def LoadAllEstimators():
db_public = SqliteDatabase('../data/public_data.sqlite')
db_gibbs = SqliteDatabase('../res/gibbs.sqlite')
if not db_gibbs.DoesTableExist('prc_pseudoisomers'):
nist_regression = NistRegression(db_gibbs)
nist_regression.Train()
tables = {
'alberty': (db_public, 'alberty_pseudoisomers', 'Alberty'),
'PRC': (db_gibbs, 'prc_pseudoisomers', 'our method (PRC)')
}
estimators = {}
for key, (db, table_name, thermo_name) in tables.iteritems():
if db.DoesTableExist(table_name):
estimators[key] = PsuedoisomerTableThermodynamics.FromDatabase(
db, table_name, name=thermo_name)
else:
logging.warning('The table %s does not exist in %s' %
(table_name, str(db)))
estimators['hatzi_gc'] = Hatzi(use_pKa=False)
#estimators['hatzi_gc_pka'] = Hatzi(use_pKa=True)
if db.DoesTableExist('bgc_pseudoisomers'):
estimators['BGC'] = GroupContribution(db=db_gibbs, transformed=True)
estimators['BGC'].init()
estimators['BGC'].name = 'our method (BGC)'
if db.DoesTableExist('pgc_pseudoisomers'):
estimators['PGC'] = GroupContribution(db=db_gibbs, transformed=False)
estimators['PGC'].init()
estimators['PGC'].name = 'our method (PGC)'
estimators['UGC'] = UnifiedGroupContribution(db=db_gibbs)
estimators['UGC'].init()
estimators['UGC'].name = 'our method (UGC)'
estimators['C1'] = ReactionThermodynamics.FromCsv(
'../data/thermodynamics/c1_reaction_thermodynamics.csv',
estimators['alberty'])
if 'PGC' in estimators:
estimators['merged'] = BinaryThermodynamics(estimators['alberty'],
estimators['PGC'])
estimators['merged_C1'] = BinaryThermodynamics(estimators['C1'],
estimators['PGC'])
for thermo in estimators.values():
thermo.load_bounds('../data/thermodynamics/concentration_bounds.csv')
return estimators
def LoadAllEstimators():
db_public = SqliteDatabase('../data/public_data.sqlite')
db_gibbs = SqliteDatabase('../res/gibbs.sqlite')
if not db_gibbs.DoesTableExist('prc_pseudoisomers'):
nist_regression = NistRegression(db_gibbs)
nist_regression.Train()
tables = {'alberty': (db_public, 'alberty_pseudoisomers', 'Alberty'),
'PRC': (db_gibbs, 'prc_pseudoisomers', 'our method (PRC)')}
estimators = {}
for key, (db, table_name, thermo_name) in tables.iteritems():
if db.DoesTableExist(table_name):
estimators[key] = PsuedoisomerTableThermodynamics.FromDatabase(
db, table_name, name=thermo_name)
else:
logging.warning('The table %s does not exist in %s' % (table_name, str(db)))
estimators['hatzi_gc'] = Hatzi(use_pKa=False)
#estimators['hatzi_gc_pka'] = Hatzi(use_pKa=True)
if db.DoesTableExist('bgc_pseudoisomers'):
estimators['BGC'] = GroupContribution(db=db_gibbs, transformed=True)
estimators['BGC'].init()
estimators['BGC'].name = 'our method (BGC)'
if db.DoesTableExist('pgc_pseudoisomers'):
estimators['PGC'] = GroupContribution(db=db_gibbs, transformed=False)
estimators['PGC'].init()
estimators['PGC'].name = 'our method (PGC)'
estimators['UGC'] = UnifiedGroupContribution(db=db_gibbs)
estimators['UGC'].init()
estimators['UGC'].name = 'our method (UGC)'
estimators['C1'] = ReactionThermodynamics.FromCsv(
'../data/thermodynamics/c1_reaction_thermodynamics.csv',
estimators['alberty'])
if 'PGC' in estimators:
