Mercurial > repos > bimib > cobraxy

comparison COBRAxy/custom_data_generator.py @ 343:4165326259cc draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author francesco_lapi
date Thu, 04 Sep 2025 22:09:42 +0000
parents 3fca9b568faf
children 25862d166f88
comparison
equal deleted inserted replaced
342:057909a104d9 343:4165326259cc
8 import utils.rule_parsing as rulesUtils 8 import utils.rule_parsing as rulesUtils
9 from typing import Optional, Tuple, Union, List, Dict 9 from typing import Optional, Tuple, Union, List, Dict
10 import utils.reaction_parsing as reactionUtils 10 import utils.reaction_parsing as reactionUtils
11 11
12 ARGS : argparse.Namespace 12 ARGS : argparse.Namespace
13 def process_args(args:List[str] = None) -> argparse.Namespace: 13 def process_args(args: List[str] = None) -> argparse.Namespace:
14 """ 14 """
15 Interfaces the script of a module with its frontend, making the user's choices for 15 Parse command-line arguments for CustomDataGenerator.
16 various parameters available as values in code. 16 """
17 17
18 Args:
19 args : Always obtained (in file) from sys.argv
20
21 Returns:
22 Namespace : An object containing the parsed arguments
23 """
24 parser = argparse.ArgumentParser( 18 parser = argparse.ArgumentParser(
25 usage = "%(prog)s [options]", 19 usage="%(prog)s [options]",
26 description = "generate custom data from a given model") 20 description="Generate custom data from a given model"
27 21 )
28 parser.add_argument("-ol", "--out_log", type = str, required = True, help = "Output log") 22
29 23 parser.add_argument("--out_log", type=str, required=True,
30 parser.add_argument("-orules", "--out_rules", type = str, required = True, help = "Output rules") 24 help="Output log file")
31 parser.add_argument("-orxns", "--out_reactions", type = str, required = True, help = "Output reactions") 25 parser.add_argument("--out_data", type=str, required=True,
32 parser.add_argument("-omedium", "--out_medium", type = str, required = True, help = "Output medium") 26 help="Single output dataset (CSV or Excel)")
33 parser.add_argument("-obnds", "--out_bounds", type = str, required = True, help = "Output bounds") 27
34 28 parser.add_argument("--model", type=str,
35 parser.add_argument("-id", "--input", type = str, required = True, help = "Input model") 29 help="Built-in model identifier (e.g., ENGRO2, Recon, HMRcore)")
36 parser.add_argument("-mn", "--name", type = str, required = True, help = "Input model name") 30 parser.add_argument("--input", type=str,
37 # ^ I need this because galaxy converts my files into .dat but I need to know what extension they were in 31 help="Custom model file (JSON or XML)")
38 parser.add_argument('-idop', '--output_path', type = str, default='result', help = 'output path for maps') 32 parser.add_argument("--name", type=str, required=True,
39 argsNamespace = parser.parse_args(args) 33 help="Model name (default or custom)")
40 # ^ can't get this one to work from xml, there doesn't seem to be a way to get the directory attribute from the collection 34
41 35 parser.add_argument("--medium_selector", type=str, required=True,
42 return argsNamespace 36 help="Medium selection option (default/custom)")
37 parser.add_argument("--medium", type=str,
38 help="Custom medium file if medium_selector=Custom")
39
40 parser.add_argument("--output_format", type=str, choices=["tabular", "xlsx"], required=True,
41 help="Output format: CSV (tabular) or Excel (xlsx)")
42
43 parser.add_argument('-idop', '--output_path', type = str, default='result',
44 help = 'output path for the result files (default: result)')
45
46
47 return parser.parse_args(args)
43 48
44 ################################- INPUT DATA LOADING -################################ 49 ################################- INPUT DATA LOADING -################################
45 def load_custom_model(file_path :utils.FilePath, ext :Optional[utils.FileFormat] = None) -> cobra.Model: 50 def load_custom_model(file_path :utils.FilePath, ext :Optional[utils.FileFormat] = None) -> cobra.Model:
46 """ 51 """
47 Loads a custom model from a file, either in JSON or XML format. 52 Loads a custom model from a file, either in JSON or XML format.
