t not in mapping[s]:
|
|
|
935 mapping[s].append(t)
|
|
|
936
|
|
|
937 # stats
|
|
|
938 one_to_one = sum(1 for v in mapping.values() if len(v) == 1)
|
|
|
939 one_to_many = sum(1 for v in mapping.values() if len(v) > 1)
|
|
|
940 logger.info(f"Mapping: {len(mapping)} source keys, {one_to_one} 1:1, {one_to_many} 1:many")
|
|
|
941 return dict(mapping)
|
|
|
942
|
|
|
943
|
|
|
944 def _translate_gpr(gpr_string: str,
|
|
|
945 gene_mapping: Dict[str, List[str]],
|
|
|
946 stats: Dict[str, int],
|
|
|
947 unmapped_genes: List[str],
|
|
|
948 multi_mapping_genes: List[Tuple[str, List[str]]],
|
|
490
|
949 logger: logging.Logger,
|
|
|
950 track_issues: bool = False) -> Union[str, Tuple[str, str]]:
|
|
426
|
951 """
|
|
|
952 Translate genes inside a GPR string using gene_mapping.
|
|
490
|
953 Returns new GPR string, and optionally translation issues if track_issues=True.
|
|
426
|
954 """
|
|
|
955 # Generic token pattern: letters, digits, :, _, -, ., (captures HGNC:1234, ENSG000..., symbols)
|
|
|
956 token_pattern = r'\b[A-Za-z0-9:_.-]+\b'
|
|
|
957 tokens = re.findall(token_pattern, gpr_string)
|
|
|
958
|
|
|
959 logical = {'and', 'or', 'AND', 'OR', '(', ')'}
|
|
|
960 tokens = [t for t in tokens if t not in logical]
|
|
|
961
|
|
|
962 new_gpr = gpr_string
|
|
490
|
963 issues = []
|
|
426
|
964
|
|
|
965 for token in sorted(set(tokens), key=lambda x: -len(x)): # longer tokens first to avoid partial replacement
|
|
|
966 norm = _normalize_gene_id(token)
|
|
|
967 if norm in gene_mapping:
|
|
|
968 targets = gene_mapping[norm]
|
|
|
969 stats['translated'] += 1
|
|
|
970 if len(targets) == 1:
|
|
|
971 stats['one_to_one'] += 1
|
|
|
972 replacement = targets[0]
|
|
|
973 else:
|
|
|
974 stats['one_to_many'] += 1
|
|
|
975 multi_mapping_genes.append((token, targets))
|
|
|
976 replacement = "(" + " or ".join(targets) + ")"
|
|
490
|
977 if track_issues:
|
|
|
978 issues.append(f"{token} -> {' or '.join(targets)}")
|
|
426
|
979
|
|
|
980 pattern = r'\b' + re.escape(token) + r'\b'
|
|
|
981 new_gpr = re.sub(pattern, replacement, new_gpr)
|
|
|
982 else:
|
|
|
983 stats['not_found'] += 1
|
|
|
984 if token not in unmapped_genes:
|
|
|
985 unmapped_genes.append(token)
|
|
|
986 logger.debug(f"Token not found in mapping (left as-is): {token}")
|
|
|
987
|
|
490
|
988 # Check for many-to-one cases (multiple source genes mapping to same target)
|
|
|
989 if track_issues:
|
|
|
990 # Build reverse mapping to detect many-to-one cases from original tokens
|
|
|
991 original_to_target = {}
|
|
|
992
|
|
|
993 for orig_token in tokens:
|
|
|
994 norm = _normalize_gene_id(orig_token)
|
|
|
995 if norm in gene_mapping:
|
|
|
996 targets = gene_mapping[norm]
|
|
|
997 for target in targets:
|
|
|
998 if target not in original_to_target:
|
|
|
999 original_to_target[target] = []
|
|
|
1000 if orig_token not in original_to_target[target]:
|
|
|
1001 original_to_target[target].append(orig_token)
|
|
|
1002
|
|
|
1003 # Identify many-to-one mappings in this specific GPR
|
|
|
1004 for target, original_genes in original_to_target.items():
|
|
|
1005 if len(original_genes) > 1:
|
|
|
1006 issues.append(f"{' or '.join(original_genes)} -> {target}")
|
|
|
1007
|
|
|
1008 issue_text = "; ".join(issues) if issues else ""
|
|
|
1009
|
|
|
1010 if track_issues:
|
|
|
1011 return new_gpr, issue_text
|
|
|
1012 else:
|
|
|
1013 return new_gpr
|
|
426
|
1014
|
|
|
1015
|
|
|
1016 def _update_model_genes(model: 'cobra.Model', logger: logging.Logger):
|
|
|
1017 """
