Mercurial > repos > bimib > cobraxy
changeset 540:7d5b35c715e8 draft
Uploaded
| author | francesco_lapi |
|---|---|
| date | Sat, 25 Oct 2025 15:08:19 +0000 |
| parents | 2fb97466e404 |
| children | fa93040a75af |
| files | COBRAxy/src/exportMetabolicModel.py COBRAxy/src/exportMetabolicModel.xml COBRAxy/src/importMetabolicModel.py COBRAxy/src/importMetabolicModel.xml COBRAxy/src/metabolicModel2Tabular.py COBRAxy/src/metabolicModel2Tabular.xml COBRAxy/src/tabular2MetabolicModel.py COBRAxy/src/tabular2MetabolicModel.xml COBRAxy/src/test/test_marea.py |
| diffstat | 9 files changed, 706 insertions(+), 706 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/COBRAxy/src/exportMetabolicModel.py Sat Oct 25 15:08:19 2025 +0000 @@ -0,0 +1,117 @@ +""" +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) + + + logging.info('Created model with name: %s (ID: %s)', model.name, model.id) + + # Save model in requested format - Galaxy handles the filename + 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) + raise ValueError(f"Unknown format: {ARGS.format}") + + + logging.info('Model successfully written to %s (format=%s)', ARGS.output, ARGS.format) + print(f"Model created successfully in {ARGS.format.upper()} format") + + except Exception as e: + # Log full traceback to the out_log so Galaxy users/admins can see what happened + logging.exception('Unhandled exception in fromCSVtoCOBRA') + print(f"ERROR: {str(e)}") + raise + + +if __name__ == '__main__': + main()
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/COBRAxy/src/exportMetabolicModel.xml Sat Oct 25 15:08:19 2025 +0000 @@ -0,0 +1,82 @@ +<tool id="exportMetabolicModel" name="Export Metabolic Model" version="1.0.0"> + <description>Export a tabular model to file format (SBML, JSON, MAT or YAML)</description> + + <!-- Python dependencies required for COBRApy --> + <requirements> + <requirement type="package" version="0.29.0">cobra</requirement> + <requirement type="package" version="1.24.4">numpy</requirement> + <requirement type="package" version="2.0.3">pandas</requirement> + <requirement type="package" version="5.2.2">lxml</requirement> + </requirements> + + <!-- Import shared macros if available --> + <macros> + <import>marea_macros.xml</import> + </macros> + + <!-- Command to run the Python script --> + <command detect_errors="exit_code"><![CDATA[ + python $__tool_directory__/exportMetabolicModel.py + --tool_dir $__tool_directory__ + --input $input + --format $format + --output $output + --out_log $log + ]]></command> + + <!-- Tool inputs --> + <inputs> + <param name="input" type="data" format="tabular,csv,tsv" label="Model tabular:"/> + <param name="model_name" type="text" value="Converted_Model" label="Output model name:" help="Name for the created COBRA model"/> + <param name="format" type="select" label="Output format"> + <option value="sbml" selected="true">SBML (.xml)</option> + <option value="json">JSON (.json)</option> + <option value="mat">MATLAB (.mat)</option> + <option value="yaml">YAML (.yml)</option> + </param> + </inputs> + + <!-- Tool outputs --> + <outputs> + <data name="log" format="txt" label="Tabular to Model Conversion - Log" /> + <data name="output" format="xml" label="${model_name}.${format}"> + <change_format> + <when input="format" value="sbml" format="xml"/> + <when input="format" value="json" format="json"/> + <when input="format" value="mat" format="mat"/> + <when input="format" value="yaml" format="yaml"/> + </change_format> + </data> + </outputs> + + <!