--- a/COBRAxy/custom_data_generator_beta.py	Mon Sep 08 22:04:46 2025 +0000
+++ b/COBRAxy/custom_data_generator_beta.py	Tue Sep 09 07:36:30 2025 +0000
@@ -8,6 +8,7 @@
 import utils.rule_parsing  as rulesUtils
 from typing import Optional, Tuple, Union, List, Dict
 import utils.reaction_parsing as reactionUtils
+import utils.model_utils as modelUtils
 
 ARGS : argparse.Namespace
 def process_args(args: List[str] = None) -> argparse.Namespace:
@@ -72,126 +73,6 @@
     raise utils.DataErr(file_path,
         f"Formato \"{file_path.ext}\" non riconosciuto, sono supportati solo file JSON e XML")
 
-################################- DATA GENERATION -################################
-ReactionId = str
-def generate_rules(model: cobra.Model, *, asParsed = True) -> Union[Dict[ReactionId, rulesUtils.OpList], Dict[ReactionId, str]]:
-    """
-    Generates a dictionary mapping reaction ids to rules from the model.
-
-    Args:
-        model : the model to derive data from.
-        asParsed : if True parses the rules to an optimized runtime format, otherwise leaves them as strings.
-
-    Returns:
-        Dict[ReactionId, rulesUtils.OpList] : the generated dictionary of parsed rules.
-        Dict[ReactionId, str] : the generated dictionary of raw rules.
-    """
-    # Is the below approach convoluted? yes
-    # Ok but is it inefficient? probably
-    # Ok but at least I don't have to repeat the check at every rule (I'm clinically insane)
-    _ruleGetter   =  lambda reaction : reaction.gene_reaction_rule
-    ruleExtractor = (lambda reaction :
-        rulesUtils.parseRuleToNestedList(_ruleGetter(reaction))) if asParsed else _ruleGetter
-
-    return {
-        reaction.id : ruleExtractor(reaction)
-        for reaction in model.reactions
-        if reaction.gene_reaction_rule }
-
-def generate_reactions(model :cobra.Model, *, asParsed = True) -> Dict[ReactionId, str]:
-    """
-    Generates a dictionary mapping reaction ids to reaction formulas from the model.
-
-    Args:
-        model : the model to derive data from.
-        asParsed : if True parses the reactions to an optimized runtime format, otherwise leaves them as they are.
-
-    Returns:
-        Dict[ReactionId, str] : the generated dictionary.
-    """
-
-    unparsedReactions = {
-        reaction.id : reaction.reaction
-        for reaction in model.reactions
-        if reaction.reaction 
-    }
-
-    if not asParsed: return unparsedReactions
-    
-    return reactionUtils.create_reaction_dict(unparsedReactions)
-
-def get_medium(model:cobra.Model) -> pd.DataFrame:
-    trueMedium=[]
-    for r in model.reactions:
-        positiveCoeff=0
-        for m in r.metabolites:
-            if r.get_coefficient(m.id)>0:
-                positiveCoeff=1;
-        if (positiveCoeff==0 and r.lower_bound<0):
-            trueMedium.append(r.id)
-
-    df_medium = pd.DataFrame()
-    df_medium["reaction"] = trueMedium
-    return df_medium
-
-def generate_bounds(model:cobra.Model) -> pd.DataFrame:
-
-    rxns = []
-    for reaction in model.reactions:
-        rxns.append(reaction.id)
-
-    bounds = pd.DataFrame(columns = ["lower_bound", "upper_bound"], index=rxns)
-
-    for reaction in model.reactions:
-        bounds.loc[reaction.id] = [reaction.lower_bound, reaction.upper_bound]
-    return bounds
-
-
-
-def generate_compartments(model: cobra.Model) -> pd.DataFrame:
-    """
-    Generates a DataFrame containing compartment information for each reaction.
-    Creates columns for each compartment position (Compartment_1, Compartment_2, etc.)
-    
-    Args:
-        model: the COBRA model to extract compartment data from.
-        
-    Returns:
-        pd.DataFrame: DataFrame with ReactionID and compartment columns
-    """
-    pathway_data = []
-
-    # First pass: determine the maximum number of pathways any reaction has
-    max_pathways = 0
-    reaction_pathways = {}
-
-    for reaction in model.reactions:
-        # Get unique pathways from all metabolites in the reaction
-        if type(reaction.annotation['pathways']) == list:
-            reaction_pathways[reaction.id] = reaction.annotation['pathways']
-            max_pathways = max(max_pathways, len(reaction.annotation['pathways']))
-        else:
-            reaction_pathways[reaction.id] = [reaction.annotation['pathways']]
-
-    # Create column names for pathways
-    pathway_columns = [f"Pathway_{i+1}" for i in range(max_pathways)]
-
-    # Second pass: create the data
-    for reaction_id, pathways in reaction_pathways.items():
-        row = {"ReactionID": reaction_id}
-        
-        # Fill pathway columns
-        for i in range(max_pathways):
-            col_name = pathway_columns[i]
-            if i < len(pathways):
-                row[col_name] = pathways[i]
-            else:
-                row[col_name] = None  # or "" if you prefer empty strings
-
-        pathway_data.append(row)
-
-    return pd.DataFrame(pathway_data)
-
 
