def build_bigg_universe_model(outputfile=None):
""" Download the whole BiGG universe database as a CBModel and (optionally) store in SBML.
Args:
outputfile (str): SBML output file (optional)
Returns:
CBModel: universe model
"""
print 'Downloading universal data from BiGG...'
model = CBModel('bigg_universe')
bigg_rxns = get_request(reactions_url)
n = len(bigg_rxns['results'])
for i, entry in enumerate(bigg_rxns['results']):
build_reaction(model, entry['bigg_id'])
progress(i, n)
print '\n'
if outputfile:
save_cbmodel(model, outputfile)
return model
def save_ensemble(ensemble, outputfile, **kwargs):
""" Save ensemble model as an SBML file.
Args:
ensemble (EnsembleModel): model ensemble
outputfile (str): output file
**kwargs (dict): additional arguments to *save_cbmodel* method
"""
for r_id, states in ensemble.reaction_states.items():
state_as_str = ' '.join([str(int(x)) for x in states])
ensemble.model.reactions[r_id].metadata['ENSEMBLE_STATE'] = state_as_str
save_cbmodel(ensemble.model, outputfile, **kwargs)
def main(inputfiles, flavor=None, split_pool=False, no_biomass=False, init=None, mediadb=None, ext_comp_id=None, outputfile=None):
if not flavor:
flavor = config.get('sbml', 'default_flavor')
if outputfile:
model_id = os.path.splitext(os.path.basename(outputfile))[0]
else:
model_id = 'community'
outputfile = 'community.xml'
if ext_comp_id is None:
ext_comp_id = 'C_e'
models = [load_cbmodel(inputfile, flavor=flavor) for inputfile in inputfiles]
community = Community(model_id, models,
extracellular_compartment_id=ext_comp_id,
merge_extracellular_compartments=(not split_pool),
create_biomass=(not no_biomass))
merged = community.generate_merged_model()
if init:
if not mediadb:
mediadb = project_dir + config.get('input', 'media_library')
try:
media_db = load_media_db(mediadb)
except IOError:
raise IOError('Failed to load media library:' + mediadb)
if split_pool:
exchange_format = "'R_EX_M_{}_e_pool'"
else:
exchange_format = "'R_EX_{}_e'"
init_env = Environment.from_compounds(media_db[init], exchange_format=exchange_format)
init_env.apply(merged, inplace=True)
save_cbmodel(merged, outputfile, flavor=flavor)
def main(inputfile, media, mediadb=None, universe=None, universe_file=None, outputfile=None, flavor=None,
exchange_format=None, verbose=False):
if verbose:
print('Loading model...')
try:
model = load_cbmodel(inputfile, flavor=flavor)
except IOError:
raise IOError('Failed to load model:' + inputfile)
if verbose:
print('Loading reaction universe...')
if not universe_file:
if universe:
universe_file = "{}{}universe_{}.xml".format(project_dir, config.get('generated', 'folder'), universe)
else:
universe_file = project_dir + config.get('generated', 'default_universe')
try:
universe_model = load_cbmodel(universe_file)
except IOError:
if universe:
raise IOError('Failed to load universe "{0}". Please run build_universe.py --{0}.'.format(universe))
else:
raise IOError('Failed to load universe model:' + universe_file)
if verbose:
print('Loading media...')
if not mediadb:
mediadb = project_dir + config.get('input', 'media_library')
try:
media_db = load_media_db(mediadb)
except IOError:
raise IOError('Failed to load media database:' + mediadb)
if verbose:
m1, n1 = len(model.metabolites), len(model.reactions)
print('Gap filling for {}...'.format(', '.join(media)))
max_uptake = config.getint('gapfill', 'max_uptake')
multiGapFill(model, universe_model, media, media_db, max_uptake=max_uptake, inplace=True,
exchange_format=exchange_format)
if verbose:
m2, n2 = len(model.metabolites), len(model.reactions)
print('Added {} reactions and {} metabolites'.format((n2 - n1), (m2 - m1)))
if verbose:
print('Saving SBML file...')
if not outputfile:
outputfile = os.path.splitext(inputfile)[0] + '_gapfill.xml'
if not flavor:
flavor = config.get('sbml', 'default_flavor')
save_cbmodel(model, outputfile, flavor=flavor)
if verbose:
print('Done.')
def curate_universe(model, model_specific_data, bigg_models, biomass_eq, taxa=None,
thermodynamics_data=None, metabolomics_data=None, thermodynamics_method=None,
manually_curated=None, unbalanced_metabolites=None, use_heuristics=True,
remove_unbalanced=True, remove_blocked=True, outputfile=None):
""" Curate universal reaction database from initial database dump.