-- Help section --> + <help><![CDATA[ +This tool exports a tabular dataset into a standard metabolic model file formats using COBRApy. + +**Input** +- A tabular/CSV/TSV file describing the metabolic properties of the model (reactions, metabolites, and genes), as generated by the Import Metabolic Model tool. + +The possible columns are: + - ReactionID: unique identifier of the reactions + - Formula: chemical equation showing the metabolites involved in the reaction and their stoichiometric coefficients. + - GPR: gene-protein-reaction association, expressed as a logical rule describing how genes contribute to catalyzing the reaction. + - lower bound: minimum allowable flux value for the reaction. + - upper bound: maximum allowable flux value for the reaction. + - Objective coefficient: coefficient used in the objective function (e.g., for pFBA or FVA analyses). + - Pathway_1,Pathway_2,etc.: possible pathways in which the reaction is involved. + - InMedium: TRUE if the reaction represents nutrient uptake from the medium, FALSE otherwise. + +Columns ReactionID and Formula are mandatory. + +**Output** +- A COBRA model in the chosen format: + - SBML (.xml) + - JSON (.json) + - MATLAB (.mat) + - YAML (.yml) + +**Notes** +- The exact table structure (columns required) depends on how you want to encode reactions and metabolites. +- You can extend the Python script to parse specific column formats. + ]]></help> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/COBRAxy/src/importMetabolicModel.py Sat Oct 25 15:08:19 2025 +0000 @@ -0,0 +1,349 @@ +""" +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. + """ + + 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, XML, MAT, YAML)") + parser.add_argument("--name", nargs='*', 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 detect_file_format(file_path: str) -> utils.FileFormat: + """ + Detect file format by examining file content and extension. + Handles Galaxy .dat files by looking at content. + """ + try: + with open(file_path, 'r') as f: + first_lines = ''.join([f.readline() for _ in range(5)]) + + # Check for XML (SBML) + if '<?xml' in first_lines or '<sbml' in first_lines: + return utils.FileFormat.XML + + # Check for JSON + if first_lines.strip().startswith('{'): + return utils.FileFormat.JSON + + # Check for YAML + if any(line.strip().endswith(':') for line in first_lines.split('\n')[:3]): + return utils.FileFormat.YML + + except: + pass + + # Fall back to extension-based detection + if file_path.endswith('.xml') or file_path.endswith('.sbml'): + return utils.FileFormat.XML + elif file_path.endswith('.json'): + return utils.FileFormat.JSON + elif file_path.endswith('.mat'): + return utils.FileFormat.MAT + elif file_path.endswith('.yml') or file_path.endswith('.yaml'): + return utils.FileFormat.YML + + # Default to XML for unknown extensions + return utils.FileFormat.XML + +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) + + # Convert name from list to string (handles names with spaces) + if isinstance(ARGS.name, list): + ARGS.name = ' '.join(ARGS.name) + + if ARGS.input: + # Load a custom model from file with auto-detected format + detected_format = detect_file_format(ARGS.input) + model = load_custom_model(utils.FilePath.fromStrPath(ARGS.input), detected_format) + else: + # Load a built-in model + if not ARGS.model: + raise utils.ArgsErr("model", "either --model or --input must be provided", "None") + + 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 + + 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.csv uses underscores now + 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.input and ARGS.gene_format != "Default": + logging.basicConfig(level=logging.INFO) + 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 using unified function + if not ARGS.out_tabular: + raise utils.ArgsErr("out_tabular", "output path (--out_tabular) is required when output_format == tabular", ARGS.out_tabular) + + merged = modelUtils.export_model_to_tabular( + model=model, + output_path=ARGS.out_tabular, + translation_issues=translation_issues, + include_objective=True, + save_function=save_as_tabular_df + ) + 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("Completed successfully") + +if __name__ == '__main__': + + main()
