# HG changeset patch # User tduigou # Date 1743067626 0 # Node ID dc1167469d620335fdfc05cbc9ade6044a18aef0 # Parent 6a2871e893527e9d4b3b656f57f8098f610074cc planemo upload for repository https://github.com/brsynth/synbiocad-galaxy-wrappers commit 94f89a44e330ccfccc8d94b5e7acf583c9d39343 diff -r 6a2871e89352 -r dc1167469d62 get_infos.py --- a/get_infos.py Wed Feb 14 15:25:38 2024 +0000 +++ b/get_infos.py Thu Mar 27 09:27:06 2025 +0000 @@ -1,179 +1,140 @@ from argparse import ArgumentParser -from libsbml import ( - readSBMLFromFile -) +from libsbml import readSBMLFromFile from taxonid import get_taxonid +from requests import get as r_get def get_biomass_rxn(sbml_doc): - ''' + """ Returns the biomass reaction of the model - + Parameters ---------- sbml_doc: libsbml.SBMLDocument SBML model - + Returns ------- biomass_rxn: libsbml.Reaction Biomass reaction - ''' + """ reactions = sbml_doc.getModel().getListOfReactions() # Search for 'biomass' keyword in reaction name for rxn in reactions: - if 'biomass' in rxn.getName().lower(): + if "biomass" in rxn.getName().lower(): return rxn # Search for 'biomass' keyword in products # AND not in reactants for rxn in reactions: in_reactants = False for reac in rxn.getListOfReactants(): - if 'biomass' in reac.getSpecies().lower(): + if "biomass" in reac.getSpecies().lower(): in_reactants = True break if not in_reactants: for prod in rxn.getListOfProducts(): - if 'biomass' in prod.getSpecies().lower(): + if "biomass" in prod.getSpecies().lower(): return rxn return None def args(): - parser = ArgumentParser('Returns cell informations') - parser.add_argument( - 'infile', - type=str, - help='SBML input file (xml)' - ) - # argument to tag file from BiGG - parser.add_argument( - '--bigg', - action='store_true', - help='Tag file from BiGG' - ) - parser.add_argument( - '--comp', - type=str, - help='Path to store cell compartments' - ) - parser.add_argument( - '--biomass', - type=str, - help='Path to store biomass reaction ID' - ) - parser.add_argument( - '--biomass-id', - type=str, - help='ID of biomass reaction' - ) - parser.add_argument( - '--hostname', - type=str, - help='Name of the host organism' - ) - parser.add_argument( - '--taxid', - type=str, - help='Path to store host taxonomy ID' - ) + parser = ArgumentParser("Returns cell informations") + parser.add_argument("infile", type=str, help="SBML input file (xml)") + parser.add_argument("--hostname-or-id", type=str, help="Hostname or model ID") + parser.add_argument("--comp", type=str, help="Path to store cell compartments") + parser.add_argument("--biomass", type=str, help="Path to store biomass reaction ID") + parser.add_argument("--biomass-id", type=str, help="ID of biomass reaction") + parser.add_argument("--taxid", type=str, help="Path to store host taxonomy ID") params = parser.parse_args() return params -def get_taxon_id(hostid: str, bigg: bool): - ''' - Returns the taxonomy ID of the host organism - - Parameters - ---------- - hostid: str - Extended name of the host organism or host ID if from BiGG - bigg: bool - True if the model is from BiGG - - Returns - ------- - taxid: str - Taxonomy ID of the host organism - ''' - if not bigg: - return get_taxonid(hostid) +def get_organism_from_bigg_model(model_id): + """Try to retrieve organism info from BiGG Models for a given model ID.""" + url = f"http://bigg.ucsd.edu/api/v2/models/{model_id}" + try: + response = r_get(url) + if response.status_code == 200: + data = response.json() + organism = data.get("organism") + return organism + except Exception as e: + print(f"Error querying BiGG: {e}") + return None - hostname = '' - # Extended Name - server = 'http://bigg.ucsd.edu/api/v2/models/' - ext = hostid - r = r_get(server+ext, headers={ "Content-Type" : "application/json"}) - if not r.ok: - print(f"Warning: unable to retrieve host name for id {hostid}") - else: - try: - hostname = r.json()["organism"] - except KeyError: - print(f"Warning: unable to retrieve host name for id {hostid}") - if not hostname: - taxid = '' - else: - # TAXON