selectBioModels.py

import os
import re
import pandas as pd
import shutil

# Function to search BioModels and create the CSV file
def search_biomodels(directory, keywords, output_file):
    biomodel_numbers_list = []
    matching_biomodels = []

    files = os.listdir(directory)
    
    for file in files:
        file_path = os.path.join(directory, file)
        
        try:
            with open(file_path, 'r', encoding='utf-8', errors='ignore') as f:
                file_content = f.read()
                
                # Find all biomodel numbers using a more flexible regex
                biomodel_numbers = re.findall(r'biomodels\.db/(\w+)', file_content)
                
                # Search for the biomodel name, case-insensitive, and allow variations
                biomodel_name_match = re.search(rf'{re.escape(keywords[0])} is "([^"]+)"', file_content, re.IGNORECASE)
                biomodel_name = biomodel_name_match.group(1) if biomodel_name_match else ''
                
                def matches_keywords(name, keywords):
                    # Check for any keyword match in the biomodel name, case-insensitive
                    return any(keyword.lower() in name.lower() for keyword in keywords)
                
                # If a matching biomodel name is found, save it
                if biomodel_name and matches_keywords(biomodel_name, keywords):
                    biomodel_numbers_list.extend(biomodel_numbers)
                    matching_biomodels.extend([biomodel_name] * len(biomodel_numbers))
        
        except Exception as e:
            print(f"Error processing file {file_path}: {e}")

    # Create a DataFrame from the collected data
    df = pd.DataFrame({
        'Biomodel Number': biomodel_numbers_list,
        'Biomodel Name': [matching_biomodels[i] if i < len(matching_biomodels) else '' for i in range(len(biomodel_numbers_list))]
    })

    # Save the DataFrame to a CSV file
    df.to_csv(output_file, index=False)
    print(f"Data saved to {output_file}")

# Function to copy matching files to final_models directory
def copy_matching_files(csv_file, data_folder, final_models_folder):
    # Create the final_models folder if it doesn't exist
    os.makedirs(final_models_folder, exist_ok=True)

    # Load the CSV file into a DataFrame
    df = pd.read_csv(csv_file)

    # Iterate through the data folder to find and copy matching files
    for root, dirs, files in os.walk(data_folder):
        for file in files:
            file_path = os.path.join(root, file)
            with open(file_path, 'r', encoding='utf-8', errors='ignore') as f:
                content = f.read()
                # Check if any biomodel name or number is in the file
                for i, row in df.iterrows():
                    biomodel_number = row['Biomodel Number']
                    biomodel_name = row['Biomodel Name']
                    if (biomodel_name and biomodel_name.lower() in content.lower()) or biomodel_number in content:
                        shutil.copy(file_path, final_models_folder)
                        print(f"Copied: {file} to final_models")

    print(f"All matching biomodel files have been copied to {final_models_folder}")

# Main execution
directory = r'C:\Users\navan\Downloads\BioModelsRAG\BioModelsRAG\data'
output_file = r'C:\Users\navan\Downloads\BioModelsRAG\biomodels_output.csv'
final_models_folder = r'C:\Users\navan\Downloads\BioModelsRAG\final_models'
user_keywords = input("Keyword you would like to search for: ").split()

# Search and copy files
search_biomodels(directory, user_keywords, output_file)
copy_matching_files(output_file, directory, final_models_folder)