 ###############################- FILE SAVING -################################
 def save_as_csv_filePath(data :dict, file_path :utils.FilePath, fieldNames :Tuple[str, str]) -> None:
@@ -296,12 +177,12 @@
         model = utils.convert_genes(model, ARGS.gene_format.replace("HGNC_", "HGNC "))
 
     # generate data
-    rules = generate_rules(model, asParsed = False)
-    reactions = generate_reactions(model, asParsed = False)
-    bounds = generate_bounds(model)
-    medium = get_medium(model)
+    rules = modelUtils.generate_rules(model, asParsed = False)
+    reactions = modelUtils.generate_reactions(model, asParsed = False)
+    bounds = modelUtils.generate_bounds(model)
+    medium = modelUtils.get_medium(model)
     if ARGS.name == "ENGRO2":
-        compartments = generate_compartments(model)
+        compartments = modelUtils.generate_compartments(model)
 
     df_rules = pd.DataFrame(list(rules.items()), columns = ["ReactionID", "Rule"])
     df_reactions = pd.DataFrame(list(reactions.items()), columns = ["ReactionID", "Reaction"])

--- a/COBRAxy/ras_to_bounds_beta.py	Mon Sep 08 22:04:46 2025 +0000
+++ b/COBRAxy/ras_to_bounds_beta.py	Tue Sep 09 07:36:30 2025 +0000
@@ -12,6 +12,7 @@
 from joblib import Parallel, delayed, cpu_count
 import utils.rule_parsing  as rulesUtils
 import utils.reaction_parsing as reactionUtils
+import utils.model_utils as modelUtils
 
 # , medium
 
@@ -151,125 +152,6 @@
                 new_bounds.loc[reaction, "upper_bound"] = valMax
     return new_bounds
 
