Mercurial > repos > bimib > marea_2
changeset 366:5b703d9a45d5 draft
Uploaded
| author | luca_milaz |
|---|---|
| date | Wed, 18 Sep 2024 09:34:01 +0000 |
| parents | d49f290ad86e |
| children | b2b2312b8f77 |
| files | marea_2/ras_to_bounds.py marea_2/ras_to_bounds.xml |
| diffstat | 2 files changed, 0 insertions(+), 341 deletions(-) [+] |
line wrap: on
line diff
--- a/marea_2/ras_to_bounds.py Wed Sep 18 09:30:38 2024 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,231 +0,0 @@ -import argparse -import utils.general_utils as utils -from typing import Optional, List -import os -import numpy as np -import pandas as pd -import cobra -import sys -import csv -from joblib import Parallel, delayed, cpu_count - -################################# process args ############################### -def process_args(args :List[str]) -> argparse.Namespace: - """ - Processes command-line arguments. - - Args: - args (list): List of command-line arguments. - - Returns: - Namespace: An object containing parsed arguments. - """ - parser = argparse.ArgumentParser(usage = '%(prog)s [options]', - description = 'process some value\'s') - - parser.add_argument( - '-ms', '--model_selector', - type = utils.Model, default = utils.Model.ENGRO2, choices = [utils.Model.ENGRO2, utils.Model.Custom], - help = 'chose which type of model you want use') - - parser.add_argument("-mo", "--model", type = str, - help = "path to input file with custom rules, if provided") - - parser.add_argument("-mn", "--model_name", type = str, help = "custom mode name") - - parser.add_argument( - '-mes', '--medium_selector', - default = "allOpen", - help = 'chose which type of medium you want use') - - parser.add_argument("-meo", "--medium", type = str, - help = "path to input file with custom medium, if provided") - - parser.add_argument('-ol', '--out_log', - help = "Output log") - - parser.add_argument('-td', '--tool_dir', - type = str, - required = True, - help = 'your tool directory') - - parser.add_argument('-ir', '--input_ras', - type=str, - required = False, - help = 'input ras') - - parser.add_argument('-rs', '--ras_selector', - required = True, - type=utils.Bool("using_RAS"), - help = 'ras selector') - - ARGS = parser.parse_args() - return ARGS - -########################### warning ########################################### -def warning(s :str) -> None: - """ - Log a warning message to an output log file and print it to the console. - - Args: - s (str): The warning message to be logged and printed. - - Returns: - None - """ - with open(ARGS.out_log, 'a') as log: - log.write(s + "\n\n") - print(s) - -############################ dataset input #################################### -def read_dataset(data :str, name :str) -> pd.DataFrame: - """ - Read a dataset from a CSV file and return it as a pandas DataFrame. - - Args: - data (str): Path to the CSV file containing the dataset. - name (str): Name of the dataset, used in error messages. - - Returns: - pandas.DataFrame: DataFrame containing the dataset. - - Raises: - pd.errors.EmptyDataError: If the CSV file is empty. - sys.exit: If the CSV file has the wrong format, the execution is aborted. - """ - try: - dataset = pd.read_csv(data, sep = '\t', header = 0, engine='python') - except pd.errors.EmptyDataError: - sys.exit('Execution aborted: wrong format of ' + name + '\n') - if len(dataset.columns) < 2: - sys.exit('Execution aborted: wrong format of ' + name + '\n') - return dataset - - -def apply_ras_bounds(model, ras_row, rxns_ids): - """ - Adjust the bounds of reactions in the model based on RAS values. - - Args: - model (cobra.Model): The metabolic model to be modified. - ras_row (pd.Series): A row from a RAS DataFrame containing scaling factors for reaction bounds. - rxns_ids (list of str): List of reaction IDs to which the scaling factors will be applied. - - Returns: - None - """ - for reaction in rxns_ids: - if reaction in ras_row.index and pd.notna(ras_row[reaction]): - rxn = model.reactions.get_by_id(reaction) - scaling_factor = ras_row[reaction] - rxn.lower_bound *= scaling_factor - rxn.upper_bound *= scaling_factor - -def process_ras_cell(cellName, ras_row, model, rxns_ids, output_folder): - """ - Process a single RAS cell, apply bounds, and save the bounds to a CSV file. - - Args: - cellName (str): The name of the RAS cell (used for naming the output file). - ras_row (pd.Series): A row from a RAS DataFrame containing scaling factors for reaction bounds. - model (cobra.Model): The metabolic model to be modified. - rxns_ids (list of str): List of reaction IDs to which the scaling factors will be applied. - output_folder (str): Folder path where the output CSV file will be saved. - - Returns: - None - """ - model_new = model.copy() - apply_ras_bounds(model_new, ras_row, rxns_ids) - bounds = pd.DataFrame([(rxn.lower_bound, rxn.upper_bound) for rxn in model_new.reactions], index=rxns_ids, columns=["lower_bound", "upper_bound"]) - bounds.to_csv(output_folder + cellName + ".csv", sep='\t', index=True) - -def generate_bounds(model: cobra.Model, medium: dict, ras=None, output_folder='output/') -> 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. - medium (dict): A dictionary where keys are reaction IDs and values are the medium conditions. - ras (pd.DataFrame, optional): A DataFrame with RAS scaling factors for different cell types. Defaults to None. - output_folder (str, optional): Folder path where output CSV files will be saved. Defaults to 'output/'. - - Returns: - pd.DataFrame: DataFrame containing the bounds of reactions in the model. - """ - rxns_ids = [rxn.id for rxn in model.reactions] - - # Set medium conditions - for reaction, value in medium.items(): - if value is not None: - model.reactions.get_by_id(reaction).lower_bound = -float(value) - - # Perform Flux Variability Analysis (FVA) - df_FVA = cobra.flux_analysis.flux_variability_analysis(model, fraction_of_optimum=0, processes=1).round(8) - - # Set FVA bounds - for reaction in rxns_ids: - rxn = model.reactions.get_by_id(reaction) - rxn.lower_bound = float(df_FVA.loc[reaction, "minimum"]) - rxn.upper_bound = float(df_FVA.loc[reaction, "maximum"]) - - if ras is not None: - Parallel(n_jobs=cpu_count())(delayed(process_ras_cell)(cellName, ras_row, model, rxns_ids, output_folder) for cellName, ras_row in ras.iterrows()) - else: - model_new = model.copy() - apply_ras_bounds(model_new, pd.Series([1]*len(rxns_ids), index=rxns_ids), rxns_ids) - bounds = pd.DataFrame([(rxn.lower_bound, rxn.upper_bound) for rxn in model_new.reactions], index=rxns_ids, columns=["lower_bound", "upper_bound"]) - bounds.to_csv(output_folder + "bounds.csv", sep='\t', index=True) - - -############################# main ########################################### -def main() -> None: - """ - Initializes everything and sets the program in motion based on the fronted input arguments. - - Returns: - None - """ - if not os.path.exists('ras_to_bounds'): - os.makedirs('ras_to_bounds') - - - global ARGS - ARGS = process_args(sys.argv) - - ARGS.output_folder = 'ras_to_bounds/' - - if(ARGS.ras_selector == True): - ras = read_dataset(ARGS.input_ras, "ras dataset") - ras.replace("None", None, inplace=True) - ras.set_index("Reactions", drop=True, inplace=True) - ras = ras.T - ras = ras.astype(float) - - model_type :utils.Model = ARGS.model_selector - if model_type is utils.Model.Custom: - model = model_type.getCOBRAmodel(customPath = utils.FilePath.fromStrPath(ARGS.model), customExtension = utils.FilePath.fromStrPath(ARGS.model_name).ext) - else: - model = model_type.getCOBRAmodel(toolDir=ARGS.tool_dir) - - if(ARGS.medium_selector == "Custom"): - medium = read_dataset(ARGS.medium, "medium dataset") - medium.set_index(medium.columns[0], inplace=True) - medium = medium.astype(float) - medium = medium[medium.columns[0]].to_dict() - else: - df_mediums = pd.read_csv(ARGS.tool_dir + "/local/medium/medium.csv", index_col = 0) - ARGS.medium_selector = ARGS.medium_selector.replace("_", " ") - medium = df_mediums[[ARGS.medium_selector]] - medium = medium[ARGS.medium_selector].to_dict() - - if(ARGS.ras_selector == True): - generate_bounds(model, medium, ras = ras, output_folder=ARGS.output_folder) - else: - generate_bounds(model, medium, output_folder=ARGS.output_folder) - - pass - -############################################################################## -if __name__ == "__main__": - main() \ No newline at end of file
