# HG changeset patch # User francesco_lapi # Date 1759160099 0 # Node ID 7a413a5ec5662d4d3a761a9853a0eb88d98bef78 # Parent c6ea189ea7e994c12150cee936b4dada77525d93 Uploaded diff -r c6ea189ea7e9 -r 7a413a5ec566 COBRAxy/fromCSVtoCOBRA.py --- a/COBRAxy/fromCSVtoCOBRA.py Mon Sep 29 15:13:21 2025 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,112 +0,0 @@ -""" -Convert a tabular (CSV/TSV/Tabular) description of a COBRA model into a COBRA file. - -Supported output formats: SBML, JSON, MATLAB (.mat), YAML. -The script logs to a user-provided file for easier debugging in Galaxy. -""" - -import os -import cobra -import argparse -from typing import List -import logging -import utils.model_utils as modelUtils - -ARGS : argparse.Namespace -def process_args(args: List[str] = None) -> argparse.Namespace: - """ - Parse command-line arguments for the CSV-to-COBRA conversion tool. - - Returns: - argparse.Namespace: Parsed arguments. - """ - parser = argparse.ArgumentParser( - usage="%(prog)s [options]", - description="Convert a tabular/CSV file to a COBRA model" - ) - - - parser.add_argument("--out_log", type=str, required=True, - help="Output log file") - - - parser.add_argument("--input", type=str, required=True, - help="Input tabular file (CSV/TSV)") - - - parser.add_argument("--format", type=str, required=True, choices=["sbml", "json", "mat", "yaml"], - help="Model format (SBML, JSON, MATLAB, YAML)") - - - parser.add_argument("--output", type=str, required=True, - help="Output model file path") - - - parser.add_argument("--tool_dir", type=str, default=os.path.dirname(__file__), - help="Tool directory (passed from Galaxy as $__tool_directory__)") - - - return parser.parse_args(args) - - -###############################- ENTRY POINT -################################ - -def main(args: List[str] = None) -> None: - """ - Entry point: parse arguments, build the COBRA model from a CSV/TSV file, - and save it in the requested format. - - Returns: - None - """ - global ARGS - ARGS = process_args(args) - - # configure logging to the requested log file (overwrite each run) - logging.basicConfig(filename=ARGS.out_log, - level=logging.DEBUG, - format='%(asctime)s %(levelname)s: %(message)s', - filemode='w') - - logging.info('Starting fromCSVtoCOBRA tool') - logging.debug('Args: input=%s format=%s output=%s tool_dir=%s', ARGS.input, ARGS.format, ARGS.output, ARGS.tool_dir) - - try: - # Basic sanity checks - if not os.path.exists(ARGS.input): - logging.error('Input file not found: %s', ARGS.input) - - out_dir = os.path.dirname(os.path.abspath(ARGS.output)) - - if out_dir and not os.path.isdir(out_dir): - try: - os.makedirs(out_dir, exist_ok=True) - logging.info('Created missing output directory: %s', out_dir) - except Exception as e: - logging.exception('Cannot create output directory: %s', out_dir) - - model = modelUtils.build_cobra_model_from_csv(ARGS.input) - - # Save model in requested format - if ARGS.format == "sbml": - cobra.io.write_sbml_model(model, ARGS.output) - elif ARGS.format == "json": - cobra.io.save_json_model(model, ARGS.output) - elif ARGS.format == "mat": - cobra.io.save_matlab_model(model, ARGS.output) - elif ARGS.format == "yaml": - cobra.io.save_yaml_model(model, ARGS.output) - else: - logging.error('Unknown format requested: %s', ARGS.format) - print(f"ERROR: Unknown format: {ARGS.format}") - - - logging.info('Model successfully written to %s (format=%s)', ARGS.output, ARGS.format) - - except Exception: - # Log full traceback to the out_log so Galaxy users/admins can see what happened - logging.exception('Unhandled exception in fromCSVtoCOBRA') - - -if __name__ == '__main__': - main() diff -r c6ea189ea7e9 -r 7a413a5ec566 COBRAxy/fromCSVtoCOBRA.xml --- a/COBRAxy/fromCSVtoCOBRA.xml Mon Sep 29 15:13:21 2025 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,69 +0,0 @@ - - Convert a tabular dataset to a COBRA model - - - - cobra - numpy - pandas - lxml - - - - - marea_macros.xml - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - diff -r c6ea189ea7e9 -r 7a413a5ec566 COBRAxy/metabolicModel2Tabular.