def maincall(inputfiles,
flavor=None,
init=None,
mediadb=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'
models = [
load_cbmodel(inputfile, flavor=flavor) for inputfile in inputfiles
]
community = Community(model_id, models)
model = community.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)
init_env = Environment.from_compounds(media_db[init])
init_env.apply(model, inplace=True)
save_cbmodel(model, outputfile, flavor=flavor)
def compute_bigg_gibbs_energy(modelfile, equi_cmpds_file, outputfile=None):
""" Calculate standard Gibbs Energy for reactions in a model (as many as possible) using eQuilibrator.
Args:
modelfile (str): SBML file
equi_cmpds_file (str): file containing KEGG compounds accepted by eQuilibrator
outputfile (str): output CSV file (optional)
Returns:
dict: standard Gibbs Energies indexed by reaction ids
dict: estimation error indexed by reaction ids
"""
model = load_cbmodel(modelfile)
kegg_compounds = pd.read_csv(equi_cmpds_file, sep='\t')
kegg_compounds = set(kegg_compounds['compound_id'])
dG0, sdG0 = calculate_deltaG0s(model, kegg_compounds, pH=default_pH, I=default_I, T=default_T)
if outputfile:
data = pd.DataFrame({'dG0': dG0, 'sdG0': sdG0})
data.to_csv(outputfile)
else:
return dG0, sdG0
def __init__(self, model):
try:
self.model = load_cbmodel(
"C:\\Users\\Pedro\\OneDrive\\Documentos\\UMinho\\WholeNewProject\\PythonThings\\Models\\"
+ model)
self.useReframed = True
except:
self.model = ProcessXML(model)
self.model.getCompartments()
self.model.getSpecies()
self.model.getReactions()
self.useReframed = False
def curate(inputfile=None, outputfile=None, taxa=None, biomass=None, biomass_db_path=None, normalize_biomass=False):
if inputfile:
universe_draft = inputfile
model_specific_data = os.path.splitext(inputfile)[0] + '.csv'
else:
universe_draft = project_dir + config.get('generated', 'bigg_universe')
model_specific_data = project_dir + config.get('generated', 'model_specific_data')
if not biomass:
biomass = 'gramneg' if taxa == 'cyanobacteria' else taxa
if not outputfile:
folder = project_dir + config.get('generated', 'folder')
outputfile = folder + f"universe_{taxa}.xml.gz"
bigg_models = project_dir + config.get('input', 'bigg_models')
bigg_models = pd.read_csv(bigg_models, sep='\t')
manual_curation = project_dir + config.get('input', 'manually_curated')
manually_curated = pd.read_csv(manual_curation, index_col=0, sep='\t')
unbalanced = project_dir + config.get('input', 'unbalanced_metabolites')
unbalanced = pd.read_csv(unbalanced, header=None)
unbalanced = unbalanced[0].tolist()
try:
model = load_cbmodel(universe_draft, flavor=config.get('sbml', 'default_flavor'))
model_specific_data = pd.read_csv(model_specific_data)
except IOError:
raise IOError('Universe draft model not found. Please run --build first to download BiGG data.')
if biomass_db_path is None:
biomass_db_path = project_dir + config.get('input', 'biomass_library')
biomass_db = load_biomass_db(biomass_db_path, normalize_weight=normalize_biomass, model=model)
if biomass not in biomass_db:
valid_ids = ','.join(biomass_db.keys())
raise RuntimeError('Biomass identifier not in database. Currently in database: ' + valid_ids)
biomass_eq = biomass_db[biomass]
curate_universe(model,
outputfile=outputfile,
taxa=taxa,
biomass_eq=biomass_eq,
model_specific_data=model_specific_data,
bigg_models=bigg_models,
manually_curated=manually_curated,
unbalanced_metabolites=unbalanced,
)
def maincall(mode, noheuristics=False, nothermo=False, allow_unbalanced=False, allow_blocked=False,
biomass=None, biomass_db_path=None, normalize_biomass=False, taxa=None, outputfile=None):
if mode == 'draft':
if outputfile:
universe_draft = outputfile