Args:
model (CBModel): universal model
model_specific_data (pandas.DataFrame): model specific data downloaded from BiGG
bigg_models (pandas.DataFrame): Additional information on BiGG models
biomass_eq (str): default biomass equation
taxa (str): filter by taxa (optional)
thermodynamics_data (pandas.DataFrame): used for reversibility estimation (optional)
metabolomics_data (pandas.DataFrame): used for reversibility estimation (optional)
thermodynamics_method (str): thermodynamics method to use (optional)
manually_curated (pandas.DataFrame): manually curated reaction bounds (optional)
unbalanced_metabolites (list): unbalanced metabolites that require sink reactions (optional)
use_heuristics (bool): apply heuristic rules (no proton pumps, no reversible ATP consumers) (default: True)
remove_unbalanced (bool): remove unbalanced reactions from model (default: True)
remove_blocked (bool): remove blocked reactions and dead-end metabolites (default: True)
outputfile (str): output SBML file (optional)
Returns:
CBModel: curated universal model
Notes:
Combines thermodynamics and heuristic rules to determine reaction reversibility.
Adds exchange reactions for all extracellular metabolites.
Adds sinks reactions for a list of known unbalanced compounds.
Adds biomass equations from local biomass database (avoids discarding biomass precursors and other
essencial reactions/metabolites that would otherwise be structurally blocked).
"""
print('Starting universe curation...')
print('(initial size: {} x {})\n'.format(len(model.metabolites), len(model.reactions)))
trusted_models = bigg_models.query('trusted == True').index.tolist()
add_bounds_from_extracted_data(model, model_specific_data, trusted_models)
if taxa:
print('Filtering by taxa:', taxa)
kingdom_map = bigg_models['domain'].to_dict()
if taxa in {'cyanobacteria', 'bacteria'}:
kingdoms = {'Bacteria'}
elif taxa == 'archaea':
kingdoms = {'Archaea', 'Bacteria'}
else:
raise ValueError('Unsupported taxa:' + taxa)
filter_reactions_by_kingdoms(model, kingdoms, kingdom_map, inplace=True)
if taxa in {'bacteria', 'archaea'}:
valid_compartments = {'C_c', 'C_p', 'C_e'}
elif taxa == 'cyanobacteria':
valid_compartments = {'C_c', 'C_p', 'C_e', 'C_u'}
other_compartments = set(model.compartments.keys()) - valid_compartments
model.remove_compartments(other_compartments, delete_metabolites=True, delete_reactions=True)
print('(size: {} x {})\n'.format(len(model.metabolites), len(model.reactions)))
if thermodynamics_data is not None:
print('Computing thermodynamics...', end=' ')
dG0 = thermodynamics_data['dG0'].to_dict()
sdG0 = thermodynamics_data['sdG0'].to_dict()
if metabolomics_data is not None:
x0 = metabolomics_data.median(axis=1).to_dict()
else:
x0 = None
compute_flux_bounds(model, dG0, sdG0, x0, method=thermodynamics_method, inplace=True, override_trusted=False)
print('done\n')
print('Applying manual curation rules...', end=' ')
if use_heuristics:
reversibility_heuristics(model, no_reverse_atp=True, no_proton_pumps=False, override_trusted=False)
# manually curated reactions
if manually_curated is not None:
for r_id, (lb, ub) in manually_curated.iterrows():
if r_id in model.reactions:
model.set_flux_bounds(r_id, lb, ub)
print('done\n')
if remove_unbalanced:
# remove arbitrary 'Z' formula from photons
if taxa == 'cyanobacteria':
for m_id in ['M_photon_e', 'M_photon_p', 'M_photon_c']:
model.metabolites[m_id].metadata['FORMULA'] = ''
print('Removing unbalanced reactions...')
remove_unbalanced_reactions(model)
print('(size: {} x {})\n'.format(len(model.metabolites), len(model.reactions)))
print('Creating pseudo-reactions...')
create_exchange_reactions(model, default_lb=-1000, default_ub=1000)
if unbalanced_metabolites:
create_sink_reactions(model, unbalanced_metabolites)
add_biomass_equation(model, biomass_eq)
add_maintenance_atp(model)
print('(size: {} x {})\n'.format(len(model.metabolites), len(model.reactions)))
if remove_blocked:
print('Removing blocked reactions and dead-end metabolites...')
simplify(model)
print('(size: {} x {})\n'.format(len(model.metabolites), len(model.reactions)))
if outputfile:
save_cbmodel(model, outputfile)
print('Done.')