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/COBRAxy/metabolicModel2Tabular.py Mon Sep 29 15:34:59 2025 +0000 @@ -0,0 +1,368 @@ +""" +Scripts to generate a tabular file of a metabolic model (built-in or custom). + +This script loads a COBRA model (built-in or custom), optionally applies +medium and gene nomenclature settings, derives reaction-related metadata +(GPR rules, formulas, bounds, objective coefficients, medium membership, +and compartments for ENGRO2), and writes a tabular summary. +""" + +import os +import csv +import cobra +import argparse +import pandas as pd +import utils.general_utils as utils +from typing import Optional, Tuple, List +import utils.model_utils as modelUtils +import logging +from pathlib import Path + + +ARGS : argparse.Namespace +def process_args(args: List[str] = None) -> argparse.Namespace: + """ + Parse command-line arguments for metabolic_model_setting. + """ + + parser = argparse.ArgumentParser( + usage="%(prog)s [options]", + description="Generate custom data from a given model" + ) + + parser.add_argument("--out_log", type=str, required=True, + help="Output log file") + + parser.add_argument("--model", type=str, + help="Built-in model identifier (e.g., ENGRO2, Recon, HMRcore)") + parser.add_argument("--input", type=str, + help="Custom model file (JSON or XML)") + parser.add_argument("--name", type=str, required=True, + help="Model name (default or custom)") + + parser.add_argument("--medium_selector", type=str, required=True, + help="Medium selection option") + + parser.add_argument("--gene_format", type=str, default="Default", + help="Gene nomenclature format: Default (original), ENSNG, HGNC_SYMBOL, HGNC_ID, ENTREZ") + + parser.add_argument("--out_tabular", type=str, + help="Output file for the merged dataset (CSV or XLSX)") + + parser.add_argument("--tool_dir", type=str, default=os.path.dirname(__file__), + help="Tool directory (passed from Galaxy as $__tool_directory__)") + + + return parser.parse_args(args) + +################################- INPUT DATA LOADING -################################ +def load_custom_model(file_path :utils.FilePath, ext :Optional[utils.FileFormat] = None) -> cobra.Model: + """ + Loads a custom model from a file, either in JSON, XML, MAT, or YML format. + + Args: + file_path : The path to the file containing the custom model. + ext : explicit file extension. Necessary for standard use in galaxy because of its weird behaviour. + + Raises: + DataErr : if the file is in an invalid format or cannot be opened for whatever reason. + + Returns: + cobra.Model : the model, if successfully opened. + """ + ext = ext if ext else file_path.ext + try: + if ext is utils.FileFormat.XML: + return cobra.io.read_sbml_model(file_path.show()) + + if ext is utils.FileFormat.JSON: + return cobra.io.load_json_model(file_path.show()) + + if ext is utils.FileFormat.MAT: + return cobra.io.load_matlab_model(file_path.show()) + + if ext is utils.FileFormat.YML: + return cobra.io.load_yaml_model(file_path.show()) + + except Exception as e: raise utils.DataErr(file_path, e.__str__()) + raise utils.DataErr( + file_path, + f"Unrecognized format '{file_path.ext}'. Only JSON, XML, MAT, YML are supported." + ) + + +###############################- FILE SAVING -################################ +def save_as_csv_filePath(data :dict, file_path :utils.FilePath, fieldNames :Tuple[str, str]) -> None: + """ + Saves any dictionary-shaped data in a .csv file created at the given file_path as FilePath. + + Args: + data : the data to be written to the file. + file_path : the path to the .csv file. + fieldNames : the names of the fields (columns) in the .csv file. + + Returns: + None + """ + with open(file_path.show(), 'w', newline='') as csvfile: + writer = csv.DictWriter(csvfile, fieldnames = fieldNames, dialect="excel-tab") + writer.writeheader() + + for key, value in data.items(): + writer.writerow({ fieldNames[0] : key, fieldNames[1] : value }) + +def save_as_csv(data :dict, file_path :str, fieldNames :Tuple[str, str]) -> None: + """ + Saves any dictionary-shaped data in a .csv file created at the given file_path as string. + + Args: + data : the data to be written to the file. + file_path : the path to the .csv file. + fieldNames : the names of the fields (columns) in the .csv file. + + Returns: + None + """ + with open(file_path, 'w', newline='') as csvfile: + writer = csv.DictWriter(csvfile, fieldnames = fieldNames, dialect="excel-tab") + writer.writeheader() + + for key, value in data.items(): + writer.writerow({ fieldNames[0] : key, fieldNames[1] : value }) + +def save_as_tabular_df(df: pd.DataFrame, path: str) -> None: + """ + Save a pandas DataFrame as a tab-separated file, creating directories as needed. + + Args: + df: The DataFrame to write. + path: Destination file path (will be written as TSV). + + Raises: + DataErr: If writing the output fails for any reason. + + Returns: + None + """ + try: + os.makedirs(os.path.dirname(path) or ".", exist_ok=True) + df.to_csv(path, sep="\t", index=False) + except Exception as e: + raise utils.DataErr(path, f"failed writing tabular output: {e}") + +def is_placeholder(gid) -> bool: + """Return True if the gene id looks like a placeholder (e.g., 0/NA/NAN/empty).""" + if gid is None: + return True + s = str(gid).strip().lower() + return s in {"0", "", "na", "nan"} # lowercase for simple matching + +def sample_valid_gene_ids(genes, limit=10): + """Yield up to `limit` valid gene IDs, skipping placeholders (e.g., the first 0 in RECON).""" + out = [] + for g in genes: + gid = getattr(g, "id", getattr(g, "gene_id", g)) + if not is_placeholder(gid): + out.append(str(gid)) + if len(out) >= limit: + break + return out + + +###############################- ENTRY POINT -################################ +def main(args:List[str] = None) -> None: + """ + Initialize and generate custom data based on the frontend input arguments. + + Returns: + None + """ + # Parse args from frontend (Galaxy XML) + global ARGS + ARGS = process_args(args) + + + if ARGS.input: + # Load a custom model from file + model = load_custom_model( + utils.FilePath.fromStrPath(ARGS.input), utils.FilePath.fromStrPath(ARGS.name).ext) + else: + # Load a built-in model + + try: + model_enum = utils.Model[ARGS.model] # e.g., Model['ENGRO2'] + except KeyError: + raise utils.ArgsErr("model", "one of Recon/ENGRO2/HMRcore/Custom_model", ARGS.model) + + # Load built-in model (Model.getCOBRAmodel uses tool_dir to locate local models) + try: + model = model_enum.getCOBRAmodel(toolDir=ARGS.tool_dir) + except Exception as e: + # Wrap/normalize load errors as DataErr for consistency + raise utils.DataErr(ARGS.model, f"failed loading built-in model: {e}") + + # Determine final model name: explicit --name overrides, otherwise use the model id + + model_name = ARGS.name if ARGS.name else ARGS.model + + if ARGS.name == "ENGRO2" and ARGS.medium_selector != "Default": + 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() + + # Reset all medium reactions lower bound to zero + for rxn_id, _ in model.medium.items(): + model.reactions.get_by_id(rxn_id).lower_bound = float(0.0) + + # Apply selected medium uptake bounds (negative for uptake) + for reaction, value in medium.items(): + if value is not None: + model.reactions.get_by_id(reaction).lower_bound = -float(value) + + # Initialize translation_issues dictionary + translation_issues = {} + + if (ARGS.name == "Recon" or ARGS.name == "ENGRO2") and ARGS.gene_format != "Default": + logging.basicConfig(level=logging.INFO) + logger = logging.getLogger(__name__) + + model, translation_issues = modelUtils.translate_model_genes( + model=model, + mapping_df= pd.read_csv(ARGS.tool_dir + "/local/mappings/genes_human.csv", dtype={'entrez_id': str}), + target_nomenclature=ARGS.gene_format, + source_nomenclature='HGNC_symbol', + logger=logger + ) + + if ARGS.name == "Custom_model" and ARGS.gene_format != "Default": + logging.basicConfig(level=logging.INFO) + logger = logging.getLogger(__name__) + + tmp_check = [] + for g in model.genes[1:5]: # check first 3 genes only + tmp_check.append(modelUtils.gene_type(g.id, "Custom_model")) + + if len(set(tmp_check)) > 1: + raise utils.DataErr("Custom_model", "The custom model contains genes with mixed or unrecognized nomenclature. Please ensure all genes use the same recognized nomenclature before applying gene_format conversion.") + else: + source_nomenclature = tmp_check[0] + + if source_nomenclature != ARGS.gene_format: + model, translation_issues = modelUtils.translate_model_genes( + model=model, + mapping_df= pd.read_csv(ARGS.tool_dir + "/local/mappings/genes_human.csv", dtype={'entrez_id': str}), + target_nomenclature=ARGS.gene_format, + source_nomenclature=source_nomenclature, + logger=logger + ) + + + + + if ARGS.name == "Custom_model" and ARGS.gene_format != "Default": + logger = logging.getLogger(__name__) + + # Take a small, clean sample of gene IDs (skipping placeholders like 0) + ids_sample = sample_valid_gene_ids(model.genes, limit=10) + if not ids_sample: + raise utils.DataErr( + "Custom_model", + "No valid gene IDs found (many may be placeholders like 0)." + ) + + # Detect source nomenclature on the sample + types = [] + for gid in ids_sample: + try: + t = modelUtils.gene_type(gid, "Custom_model") + except Exception as e: + # Keep it simple: skip problematic IDs + logger.debug(f"gene_type failed for {gid}: {e}") + t = None + if t: + types.append(t) + + if not types: + raise utils.DataErr( + "Custom_model", + "Could not detect a known gene nomenclature from the sample." + ) + + unique_types = set(types) + if len(unique_types) > 1: + raise utils.DataErr( + "Custom_model", + "Mixed or inconsistent gene nomenclatures detected. " + "Please unify them before converting." + ) + + source_nomenclature = types[0] + + # Convert only if needed + if source_nomenclature != ARGS.gene_format: + model, translation_issues = modelUtils.translate_model_genes( + model=model, + mapping_df= pd.read_csv(ARGS.tool_dir + "/local/mappings/genes_human.csv", dtype={'entrez_id': str}), + target_nomenclature=ARGS.gene_format, + source_nomenclature=source_nomenclature, + logger=logger + ) + + # generate data + rules = modelUtils.generate_rules(model, asParsed = False) + reactions = modelUtils.generate_reactions(model, asParsed = False) + bounds = modelUtils.generate_bounds(model) + medium = modelUtils.get_medium(model) + objective_function = modelUtils.extract_objective_coefficients(model) + + if ARGS.name == "ENGRO2": + compartments = modelUtils.generate_compartments(model) + + df_rules = pd.DataFrame(list(rules.items()), columns = ["ReactionID", "GPR"]) + df_reactions = pd.DataFrame(list(reactions.items()), columns = ["ReactionID", "Formula"]) + + # Create DataFrame for translation issues + df_translation_issues = pd.DataFrame([ + {"ReactionID": rxn_id, "TranslationIssues": issues} + for rxn_id, issues in translation_issues.items() + ]) + + df_bounds = bounds.reset_index().rename(columns = {"index": "ReactionID"}) + df_medium = medium.rename(columns = {"reaction": "ReactionID"}) + df_medium["InMedium"] = True + + merged = df_reactions.merge(df_rules, on = "ReactionID", how = "outer") + merged = merged.merge(df_bounds, on = "ReactionID", how = "outer") + merged = merged.merge(objective_function, on = "ReactionID", how = "outer") + if ARGS.name == "ENGRO2": + merged = merged.merge(compartments, on = "ReactionID", how = "outer") + merged = merged.merge(df_medium, on = "ReactionID", how = "left") + + # Add translation issues column + if not df_translation_issues.empty: + merged = merged.merge(df_translation_issues, on = "ReactionID", how = "left") + merged["TranslationIssues"] = merged["TranslationIssues"].fillna("") + else: + # Add empty TranslationIssues column if no issues found + #merged["TranslationIssues"] = "" + pass + + merged["InMedium"] = merged["InMedium"].fillna(False) + + merged = merged.sort_values(by = "InMedium", ascending = False) + + if not ARGS.out_tabular: + raise utils.ArgsErr("out_tabular", "output path (--out_tabular) is required when output_format == tabular", ARGS.out_tabular) + save_as_tabular_df(merged, ARGS.out_tabular) + expected = ARGS.out_tabular + + # verify output exists and non-empty + if not expected or not os.path.exists(expected) or os.path.getsize(expected) == 0: + raise utils.DataErr(expected, "Output not created or empty") + + print("Metabolic_model_setting: completed successfully") + +if __name__ == '__main__': + + main() diff -r c6ea189ea7e9 -r 7a413a5ec566 COBRAxy/metabolicModel2Tabular.