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/COBRAxy/src/importMetabolicModel.xml Sat Oct 25 15:08:19 2025 +0000 @@ -0,0 +1,154 @@ +<tool id="importMetabolicModel" name="Import Metabolic Model" version="2.0.0"> + + <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> + </requirements> + + <macros> + <import>marea_macros.xml</import> + </macros> + + <command detect_errors="exit_code"> + <![CDATA[ + python $__tool_directory__/importMetabolicModel.py + --tool_dir $__tool_directory__ + --medium_selector $cond_model.cond_medium.medium_selector + #if $cond_model.model_selector == 'Custom_model' + --input $cond_model.input + --name $cond_model.input.element_identifier + --out_tabular $out_tabular_custom + #elif $cond_model.model_selector == 'ENGRO2' + --model $cond_model.model_selector + --name $cond_model.model_selector + --out_tabular $out_tabular_engro2 + #else + --model $cond_model.model_selector + --name $cond_model.model_selector + --out_tabular $out_tabular_recon + #end if + --gene_format $cond_model.gene_format + --out_log $log + ]]> + </command> + <inputs> + <conditional name="cond_model"> + <expand macro="options_model"/> + + <!-- ENGRO2 --> + <when value="ENGRO2"> + + <conditional name="cond_medium"> + <expand macro="options_ras_to_bounds_medium"/> + </conditional> + + <param name="gene_format" argument="--gene_format" type="select" label="Gene nomenclature format:"> + <option value="Default" selected="true">Keep original gene nomenclature (HGNC Symbol)</option> + <option value="ENSG">ENSG (Ensembl Gene ID)</option> + <option value="HGNC_ID">HGNC ID</option> + <option value="entrez_id">Entrez Gene ID</option> + </param> + </when> + + <!-- Recon --> + <when value="Recon"> + + <conditional name="cond_medium"> + <param name="medium_selector" argument="--medium_selector" type="select" label="Medium"> + <option value="Default" selected="true">Default (Recon built-in medium)</option> + </param> + <when value="Default"> + <!-- Nessun parametro aggiuntivo necessario --> + </when> + </conditional> + <param name="gene_format" argument="--gene_format" type="select" label="Gene nomenclature format:"> + <option value="Default" selected="true">Keep original gene nomenclature (HGNC Symbol)</option> + <option value="ENSG">ENSG (Ensembl Gene ID)</option> + <option value="HGNC_ID">HGNC ID</option> + <option value="entrez_id">Entrez Gene ID</option> + </param> + </when> + + <!-- Custom model --> + <when value="Custom_model"> + <param name="input" argument="--input" type="data" format="json,xml,sbml" label="Custom model file:" /> + <conditional name="cond_medium"> + <param name="medium_selector" argument="--medium_selector" type="select" label="Medium"> + <option value="Default" selected="true">Default (custom model medium)</option> + </param> + <when value="Default"> + <!-- Nessun parametro aggiuntivo necessario --> + </when> + </conditional> + <param name="gene_format" argument="--gene_format" type="select" label="Gene nomenclature format:"> + <option value="Default" selected="true">Keep original gene nomenclature</option> + <option value="HGNC_symbol">HGNC Symbol</option> + <option value="ENSG">ENSG (Ensembl Gene ID)</option> + <option value="HGNC_ID">HGNC ID</option> + <option value="entrez_id">Entrez Gene ID</option> + </param> + </when> + </conditional> + + </inputs> + + <outputs> + <data name="log" format="txt" label="MetabolicModelSetting - Log" /> + + <data name="out_tabular_engro2" format="tabular" label="ENGRO2_model_tabular"> + <filter>cond_model['model_selector'] == 'ENGRO2'</filter> + </data> + + <data name="out_tabular_recon" format="tabular" label="Recon_model_tabular"> + <filter>cond_model['model_selector'] == 'Recon'</filter> + </data> + + <data name="out_tabular_custom" format="tabular" label="${cond_model.input.element_identifier}_model_tabular"> + <filter>cond_model['model_selector'] == 'Custom_model'</filter> + </data> + </outputs> + + <help> + <![CDATA[ +Overview +------------- +This tool generates a Tabular file (.tabular) containing the main information of the metabolic model, starting -either from a built-in model or a user-provided model file. +For built-in models, users can select among different nutrient-informed variants (i.e., different media composition) and gene nomenclature formats. + +The generated tabular file can be used as input for tools