def AnalyzeConcentrationGradient(prefix,
thermo,
csv_output_fname,
cid=13): # default compound is PPi
compound_name = thermo.kegg.cid2name(cid)
kegg_file = ParsedKeggFile.FromKeggFile('../data/thermodynamics/%s.txt' %
prefix)
html_writer = HtmlWriter('../res/%s.html' % prefix)
null_html_writer = NullHtmlWriter()
if csv_output_fname:
csv_output = csv.writer(open(csv_output_fname, 'w'))
csv_output.writerow(['pH', 'I', 'T', '[C%05d]' % cid] +
kegg_file.entries())
else:
csv_output = None
pH_vec = np.array(
[7]) # this needs to be fixed so that the txt file will set the pH
conc_vec = 10**(-np.arange(2, 6.0001, 0.25)
) # logarithmic scale between 10mM and 1nM
override_bounds = {}
fig = plt.figure(figsize=(6, 6), dpi=90)
legend = []
for pH in pH_vec.flat:
obd_vec = []
for conc in conc_vec.flat:
override_bounds[cid] = (conc, conc)
logging.info("pH = %g, [%s] = %.1e M" % (pH, compound_name, conc))
data, labels = pareto(kegg_file,
null_html_writer,
thermo,
pH=pH,
section_prefix="",
balance_water=True,
override_bounds=override_bounds)
obd_vec.append(data[:, 1])
csv_output.writerow([pH, thermo.I, thermo.T, conc] +
list(data[:, 1].flat))
obd_mat = np.matrix(
obd_vec) # rows are pathways and columns are concentrations
plt.plot(conc_vec, obd_mat, '.-', figure=fig)
legend += ['%s, pH = %g' % (l, pH) for l in labels]
plt.title("ODB vs. [%s] (I = %gM, T = %gK)" %
(compound_name, thermo.I, thermo.T),
figure=fig)
plt.xscale('log')
plt.xlabel('Concentration of %s [M]' % thermo.kegg.cid2name(cid),
figure=fig)
plt.ylabel('Optimized Distributed Bottleneck [kJ/mol]', figure=fig)
plt.legend(legend)
html_writer.write('<h2 id="figure_%s">Summary figure</h1>\n' % prefix)
html_writer.embed_matplotlib_figure(fig, name=prefix)
html_writer.close()
def main():
html_writer = HtmlWriter("../res/formation_resolve.html")
estimators = LoadAllEstimators()
for name in ['alberty']:
thermo = estimators[name]
nist = Nist()
nist.verify_formation(html_writer=html_writer,
thermodynamics=thermo,
name=name)
html_writer.close()
def test_single_modules(mids):
from pygibbs.groups import GroupContribution
db = SqliteDatabase('../res/gibbs.sqlite')
html_writer = HtmlWriter("../res/thermodynamic_module_analysis.html")
gc = GroupContribution(db, html_writer)
gc.init()
for mid in mids:
html_writer.write("<h2>M%05d</h2>\n" % mid)
S, rids, fluxes, cids = gc.kegg.get_module(mid)
thermodynamic_pathway_analysis(S, rids, fluxes, cids, gc, html_writer)
def AnalyzePareto(pathway_file, output_prefix, thermo, pH=None):
pathway_list = KeggFile2PathwayList(pathway_file)
pathway_names = [entry for (entry, _) in pathway_list]
html_writer = HtmlWriter('%s.html' % output_prefix)
xls_workbook = Workbook()
logging.info("running OBD analysis for all pathways")
data = GetAllOBDs(pathway_list,
html_writer,
thermo,
pH=pH,
section_prefix="pareto",
balance_water=True,
override_bounds={})
for d in data:
sheet = xls_workbook.add_sheet(d['entry'])
sheet.write(0, 0, "reaction")
sheet.write(0, 1, "formula")
sheet.write(0, 2, "flux")
sheet.write(0, 3, "delta_r G'")
sheet.write(0, 4, "shadow price")
for r, rid in enumerate(d['rids']):
sheet.write(r + 1, 0, rid)
sheet.write(r + 1, 1, d['formulas'][r])