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/COBRAxy/metabolicModel2Tabular.xml Mon Sep 29 15:34:59 2025 +0000 @@ -0,0 +1,121 @@ + + + + numpy + pandas + cobra + lxml + + + + marea_macros.xml + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff -r c6ea189ea7e9 -r 7a413a5ec566 COBRAxy/metabolic_model_setting.py --- a/COBRAxy/metabolic_model_setting.py Mon Sep 29 15:13:21 2025 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,368 +0,0 @@ -""" -Scripts to generate a tabular file of a metabolic model (built-in or custom). - -This script loads a COBRA model (built-in or custom), optionally applies -medium and gene nomenclature settings, derives reaction-related metadata -(GPR rules, formulas, bounds, objective coefficients, medium membership, -and compartments for ENGRO2), and writes a tabular summary. -""" - -import os -import csv -import cobra -import argparse -import pandas as pd -import utils.general_utils as utils -from typing import Optional, Tuple, List -import utils.model_utils as modelUtils -import logging -from pathlib import Path - - -ARGS : argparse.Namespace -def process_args(args: List[str] = None) -> argparse.Namespace: - """ - Parse command-line arguments for metabolic_model_setting. - """ - - parser = argparse.ArgumentParser( - usage="%(prog)s [options]", - description="Generate custom data from a given model" - ) - - parser.add_argument("--out_log", type=str, required=True, - help="Output log file") - - parser.add_argument("--model", type=str, - help="Built-in model identifier (e.g., ENGRO2, Recon, HMRcore)") - parser.add_argument("--input", type=str, - help="Custom model file (JSON or XML)") - parser.add_argument("--name", type=str, required=True, - help="Model name (default or custom)") - - parser.add_argument("--medium_selector", type=str, required=True, - help="Medium selection option") - - parser.add_argument("--gene_format", type=str, default="Default", - help="Gene nomenclature format: Default (original), ENSNG, HGNC_SYMBOL, HGNC_ID, ENTREZ") - - parser.add_argument("--out_tabular", type=str, - help="Output file for the merged dataset (CSV or XLSX)") - - parser.add_argument("--tool_dir", type=str, default=os.path.dirname(__file__), - help="Tool directory (passed from Galaxy as $__tool_directory__)") - - - return parser.parse_args(args) - -################################- INPUT DATA LOADING -################################ -def load_custom_model(file_path :utils.FilePath, ext :Optional[utils.FileFormat] = None) -> cobra.Model: - """ - Loads a custom model from a file, either in JSON, XML, MAT, or YML format. - - Args: - file_path : The path to the file containing the custom model. - ext : explicit file extension. Necessary for standard use in galaxy because of its weird behaviour. - - Raises: - DataErr : if the file is in an invalid format or cannot be opened for whatever reason. - - Returns: - cobra.Model : the model, if successfully opened. - """ - ext = ext if ext else file_path.ext - try: - if ext is utils.FileFormat.XML: - return cobra.io.read_sbml_model(file_path.show()) - - if ext is utils.FileFormat.JSON: - return cobra.io.load_json_model(file_path.show()) - - if ext is utils.FileFormat.MAT: - return cobra.io.load_matlab_model(file_path.show()) - - if ext is utils.FileFormat.YML: - return cobra.io.load_yaml_model(file_path.show()) - - except Exception as e: raise utils.DataErr(file_path, e.__str__()) - raise utils.DataErr( - file_path, - f"Unrecognized format '{file_path.ext}'. Only JSON, XML, MAT, YML are supported." - ) - - -###############################- FILE SAVING -################################ -def save_as_csv_filePath(data :dict, file_path :utils.FilePath, fieldNames :Tuple[str, str]) -> None: - """ - Saves any dictionary-shaped data in a .csv file created at the given file_path as FilePath. - - Args: - data : the data to be written to the file. - file_path : the path to the .csv file. - fieldNames : the names of the fields (columns) in the .csv file. - - Returns: - None - """ - with open(file_path.show(), 'w', newline='') as csvfile: - writer = csv.DictWriter(csvfile, fieldnames = fieldNames, dialect="excel-tab") - writer.writeheader() - - for key, value in data.items(): - writer.writerow({ fieldNames[0] : key, fieldNames[1] : value }) - -def save_as_csv(data :dict, file_path :str, fieldNames :Tuple[str, str]) -> None: - """ - Saves any dictionary-shaped