def get_thermo_data():
# Load Thermo data
thermo_data = load_thermoDB(pjoin(file_dir,'../../../pytfa/data/thermo_data.thermodb'))
lexicon = read_lexicon('thermo_data/iJO1366_lexicon.csv')
# lexicon = curate_lexicon(read_lexicon('thermo_data/iJO1366_lexicon.csv'))
compartment_data = read_compartment_data('thermo_data/iJO1366_compartment_data.json')
def curate_lexicon(lexicon):
ix = pd.Series(lexicon.index)
ix = ix.apply(lambda s: str.replace(s,'-','__'))
ix = ix.apply(lambda s: '_'+s if s[0].isdigit() else s)
lexicon.index = ix
return lexicon
lexicon = curate_lexicon(lexicon)
return thermo_data, lexicon, compartment_data
def load_data(model_name):
"""
Loads pre-curated model-specific thermodynamic information.
Parameters
----------
model_name : str
The name of a model.
Returns
-------
thermo_data : dict
A thermodynamic database.
lexicon : pandas.DataFrame
A dataframe linking metabolite IDs to SEED compound IDs.
compartment_data : dict
A dictionary with information about each compartment of the model.
"""
thermo_data = load_thermoDB(static_path("thermo_data.thermodb"))
lexicon = read_lexicon(static_path(model_name, "lexicon.csv"))
compartment_data = read_compartment_data(
static_path(model_name, "compartment_data.json"))
return thermo_data, lexicon, compartment_data
solver = GUROBI
case = 'full' # 'reduced' or full'
# Load reaction DB
print("Loading thermo data...")
thermo_data = load_thermoDB(thermo_database)
print("Done !")
#biomass_rxn = 'BIOMASS_Ec_iJO1366_WT_53p95M'
biomass_rxn = 'Ec_biomass_iJO1366_WT_53p95M'
# We import pre-compiled data as it is faster for bigger models
model_path = '/projectnb2/bioinfor/SEGRE/goldford/CoenzymeSpecificity/pytfa/models'
cobra_model = load_json_model(model_path + '/iJO1366_NAD_ratio_1.fromTFA.json')
lexicon = read_lexicon(model_path + '/iJO1366/lexicon.csv')
compartment_data = read_compartment_data(model_path +
'/iJO1366/compartment_data.json')
# Initialize the cobra_model
mytfa = pytfa.ThermoModel(thermo_data, cobra_model)
# Annotate the cobra_model
annotate_from_lexicon(mytfa, lexicon)
apply_compartment_data(mytfa, compartment_data)
mytfa.name = 'iJO1366[NAD]'
mytfa.solver = solver
mytfa.objective = biomass_rxn
# Solver settings
return model
m = cobra_model.copy()
rxn_ids = [x.id for x in cobra_model.reactions]
m = cobra_model.copy()
rxn_ids = [x.id for x in cobra_model.reactions]
for rxnid in rxn_ids:
m = single_coenzyme_transform(m, rxnid)
m.remove_reactions([x for x in m.reactions if x.id == 'NADTRHD[condensed]'][0])
m.objective = 'Ec_biomass_iJO1366_WT_53p95M[condensed]'
# Load reaction DB
thermo_data = load_thermoDB(root_dir + 'data/thermo_data.thermodb')
lexicon = read_lexicon(root_dir + 'models/small_ecoli/lexicon.csv')
compartment_data = read_compartment_data(
root_dir + 'models/small_ecoli/compartment_data.json')
def convert2thermo(model, name):
# Initialize the model
tmodel = pytfa.ThermoModel(thermo_data, model)
tmodel.name = name
# Annotate the model
annotate_from_lexicon(tmodel, lexicon)
apply_compartment_data(tmodel, compartment_data)
## TFA conversion
tmodel.prepare()
# Load reaction DB
print("Loading thermo data...")
thermo_data = load_thermoDB('../data/thermo_data.thermodb')
print("Done !")