Expression2RAS, Expression2RPS, RAS2Bounds, Flux Simulation and Export Metabolic Model - within the COBRAxy suite. + +Input parameters: +------------- + +The tool has three input parameters: + - Model: a file containing metabolic information (reactions, metabolites, genes). Ready-to-use models are ENGRO2 and Recon3D. + The user can also upload a custom model (see TIP 1). + - Medium: choose a growth medium typically used for cell culture (see TIP 2 & 3). + - Gene nomenclature format: use the original GPR gene names or translate them into another nomenclature. + +Output files: +------------- + +The tool generates: + - one tabular file (.tabular) containing reaction IDs, reaction formula, GPR rules, reaction bounds, objective function coefficients, pathways in which the reaction is involved and a flag indicating whether the reaction is an exchange reaction (i.e., related to the growth medium). + - a log file (.txt). + +**TIP 1**: Different input files can be used as the input model. The possible formats are XML (SBML), JSON, MAT or YAML (.yml). + Supported compressed formats: .zip, .gz and .bz2. Filename must follow the pattern: {model_name}.{extension}.[zip|gz|bz2] + More detail can be found at https://cobrapy.readthedocs.io/en/latest/io.html + +**TIP 2**: for pre-existing models ENGRO2 and RECON3D, the user can select the default built-in medium or one of the possible growth medium typically used for cell line cultures. +In case no specific information is available, it is possible to set an "OPEN" medium in which all the nutrients are available in unlimited quantity. + +**TIP 3:** Medium composition can be derived from the tabular file. Exchange reactions with `InMedium = TRUE` are included. Nutrient values correspond to the lower bound (e.g., EX_Glc_D_e lower bound -10 → nutrient value 10). +More info: [COBRApy Media](https://cobrapy-cdiener.readthedocs.io/en/latest/media.html) + + ]]> + </help> + <expand macro="citations" /> + +</tool> + +
--- a/COBRAxy/src/metabolicModel2Tabular.py Sat Oct 25 14:55:13 2025 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,349 +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. - """ - - 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, XML, MAT, YAML)") - parser.add_argument("--name", nargs='*', 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 detect_file_format(file_path: str) -> utils.FileFormat: - """ - Detect file format by examining file content and extension. - Handles Galaxy .dat files by looking at content. - """ - try: - with open(file_path, 'r') as f: - first_lines = ''.join([f.readline() for _ in range(5)]) - - # Check for XML (SBML) - if '<?xml' in first_lines or '<sbml' in first_lines: - return utils.FileFormat.XML - - # Check for JSON - if first_lines.strip().startswith('{'): - return utils.FileFormat.JSON - - # Check for YAML - if any(line.strip().endswith(':') for line in first_lines.split('\n')[:3]): - return utils.FileFormat.YML - - except: - pass - - # Fall back to extension-based detection - if file_path.endswith('.xml') or file_path.endswith('.sbml'): - return utils.FileFormat.XML - elif file_path.endswith('.json'): - return utils.FileFormat.JSON - elif file_path.endswith('.mat'): - return utils.FileFormat.MAT - elif file_path.endswith('.yml') or file_path.endswith('.yaml'): - return utils.FileFormat.YML - - # Default to XML for unknown extensions - return utils.FileFormat.XML - -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) - - # Convert name from list to string (handles names with spaces) - if isinstance(ARGS.name, list): - ARGS.name = ' '.join(ARGS.name) - - if ARGS.input: - # Load a custom model from file with auto-detected format - detected_format = detect_file_format(ARGS.input) - model = load_custom_model(utils.FilePath.fromStrPath(ARGS.input), detected_format) - else: - # Load a built-in model - if not ARGS.model: - raise utils.ArgsErr("model", "either --model or --input must be provided", "None") - - 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 - - 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.csv