data in a .csv file created at the given file_path as string. - - Args: - data : the data to be written to the file. - file_path : the path to the .csv file. - fieldNames : the names of the fields (columns) in the .csv file. - - Returns: - None - """ - with open(file_path, 'w', newline='') as csvfile: - writer = csv.DictWriter(csvfile, fieldnames = fieldNames, dialect="excel-tab") - writer.writeheader() - - for key, value in data.items(): - writer.writerow({ fieldNames[0] : key, fieldNames[1] : value }) - -def save_as_tabular_df(df: pd.DataFrame, path: str) -> None: - """ - Save a pandas DataFrame as a tab-separated file, creating directories as needed. - - Args: - df: The DataFrame to write. - path: Destination file path (will be written as TSV). - - Raises: - DataErr: If writing the output fails for any reason. - - Returns: - None - """ - try: - os.makedirs(os.path.dirname(path) or ".", exist_ok=True) - df.to_csv(path, sep="\t", index=False) - except Exception as e: - raise utils.DataErr(path, f"failed writing tabular output: {e}") - -def is_placeholder(gid) -> bool: - """Return True if the gene id looks like a placeholder (e.g., 0/NA/NAN/empty).""" - if gid is None: - return True - s = str(gid).strip().lower() - return s in {"0", "", "na", "nan"} # lowercase for simple matching - -def sample_valid_gene_ids(genes, limit=10): - """Yield up to `limit` valid gene IDs, skipping placeholders (e.g., the first 0 in RECON).""" - out = [] - for g in genes: - gid = getattr(g, "id", getattr(g, "gene_id", g)) - if not is_placeholder(gid): - out.append(str(gid)) - if len(out) >= limit: - break - return out - - -###############################- ENTRY POINT -################################ -def main(args:List[str] = None) -> None: - """ - Initialize and generate custom data based on the frontend input arguments. - - Returns: - None - """ - # Parse args from frontend (Galaxy XML) - global ARGS - ARGS = process_args(args) - - - if ARGS.input: - # Load a custom model from file - model = load_custom_model( - utils.FilePath.fromStrPath(ARGS.input), utils.FilePath.fromStrPath(ARGS.name).ext) - else: - # Load a built-in model - - try: - model_enum = utils.Model[ARGS.model] # e.g., Model['ENGRO2'] - except KeyError: - raise utils.ArgsErr("model", "one of Recon/ENGRO2/HMRcore/Custom_model", ARGS.model) - - # Load built-in model (Model.getCOBRAmodel uses tool_dir to locate local models) - try: - model = model_enum.getCOBRAmodel(toolDir=ARGS.tool_dir) - except Exception as e: - # Wrap/normalize load errors as DataErr for consistency - raise utils.DataErr(ARGS.model, f"failed loading built-in model: {e}") - - # Determine final model name: explicit --name overrides, otherwise use the model id - - model_name = ARGS.name if ARGS.name else ARGS.model - - if ARGS.name == "ENGRO2" and ARGS.medium_selector != "Default": - 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() - - # Reset all medium reactions lower bound to zero - for rxn_id, _ in model.medium.items(): - model.reactions.get_by_id(rxn_id).lower_bound = float(0.0) - - # Apply selected medium uptake bounds (negative for uptake) - for reaction, value in medium.items(): - if value is not None: - model.reactions.get_by_id(reaction).lower_bound = -float(value) - - # Initialize translation_issues dictionary - translation_issues = {} - - if (ARGS.name == "Recon" or ARGS.name == "ENGRO2") and ARGS.gene_format != "Default": - logging.basicConfig(level=logging.INFO) - logger = logging.getLogger(__name__) - - model, translation_issues = modelUtils.translate_model_genes( - model=model, - mapping_df= pd.read_csv(ARGS.tool_dir + "/local/mappings/genes_human.csv", dtype={'entrez_id': str}), - target_nomenclature=ARGS.gene_format, - source_nomenclature='HGNC_symbol', - logger=logger - ) - - if ARGS.name == "Custom_model" and ARGS.gene_format != "Default": - logging.basicConfig(level=logging.INFO) - logger = logging.getLogger(__name__) - - tmp_check = [] - for g in model.genes[1:5]: # check first 3 genes only - tmp_check.append(modelUtils.gene_type(g.id, "Custom_model")) - - if len(set(tmp_check)) > 1: - raise utils.DataErr("Custom_model", "The custom model contains genes with mixed or unrecognized