model_specific_data = os.path.splitext(outputfile)[0] + '.csv'
bigg_gprs = os.path.splitext(outputfile)[0] + '_gprs.csv'
# fasta_file = os.path.splitext(outputfile)[0] + '.faa'
else:
universe_draft = project_dir + config.get('generated', 'universe_draft')
model_specific_data = project_dir + config.get('generated', 'model_specific_data')
bigg_gprs = project_dir + config.get('generated', 'bigg_gprs')
# fasta_file = project_dir + config.get('input', 'fasta_file')
build_bigg_universe_model(universe_draft)
data = download_model_specific_data(model_specific_data)
gprs = create_gpr_table(data, outputfile=bigg_gprs)
# download_gene_sequences(gprs, outputfile=fasta_file)
elif mode == 'thermo':
universe_draft = project_dir + config.get('generated', 'universe_draft')
equilibrator_compounds = project_dir + config.get('input', 'equilibrator_compounds')
if outputfile:
bigg_gibbs = outputfile
else:
bigg_gibbs = project_dir + config.get('generated', 'bigg_gibbs')
compute_bigg_gibbs_energy(universe_draft, equilibrator_compounds, bigg_gibbs)
elif mode == 'curated':
universe_draft = project_dir + config.get('generated', 'universe_draft')
model_specific_data = project_dir + config.get('generated', 'model_specific_data')
if not biomass:
if taxa == 'archaea':
biomass = 'archaea'
else:
biomass = config.get('universe', 'default_biomass')
if outputfile:
universe_final = outputfile
else:
tag = taxa if taxa != 'bacteria' else biomass
universe_final = "{}{}universe_{}.xml.gz".format(project_dir, config.get('generated', 'folder'), tag)
bigg_models = project_dir + config.get('input', 'bigg_models')
bigg_models = pd.read_csv(bigg_models, index_col=0)
manual_curation = project_dir + config.get('input', 'manually_curated')
manually_curated = pd.read_csv(manual_curation, index_col=0)
unbalanced = project_dir + config.get('input', 'unbalanced_metabolites')
unbalanced = pd.read_csv(unbalanced, header=None)
unbalanced = unbalanced[0].tolist()
try:
model = load_cbmodel(universe_draft, flavor=config.get('sbml', 'default_flavor'))
model_specific_data = pd.read_csv(model_specific_data)
except IOError:
raise IOError('Universe draft not found. Please run --draft first to download BiGG data.')
if biomass_db_path is None:
biomass_db_path = project_dir + config.get('input', 'biomass_library')
biomass_db = load_biomass_db(biomass_db_path, normalize_weight=normalize_biomass, model=model)
if biomass not in biomass_db:
valid_ids = ','.join(biomass_db.keys())
raise RuntimeError('Biomass identifier not in database. Currently in database: ' + valid_ids)
biomass_eq = biomass_db[biomass]
if nothermo:
thermodynamics_data = None
metabolomics_data = None
else:
try:
bigg_gibbs = project_dir + config.get('generated', 'bigg_gibbs')
thermodynamics_data = pd.read_csv(bigg_gibbs, index_col=0)
except IOError:
raise IOError('Thermodynamic data not found. Please run --thermo first to generate thermodynamic data.')
metabolomics = project_dir + config.get('input', 'metabolomics')
metabolomics_data = pd.read_csv(metabolomics, index_col=1)
curate_universe(model,
taxa=taxa,
outputfile=universe_final,
model_specific_data=model_specific_data,
bigg_models=bigg_models,
thermodynamics_data=thermodynamics_data,
metabolomics_data=metabolomics_data,
manually_curated=manually_curated,
unbalanced_metabolites=unbalanced,
biomass_eq=biomass_eq,
use_heuristics=(not noheuristics),
remove_unbalanced=(not allow_unbalanced),
remove_blocked=(not allow_blocked))
else:
print('Unrecognized option:', mode)
def maincall(inputfile,
media,
mediadb=None,
universe=None,
universe_file=None,
outputfile=None,
flavor=None,
spent=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 spent:
if verbose:
print('Loading model for spent medium species...')