193 # get args from frontend (related xml) 198 # get args from frontend (related xml)
194 global ARGS 199 global ARGS
195 ARGS = process_args(args) 200 ARGS = process_args(args)
196 201
197 # this is the worst thing I've seen so far, congrats to the former MaREA devs for suggesting this! 202 # this is the worst thing I've seen so far, congrats to the former MaREA devs for suggesting this!
198 if os.path.isdir(ARGS.output_path) == False: os.makedirs(ARGS.output_path) 203 if os.path.isdir(ARGS.output_path) == False:
199 204 os.makedirs(ARGS.output_path)
200 # load custom model 205
201 model = load_custom_model( 206 if ARGS.input != "None":
202 utils.FilePath.fromStrPath(ARGS.input), utils.FilePath.fromStrPath(ARGS.name).ext) 207 # load custom model
208 model = load_custom_model(
209 utils.FilePath.fromStrPath(ARGS.input), utils.FilePath.fromStrPath(ARGS.name).ext)
210 else:
211 # load built-in model
212
213 try:
214 model_enum = utils.Model[ARGS.model] # e.g., Model['ENGRO2']
215 except KeyError:
216 raise utils.ArgsErr("model", "one of Recon/ENGRO2/HMRcore/Custom_model", ARGS.model)
217
218 # Load built-in model (Model.getCOBRAmodel uses tool_dir to locate local models)
219 try:
220 model = model_enum.getCOBRAmodel(toolDir='../../COBRAxy')
221 except Exception as e:
222 # Wrap/normalize load errors as DataErr for consistency
223 raise utils.DataErr(ARGS.model, f"failed loading built-in model: {e}")
224
225 # Determine final model name: explicit --name overrides, otherwise use the model id
226 model_name = ARGS.name if ARGS.name else ARGS.model
203 227
204 # generate data 228 # generate data
205 rules = generate_rules(model, asParsed = False) 229 rules = generate_rules(model, asParsed = False)
206 reactions = generate_reactions(model, asParsed = False) 230 reactions = generate_reactions(model, asParsed = False)
207 bounds = generate_bounds(model) 231 bounds = generate_bounds(model)
208 medium = get_medium(model) 232 medium = get_medium(model)
209 233
210 # save files out of collection: path coming from xml 234 df_rules = pd.DataFrame(list(rules.items()), columns = ["ReactionID", "Rule"])
211 save_as_csv(rules, ARGS.out_rules, ("ReactionID", "Rule")) 235 df_reactions = pd.DataFrame(list(reactions.items()), columns = ["ReactionID", "Reaction"])
212 save_as_csv(reactions, ARGS.out_reactions, ("ReactionID", "Reaction")) 236
213 bounds.to_csv(ARGS.out_bounds, sep = '\t') 237 df_bounds = bounds.reset_index().rename(columns = {"index": "ReactionID"})
214 medium.to_csv(ARGS.out_medium, sep = '\t') 238 df_medium = medium.rename(columns = {"reaction": "ReactionID"})
239 df_medium["InMedium"] = True # flag per indicare la presenza nel medium
240
241 merged = df_reactions.merge(df_rules, on = "ReactionID", how = "outer")
242 merged = merged.merge(df_bounds, on = "ReactionID", how = "outer")
243
244 merged = merged.merge(df_medium, on = "ReactionID", how = "left")
245
246 merged["InMedium"] = merged["InMedium"].fillna(False)
247
248 merged = merged.sort_values(by = "InMedium", ascending = False)
249
250 out_file = os.path.join(ARGS.output_path, f"{os.path.basename(ARGS.name).split('.')[0]}_custom_data")
251
252 #merged.to_csv(out_file, sep = '\t', index = False)
253
254
255 ####
256 out_data_path = out_file #ARGS.out_data
257
258 # If Galaxy provided a .dat name, ensure a correct extension according to output_format
259 if ARGS.output_format == "xlsx":
260 if not out_data_path.lower().endswith(".xlsx"):
261 out_data_path = out_data_path + ".xlsx"
262 merged.to_excel(out_data_path, index=False)
263 else:
264 # 'tabular' -> tab-separated, extension .csv is fine and common for Galaxy tabular
265 if not (out_data_path.lower().endswith(".csv") or out_data_path.lower().endswith(".tsv")):
266 out_data_path = out_data_path + ".csv"
267 merged.to_csv(out_data_path, sep="\t", index=False)
268
215 269
216 if __name__ == '__main__': 270 if __name__ == '__main__':
217 main() 271 main()