nomenclature. Please ensure all genes use the same recognized nomenclature before applying gene_format conversion.") - else: - source_nomenclature = tmp_check[0] - - if source_nomenclature != ARGS.gene_format: - model, translation_issues = modelUtils.translate_model_genes( - model=model, - mapping_df= pd.read_csv(ARGS.tool_dir + "/local/mappings/genes_human.csv", dtype={'entrez_id': str}), - target_nomenclature=ARGS.gene_format, - source_nomenclature=source_nomenclature, - logger=logger - ) - - - - - if ARGS.name == "Custom_model" and ARGS.gene_format != "Default": - logger = logging.getLogger(__name__) - - # Take a small, clean sample of gene IDs (skipping placeholders like 0) - ids_sample = sample_valid_gene_ids(model.genes, limit=10) - if not ids_sample: - raise utils.DataErr( - "Custom_model", - "No valid gene IDs found (many may be placeholders like 0)." - ) - - # Detect source nomenclature on the sample - types = [] - for gid in ids_sample: - try: - t = modelUtils.gene_type(gid, "Custom_model") - except Exception as e: - # Keep it simple: skip problematic IDs - logger.debug(f"gene_type failed for {gid}: {e}") - t = None - if t: - types.append(t) - - if not types: - raise utils.DataErr( - "Custom_model", - "Could not detect a known gene nomenclature from the sample." - ) - - unique_types = set(types) - if len(unique_types) > 1: - raise utils.DataErr( - "Custom_model", - "Mixed or inconsistent gene nomenclatures detected. " - "Please unify them before converting." - ) - - source_nomenclature = types[0] - - # Convert only if needed - if source_nomenclature != ARGS.gene_format: - model, translation_issues = modelUtils.translate_model_genes( - model=model, - mapping_df= pd.read_csv(ARGS.tool_dir + "/local/mappings/genes_human.csv", dtype={'entrez_id': str}), - target_nomenclature=ARGS.gene_format, - source_nomenclature=source_nomenclature, - logger=logger - ) - - # generate data - rules = modelUtils.generate_rules(model, asParsed = False) - reactions = modelUtils.generate_reactions(model, asParsed = False) - bounds = modelUtils.generate_bounds(model) - medium = modelUtils.get_medium(model) - objective_function = modelUtils.extract_objective_coefficients(model) - - if ARGS.name == "ENGRO2": - compartments = modelUtils.generate_compartments(model) - - df_rules = pd.DataFrame(list(rules.items()), columns = ["ReactionID", "GPR"]) - df_reactions = pd.DataFrame(list(reactions.items()), columns = ["ReactionID", "Formula"]) - - # Create DataFrame for translation issues - df_translation_issues = pd.DataFrame([ - {"ReactionID": rxn_id, "TranslationIssues": issues} - for rxn_id, issues in translation_issues.items() - ]) - - df_bounds = bounds.reset_index().rename(columns = {"index": "ReactionID"}) - df_medium = medium.rename(columns = {"reaction": "ReactionID"}) - df_medium["InMedium"] = True - - merged = df_reactions.merge(df_rules, on = "ReactionID", how = "outer") - merged = merged.merge(df_bounds, on = "ReactionID", how = "outer") - merged = merged.merge(objective_function, on = "ReactionID", how = "outer") - if ARGS.name == "ENGRO2": - merged = merged.merge(compartments, on = "ReactionID", how = "outer") - merged = merged.merge(df_medium, on = "ReactionID", how = "left") - - # Add translation issues column - if not df_translation_issues.empty: - merged = merged.merge(df_translation_issues, on = "ReactionID", how = "left") - merged["TranslationIssues"] = merged["TranslationIssues"].fillna("") - else: - # Add empty TranslationIssues column if no issues found - #merged["TranslationIssues"] = "" - pass - - merged["InMedium"] = merged["InMedium"].fillna(False) - - merged = merged.sort_values(by = "InMedium", ascending = False) - - if not ARGS.out_tabular: - raise utils.ArgsErr("out_tabular", "output path (--out_tabular) is required when output_format == tabular", ARGS.out_tabular) - save_as_tabular_df(merged, ARGS.out_tabular) - expected = ARGS.out_tabular - - # verify output exists and non-empty - if not expected or not os.path.exists(expected) or os.path.getsize(expected) == 0: - raise utils.DataErr(expected, "Output not created or empty") - - print("Metabolic_model_setting: completed successfully") - -if __name__ == '__main__': - - main() diff -r c6ea189ea7e9 -r 7a413a5ec566 COBRAxy/metabolic_model_setting.xml --- a/COBRAxy/metabolic_model_setting.xml Mon Sep 29 15:13:21 2025 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,121 +0,0 @@ - - - - numpy - pandas - cobra - lxml - - - - marea_macros.xml - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - diff -r c6ea189ea7e9 -r 7a413a5ec566 COBRAxy/tabular2MetabolicModel.