comparison COBRAxy/ras_to_bounds_beta.py @ 414:5086145cfb96 draft

Uploaded

413:7a3ccf066b2c

from cobra import Model, Reaction, Metabolite
import re
import sys
import csv
from joblib import Parallel, delayed, cpu_count

# , medium

################################# process args ###############################
def process_args(args :List[str] = None) -> argparse.Namespace:

            if upper_bound!=0 and lower_bound!=0:
                new_bounds.loc[reaction, "lower_bound"] = valMin
                new_bounds.loc[reaction, "upper_bound"] = valMax
    return new_bounds

def save_model(model, filename, output_folder, file_format='csv'):
    """
    Save a COBRA model to file in the specified format.
    
    Args:

    try:
        if file_format == 'tabular' or file_format == 'csv':
            # Special handling for tabular format using utils functions
            filepath = os.path.join(output_folder, f"{filename}.csv")
            
            rules = utils.generate_rules(model, asParsed = False)
            reactions = utils.generate_reactions(model, asParsed = False)
            bounds = utils.generate_bounds(model)
            medium = utils.get_medium(model)
            
            try:
                compartments = utils.generate_compartments(model)
            except:
                compartments = None

        modified_model = apply_bounds_to_model(model, new_bounds)
        save_model(modified_model, cellName, save_models_path, save_models_format)
    
    pass

def generate_bounds(model: cobra.Model, ras=None, output_folder='output/', save_models=False, save_models_path='saved_models/', save_models_format='csv') -> pd.DataFrame:
    """
    Generate reaction bounds for a metabolic model based on medium conditions and optional RAS adjustments.
    
    Args:
        model (cobra.Model): The metabolic model for which bounds will be generated.

    print("\n=== VALIDAZIONE MODELLO ===")
    for key, value in validation.items():
        print(f"{key}: {value}")

    if(ARGS.ras_selector == True):
        generate_bounds(model, ras=ras_combined, output_folder=ARGS.output_path,
                       save_models=ARGS.save_models, save_models_path=ARGS.save_models_path,
                       save_models_format=ARGS.save_models_format)
        class_assignments.to_csv(ARGS.cell_class, sep='\t', index=False)
    else:
        generate_bounds(model, output_folder=ARGS.output_path,
                       save_models=ARGS.save_models, save_models_path=ARGS.save_models_path,
                       save_models_format=ARGS.save_models_format)

    pass
        

414:5086145cfb96

from cobra import Model, Reaction, Metabolite
import re
import sys
import csv
from joblib import Parallel, delayed, cpu_count
import utils.rule_parsing  as rulesUtils

# , medium

################################# process args ###############################
def process_args(args :List[str] = None) -> argparse.Namespace:

            if upper_bound!=0 and lower_bound!=0:
                new_bounds.loc[reaction, "lower_bound"] = valMin
                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'):
    """
    Save a COBRA model to file in the specified format.
    
    Args:

    try:
        if file_format == 'tabular' or file_format == 'csv':
            # 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)
            
            try:
                compartments = utils.generate_compartments(model)
            except:
                compartments = None

        modified_model = apply_bounds_to_model(model, new_bounds)
        save_model(modified_model, cellName, save_models_path, save_models_format)
    
    pass

def generate_bounds_model(model: cobra.Model, ras=None, output_folder='output/', save_models=False, save_models_path='saved_models/', save_models_format='csv') -> pd.DataFrame:
    """
    Generate reaction bounds for a metabolic model based on medium conditions and optional RAS adjustments.
    
    Args:
        model (cobra.Model): The metabolic model for which bounds will be generated.

    print("\n=== VALIDAZIONE MODELLO ===")
    for key, value in validation.items():
        print(f"{key}: {value}")

    if(ARGS.ras_selector == True):
        generate_bounds_model(model, ras=ras_combined, output_folder=ARGS.output_path,
                       save_models=ARGS.save_models, save_models_path=ARGS.save_models_path,
                       save_models_format=ARGS.save_models_format)
        class_assignments.to_csv(ARGS.cell_class, sep='\t', index=False)
    else:
        generate_bounds_model(model, output_folder=ARGS.output_path,
                       save_models=ARGS.save_models, save_models_path=ARGS.save_models_path,
                       save_models_format=ARGS.save_models_format)

    pass