if case == 'reduced':
cobra_model = import_matlab_model('../models/small_ecoli.mat')
mytfa = pytfa.ThermoModel(thermo_data, cobra_model)
biomass_rxn = 'Ec_biomass_iJO1366_WT_53p95M'
elif case == 'full':
# We import pre-compiled data as it is faster for bigger models
cobra_model = load_json_model('../models/iJO1366.json')
lexicon = read_lexicon('../models/iJO1366/lexicon.csv')
compartment_data = read_compartment_data('../models/iJO1366/compartment_data.json')
# Initialize the cobra_model
mytfa = pytfa.ThermoModel(thermo_data, cobra_model)
# Annotate the cobra_model
annotate_from_lexicon(mytfa, lexicon)
apply_compartment_data(mytfa, compartment_data)
biomass_rxn = 'Ec_biomass_iJO1366_WT_53p95M'
mytfa.name = 'tutorial_basics'
mytfa.solver = solver
mytfa.objective = biomass_rxn
def apply_annotation_data(self):
# for met in self.model.metabolites:
# if 'seed.compound' in met.annotation:
# met.annotation = {'seed_id': met.annotation['seed.compound'][0]}
annotate_from_lexicon(
self.model, read_lexicon(join(data_dir, 'thermo/lexicon.csv')))
def __init__(self,
model_code='ecoli:iJO1366',
solver='gurobi',
min_biomass=0.55):
start_time = time.time()
super().__init__(model_code, solver, min_biomass)
if self.species == 'ecoli':
# Add cystein -> selenocystein transformation for convenience
selcys = Metabolite(id='selcys__L_c',
compartment='c',
formula='C3H7NO2Se')
selcys_rxn = Reaction(id='PSEUDO_selenocystein_synthase',
name='PSEUDO Selenocystein_Synthase')
selcys_rxn.add_metabolites({
self.model.metabolites.cys__L_c: -1,
selcys: +1
})
self.model.add_reactions([selcys_rxn])
self._sanitize_varnames()
# self.model.reactions.EX_glc__D_e.lower_bound = -1 * glc_uptake - glc_uptake_std
# self.model.reactions.EX_glc__D_e.upper_bound = -1 * glc_uptake + glc_uptake_std
# time_str = get_timestr()
coupling_dict = get_coupling_dict(self.model,
mode='kmax',
atps_name='ATPS4rpp',
infer_missing_enz=True)
aa_dict, rna_nucleotides, rna_nucleotides_mp, dna_nucleotides = get_monomers_dict(
)
essentials = get_essentials()
# if has_thermo:
thermo_db = load_thermoDB(
join(data_dir, 'thermo/thermo_data.thermodb'))
self.model = ThermoMEModel(thermo_db,
model=self.model,
growth_reaction=self.biomass_reaction,
mu_range=mu_range,
n_mu_bins=n_mu_bins)
self.model.name = self.model_name
# annotate_from_lexicon(self.model, read_lexicon(dir_path + '/data/thermo/lexicon.csv'))
# compartment_data = read_compartment_data(dir_path + '/data/thermo/compartment_data.json')
# apply_compartment_data(self.model, compartment_data)
apply_compartment_data(
self.model,
read_compartment_data(
join(data_dir, 'thermo/compartment_data.json')))
annotate_from_lexicon(
self.model, read_lexicon(join(data_dir, 'thermo/lexicon.csv')))
self.model.prepare()
# self.model.reactions.MECDPS.thermo['computed'] = False
# self.model.reactions.NDPK4.thermo['computed'] = False
# self.model.reactions.TMDPP.thermo['computed'] = False
# self.model.reactions.ARGAGMt7pp.thermo['computed'] = False
self.model.convert()
# else:
# self.model = MEModel(model=self.model, growth_reaction=growth_reaction_id, mu_range=mu_range,
# n_mu_bins=n_mu_bins, name=name)
# mrna_dict = get_mrna_dict(self.model)
# nt_sequences = get_nt_sequences()
nt_sequences = pd.read_csv(join(
data_dir, f'{self.species}/{self.model_name}_nt_seq_kegg.csv'),
index_col=0,
header=None).iloc[:, 0]
mrna_dict = self.get_mrna_dict(nt_sequences)
rnap = get_rnap()
rib = get_rib()
# Remove nucleotides and amino acids from biomass reaction as they will be
# taken into account by the expression
remove_from_biomass_equation(model=self.model,
nt_dict=rna_nucleotides,
aa_dict=aa_dict,
essentials_dict=essentials)
self.model.add_nucleotide_sequences(nt_sequences)
self.model.add_essentials(essentials=essentials,
aa_dict=aa_dict,
rna_nucleotides=rna_nucleotides,
rna_nucleotides_mp=rna_nucleotides_mp)
self.model.add_mrnas(mrna_dict.values())
self.model.add_ribosome(rib, free_ratio=0.2)
# http://bionumbers.hms.harvard.edu/bionumber.aspx?id=102348&ver=1&trm=rna%20polymerase%20half%20life&org=
# Name Fraction of active RNA Polymerase
# Bionumber ID 102348
# Value 0.17-0.3 unitless
# Source Bremer, H., Dennis, P. P. (1996) Modulation of chemical composition and other parameters of the cell by growth rate.