-################################- DATA GENERATION -################################
-ReactionId = str
-def generate_rules(model: cobra.Model, *, asParsed = True) -> Union[Dict[ReactionId, rulesUtils.OpList], Dict[ReactionId, str]]:
-    """
-    Generates a dictionary mapping reaction ids to rules from the model.
-
-    Args:
-        model : the model to derive data from.
-        asParsed : if True parses the rules to an optimized runtime format, otherwise leaves them as strings.
-
-    Returns:
-        Dict[ReactionId, rulesUtils.OpList] : the generated dictionary of parsed rules.
-        Dict[ReactionId, str] : the generated dictionary of raw rules.
-    """
-    # Is the below approach convoluted? yes
-    # Ok but is it inefficient? probably
-    # Ok but at least I don't have to repeat the check at every rule (I'm clinically insane)
-    _ruleGetter   =  lambda reaction : reaction.gene_reaction_rule
-    ruleExtractor = (lambda reaction :
-        rulesUtils.parseRuleToNestedList(_ruleGetter(reaction))) if asParsed else _ruleGetter
-
-    return {
-        reaction.id : ruleExtractor(reaction)
-        for reaction in model.reactions
-        if reaction.gene_reaction_rule }
-
-def generate_reactions(model :cobra.Model, *, asParsed = True) -> Dict[ReactionId, str]:
-    """
-    Generates a dictionary mapping reaction ids to reaction formulas from the model.
-
-    Args:
-        model : the model to derive data from.
-        asParsed : if True parses the reactions to an optimized runtime format, otherwise leaves them as they are.
-
-    Returns:
-        Dict[ReactionId, str] : the generated dictionary.
-    """
-
-    unparsedReactions = {
-        reaction.id : reaction.reaction
-        for reaction in model.reactions
-        if reaction.reaction 
-    }
-
-    if not asParsed: return unparsedReactions
-    
-    return reactionUtils.create_reaction_dict(unparsedReactions)
-
-def get_medium(model:cobra.Model) -> pd.DataFrame:
-    trueMedium=[]
-    for r in model.reactions:
-        positiveCoeff=0
-        for m in r.metabolites:
-            if r.get_coefficient(m.id)>0:
-                positiveCoeff=1;
-        if (positiveCoeff==0 and r.lower_bound<0):
-            trueMedium.append(r.id)
-
-    df_medium = pd.DataFrame()
-    df_medium["reaction"] = trueMedium
-    return df_medium
-
-def generate_bounds(model:cobra.Model) -> pd.DataFrame:
-
-    rxns = []
-    for reaction in model.reactions:
-        rxns.append(reaction.id)
-
-    bounds = pd.DataFrame(columns = ["lower_bound", "upper_bound"], index=rxns)
-
-    for reaction in model.reactions:
-        bounds.loc[reaction.id] = [reaction.lower_bound, reaction.upper_bound]
-    return bounds
-
-
-
-def generate_compartments(model: cobra.Model) -> pd.DataFrame:
-    """
-    Generates a DataFrame containing compartment information for each reaction.
-    Creates columns for each compartment position (Compartment_1, Compartment_2, etc.)
-    
-    Args:
-        model: the COBRA model to extract compartment data from.
-        
-    Returns:
-        pd.DataFrame: DataFrame with ReactionID and compartment columns
-    """
-    pathway_data = []
-
-    # First pass: determine the maximum number of pathways any reaction has
-    max_pathways = 0
-    reaction_pathways = {}
-
-    for reaction in model.reactions:
-        # Get unique pathways from all metabolites in the reaction
-        if type(reaction.annotation['pathways']) == list:
-            reaction_pathways[reaction.id] = reaction.annotation['pathways']
-            max_pathways = max(max_pathways, len(reaction.annotation['pathways']))
-        else:
-            reaction_pathways[reaction.id] = [reaction.annotation['pathways']]
-
-    # Create column names for pathways
-    pathway_columns = [f"Pathway_{i+1}" for i in range(max_pathways)]
-
-    # Second pass: create the data
-    for reaction_id, pathways in reaction_pathways.items():
-        row = {"ReactionID": reaction_id}
-        
-        # Fill pathway columns
-        for i in range(max_pathways):
-            col_name = pathway_columns[i]
-            if i < len(pathways):
-                row[col_name] = pathways[i]
-            else:
-                row[col_name] = None  # or "" if you prefer empty strings
-
-        pathway_data.append(row)
-
-    return pd.DataFrame(pathway_data)
 
 def save_model(model, filename, output_folder, file_format='csv'):
     """
@@ -292,13 +174,13 @@
             # Special handling for tabular format using utils functions
             filepath = os.path.join(output_folder, f"{filename}.csv")
             
-            rules = generate_rules(model, asParsed = False)
-            reactions = generate_reactions(model, asParsed = False)
-            bounds = generate_bounds(model)
-            medium = get_medium(model)
+            rules = modelUtils.generate_rules(model, asParsed = False)
+            reactions = modelUtils.generate_reactions(model, asParsed = False)
+            bounds = modelUtils.generate_bounds(model)
+            medium = modelUtils.get_medium(model)
             
             try:
-                compartments = utils.generate_compartments(model)
+                compartments = modelUtils.generate_compartments(model)
             except:
                 compartments = None
 