uses underscores now - 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.input and ARGS.gene_format != "Default": - logging.basicConfig(level=logging.INFO) - 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 using unified function - if not ARGS.out_tabular: - raise utils.ArgsErr("out_tabular", "output path (--out_tabular) is required when output_format == tabular", ARGS.out_tabular) - - merged = modelUtils.export_model_to_tabular( - model=model, - output_path=ARGS.out_tabular, - translation_issues=translation_issues, - include_objective=True, - save_function=save_as_tabular_df - ) - 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("Completed successfully") - -if __name__ == '__main__': - - main()
--- a/COBRAxy/src/metabolicModel2Tabular.xml Sat Oct 25 14:55:13 2025 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,154 +0,0 @@ -<tool id="metabolicModel2Tabular" name="Import Metabolic Model" version="2.0.0"> - - <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> - </requirements> - - <macros> - <import>marea_macros.xml</import> - </macros> - - <command detect_errors="exit_code"> - <![CDATA[ - python $__tool_directory__/metabolicModel2Tabular.py - --tool_dir $__tool_directory__ - --medium_selector $cond_model.cond_medium.medium_selector - #if $cond_model.model_selector == 'Custom_model' - --input $cond_model.input - --name $cond_model.input.element_identifier - --out_tabular $out_tabular_custom - #elif $cond_model.model_selector == 'ENGRO2' - --model $cond_model.model_selector - --name $cond_model.model_selector - --out_tabular $out_tabular_engro2 - #else - --model $cond_model.model_selector - --name $cond_model.model_selector - --out_tabular $out_tabular_recon - #end if - --gene_format $cond_model.gene_format - --out_log $log - ]]> - </command> - <inputs> - <conditional name="cond_model"> - <expand macro="options_model"/> - - <!-- ENGRO2 --> - <when value="ENGRO2"> - - <conditional name="cond_medium"> - <expand macro="options_ras_to_bounds_medium"/> - </conditional> - - <param name="gene_format" argument="--gene_format" type="select" label="Gene nomenclature format:"> - <option value="Default" selected="true">Keep original gene nomenclature (HGNC Symbol)</option> - <option value="ENSG">ENSG (Ensembl Gene ID)</option> - <option value="HGNC_ID">HGNC ID</option> - <option value="entrez_id">Entrez Gene ID</option> - </param> - </when> - - <!-- Recon --> - <when value="Recon"> - - <conditional name="cond_medium"> - <param name="medium_selector" argument="--medium_selector" type="select" label="Medium"> - <option value="Default" selected="true">Default (Recon built-in medium)</option> - </param> - <when value="Default"> - <!-- Nessun parametro aggiuntivo necessario --> - </when> - </conditional> - <param name="gene_format" argument="--gene_format" type="select" label="Gene nomenclature format:"> - <option value="Default" selected="true">Keep original gene nomenclature (HGNC Symbol)</option> - <option value="ENSG">ENSG (Ensembl Gene ID)</option> - <option value="HGNC_ID">HGNC ID</option> - <option value="entrez_id">Entrez Gene ID</option> - </param> - </when> - - <!-- Custom model --> - <when value="Custom_model"> - <param name="input" argument="--input" type="data" format="json,xml,sbml" label="Custom model file:" /> - <conditional name="cond_medium"> - <param name="medium_selector" argument="--medium_selector" type="select" label="Medium"> - <option value="Default" selected="true">Default (custom model medium)</option> - </param> - <when value="Default"> - <!