ID - server = 'https://rest.ensembl.org' - ext = f'/taxonomy/id/{hostname}?' - r = r_get(server+ext, headers={ "Content-Type" : "application/json"}) - if not r.ok: - print(f"Warning: unable to retrieve taxonomy ID for host organism {hostname}") - else: - try: - taxid = r.json()["id"] - except KeyError: - print(f"Warning: unable to retrieve taxonomy ID for host organism {hostname}") - taxid = '' - return taxid +def get_taxon_id(input_name): + """Try BiGG model name first, then NCBI directly.""" + print(f"Trying input: {input_name}") + + # Try resolving as a BiGG model + organism = get_organism_from_bigg_model(input_name) + if organism: + print(f"Model '{input_name}' maps to organism: {organism}") + taxon_id = get_taxonid(organism) + if taxon_id: + return taxon_id + + # If not a model, try directly as an organism name + print(f"Trying NCBI search with input: {input_name}") + return get_taxonid(input_name) def entry_point(): + params = args() - params = args() + # test if the file exists + with open(params.infile): + pass sbml_doc = readSBMLFromFile(params.infile) compartments = sbml_doc.getModel().getListOfCompartments() - comp_str = '' + comp_str = "" for comp in compartments: - comp_str += f'{comp.getId()}\t{comp.getName()}\n' + comp_str += f"{comp.getId()}\t{comp.getName()}\n" + print("Compartments:") + for comp in compartments: + print(f"{comp.getId()}\t{comp.getName()}".replace("\n", " | ")) if params.comp: - with open(params.comp, 'w') as f: - f.write('#ID\tNAME\n') + with open(params.comp, "w") as f: + f.write("#ID\tNAME\n") f.write(comp_str) - else: - print('Compartments:') - for comp in compartments: - print(f'{comp.getId()}\t{comp.getName()}'.replace('\n', ' | ')) if params.biomass_id: biomass_rxn = sbml_doc.getModel().getReaction(params.biomass_id) else: biomass_rxn = get_biomass_rxn(sbml_doc) if not biomass_rxn: - print('Warning: unable to retrieve biomass reaction') - biomass_id = '' + print("Warning: unable to retrieve biomass reaction") + biomass_id = "" else: biomass_id = biomass_rxn.getId() + print(f"Biomass reaction ID: {biomass_id}") if params.biomass: - with open(params.biomass, 'w') as f: - f.write('#ID\n') - f.write(f'{biomass_id}\n') + with open(params.biomass, "w") as f: + f.write("#ID\n") + f.write(f"{biomass_id}\n") + + if params.hostname_or_id: + taxid = get_taxon_id(params.hostname_or_id) else: - print(f'Biomass reaction ID: {biomass_id}') - - taxid = get_taxon_id(params.hostname, params.bigg) + model_id = sbml_doc.getModel().getId() + taxid = -1 + if model_id: + taxid = get_taxon_id(sbml_doc.getModel().getId()) + if taxid == -1: + # Try with model name + model_name = sbml_doc.getModel().getName() + if model_name: + taxid = get_taxon_id(sbml_doc.getModel().getName()) + print(f"Taxonomy ID: {taxid}") if params.taxid: - with open(params.taxid, 'w') as f: - f.write('#ID\n') - f.write(f'{taxid}\n') - else: - print(f'Taxonomy ID: {taxid}') + with open(params.taxid, "w") as f: + f.write("#ID\n") + f.write(f"{taxid}\n") if __name__ == "__main__": - entry_point() \ No newline at end of file + entry_point() diff -r 6a2871e89352 -r dc1167469d62 get_sbml_model.xml --- a/get_sbml_model.xml Wed Feb 14 15:25:38 2024 +0000 +++ b/get_sbml_model.xml Thu Mar 27 09:27:06 2025 +0000 @@ -1,4 +1,4 @@ - + Get an SBML model (BiGG) curl @@ -8,17 +8,15 @@ taxonid '$model' && + curl -o - 'http://bigg.ucsd.edu/static/models/${cond_src.hostid.hostid}.xml.gz' | gunzip > '$model' && + #else + #set model=$cond_src.input_file #end if python '$__tool_directory__/'get_infos.py - #if str($cond_src.from_src) == 'from_bigg' - '$model' - --bigg - #else - '${cond_src.input_file}' - #end if - --hostname '${cond_src.hostid}' + '$model' + --hostname-or-id '$cond_src.hostid.hostid' --taxid '$taxid' --comp '$compartments' --biomass '$biomass' @@ -30,92 +28,124 @@ - - - +
+ +
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
- + cond_src['from_src'] == 'from_bigg' - - - + + + - - - + + + +
+ +
+ - + - + - + - - +
+ +
+ + + + + + + + + +
+ +
- + - + + + + +
+ +
+ + + + + +