sheet.write(r + 1, 2, d['fluxes'][0, r])
sheet.write(r + 1, 3, d['dG_r_prime'][0, r])
sheet.write(r + 1, 4, d['reaction prices'][r, 0])
xls_workbook.save('%s.xls' % output_prefix)
obds = []
minus_avg_tg = []
for i, d in enumerate(data):
obds.append(d['OBD'])
if d['sum of fluxes']:
minus_avg_tg.append(-d['max total dG'] / d['sum of fluxes'])
else:
minus_avg_tg.append(0)
fig = plt.figure(figsize=(6, 6), dpi=90)
plt.plot(minus_avg_tg, obds, 'o', figure=fig)
plt.plot([0, max(minus_avg_tg)], [0, max(minus_avg_tg)], '--g')
for i, name in enumerate(pathway_names):
plt.text(minus_avg_tg[i], obds[i], name)
plt.title('OBD vs. Average $\Delta_r G$')
plt.ylim(ymin=0)
plt.xlim(xmin=0)
plt.xlabel(r'- Average $\Delta_r G$ [kJ/mol]')
plt.ylabel(r'Optimized Distributed Bottleneck [kJ/mol]')
html_writer.write('<h2>Pareto figure</h1>\n')
html_writer.embed_matplotlib_figure(fig)
html_writer.close()
def compare_charges():
#db_public = SqliteDatabase('../data/public_data.sqlite')
db_gibbs = SqliteDatabase('../res/gibbs.sqlite')
print "Writing Compare Charges report to ../res/groups_report.html"
html_writer = HtmlWriter("../res/groups_report.html")
kegg = Kegg.getInstance()
#pH, I, pMg, T = default_pH, default_I, default_pMg, default_T
pH, I, pMg, T = default_pH, 0, 14, default_T
cid2error = {}
for row_dict in db_gibbs.DictReader("gc_errors"):
cid = int(row_dict['cid'])
cid2error[cid] = row_dict['error']
estimators = {}
estimators['hatzi'] = Hatzi(use_pKa=False)
estimators['milo'] = PsuedoisomerTableThermodynamics.FromDatabase(
db_gibbs, 'gc_pseudoisomers', name='Milo Group Contribution')
all_cids = set(lsum([e.get_all_cids() for e in estimators.values()]))
dict_list = []
for cid in all_cids:
try:
name = kegg.cid2name(cid)
link = kegg.cid2compound(cid).get_link()
except KeyError:
name = "unknown"
link = ""
row_dict = {
'cid': '<a href="%s">C%05d</a>' % (link, cid),
'name': name,
'error': cid2error.get(cid, None)
}
for key, est in estimators.iteritems():
try:
pmap = est.cid2PseudoisomerMap(cid)
dG0, dG0_tag, nH, z, nMg = pmap.GetMostAbundantPseudoisomer(
pH, I, pMg, T)
except MissingCompoundFormationEnergy:
dG0, dG0_tag, nH, z, nMg = "", "", "", "", ""
row_dict['nH_' + key] = nH
row_dict['charge_' + key] = z
row_dict['nMg_' + key] = nMg
row_dict['dG0_' + key] = dG0
row_dict['dG0_tag_' + key] = dG0_tag
dict_list.append(row_dict)
html_writer.write_table(
dict_list,
headers=['cid', 'name', 'charge_hatzi', 'charge_milo', 'error'])
html_writer.close()
def example_reductive(thermo):
pl = Pathologic(db=SqliteDatabase('../res/gibbs.sqlite', 'r'),
public_db=SqliteDatabase('../data/public_data.sqlite'),
html_writer=HtmlWriter('../res/pathologic.html'),
thermo=thermo,
max_solutions=None,
max_reactions=15,
maximal_dG=0.0,
thermodynamic_method=OptimizationMethods.GLOBAL,
update_file=None)
add_cofactor_reactions(pl)
add_redox_reactions(pl)
r = Reaction.FromFormula("3 C00011 => C00022")
#r.Balance()
pl.find_path("reductive", r)
def example_oxidative(thermo):
pl = Pathologic(db=SqliteDatabase('../res/gibbs.sqlite', 'r'),
public_db=SqliteDatabase('../data/public_data.sqlite'),
html_writer=HtmlWriter('../res/pathologic.html'),
thermo=thermo,
max_solutions=None,