-- Nessun parametro aggiuntivo necessario --> - </when> - </conditional> - <param name="gene_format" argument="--gene_format" type="select" label="Gene nomenclature format:"> - <option value="Default" selected="true">Keep original gene nomenclature</option> - <option value="HGNC_symbol">HGNC Symbol</option> - <option value="ENSG">ENSG (Ensembl Gene ID)</option> - <option value="HGNC_ID">HGNC ID</option> - <option value="entrez_id">Entrez Gene ID</option> - </param> - </when> - </conditional> - - </inputs> - - <outputs> - <data name="log" format="txt" label="MetabolicModelSetting - Log" /> - - <data name="out_tabular_engro2" format="tabular" label="ENGRO2_model_tabular"> - <filter>cond_model['model_selector'] == 'ENGRO2'</filter> - </data> - - <data name="out_tabular_recon" format="tabular" label="Recon_model_tabular"> - <filter>cond_model['model_selector'] == 'Recon'</filter> - </data> - - <data name="out_tabular_custom" format="tabular" label="${cond_model.input.element_identifier}_model_tabular"> - <filter>cond_model['model_selector'] == 'Custom_model'</filter> - </data> - </outputs> - - <help> - <![CDATA[ -Overview -------------- -This tool generates a Tabular file (.tabular) containing the main information of the metabolic model, starting -either from a built-in model or a user-provided model file. -For built-in models, users can select among different nutrient-informed variants (i.e., different media composition) and gene nomenclature formats. - -The generated tabular file can be used as input for tools Expression2RAS, Expression2RPS, RAS2Bounds, Flux Simulation and Export Metabolic Model - within the COBRAxy suite. - -Input parameters: -------------- - -The tool has three input parameters: - - Model: a file containing metabolic information (reactions, metabolites, genes). Ready-to-use models are ENGRO2 and Recon3D. - The user can also upload a custom model (see TIP 1). - - Medium: choose a growth medium typically used for cell culture (see TIP 2 & 3). - - Gene nomenclature format: use the original GPR gene names or translate them into another nomenclature. - -Output files: -------------- - -The tool generates: - - one tabular file (.tabular) containing reaction IDs, reaction formula, GPR rules, reaction bounds, objective function coefficients, pathways in which the reaction is involved and a flag indicating whether the reaction is an exchange reaction (i.e., related to the growth medium). - - a log file (.txt). - -**TIP 1**: Different input files can be used as the input model. The possible formats are XML (SBML), JSON, MAT or YAML (.yml). - Supported compressed formats: .zip, .gz and .bz2. Filename must follow the pattern: {model_name}.{extension}.[zip|gz|bz2] - More detail can be found at https://cobrapy.readthedocs.io/en/latest/io.html - -**TIP 2**: for pre-existing models ENGRO2 and RECON3D, the user can select the default built-in medium or one of the possible growth medium typically used for cell line cultures. -In case no specific information is available, it is possible to set an "OPEN" medium in which all the nutrients are available in unlimited quantity. - -**TIP 3:** Medium composition can be derived from the tabular file. Exchange reactions with `InMedium = TRUE` are included. Nutrient values correspond to the lower bound (e.g., EX_Glc_D_e lower bound -10 → nutrient value 10). -More info: [COBRApy Media](https://cobrapy-cdiener.readthedocs.io/en/latest/media.html) - - ]]> - </help> - <expand macro="citations" /> - -</tool> - -
--- a/COBRAxy/src/tabular2MetabolicModel.py Sat Oct 25 14:55:13 2025 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,117 +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) - - - logging.info('Created model with name: %s (ID: %s)', model.name, model.id) - - # Save model in requested format - Galaxy handles the filename - 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) - raise ValueError(f"Unknown format: {ARGS.format}") - - - logging.info('Model successfully written to %s (format=%s)', ARGS.output, ARGS.format) - print(f"Model created successfully in {ARGS.format.upper()} format") - - except Exception as e: - # Log full traceback to the out_log so Galaxy users/admins can see what happened - logging.exception('Unhandled exception in fromCSVtoCOBRA') - print(f"ERROR: {str(e)}") - raise - - -if __name__ == '__main__': - main()