estimators['merged'] = BinaryThermodynamics(estimators['alberty'],
estimators['PGC'])
estimators['merged_C1'] = BinaryThermodynamics(estimators['C1'],
estimators['PGC'])
for thermo in estimators.values():
thermo.load_bounds('../data/thermodynamics/concentration_bounds.csv')
return estimators
def Initialize(self, db):
from pygibbs.unified_group_contribution import UnifiedGroupContribution
ugc = UnifiedGroupContribution(db)
ugc.LoadGroups(FromDatabase=True)
ugc.LoadObservations(FromDatabase=True)
ugc.LoadGroupVectors(FromDatabase=True)
ugc.LoadData(FromDatabase=True)
ugc.init()
self.groups_data = ugc.groups_data
self.group_decomposer = ugc.group_decomposer
result_dict = ugc._GetContributionData(ugc.S.copy(), ugc.cids,
ugc.b.copy(), ugc.anchored)
self.g_pgc = result_dict['group_contributions']
self.P_L_pgc = result_dict['pgc_conservations']
def Initialize(self, db):
from pygibbs.unified_group_contribution import UnifiedGroupContribution
ugc = UnifiedGroupContribution(db)
ugc.LoadGroups(FromDatabase=True)
ugc.LoadObservations(FromDatabase=True)
ugc.LoadGroupVectors(FromDatabase=True)
ugc.LoadData(FromDatabase=True)
ugc.init()
self.groups_data = ugc.groups_data
self.group_decomposer = ugc.group_decomposer
result_dict = ugc._GetContributionData(ugc.S.copy(), ugc.cids,
ugc.b.copy(), ugc.anchored)
self.g_pgc = result_dict['group_contributions']
self.P_L_pgc = result_dict['pgc_conservations']
plt.xlabel('value in iAF1260 [kJ/mol]')
plt.ylabel('UGCM estimation [kJ/mol]')
plt.title('Unobserved data, N = %d, RMSE = %.1f [kJ/mol]' % (len(non_nist_idx), rms_feist_ugcm2))
plt.tight_layout()
plt.savefig(FIG_FNAME + "_fig2.svg", fmt='.svg')
plt.figure(figsize=(6, 6), dpi=90)
bins = np.arange(-30, 30, 2)
plt.hist([err_feist_nist, err_ugcm_nist], bins=bins, histtype='bar', cumulative=False, normed=False)
plt.xlabel('Error in kJ/mol')
plt.ylabel('# of reactions')
plt.legend(['value in iAF1260', 'UGCM estimation'])
plt.savefig(FIG_FNAME + "_fig3.svg", fmt='.svg')
db = SqliteDatabase('../res/gibbs.sqlite', 'w')
ugc = UnifiedGroupContribution(db)
ugc.LoadGroups(True)
ugc.LoadObservations(True)
ugc.LoadGroupVectors(True)
ugc.LoadData(True)
ugc.init()
r_list = []
#r_list += [Reaction.FromFormula("C00036 + C00044 = C00011 + C00035 + C00074")]
#r_list += [Reaction.FromFormula("C00003 + C00037 + C00101 = C00004 + C00011 + C00014 + C00080 + C00143")] # glycine synthase
r_list += [Reaction.FromFormula("C00001 + C00002 + C00064 + C04376 => C00008 + C00009 + C00025 + C04640")]
#r_list += [Reaction.FromFormula("C00001 + 2 C00002 + C00064 + C00288 <=> 2 C00008 + C00009 + C00025 + C00169")]
kegg = Kegg.getInstance()
S, cids = kegg.reaction_list_to_S(r_list)
def CalculateThermo():
options, _ = MakeOpts().parse_args(sys.argv)
if options.csv_output_filename is not None:
out_fp = open(options.csv_output_filename, 'w')
print "writing results to %s ... " % options.csv_output_filename
else:
out_fp = sys.stdout
csv_writer = csv.writer(out_fp)
csv_writer.writerow(['ID', 'error', 'nH', 'nMg', 'charge', 'dG0', 'kernel'])
db = SqliteDatabase('../res/gibbs.sqlite', 'w')
ugc = UnifiedGroupContribution(db)
ugc.LoadGroups(True)
ugc.LoadObservations(True)