max_reactions=10,
maximal_dG=0,
thermodynamic_method=OptimizationMethods.MAX_TOTAL,
update_file=None)
add_cofactor_reactions(pl)
add_redox_reactions(pl, NAD_only=False)
r = Reaction.FromFormula("C00022 => 3 C00011")
#r.Balance()
pl.find_path("oxidative", r)
def runBeta2Alpha(thermo, reactionList):
pl = Pathologic(db=SqliteDatabase('../res/gibbs.sqlite', 'r'),
public_db=SqliteDatabase('../data/public_data.sqlite'),
html_writer=HtmlWriter('../res/Beta2Alpha.html'),
thermo=thermo,
max_solutions=None,
max_reactions=15,
maximal_dG=0.0,
thermodynamic_method=OptimizationMethods.GLOBAL,
update_file=None)
add_cofactor_reactions(pl)
add_redox_reactions(pl)
for r in reactionList:
pl.add_reaction(Reaction.FromFormula(r, "Auto generate #%s" % hash(r)))
r = Reaction.FromFormula("C00099 => C01401")
pl.find_path("Beta2Alpha", r)
def __init__(self, html_fname):
self.serv = None
self.db = SqliteDatabase('channeling/channeling.sqlite', 'w')
self.html_writer = HtmlWriter(html_fname)
self.COMPOUND_TABLE_NAME = 'kegg_compounds'
self.GENE_TABLE_NAME = 'kegg_genes'
self.GENE_REACTION_TABLE_NAME = 'kegg_genes_to_reactions'
self.REACTION_TABLE_NAME = 'kegg_reactions'
self.EQUATION_TABLE_NAME = 'kegg_equations'
self.STOICHIOMETRY_TABLE_NAME = 'kegg_stoichiometry'
self.GIBBS_ENERGY_TABLE_NAME = 'kegg_gibbs_energies'
self.GENE_ENERGY_TABLE_NAME = 'kegg_gene_energies'
self.FUNCTIONAL_INTERATCTIONS_TABLE = 'parkinson_functional_interactions'
self.GENE_PAIRS_TABLE_NAME = 'kegg_gene_pairs'
self.COFACTOR_TABLE_NAME = 'kegg_cofactors'
def example_lower_glycolysis(thermo):
pl = Pathologic(db=SqliteDatabase('../res/gibbs.sqlite', 'r'),
public_db=SqliteDatabase('../data/public_data.sqlite'),
html_writer=HtmlWriter('../res/pathologic.html'),
thermo=thermo,
max_solutions=None,
max_reactions=8,
maximal_dG=0.0,
thermodynamic_method=OptimizationMethods.GLOBAL,
update_file=None)
add_cofactor_reactions(pl)
add_redox_reactions(pl)
#r = Reaction.FromFormula("C00003 + C00118 + C00001 => C00022 + C00004 + C00009")
r = Reaction.FromFormula("C00118 => C00022")
#r.Balance()
pl.find_path("GAP => PYR", r)
def example_glycolysis(thermo):
pl = Pathologic(db=SqliteDatabase('../res/gibbs.sqlite', 'r'),
public_db=SqliteDatabase('../data/public_data.sqlite'),
html_writer=HtmlWriter('../res/pathologic.html'),
thermo=thermo,
max_solutions=None,
max_reactions=15,
maximal_dG=0.0,
thermodynamic_method=OptimizationMethods.GLOBAL,
update_file=None)
add_cofactor_reactions(pl, free_ATP_hydrolysis=False)
ban_toxic_compounds(pl)
#add_carbon_counts(pl)
#r = Reaction.FromFormula("C00031 => 6 C06265")
r = Reaction.FromFormula("C00031 + 3 C00008 => 2 C00186 + 3 C00002")
#r.Balance()
pl.find_path("GLC => 2 LAC, 3 ATP, No methylglyoxal", r)
def example_three_acetate(thermo):
pl = Pathologic(db=SqliteDatabase('../res/gibbs.sqlite', 'r'),
public_db=SqliteDatabase('../data/public_data.sqlite'),
html_writer=HtmlWriter('../res/pathologic.html'),
thermo=thermo,
max_solutions=None,
max_reactions=20,
maximal_dG=0.0,
thermodynamic_method=OptimizationMethods.GLOBAL,
update_file=None)
add_cofactor_reactions(pl)
#add_redox_reactions(pl)
pl.delete_reaction(761) # F6P + Pi = E4P + acetyl-P