# Neidhardt, et al. eds. Escherichia coli and Salmonella typhimurium: Cellular
# and Molecular Biology, 2nd ed. chapter 97 Table 1
self.model.add_rnap(rnap, free_ratio=0.75)
self.model.build_expression()
self.model.add_enzymatic_coupling(coupling_dict)
# if has_neidhardt:
# nt_ratios, aa_ratios = get_ratios()
# chromosome_len, gc_ratio = get_ecoli_gen_stats()
# kdeg_mrna, mrna_length_avg = get_mrna_metrics()
# kdeg_enz, peptide_length_avg = get_enz_metrics()
# neidhardt_mu, neidhardt_rrel, neidhardt_prel, neidhardt_drel = get_neidhardt_data()
#
# add_interpolation_variables(self.model)
# self.model.add_dummies(nt_ratios=nt_ratios, mrna_kdeg=kdeg_mrna, mrna_length=mrna_length_avg,
# aa_ratios=aa_ratios, enzyme_kdeg=kdeg_enz, peptide_length=peptide_length_avg)
# add_protein_mass_requirement(self.model, neidhardt_mu, neidhardt_prel)
# add_rna_mass_requirement(self.model, neidhardt_mu, neidhardt_rrel)
# add_dna_mass_requirement(self.model, mu_values=neidhardt_mu, dna_rel=neidhardt_drel, gc_ratio=gc_ratio,
# chromosome_len=chromosome_len, dna_dict=dna_nucleotides)
# Need to put after, because dummy has to be taken into account if used.
self.model.populate_expression()
self.model.add_trna_mass_balances()
# self.model.growth_reaction.lower_bound = objective_lb
self.model.repair()
print(
f"Building ETFL model costs {time.time() - start_time:.2f} seconds!"
)
try:
start_time = time.time()
self.model.optimize()
except (AttributeError, SolverError):
print(
f"Solving no relaxed model costs {time.time() - start_time:.2f} seconds!"
)
start_time = time.time()
self.model, _, _ = relax_dgo(self.model, in_place=True)
print(
f"Relaxing model costs {time.time() - start_time:.2f} seconds!"
)
# self.model.growth_reaction.lower_bound = 0
# print(f"Build ETFL model for {time.time() - start_time:.2f} seconds!")
self.model.print_info()
path_to_params = join(this_directory, '..', 'tests/redgem_params.yml')
thermoDB = join(this_directory, '..', 'data/thermo_data.thermodb')
path_to_lexicon = join(this_directory, '..', 'models/iJO1366/lexicon.csv')
path_to_compartment_data = join(this_directory, '..',
'models/iJO1366/compartment_data.json')
# Scaling to avoid numerical errors with bad lumps
for rxn in model.reactions:
if rxn.id.startswith('LMPD_'):
rxn.add_metabolites(
{x: v * (0.1 - 1)
for x, v in rxn.metabolites.items()})
thermo_data = load_thermoDB(thermoDB)
lexicon = read_lexicon(path_to_lexicon)
compartment_data = read_compartment_data(path_to_compartment_data)
tfa_model = ThermoModel(thermo_data, model)
annotate_from_lexicon(tfa_model, lexicon)
apply_compartment_data(tfa_model, compartment_data)
tfa_model.name = 'Lumped Model'
tfa_model.prepare()
tfa_model.convert()
# tfa_model.solver.configuration.verbosity = True
tfa_model.logger.setLevel = 30
def test_redgem():
import re
data_dir = '../organism_data/info_ecoli'
vanilla_model = cobra.io.load_json_model('iJO1366_with_xrefs.json')
solver = 'optlang-gurobi'
# solver = 'optlang-cplex'
# Relax ATPM
# vanilla_model.reactions.ATPM.lower_bound = 0
# Load Thermo data
thermo_data = load_thermoDB('../../pytfa/data/thermo_data.thermodb')
lexicon = read_lexicon('thermo_data/iJO1366_lexicon.csv')
# lexicon = curate_lexicon(read_lexicon('thermo_data/iJO1366_lexicon.csv'))
compartment_data = read_compartment_data('thermo_data/iJO1366_compartment_data.json')
# McCloskey2014 values
glc_uptake = 7.54
glc_uptake_std = 0.56
observed_growth = 0.61 - 0.02
vanilla_model.reactions.EX_glc__D_e.lower_bound = -1*glc_uptake - glc_uptake_std
vanilla_model.reactions.EX_glc__D_e.upper_bound = -1*glc_uptake + glc_uptake_std
growth_reaction_id = 'BIOMASS_Ec_iJO1366_WT_53p95M'
#------------------------------------------------------------
from pytfa.optim.variables import DeltaG, DeltaGstd, ThermoDisplacement
from pytfa.analysis import variability_analysis, \
apply_reaction_variability, \
apply_generic_variability, \
apply_directionality
CPLEX = 'optlang-cplex'
GUROBI = 'optlang-gurobi'
GLPK = 'optlang-glpk'
# Load the cobra_model
cobra_model = load_matlab_model('../models/small_ecoli.mat')
# Load reaction DB
thermo_data = load_thermoDB('../data/thermo_data.thermodb')
lexicon = read_lexicon('../models/small_ecoli/lexicon.csv')
compartment_data = read_compartment_data(
'../models/small_ecoli/compartment_data.json')
# Initialize the cobra_model
tmodel = pytfa.ThermoModel(thermo_data, cobra_model)
tmodel.name = 'tutorial'
# Annotate the cobra_model
annotate_from_lexicon(tmodel, lexicon)
apply_compartment_data(tmodel, compartment_data)
# Set the solver
tmodel.solver = GLPK
## TFA conversion