ugc.LoadGroupVectors(True)
ugc.LoadData(True)
result_dict = ugc._GetContributionData(ugc.S.copy(), ugc.cids,
ugc.b.copy(), ugc.anchored)
g_pgc = result_dict['group_contributions']
P_L_pgc = result_dict['pgc_conservations']
sdfile = pybel.readfile("sdf", options.sdf_input_filename)
for m in sdfile:
try:
try:
mol = Molecule.FromOBMol(m.OBMol)
except OpenBabelError:
raise UnknownReactionEnergyError("Cannot convert to OBMol object")
mol.title = m.title
mol.RemoveHydrogens()
if mol.GetNumAtoms() > 200:
raise UnknownReactionEnergyError("Compound contains more than 200 atoms (n = %d)" % mol.GetNumAtoms())
try:
decomposition = ugc.group_decomposer.Decompose(mol,
ignore_protonations=False, strict=True)
except GroupDecompositionError:
raise UnknownReactionEnergyError("cannot decompose")
groupvec = decomposition.AsVector()
gv = np.matrix(groupvec.Flatten())
dG0 = float(g_pgc * gv.T)
nH = decomposition.Hydrogens()
nMg = decomposition.Magnesiums()
ker = list((P_L_pgc * gv.T).round(10).flat)
try:
diss_table = mol.GetDissociationTable()
diss_table.SetFormationEnergyByNumHydrogens(
dG0=dG0, nH=nH, nMg=nMg)
except MissingDissociationConstantError:
raise UnknownReactionEnergyError("missing pKa data")
pmap = diss_table.GetPseudoisomerMap()
for p_nH, p_z, p_nMg, p_dG0 in pmap.ToMatrix():
csv_writer.writerow([m.title, None, p_nH, p_z, p_nMg, round(p_dG0, 1), str(ker)])
except UnknownReactionEnergyError as e:
csv_writer.writerow([m.title, str(e), None, None, None, None, None])
out_fp.flush()
plt.savefig(FIG_FNAME + "_fig2.svg", fmt='.svg')
plt.figure(figsize=(6, 6), dpi=90)
bins = np.arange(-30, 30, 2)
plt.hist([err_feist_nist, err_ugcm_nist],
bins=bins,
histtype='bar',
cumulative=False,
normed=False)
plt.xlabel('Error in kJ/mol')
plt.ylabel('# of reactions')
plt.legend(['value in iAF1260', 'UGCM estimation'])
plt.savefig(FIG_FNAME + "_fig3.svg", fmt='.svg')
db = SqliteDatabase('../res/gibbs.sqlite', 'w')
ugc = UnifiedGroupContribution(db)
ugc.LoadGroups(True)
ugc.LoadObservations(True)
ugc.LoadGroupVectors(True)
ugc.LoadData(True)
ugc.init()
r_list = []
#r_list += [Reaction.FromFormula("C00036 + C00044 = C00011 + C00035 + C00074")]
#r_list += [Reaction.FromFormula("C00003 + C00037 + C00101 = C00004 + C00011 + C00014 + C00080 + C00143")] # glycine synthase
r_list += [
Reaction.FromFormula(
"C00001 + C00002 + C00064 + C04376 => C00008 + C00009 + C00025 + C04640"
)
]
#r_list += [Reaction.FromFormula("C00001 + 2 C00002 + C00064 + C00288 <=> 2 C00008 + C00009 + C00025 + C00169")]
def CalculateThermo():
options, _ = MakeOpts().parse_args(sys.argv)
if options.csv_output_filename is not None:
out_fp = open(options.csv_output_filename, 'w')
print "writing results to %s ... " % options.csv_output_filename
else:
out_fp = sys.stdout
csv_writer = csv.writer(out_fp)
csv_writer.writerow(
['ID', 'error', 'nH', 'nMg', 'charge', 'dG0', 'kernel'])
db = SqliteDatabase('../res/gibbs.sqlite', 'w')
ugc = UnifiedGroupContribution(db)
ugc.LoadGroups(True)
ugc.LoadObservations(True)
ugc.LoadGroupVectors(True)
ugc.LoadData(True)
result_dict = ugc._GetContributionData(ugc.S.copy(), ugc.cids,
ugc.b.copy(), ugc.anchored)