pl.delete_reaction(1621) # X5P + Pi = GA3P + acetyl-P
r = Reaction.FromFormula("C00031 => 3 C00033")
#r.Balance()
pl.find_path("three_acetate", r)
def example_rpi_bypass(thermo):
pl = Pathologic(db=SqliteDatabase('../res/gibbs.sqlite', 'r'),
public_db=SqliteDatabase('../data/public_data.sqlite'),
html_writer=HtmlWriter('../res/pathologic.html'),
thermo=thermo,
max_solutions=None,
max_reactions=10,
maximal_dG=0.0,
thermodynamic_method=OptimizationMethods.GLOBAL,
update_file=None)
add_cofactor_reactions(pl)
#add_redox_reactions(pl)
pl.delete_reaction(1056) # ribose-phosphate isomerase
pl.delete_reaction(1081) # ribose isomerase
r = Reaction.FromFormula("C00117 => C01182")
#r.Balance()
pl.find_path("rpi_bypass", r)
def example_glucose_to_ethanol_and_formate(thermo):
pl = Pathologic(db=SqliteDatabase('../res/gibbs.sqlite', 'r'),
public_db=SqliteDatabase('../data/public_data.sqlite'),
html_writer=HtmlWriter('../res/pathologic.html'),
thermo=thermo,
max_solutions=None,
max_reactions=15,
maximal_dG=0.0,
thermodynamic_method=OptimizationMethods.GLOBAL,
update_file=None)
#add_cofactor_reactions(pl)
#add_XTP_reactions(pl, '=>')
#add_redox_reactions(pl)
#pl.delete_reaction(761) # F6P + Pi = E4P + acetyl-P
#pl.delete_reaction(1621) # X5P + Pi = GA3P + acetyl-P
r = Reaction.FromFormula("2 C00031 + 3 C00001 => 6 C00058 + 3 C00469")
r.Balance()
pl.find_path("glucose_to_ethanol_and_formate", r)
def example_more_than_two_pyruvate(thermo):
pl = Pathologic(db=SqliteDatabase('../res/gibbs.sqlite', 'r'),
public_db=SqliteDatabase('../data/public_data.sqlite'),
html_writer=HtmlWriter('../res/pathologic.html'),
thermo=thermo,
max_solutions=None,
max_reactions=20,
maximal_dG=0.0,
thermodynamic_method=OptimizationMethods.GLOBAL,
update_file=None)
#add_cofactor_reactions(pl)
#add_XTP_reactions(pl, '=>')
#add_redox_reactions(pl)
#pl.delete_reaction(761) # F6P + Pi = E4P + acetyl-P
#pl.delete_reaction(1621) # X5P + Pi = GA3P + acetyl-P
r = Reaction.FromFormula("3 C00031 + 3 C00011 + C00003 => 7 C00022 + 3 C00001 + C00004")
r.Balance()
pl.find_path("more_than_two_pyr", r)
def main():
options, _ = MakeOpts().parse_args(sys.argv)
db = SqliteDatabase("../res/gibbs.sqlite")
public_db = SqliteDatabase("../data/public_data.sqlite")
output_filename = os.path.abspath(options.output_filename)
logging.info('Will write output to %s' % output_filename)
html_writer = HtmlWriter(output_filename)
nist = Nist(T_range=None)
nist_regression = NistRegression(db, html_writer=html_writer, nist=nist)
nist_regression.std_diff_threshold = 5 # the threshold over which to print an analysis of a reaction
#nist_regression.nist.T_range = None(273.15 + 24, 273.15 + 40)
#nist_regression.nist.override_I = 0.25
#nist_regression.nist.override_pMg = 14.0
html_writer.write("<h2>NIST regression:</h2>")
if options.use_prior:
logging.info('Using the data from Alberty as fixed prior')
prior_thermo = PsuedoisomerTableThermodynamics.FromDatabase(
public_db, 'alberty_pseudoisomers', name="Alberty")
else:
prior_thermo = None
html_writer.write('</br><b>Regression Tables</b>\n')
html_writer.insert_toggle(start_here=True)
nist_regression.Train(options.from_database, prior_thermo)
html_writer.div_end()