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/COBRAxy/utils/model_utils.py	Tue Sep 09 07:36:30 2025 +0000
@@ -0,0 +1,129 @@
+import os
+import csv
+import cobra
+import pickle
+import argparse
+import pandas as pd
+from typing import Optional, Tuple, Union, List, Dict
+import utils.general_utils as utils
+import utils.rule_parsing  as rulesUtils
+
+################################- DATA GENERATION -################################
+ReactionId = str
+def generate_rules(model: cobra.Model, *, asParsed = True) -> Union[Dict[ReactionId, rulesUtils.OpList], Dict[ReactionId, str]]:
+    """
+    Generates a dictionary mapping reaction ids to rules from the model.
+
+    Args:
+        model : the model to derive data from.
+        asParsed : if True parses the rules to an optimized runtime format, otherwise leaves them as strings.
+
+    Returns:
+        Dict[ReactionId, rulesUtils.OpList] : the generated dictionary of parsed rules.
+        Dict[ReactionId, str] : the generated dictionary of raw rules.
+    """
+    # Is the below approach convoluted? yes
+    # Ok but is it inefficient? probably
+    # Ok but at least I don't have to repeat the check at every rule (I'm clinically insane)
+    _ruleGetter   =  lambda reaction : reaction.gene_reaction_rule
+    ruleExtractor = (lambda reaction :
+        rulesUtils.parseRuleToNestedList(_ruleGetter(reaction))) if asParsed else _ruleGetter
+
+    return {
+        reaction.id : ruleExtractor(reaction)
+        for reaction in model.reactions
+        if reaction.gene_reaction_rule }
+
+def generate_reactions(model :cobra.Model, *, asParsed = True) -> Dict[ReactionId, str]:
+    """
+    Generates a dictionary mapping reaction ids to reaction formulas from the model.
+
+    Args:
+        model : the model to derive data from.
+        asParsed : if True parses the reactions to an optimized runtime format, otherwise leaves them as they are.
+
+    Returns:
+        Dict[ReactionId, str] : the generated dictionary.
+    """
+
+    unparsedReactions = {
+        reaction.id : reaction.reaction
+        for reaction in model.reactions
+        if reaction.reaction 
+    }
+
+    if not asParsed: return unparsedReactions
+    
+    return reactionUtils.create_reaction_dict(unparsedReactions)
+
+def get_medium(model:cobra.Model) -> pd.DataFrame:
+    trueMedium=[]
+    for r in model.reactions:
+        positiveCoeff=0
+        for m in r.metabolites:
+            if r.get_coefficient(m.id)>0:
+                positiveCoeff=1;
+        if (positiveCoeff==0 and r.lower_bound<0):
+            trueMedium.append(r.id)
+
+    df_medium = pd.DataFrame()
+    df_medium["reaction"] = trueMedium
+    return df_medium
+
+def generate_bounds(model:cobra.Model) -> pd.DataFrame:
+
+    rxns = []
+    for reaction in model.reactions:
+        rxns.append(reaction.id)
+
+    bounds = pd.DataFrame(columns = ["lower_bound", "upper_bound"], index=rxns)
+
+    for reaction in model.reactions:
+        bounds.loc[reaction.id] = [reaction.lower_bound, reaction.upper_bound]
+    return bounds
+
+
+
+def generate_compartments(model: cobra.Model) -> pd.DataFrame:
+    """
+    Generates a DataFrame containing compartment information for each reaction.
+    Creates columns for each compartment position (Compartment_1, Compartment_2, etc.)
+    
+    Args:
+        model: the COBRA model to extract compartment data from.
+        
+    Returns:
+        pd.DataFrame: DataFrame with ReactionID and compartment columns
+    """
+    pathway_data = []
+
+    # First pass: determine the maximum number of pathways any reaction has
+    max_pathways = 0
+    reaction_pathways = {}
+
+    for reaction in model.reactions:
+        # Get unique pathways from all metabolites in the reaction
+        if type(reaction.annotation['pathways']) == list:
+            reaction_pathways[reaction.id] = reaction.annotation['pathways']
+            max_pathways = max(max_pathways, len(reaction.annotation['pathways']))
+        else:
+            reaction_pathways[reaction.id] = [reaction.annotation['pathways']]
+
+    # Create column names for pathways
+    pathway_columns = [f"Pathway_{i+1}" for i in range(max_pathways)]
+
+    # Second pass: create the data
+    for reaction_id, pathways in reaction_pathways.items():
+        row = {"ReactionID": reaction_id}
+        
+        # Fill pathway columns
+        for i in range(max_pathways):
+            col_name = pathway_columns[i]
+            if i < len(pathways):
+                row[col_name] = pathways[i]
+            else:
+                row[col_name] = None  # or "" if you prefer empty strings
+
+        pathway_data.append(row)
+
+    return pd.DataFrame(pathway_data)
\ No newline at end of file