g_pgc = result_dict['group_contributions']
P_L_pgc = result_dict['pgc_conservations']
sdfile = pybel.readfile("sdf", options.sdf_input_filename)
for m in sdfile:
try:
try:
mol = Molecule.FromOBMol(m.OBMol)
except OpenBabelError:
raise UnknownReactionEnergyError(
"Cannot convert to OBMol object")
mol.title = m.title
mol.RemoveHydrogens()
if mol.GetNumAtoms() > 200:
raise UnknownReactionEnergyError(
"Compound contains more than 200 atoms (n = %d)" %
mol.GetNumAtoms())
try:
decomposition = ugc.group_decomposer.Decompose(
mol, ignore_protonations=False, strict=True)
except GroupDecompositionError:
raise UnknownReactionEnergyError("cannot decompose")
groupvec = decomposition.AsVector()
gv = np.matrix(groupvec.Flatten())
dG0 = float(g_pgc * gv.T)
nH = decomposition.Hydrogens()
nMg = decomposition.Magnesiums()
ker = list((P_L_pgc * gv.T).round(10).flat)
try:
diss_table = mol.GetDissociationTable()
diss_table.SetFormationEnergyByNumHydrogens(dG0=dG0,
nH=nH,
nMg=nMg)
except MissingDissociationConstantError:
raise UnknownReactionEnergyError("missing pKa data")
pmap = diss_table.GetPseudoisomerMap()
for p_nH, p_z, p_nMg, p_dG0 in pmap.ToMatrix():
csv_writer.writerow([
m.title, None, p_nH, p_z, p_nMg,
round(p_dG0, 1),
str(ker)
])
except UnknownReactionEnergyError as e:
csv_writer.writerow(
[m.title, str(e), None, None, None, None, None])
out_fp.flush()
# This file reads the data stored in the gibbs.sqlite database and
import os, sys
orig_dir = os.getcwd()
pygibbs_path, _ = os.path.split(orig_dir)
src_path, _ = os.path.split(pygibbs_path)
os.chdir(src_path)
print src_path
sys.path.append(src_path)
import numpy as np
from pygibbs.unified_group_contribution import UnifiedGroupContribution
from toolbox.database import SqliteDatabase
db = SqliteDatabase('../res/gibbs.sqlite', 'r')
ugc = UnifiedGroupContribution(db)
ugc.LoadGroups(FromDatabase=True)
ugc.LoadObservations(FromDatabase=True)
ugc.LoadGroupVectors(FromDatabase=True)
ugc.LoadData(FromDatabase=True)
ugc.init()
result_dict = ugc._GetContributionData(ugc.S.copy(), ugc.cids,
ugc.b.copy(), ugc.anchored)
g_pgc = result_dict['group_contributions']
P_L_pgc = result_dict['pgc_conservations']
os.chdir(orig_dir)
print os.getcwd()
np.save('g_pgc.gz', g_pgc)
np.save('P_L_g_pgc.gz', P_L_pgc)
# This file reads the data stored in the gibbs.sqlite database and
import os, sys
orig_dir = os.getcwd()
pygibbs_path, _ = os.path.split(orig_dir)
src_path, _ = os.path.split(pygibbs_path)
os.chdir(src_path)
print src_path
sys.path.append(src_path)
import numpy as np
from pygibbs.unified_group_contribution import UnifiedGroupContribution
from toolbox.database import SqliteDatabase
db = SqliteDatabase('../res/gibbs.sqlite', 'r')
ugc = UnifiedGroupContribution(db)
ugc.LoadGroups(FromDatabase=True)
ugc.LoadObservations(FromDatabase=True)
ugc.LoadGroupVectors(FromDatabase=True)
ugc.LoadData(FromDatabase=True)
ugc.init()
result_dict = ugc._GetContributionData(ugc.S.copy(), ugc.cids, ugc.b.copy(),
ugc.anchored)
g_pgc = result_dict['group_contributions']
P_L_pgc = result_dict['pgc_conservations']
os.chdir(orig_dir)
print os.getcwd()
np.save('g_pgc.gz', g_pgc)
np.save('P_L_g_pgc.gz', P_L_pgc)