html_writer.write('</br><b>PRC results</b>\n')
html_writer.insert_toggle(start_here=True)
nist_regression.WriteDataToHtml(html_writer)
html_writer.div_end()
html_writer.write('</br><b>Transformed reaction energies - PRC vs. Observed</b>\n')
html_writer.insert_toggle(start_here=True)
N, rmse = nist_regression.VerifyResults()
html_writer.div_end()
logging.info("Regression results for transformed data:")
logging.info("N = %d, RMSE = %.1f" % (N, rmse))
html_writer.close()
def main():
estimators = LoadAllEstimators()
parser = MakeArgParser(estimators)
args = parser.parse_args()
thermo = estimators[args.thermodynamics_source]
kegg_file = ParsedKeggFile.FromKeggFile(args.config_fname)
entries = kegg_file.entries()
if len(entries) == 0:
raise ValueError('No entries in configuration file')
entry = 'CONFIGURATION'
if entry not in entries:
logging.warning(
'Configuration file does not contain the entry "CONFIGURATION". '
'Using the first entry by default: %s' % entries[0])
entry = entries[0]
p_data = PathwayData.FromFieldMap(kegg_file[entry])
thermo.SetConditions(pH=p_data.pH, I=p_data.I, T=p_data.T, pMg=p_data.pMg)
thermo.c_range = p_data.c_range
bounds = p_data.GetBounds()
html_writer = HtmlWriter(args.output_prefix + ".html")
rowdicts = []
headers = ['Module', 'Name', 'OBD [kJ/mol]', 'Length']
kegg = Kegg.getInstance()
for mid in kegg.get_all_mids():
html_writer.write('<h2 id=M%05d>M%05d: %s</h2>' %
(mid, mid, kegg.get_module_name(mid)))
try:
d = AnalyzeKeggModule(thermo, mid, bounds, html_writer)
except KeyError:
continue
d['Module'] = '<a href="#M%05d">M%05d</a>' % (mid, mid)
d['Name'] = kegg.get_module_name(mid)
rowdicts.append(d)
rowdicts.sort(key=lambda x: x['OBD [kJ/mol]'])
html_writer.write_table(rowdicts, headers, decimal=1)
html_writer.close()
def example_formate(thermo, product_cid=22, co2_conc=1e-5):
co2_hydration = Reaction.FromFormula("C00011 + C00001 => C00288")
co2_hydration_dG0_prime = float(thermo.GetTransfromedKeggReactionEnergies([co2_hydration]))
carbonate_conc = co2_conc * np.exp(-co2_hydration_dG0_prime / (R*default_T))
thermo.bounds[11] = (co2_conc, co2_conc)
thermo.bounds[288] = (carbonate_conc, carbonate_conc)
pl = Pathologic(db=SqliteDatabase('../res/gibbs.sqlite', 'r'),
public_db=SqliteDatabase('../data/public_data.sqlite'),
html_writer=HtmlWriter('../res/pathologic.html'),
thermo=thermo,
max_solutions=None,
max_reactions=20,
maximal_dG=0.0,
thermodynamic_method=OptimizationMethods.GLOBAL,
update_file=None)
add_cofactor_reactions(pl, free_ATP_hydrolysis=True)
add_redox_reactions(pl, NAD_only=False)
pl.delete_reaction(134) # formate:NADP+ oxidoreductase
pl.delete_reaction(519) # Formate:NAD+ oxidoreductase
pl.delete_reaction(24) # Rubisco
pl.delete_reaction(581) # L-serine:NAD+ oxidoreductase (deaminating)
pl.delete_reaction(220) # L-serine ammonia-lyase
pl.delete_reaction(13) # glyoxylate carboxy-lyase (dimerizing; tartronate-semialdehyde-forming)
pl.delete_reaction(585) # L-Serine:pyruvate aminotransferase
pl.delete_reaction(1440) # D-Xylulose-5-phosphate:formaldehyde glycolaldehydetransferase
pl.delete_reaction(5338) # 3-hexulose-6-phosphate synthase
pl.add_reaction(Reaction.FromFormula("C06265 => C00011", name="CO2 uptake"))