try:
spent_model = load_cbmodel(spent, flavor=flavor)
except IOError:
raise IOError('Failed to load model:' + spent)
else:
spent_model = None
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, flavor='cobra')
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,
spent_model=spent_model)
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 load_models():
models = {}
for org_id in organisms:
models[org_id] = load_cbmodel(f"{data_path}/models/{org_id}.xml",
flavor='bigg')
return models
def maincall(inputfile, input_type='protein', outputfile=None, diamond_args=None, universe=None, universe_file=None,
ensemble_size=None, verbose=False, debug=False, flavor=None, gapfill=None, blind_gapfill=False, init=None,
mediadb=None, default_score=None, uptake_score=None, soft_score=None, soft=None, hard=None, reference=None,
ref_score=None, recursive_mode=False):
if recursive_mode:
model_id = os.path.splitext(os.path.basename(inputfile))[0]
if outputfile:
outputfile = f'{outputfile}/{model_id}.xml'
else:
outputfile = os.path.splitext(inputfile)[0] + '.xml'
else:
if outputfile:
model_id = os.path.splitext(os.path.basename(outputfile))[0]
else:
model_id = os.path.splitext(os.path.basename(inputfile))[0]
outputfile = os.path.splitext(inputfile)[0] + '.xml'
model_id = build_model_id(model_id)
outputfolder = os.path.abspath(os.path.dirname(outputfile))
if not os.path.exists(outputfolder):
try:
os.makedirs(outputfolder)
except:
print('Unable to create output folder:', outputfolder)
return
if soft:
try:
soft_constraints = load_soft_constraints(soft)
except IOError:
raise IOError('Failed to load soft-constraints file:' + soft)
else:
soft_constraints = None
if hard:
try:
hard_constraints = load_hard_constraints(hard)
except IOError:
raise IOError('Failed to load hard-constraints file:' + hard)
else:
hard_constraints = None
if input_type == 'refseq':
if verbose:
print(f'Downloading genome {inputfile} from NCBI...')
ncbi_table = load_ncbi_table(project_dir + config.get('input', 'refseq'))
inputfile = download_ncbi_genome(inputfile, ncbi_table)
if not inputfile:
print('Failed to download genome from NCBI.')
return
input_type = 'protein' if inputfile.endswith('.faa.gz') else 'dna'
if input_type == 'protein' or input_type == 'dna':
if verbose:
print('Running diamond...')
diamond_db = project_dir + config.get('generated', 'diamond_db')
blast_output = os.path.splitext(inputfile)[0] + '.tsv'
exit_code = run_blast(inputfile, input_type, blast_output, diamond_db, diamond_args, verbose)
if exit_code is None:
print('Unable to run diamond (make sure diamond is available in your PATH).')
return
if exit_code != 0:
print('Failed to run diamond.')
if diamond_args is not None:
print('Incorrect diamond args? Please check documentation or use default args.')
return
annotations = load_diamond_results(blast_output)
elif input_type == 'eggnog':
annotations = load_eggnog_data(inputfile)
elif input_type == 'diamond':
annotations = load_diamond_results(inputfile)
else:
raise ValueError('Invalid input type: ' + input_type)
if verbose:
print('Loading universe model...')
if not universe_file:
if universe:
universe_file = f"{project_dir}{config.get('generated', 'folder')}universe_{universe}.xml.gz"
else:
universe_file = project_dir + config.get('generated', 'default_universe')
try:
universe_model = load_cbmodel(universe_file, flavor='bigg')
universe_model.id = model_id
except IOError:
available = '\n'.join(glob(f"{project_dir}{config.get('generated', 'folder')}universe_*.xml.gz"))
raise IOError(f'Failed to load universe model: {universe_file}\nAvailable universe files:\n{available}')
if reference:
if verbose:
print('Loading reference model...')
try:
ref_model = load_cbmodel(reference)
except:
raise IOError('Failed to load reference model.')
else:
ref_model = None
if gapfill or init:
if verbose:
print('Loading media library...')
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 verbose:
print('Scoring reactions...')
gene_annotations = pd.read_csv(project_dir + config.get('generated', 'gene_annotations'), sep='\t')
bigg_gprs = project_dir + config.get('generated', 'bigg_gprs')
gprs = pd.read_csv(bigg_gprs)
gprs = gprs[gprs.reaction.isin(universe_model.reactions)]
debug_output = model_id if debug else None
scores, gene2gene = reaction_scoring(annotations, gprs, debug_output=debug_output)
if scores is None:
print('The input genome did not match sufficient genes/reactions in the database.')
return
if not flavor:
flavor = config.get('sbml', 'default_flavor')
init_env = None
if init:
if init in media_db:
init_env = Environment.from_compounds(media_db[init])
else:
print(f'Error: medium {init} not in media database.')
universe_model.metadata['Description'] = 'This model was built with CarveMe version ' + version
if ensemble_size is None or ensemble_size <= 1:
if verbose:
print('Reconstructing a single model')
model = carve_model(universe_model, scores, inplace=(not gapfill), default_score=default_score,
uptake_score=uptake_score, soft_score=soft_score, soft_constraints=soft_constraints,
hard_constraints=hard_constraints, ref_model=ref_model, ref_score=ref_score,
init_env=init_env, debug_output=debug_output)
annotate_genes(model, gene2gene, gene_annotations)
else:
if verbose:
print('Building an ensemble of', ensemble_size, 'models')
ensemble = build_ensemble(universe_model, scores, ensemble_size, init_env=init_env)
annotate_genes(ensemble, gene2gene, gene_annotations)
save_ensemble(ensemble, outputfile, flavor=flavor)
if model is None:
print("Failed to build model.")
return
if not gapfill:
save_cbmodel(model, outputfile, flavor=flavor)
else:
media = gapfill.split(',')
if verbose:
m1, n1 = len(model.metabolites), len(model.reactions)
print(f"Gap filling for {', '.join(media)}...")
max_uptake = config.getint('gapfill', 'max_uptake')
if blind_gapfill:
scores = None
else:
scores = dict(scores[['reaction', 'normalized_score']].values)
multiGapFill(model, universe_model, media, media_db, scores=scores, max_uptake=max_uptake, inplace=True)
if verbose:
m2, n2 = len(model.metabolites), len(model.reactions)
print(f'Added {(n2 - n1)} reactions and {(m2 - m1)} metabolites')
if init_env: # Initializes environment again as new exchange reactions can be acquired during gap-filling
init_env.apply(model, inplace=True, warning=False)
save_cbmodel(model, outputfile, flavor=flavor)
if verbose:
print('Done.')
def simulate(wrappers, medium, method):
"""
Run a SteadyCom community simulation.
Parameters
----------
wrappers: list(storage.ModelWrapper)
A list of model wrappers containing cobrapy model instances.
medium: list(str)
A list of compound names. Exchange reaction identifiers are assumed to
be formatted according to: "EX_{compound}_e"
method: str
The community simulation method. Currently accepted strings:
"steadycom" or "steadiercom".
"""
if method not in METHODS:
raise ValueError(f"Unsupported community simulation method '{method}'")
with warnings.catch_warnings(record=True) as reframed_warnings:
logger.debug("Converting cobrapy models to reframed models")
rf_models = []
for model in [wrapper.model for wrapper in wrappers]:
# The most funcational approach (albeit slow) seems to be to write and
# reload SBML. reframed's cobrapy integration is currently pretty
# minimal.
with tempfile.NamedTemporaryFile() as file_:
cobra.io.write_sbml_model(model, file_.name)
# TODO: Consider accepting the flavor argument as a parameter
# instead of always assuming BiGG.
rf_models.append(
reframed.load_cbmodel(file_.name, flavor="bigg"))
logger.debug("Merging individual models to a community")
community = reframed.Community("community", rf_models)
logger.debug("Applying medium to the community")
environment = reframed.Environment.from_compounds(
medium, fmt_func=lambda x: f"R_EX_M_{x}_e")
environment.apply(community.merged_model, inplace=True)
if method == "steadycom":
logger.info(f"Simulating community model with SteadyCom")
solution = reframed.SteadyCom(community)
elif method == "steadiercom":
logger.info(f"Simulating community model with SteadyCom")
solution = reframed.SteadierCom(community)
logger.debug(f"Formatting solution response")
def model_id(original_id):
"""Map the models original name back to our platform internal DB IDs."""
return next(wrapper.id for wrapper in wrappers
if wrapper.model.id == original_id)
# Calculate transactions (cross-feeding, uptake and secretion)
logger.debug(
f"Calculating transactions (cross-feeding, uptake and secretion)")
ex_met_ids = solution.community.merged_model.get_external_metabolites()
met_id2name = create_metabolite_id2name_mapping(ex_met_ids, community)
transactions = generate_transactions(met_id2name,
solution.exchange_map)
# Convert the iterables to dictionaries for easier handling on the frontend
abundance = [{
"id": model_id(original_id),
"value": abundance
} for original_id, abundance in solution.abundance.items()]
cross_feeding = []
for transaction in transactions:
if transaction[0] == "medium":
cross_feeding.append({
"from": "medium",
"to": model_id(transaction[1]),
"metabolite_id": transaction[2],
"metabolite_name": transaction[3],
"value": transaction[4],
})
elif transaction[1] == "medium":
cross_feeding.append({
"from": model_id(transaction[0]),
"to": "medium",
"metabolite_id": transaction[2],
"metabolite_name": transaction[3],
"value": transaction[4],
})
else:
cross_feeding.append({
"from": model_id(transaction[0]),
"to": model_id(transaction[1]),
"metabolite_id": transaction[2],
"metabolite_name": transaction[3],
"value": transaction[4],
})
return {
"growth_rate": solution.growth,
"abundance": abundance,
"cross_feeding": cross_feeding,
"warnings": [" ".join(w.message.args) for w in reframed_warnings],
}