--- a/marea_2/ras_to_bounds.xml Wed Sep 18 09:30:38 2024 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,110 +0,0 @@ -<tool id="MaREA RAS to bounds" name="RAStoBounds" version="2.0.0"> - - <macros> - <import>marea_macros.xml</import> - </macros> - - <requirements> - <requirement type="package" version="1.24.4">numpy</requirement> - <requirement type="package" version="2.0.3">pandas</requirement> - <requirement type="package" version="0.29.0">cobra</requirement> - <requirement type="package" version="5.2.2">lxml</requirement> - <requirement type="package" version="1.4.2">joblib</requirement> - </requirements> - - <command detect_errors="exit_code"> - <![CDATA[ - python $__tool_directory__/ras_to_bounds.py - --tool_dir $__tool_directory__ - --model_selector $cond_model.model_selector - #if $cond_model.model_selector == 'Custom' - --model $model - --model_name $model.element_identifier - #end if - --medium_selector $cond_medium.medium_selector - #if $cond_medium.medium_selector == 'Custom' - --medium $medium - #end if - --ras_selector $cond_ras.ras_choice - #if $cond_ras.ras_choice == "True" - --input_ras $cond_ras.input_ras - #end if - --out_log $log - ]]> - </command> - <inputs> - <conditional name="cond_model"> - <expand macro="options_ras_to_bounds_model"/> - <when value="Custom"> - <param name="model" argument="--model" type="data" format="json, xml" label="Custom model" /> - </when> - </conditional> - - <conditional name="cond_ras"> - <param name="ras_choice" argument="--ras_choice" type="select" label="Do want to use RAS?"> - <option value="True" selected="true">Yes</option> - <option value="False">No</option> - </param> - <when value="True"> - <param name="input_ras" argument="--input_ras" multiple="false" type="data" format="tabular, csv, tsv" label="RAS matrix:" /> - </when> - </conditional> - - <conditional name="cond_medium"> - <expand macro="options_ras_to_bounds_medium"/> - <when value="Custom"> - <param name="medium" argument="--medium" type="data" format="tabular, csv, tsv" label="Custom medium" /> - </when> - </conditional> - - </inputs> - - <outputs> - <data format="txt" name="log" label="RAStoBounds- Log" /> - - <collection name="ras_to_bounds" type="list" label="Ras to Bounds"> - <discover_datasets name = "collection" pattern="__name_and_ext__" directory="ras_to_bounds"/> - </collection> - - </outputs> - - <help> - - <![CDATA[ - -What it does -------------- - -This tool generates the reactions bounds for a given metabolic model (JSON or XML format) with and without the injection of the Reaction Activity Scores (RAS) within the metabolic model. -Moreover, it enables to use custom/pre-defined growth mediums to constrain exchange reactions. For custom medium, It is suggested to use the template file returned by the Custom Data Generator tool. -If the RAS matrix, generated by the RAS generator tool, is used, then a file of bounds is generated for each cell. Otherwise, a single bounds file is returned. - -Accepted files: - - A model: JSON or XML file reporting reactions and rules contained in the model. - - RAS matrix: tab-separated RAS file as returned by RAS generator. - - Medium: tab-separated file containing lower and upper-bounds of medium reactions. - -Example medium file -------------- - -Custom medium: - -+------------+----------------+----------------+ -| Reaction ID| lower_bound | upper_bound | -+============+================+================+ -| r1 | 0.123167 | 0.371355 | -+------------+----------------+----------------+ -| r2 | 0.268765 | 0.765567 | -+------------+----------------+----------------+ - - -Output: -------------- - -The tool generates: - - bounds: reporting the bounds of the model, or cells if RAS is used. Format: tab-separated. - - a log file (.txt). - ]]> - </help> - <expand macro="citations" /> -</tool> \ No newline at end of file