--- a/COBRAxy/src/tabular2MetabolicModel.xml Sat Oct 25 14:55:13 2025 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,82 +0,0 @@ -<tool id="tabular2MetabolicModel" name="Export Metabolic Model" version="1.0.0"> - <description>Export a tabular model to file format (SBML, JSON, MAT or YAML)</description> - - <!-- Python dependencies required for COBRApy --> - <requirements> - <requirement type="package" version="0.29.0">cobra</requirement> - <requirement type="package" version="1.24.4">numpy</requirement> - <requirement type="package" version="2.0.3">pandas</requirement> - <requirement type="package" version="5.2.2">lxml</requirement> - </requirements> - - <!-- Import shared macros if available --> - <macros> - <import>marea_macros.xml</import> - </macros> - - <!-- Command to run the Python script --> - <command detect_errors="exit_code"><![CDATA[ - python $__tool_directory__/tabular2MetabolicModel.py - --tool_dir $__tool_directory__ - --input $input - --format $format - --output $output - --out_log $log - ]]></command> - - <!-- Tool inputs --> - <inputs> - <param name="input" type="data" format="tabular,csv,tsv" label="Model tabular:"/> - <param name="model_name" type="text" value="Converted_Model" label="Output model name:" help="Name for the created COBRA model"/> - <param name="format" type="select" label="Output format"> - <option value="sbml" selected="true">SBML (.xml)</option> - <option value="json">JSON (.json)</option> - <option value="mat">MATLAB (.mat)</option> - <option value="yaml">YAML (.yml)</option> - </param> - </inputs> - - <!-- Tool outputs --> - <outputs> - <data name="log" format="txt" label="Tabular to Model Conversion - Log" /> - <data name="output" format="xml" label="${model_name}.${format}"> - <change_format> - <when input="format" value="sbml" format="xml"/> - <when input="format" value="json" format="json"/> - <when input="format" value="mat" format="mat"/> - <when input="format" value="yaml" format="yaml"/> - </change_format> - </data> - </outputs> - - <!-- Help section --> - <help><![CDATA[ -This tool exports a tabular dataset into a standard metabolic model file formats using COBRApy. - -**Input** -- A tabular/CSV/TSV file describing the metabolic properties of the model (reactions, metabolites, and genes), as generated by the Import Metabolic Model tool. - -The possible columns are: - - ReactionID: unique identifier of the reactions - - Formula: chemical equation showing the metabolites involved in the reaction and their stoichiometric coefficients. - - GPR: gene-protein-reaction association, expressed as a logical rule describing how genes contribute to catalyzing the reaction. - - lower bound: minimum allowable flux value for the reaction. - - upper bound: maximum allowable flux value for the reaction. - - Objective coefficient: coefficient used in the objective function (e.g., for pFBA or FVA analyses). - - Pathway_1,Pathway_2,etc.: possible pathways in which the reaction is involved. - - InMedium: TRUE if the reaction represents nutrient uptake from the medium, FALSE otherwise. - -Columns ReactionID and Formula are mandatory. - -**Output** -- A COBRA model in the chosen format: - - SBML (.xml) - - JSON (.json) - - MATLAB (.mat) - - YAML (.yml) - -**Notes** -- The exact table structure (columns required) depends on how you want to encode reactions and metabolites. -- You can extend the Python script to parse specific column formats. - ]]></help> -</tool>
--- a/COBRAxy/src/test/test_marea.py Sat Oct 25 14:55:13 2025 +0000 +++ b/COBRAxy/src/test/test_marea.py Sat Oct 25 15:08:19 2025 +0000 @@ -147,16 +147,16 @@ def test_tabular_to_model(self): """Test tabular to model conversion""" - import tabular2MetabolicModel + import COBRAxy.src.exportMetabolicModel as exportMetabolicModel - args = tabular2MetabolicModel.process_args([]) + args = exportMetabolicModel.process_args([]) assert hasattr(args, 'tool_dir') def test_model_to_tabular(self): """Test model to tabular conversion""" - import metabolicModel2Tabular + import COBRAxy.src.importMetabolicModel as importMetabolicModel - args = metabolicModel2Tabular.process_args([]) + args = importMetabolicModel.process_args([]) assert hasattr(args, 'tool_dir')