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/COBRAxy/tabular2MetabolicModel.py Mon Sep 29 15:34:59 2025 +0000 @@ -0,0 +1,112 @@ +""" +Convert a tabular (CSV/TSV/Tabular) description of a COBRA model into a COBRA file. + +Supported output formats: SBML, JSON, MATLAB (.mat), YAML. +The script logs to a user-provided file for easier debugging in Galaxy. +""" + +import os +import cobra +import argparse +from typing import List +import logging +import utils.model_utils as modelUtils + +ARGS : argparse.Namespace +def process_args(args: List[str] = None) -> argparse.Namespace: + """ + Parse command-line arguments for the CSV-to-COBRA conversion tool. + + Returns: + argparse.Namespace: Parsed arguments. + """ + parser = argparse.ArgumentParser( + usage="%(prog)s [options]", + description="Convert a tabular/CSV file to a COBRA model" + ) + + + parser.add_argument("--out_log", type=str, required=True, + help="Output log file") + + + parser.add_argument("--input", type=str, required=True, + help="Input tabular file (CSV/TSV)") + + + parser.add_argument("--format", type=str, required=True, choices=["sbml", "json", "mat", "yaml"], + help="Model format (SBML, JSON, MATLAB, YAML)") + + + parser.add_argument("--output", type=str, required=True, + help="Output model file path") + + + parser.add_argument("--tool_dir", type=str, default=os.path.dirname(__file__), + help="Tool directory (passed from Galaxy as $__tool_directory__)") + + + return parser.parse_args(args) + + +###############################- ENTRY POINT -################################ + +def main(args: List[str] = None) -> None: + """ + Entry point: parse arguments, build the COBRA model from a CSV/TSV file, + and save it in the requested format. + + Returns: + None + """ + global ARGS + ARGS = process_args(args) + + # configure logging to the requested log file (overwrite each run) + logging.basicConfig(filename=ARGS.out_log, + level=logging.DEBUG, + format='%(asctime)s %(levelname)s: %(message)s', + filemode='w') + + logging.info('Starting fromCSVtoCOBRA tool') + logging.debug('Args: input=%s format=%s output=%s tool_dir=%s', ARGS.input, ARGS.format, ARGS.output, ARGS.tool_dir) + + try: + # Basic sanity checks + if not os.path.exists(ARGS.input): + logging.error('Input file not found: %s', ARGS.input) + + out_dir = os.path.dirname(os.path.abspath(ARGS.output)) + + if out_dir and not os.path.isdir(out_dir): + try: + os.makedirs(out_dir, exist_ok=True) + logging.info('Created missing output directory: %s', out_dir) + except Exception as e: + logging.exception('Cannot create output directory: %s', out_dir) + + model = modelUtils.build_cobra_model_from_csv(ARGS.input) + + # Save model in requested format + if ARGS.format == "sbml": + cobra.io.write_sbml_model(model, ARGS.output) + elif ARGS.format == "json": + cobra.io.save_json_model(model, ARGS.output) + elif ARGS.format == "mat": + cobra.io.save_matlab_model(model, ARGS.output) + elif ARGS.format == "yaml": + cobra.io.save_yaml_model(model, ARGS.output) + else: + logging.error('Unknown format requested: %s', ARGS.format) + print(f"ERROR: Unknown format: {ARGS.format}") + + + logging.info('Model successfully written to %s (format=%s)', ARGS.output, ARGS.format) + + except Exception: + # Log full traceback to the out_log so Galaxy users/admins can see what happened + logging.exception('Unhandled exception in fromCSVtoCOBRA') + + +if __name__ == '__main__': + main() diff -r c6ea189ea7e9 -r 7a413a5ec566 COBRAxy/tabular2MetabolicModel.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/COBRAxy/tabular2MetabolicModel.xml Mon Sep 29 15:34:59 2025 +0000 @@ -0,0 +1,69 @@ + + Convert a tabular dataset to a COBRA model + + + + cobra + numpy + pandas + lxml + + + + + marea_macros.xml + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +