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 first_run_check():
diamond_db = project_dir + config.get('generated', 'diamond_db')
if not os.path.exists(diamond_db):
print("Running diamond for the first time, please wait while we build the internal database...")
fasta_file = project_dir + config.get('generated', 'fasta_file')
cmd = ['diamond', 'makedb', '--in', fasta_file, '-d', diamond_db[:-5]]
try:
exit_code = subprocess.call(cmd)
except OSError:
print('Unable to run diamond (make sure diamond is available in your PATH).')
else:
if exit_code != 0:
print('Failed to run diamond (wrong arguments).')
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 main():
parser = argparse.ArgumentParser(
description="Generate universal model to use with CarveMe")
parser.add_argument('-o', '--output', dest='output', help="Output file")
args = parser.parse_args()
if args.output:
universe_draft = args.output
model_specific_data = os.path.splitext(args.output)[0] + '.csv'
bigg_gprs = os.path.splitext(args.output)[0] + '_gprs.csv'
fasta_file = os.path.splitext(args.output)[0] + '.faa'
gene_annotations = os.path.splitext(args.output)[0] + '.tsv'
else:
universe_draft = project_dir + config.get('generated', 'bigg_universe')
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('generated', 'fasta_file')
gene_annotations = project_dir + config.get('generated',
'gene_annotations')
cpd_annotation = project_dir + config.get('input', 'mnx_compounds')
download_universal_model(universe_draft, cpd_annotation)
download_model_specific_data(model_specific_data, bigg_gprs, fasta_file,
gene_annotations)
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():
parser = argparse.ArgumentParser(
description=
"Merge single species models into a microbial community model")
parser.add_argument('input',
metavar='INPUTFILES',
nargs='+',
help="SBML input files (single species)")
parser.add_argument('-o',
'--output',
dest='output',
help="SBML output file (community)")
parser.add_argument('-i',
'--init',
dest='init',
help="Initialize model with given medium")
parser.add_argument('--mediadb', help="Media database file")
sbml = parser.add_mutually_exclusive_group()
sbml.add_argument('--cobra',
action='store_true',
help="SBML input/output in old cobra format")
sbml.add_argument('--fbc2',
action='store_true',
help="SBML input/output in sbml-fbc2 format")
args = parser.parse_args()
if len(args.input) < 2:
print(args.input)
parser.error(
"Please provide two or more single species models as input files.")
if args.fbc2:
flavor = 'fbc2'
elif args.cobra:
flavor = 'cobra'
else:
flavor = config.get('sbml', 'default_flavor')
maincall(inputfiles=args.input,
flavor=flavor,
init=args.init,
mediadb=args.mediadb,
outputfile=args.output)
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 main():
parser = argparse.ArgumentParser(
description="GapFill a metabolic model for a given set of media")
parser.add_argument('input', metavar='INPUTFILE', help="SBML input file")
parser.add_argument('-m',
'--media',
dest='media',
required=True,
help="List of media (comma-separated)")
parser.add_argument('--mediadb', help="Media database file")
parser.add_argument(
'--spent-medium',
metavar='SPECIES',
dest='spent',
help=
"Add spent medium compounds generated from given species (SBML model)."
)
univ = parser.add_mutually_exclusive_group()
univ.add_argument('-u',
'--universe',
dest='universe',
help="Pre-built universe model (default: bacteria)")
univ.add_argument('--universe-file',
dest='universe_file',
help="Reaction universe file (SBML format)")
parser.add_argument('-o',
'--output',
dest='output',
type=str,
help="SBML output file")
parser.add_argument('-v',
'--verbose',
action='store_true',
dest='verbose',
help="Switch to verbose mode")
sbml = parser.add_mutually_exclusive_group()
sbml.add_argument('--cobra',
action='store_true',
help="Input SBML in old cobra format")
sbml.add_argument('--fbc2',
action='store_true',
help="Input SBML in sbml-fbc2 format")
args = parser.parse_args()
if args.fbc2:
flavor = 'fbc2'
elif args.cobra:
flavor = 'cobra'
else:
flavor = config.get('sbml', 'default_flavor')
maincall(inputfile=args.input,
media=args.media.split(','),
mediadb=args.mediadb,
universe=args.universe,
universe_file=args.universe_file,
outputfile=args.output,
flavor=flavor,
spent=args.spent,
verbose=args.verbose)
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 main():
parser = argparse.ArgumentParser(description="Reconstruct a metabolic model using CarveMe",
formatter_class=argparse.RawTextHelpFormatter)
parser.add_argument('input', metavar='INPUT', nargs='+',
help="Input (protein fasta file by default, see other options for details).\n" +
"When used with -r an input pattern with wildcards can also be used.\n" +
"When used with --refseq an NCBI RefSeq assembly accession is expected."
)
input_type_args = parser.add_mutually_exclusive_group()
input_type_args.add_argument('--dna', action='store_true', help="Build from DNA fasta file")
input_type_args.add_argument('--egg', action='store_true', help="Build from eggNOG-mapper output file")
input_type_args.add_argument('--diamond', action='store_true', help=argparse.SUPPRESS)
input_type_args.add_argument('--refseq', action='store_true', help="Download genome from NCBI RefSeq and build")
parser.add_argument('--diamond-args', help="Additional arguments for running diamond")
parser.add_argument('-r', '--recursive', action='store_true', dest='recursive',
help="Bulk reconstruction from folder with genome files")
parser.add_argument('-o', '--output', dest='output', help="SBML output file (or output folder if -r is used)")
univ = parser.add_mutually_exclusive_group()
univ.add_argument('-u', '--universe', dest='universe', help="Pre-built universe model (default: bacteria)")
univ.add_argument('--universe-file', dest='universe_file', help="Reaction universe file (SBML format)")
sbml = parser.add_mutually_exclusive_group()
sbml.add_argument('--cobra', action='store_true', help="Output SBML in old cobra format")
sbml.add_argument('--fbc2', action='store_true', help="Output SBML in sbml-fbc2 format")
parser.add_argument('-n', '--ensemble', type=int, dest='ensemble',
help="Build model ensemble with N models")
parser.add_argument('-g', '--gapfill', dest='gapfill',
help="Gap fill model for given media")
parser.add_argument('-i', '--init', dest='init',
help="Initialize model with given medium")
parser.add_argument('--mediadb', help="Media database file")
parser.add_argument('-v', '--verbose', action='store_true', dest='verbose', help="Switch to verbose mode")
parser.add_argument('-d', '--debug', action='store_true', dest='debug',
help="Debug mode: writes intermediate results into output files")
parser.add_argument('--soft', help="Soft constraints file")
parser.add_argument('--hard', help="Hard constraints file")
parser.add_argument('--reference', help="Manually curated model of a close reference species.")
parser.add_argument('--default-score', type=float, default=-1.0, help=argparse.SUPPRESS)
parser.add_argument('--uptake-score', type=float, default=0.0, help=argparse.SUPPRESS)
parser.add_argument('--soft-score', type=float, default=1.0, help=argparse.SUPPRESS)
parser.add_argument('--reference-score', type=float, default=0.0, help=argparse.SUPPRESS)
parser.add_argument('--blind-gapfill', action='store_true', help=argparse.SUPPRESS)
args = parser.parse_args()
if args.gapfill and args.ensemble:
parser.error('Gap fill and ensemble generation cannot currently be combined (not implemented yet).')
if (args.soft or args.hard) and args.ensemble:
parser.error('Soft/hard constraints and ensemble generation cannot currently be combined (not implemented yet).')
if args.mediadb and not args.gapfill:
parser.error('--mediadb can only be used with --gapfill')
if args.recursive and args.refseq:
parser.error('-r cannot be combined with --refseq')
if args.egg:
input_type = 'eggnog'
elif args.dna:
input_type = 'dna'
elif args.diamond:
input_type = 'diamond'
elif args.refseq:
input_type = 'refseq'
else:
input_type = 'protein'
if args.fbc2:
flavor = 'fbc2'
elif args.cobra:
flavor = 'cobra'
else:
flavor = config.get('sbml', 'default_flavor')
first_run_check()
if not args.recursive:
if len(args.input) > 1:
parser.error('Use -r when specifying more than one input file')
maincall(
inputfile=args.input[0],
input_type=input_type,
outputfile=args.output,
diamond_args=args.diamond_args,
universe=args.universe,
universe_file=args.universe_file,
ensemble_size=args.ensemble,
verbose=args.verbose,
debug=args.debug,
flavor=flavor,
gapfill=args.gapfill,
blind_gapfill=False,
init=args.init,
mediadb=args.mediadb,
default_score=args.default_score,
uptake_score=args.uptake_score,
soft_score=args.soft_score,
soft=args.soft,
hard=args.hard,
reference=args.reference,
ref_score=args.reference_score
)
else:
def f(x):
maincall(
inputfile=x,
input_type=input_type,
outputfile=args.output,
diamond_args=args.diamond_args,
universe=args.universe,
universe_file=args.universe_file,
ensemble_size=args.ensemble,
verbose=args.verbose,
flavor=flavor,
gapfill=args.gapfill,
blind_gapfill=False,
init=args.init,
mediadb=args.mediadb,
default_score=args.default_score,
uptake_score=args.uptake_score,
soft_score=args.soft_score,
soft=args.soft,
hard=args.hard,
reference=args.reference,
ref_score=args.reference_score,
recursive_mode=True
)
p = Pool()
p.map(f, args.input)
def main(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, specified_solver=None, feas_tol=None, opt_tol=None, int_feas_tol=None):
if recursive_mode:
model_id = os.path.splitext(os.path.basename(inputfile))[0]
if outputfile:
outputfile = '{}/{}.xml'.format(outputfile, model_id)
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' or input_type == 'genbank':
if verbose:
print('Downloading genome {} from NCBI...'.format(inputfile))
ncbi_table = load_ncbi_table(project_dir + config.get('ncbi', input_type))
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('input', '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 = "{}{}universe_{}.xml.gz".format(project_dir, config.get('generated', 'folder'), universe)
else:
universe_file = project_dir + config.get('generated', 'default_universe')
# change default solver if a solver is specified in the input
if specified_solver is not None:
if specified_solver != config.get('solver', 'default_solver'):
set_default_solver(specified_solver)
params_to_set = {'FEASIBILITY_TOL': feas_tol,
'OPTIMALITY_TOL': opt_tol,
'INT_FEASIBILITY_TOL': int_feas_tol}
for key,value in params_to_set.items():
if value is not None:
set_default_parameter(getattr(Parameter, key), value)
try:
universe_model = load_cbmodel(universe_file, flavor=config.get('sbml', 'default_flavor'))
universe_model.id = model_id
except IOError:
available = '\n'.join(glob("{}{}universe_*.xml.gz".format(project_dir, config.get('generated', 'folder'))))
raise IOError('Failed to load universe model: {}\nAvailable universe files:\n{}'.format(universe_file, 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...')
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 = 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('Error: medium {} not in media database.'.format(init))
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')
if not gapfill:
carve_model(universe_model, scores,
outputfile=outputfile,
flavor=flavor,
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)
else:
model = carve_model(universe_model, scores,
inplace=False,
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)
else:
if verbose:
print('Building an ensemble of', ensemble_size, 'models')
build_ensemble(universe_model, scores, ensemble_size, outputfile, flavor, init_env=init_env)
if gapfill and model is not None:
media = gapfill.split(',')
if verbose:
m1, n1 = len(model.metabolites), len(model.reactions)
print('Gap filling for {}...'.format(', '.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('Added {} reactions and {} metabolites'.format((n2 - n1), (m2 - m1)))
if init_env: #Should initialize enviroment 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.')