|
|
|
1018 Rebuild model.genes from gene_reaction_rule content.
|
|
|
1019 Removes genes not referenced and adds missing ones.
|
|
|
1020 """
|
|
|
1021 # collect genes in GPRs
|
|
|
1022 gene_pattern = r'\b[A-Za-z0-9:_.-]+\b'
|
|
|
1023 logical = {'and', 'or', 'AND', 'OR', '(', ')'}
|
|
|
1024 genes_in_gpr: Set[str] = set()
|
|
|
1025
|
|
|
1026 for rxn in model.reactions:
|
|
|
1027 gpr = rxn.gene_reaction_rule
|
|
|
1028 if gpr and gpr.strip():
|
|
|
1029 toks = re.findall(gene_pattern, gpr)
|
|
|
1030 toks = [t for t in toks if t not in logical]
|
|
|
1031 # normalize IDs consistent with mapping normalization
|
|
|
1032 toks = [_normalize_gene_id(t) for t in toks]
|
|
|
1033 genes_in_gpr.update(toks)
|
|
|
1034
|
|
|
1035 # existing gene ids
|
|
|
1036 existing = {g.id for g in model.genes}
|
|
|
1037
|
|
|
1038 # remove obsolete genes
|
|
|
1039 to_remove = [gid for gid in existing if gid not in genes_in_gpr]
|
|
|
1040 removed = 0
|
|
|
1041 for gid in to_remove:
|
|
|
1042 try:
|
|
|
1043 gene_obj = model.genes.get_by_id(gid)
|
|
|
1044 model.genes.remove(gene_obj)
|
|
|
1045 removed += 1
|
|
|
1046 except Exception:
|
|
|
1047 # safe-ignore
|
|
|
1048 pass
|
|
|
1049
|
|
|
1050 # add new genes
|
|
|
1051 added = 0
|
|
|
1052 for gid in genes_in_gpr:
|
|
|
1053 if gid not in existing:
|
|
|
1054 new_gene = cobra.Gene(gid)
|
|
|
1055 try:
|
|
|
1056 model.genes.add(new_gene)
|
|
|
1057 except Exception:
|
|
|
1058 # fallback: if model.genes doesn't support add, try append or model.add_genes
|
|
|
1059 try:
|
|
|
1060 model.genes.append(new_gene)
|
|
|
1061 except Exception:
|
|
|
1062 try:
|
|
|
1063 model.add_genes([new_gene])
|
|
|
1064 except Exception:
|
|
|
1065 logger.warning(f"Could not add gene object for {gid}")
|
|
|
1066 added += 1
|
|
|
1067
|
|
|
1068 logger.info(f"Model genes updated: removed {removed}, added {added}")
|
|
|
1069
|
|
|
1070
|
|
|
1071 def _log_translation_statistics(stats: Dict[str, int],
|
|
|
1072 unmapped_genes: List[str],
|
|
|
1073 multi_mapping_genes: List[Tuple[str, List[str]]],
|
|
|
1074 original_genes: Set[str],
|
|
|
1075 final_genes,
|
|
|
1076 logger: logging.Logger):
|
|
|
1077 logger.info("=== TRANSLATION STATISTICS ===")
|
|
|
1078 logger.info(f"Translated: {stats.get('translated', 0)} (1:1 = {stats.get('one_to_one', 0)}, 1:many = {stats.get('one_to_many', 0)})")
|
|
|
1079 logger.info(f"Not found tokens: {stats.get('not_found', 0)}")
|
|
455
|
1080 logger.info(f"Simplified GPRs: {stats.get('simplified_gprs', 0)}")
|
|
493
|
1081 logger.info(f"Flattened OR-only GPRs with issues: {stats.get('flattened_or_gprs', 0)}")
|
|
426
|
1082
|
|
|
1083 final_ids = {g.id for g in final_genes}
|
|
|
1084 logger.info(f"Genes in model: {len(original_genes)} -> {len(final_ids)}")
|
|
|
1085
|
|
|
1086 if unmapped_genes:
|
|
|
1087 logger.warning(f"Unmapped tokens ({len(unmapped_genes)}): {', '.join(unmapped_genes[:20])}{(' ...' if len(unmapped_genes)>20 else '')}")
|
|
|
1088 if multi_mapping_genes:
|
|
|
1089 logger.info(f"Multi-mapping examples ({len(multi_mapping_genes)}):")
|
|
|
1090 for orig, targets in multi_mapping_genes[:10]:
|
|
490
|
1091 logger.info(f" {orig} -> {', '.join(targets)}")
|
|
493
|
1092
|
|
|
1093 # Log summary of flattened GPRs if any
|
|
|
1094 if stats.get('flattened_or_gprs', 0) > 0:
|
|
|
1095 logger.info(f"Flattened {stats['flattened_or_gprs']} OR-only GPRs that had translation issues (removed parentheses, created unique gene sets)")
|
|
490
|
1096
|
|
|
1097 |