pl.add_reaction(Reaction.FromFormula("C06265 => C00288", name="carbonate uptake"))
pl.add_reaction(Reaction.FromFormula("C06265 => C00058", name="formate uptake"))
r = Reaction.FromFormula("5 C06265 + C00058 => C%05d" % product_cid) # at least one formate to product
#r.Balance()
kegg = Kegg.getInstance()
pl.find_path("formate to %s" % kegg.cid2name(product_cid), r)
def runPathologic(thermo, reactionList):
pl = Pathologic(db=SqliteDatabase('../res/gibbs.sqlite', 'r'),
public_db=SqliteDatabase('../data/public_data.sqlite'),
html_writer=HtmlWriter('../res/mog_finder.html'),
thermo=thermo,
max_solutions=None,
max_reactions=15,
maximal_dG=-3.0,
thermodynamic_method=OptimizationMethods.GLOBAL,
update_file=None)
add_cofactor_reactions(pl)
add_redox_reactions(pl)
for r in reactionList:
pl.add_reaction(Reaction.FromFormula(r, "Auto generate #%s" % hash(r)))
pl.delete_reaction(134)
pl.delete_reaction(344)
pl.delete_reaction(575)
pl.delete_reaction(212)
#pl.add_reaction(Reaction.FromFormula('C00149 + C00006 <=> C00036 + C00005 + C00080',
# 'malate + NADP+ = oxaloacetate + NADPH',343))
#pl.add_reaction(Reaction.FromFormula('C00222 + C00010 + C00006 <=> C00083 + C00005',
# 'malonate-semialdehyde + CoA + NADP+ = malonyl-CoA + NADPH',740))
r = Reaction.FromFormula("2 C00288 => C00048")
pl.find_path("MOG_finder", r)
continue
if self.override_pMg or self.override_I or self.override_T:
nist_row_copy = nist_row_data.Clone()
if self.override_pMg:
nist_row_copy.pMg = self.override_pMg
if self.override_I:
nist_row_copy.I = self.override_I
if self.override_T:
nist_row_copy.T = self.override_T
rows.append(nist_row_copy)
else:
rows.append(nist_row_data)
return rows
def GetUniqueReactionSet(self):
return set([row.reaction for row in self.data])
if __name__ == '__main__':
#logging.getLogger('').setLevel(logging.DEBUG)
_mkdir("../res/nist")
html_writer = HtmlWriter("../res/nist/statistics.html")
nist = Nist()
fp = open('../res/nist_kegg_ids.txt', 'w')
for cid in nist.GetAllCids():
fp.write("C%05d\n" % cid)
fp.close()
nist.AnalyzeStats(html_writer)
nist.AnalyzeConnectivity(html_writer)
html_writer.close()
#print m.ToFormat('mol')
#print m.ToFormat('mol2')
#print m.ToFormat('smi')
#print m.ToFormat('inchi')
#print m.ToFormat('sdf')
diss_table = Molecule._GetDissociationTable('C(=O)(O)CN',
fmt='smiles',
mid_pH=default_pH,
min_pKa=0,
max_pKa=14,
T=default_T)
print "glycine\n", diss_table
html_writer = HtmlWriter('../res/molecule.html')
from pygibbs.kegg import Kegg
kegg = Kegg.getInstance()
html_writer.write('<h1>pKa estimation using ChemAxon</h1>\n')
for cid in [41]:
m = kegg.cid2mol(cid)
html_writer.write("<h2>C%05d : %s</h2>\n" % (cid, str(m)))
diss_table = m.GetDissociationTable()
pmap = diss_table.GetPseudoisomerMap()
diss_table.WriteToHTML(html_writer)
pmap.WriteToHTML(html_writer)
html_writer.write("</p>\n")
#print m.GetDissociationConstants()
#print m.GetMacrospecies()
#obmol = m.ToOBMol()
return parser
if __name__ == '__main__':
parser = MakeOpts()
args = parser.parse_args()
util._mkdir('../res')
db = SqliteDatabase('../res/gibbs.sqlite', 'w')
if args.transformed:
prefix = 'bgc'
else:
prefix = 'pgc'
if args.test_only:
html_writer = HtmlWriter('../res/%s_test.html' % prefix)
elif args.train_only:
html_writer = HtmlWriter('../res/%s_train.html' % prefix)
else:
html_writer = HtmlWriter('../res/%s.html' % prefix)
G = GroupContribution(db=db,
html_writer=html_writer,
transformed=args.transformed)
G.LoadGroups(FromDatabase=args.from_database, FromFile=args.groups_species)
G.LoadObservations(args.from_database)
G.LoadGroupVectors(args.from_database)
if args.test_only:
G.LoadContributionsFromDB()
args, _ = MakeOpts(estimators).parse_args(sys.argv)
input_filename = os.path.abspath(args.input_filename)
output_filename = os.path.abspath(args.output_filename)
if not os.path.exists(input_filename):
logging.fatal('Input filename %s doesn\'t exist' % input_filename)
print 'Will read pathway definitions from %s' % input_filename
print 'Will write output to %s' % output_filename
db_loc = args.db_filename
print 'Reading from DB %s' % db_loc
db = SqliteDatabase(db_loc)
thermo = estimators[args.thermodynamics_source]
print "Using the thermodynamic estimations of: " + thermo.name
kegg = Kegg.getInstance()
thermo.bounds = deepcopy(kegg.cid2bounds)
dirname = os.path.dirname(output_filename)
if not os.path.exists(dirname):
print 'Making output directory %s' % dirname
_mkdir(dirname)
print 'Executing thermodynamic pathway analysis'
html_writer = HtmlWriter(output_filename)
thermo_analyze = ThermodynamicAnalysis(db, html_writer, thermodynamics=thermo)
thermo_analyze.analyze_pathway(input_filename)
def main():
db = database.SqliteDatabase('../res/gibbs.sqlite')
html_writer = HtmlWriter("../res/nist/report.html")
gc = GroupContribution(db)
gc.override_gc_with_measurements = True
gc.init()
grad = GradientAscent(gc)
nist = Nist(db, html_writer, gc.kegg())
nist.FromDatabase()
alberty = Alberty()
hatzi = Hatzi()
if True:
grad.load_nist_data(nist,
alberty,
skip_missing_reactions=False,
T_range=(298, 314))
grad.verify_results("Alberty", alberty, html_writer)
#grad.write_pseudoisomers("../res/nist/nist_dG0_f.csv")
#html_writer.write("<h2>Using Group Contribution (Hatzimanikatis' implementation)</h2>")
#html_writer.write("<h3>Correlation with the reduced NIST database (containing only compounds that appear in Alberty's list)</h3>")
#logging.info("calculate the correlation between Hatzimanikatis' predictions and the reduced NIST database")
#grad.verify_results("Hatzimanikatis_Reduced", hatzi, html_writer)
#grad.load_nist_data(nist, hatzi, skip_missing_reactions=True, T_range=(298, 314))
grad.verify_results("Hatzimanikatis", hatzi, html_writer)
#grad.load_nist_data(nist, gc, skip_missing_reactions=True, T_range=(298, 314))
grad.verify_results("Milo", gc, html_writer)
elif False:
# Run the gradient ascent algorithm, where the starting point is the same file used for training the GC algorithm
grad.load_dG0_data("../data/thermodynamics/dG0.csv")
# load the data for the anchors (i.e. compounds whose dG0 should not be changed - usually their value will be 0).
grad.anchors = grad.load_dG0_data(
"../data/thermodynamics/nist_anchors.csv")
grad.load_nist_data(nist, grad, skip_missing_reactions=True)
print "Training %d compounds using %d reactions: " % (len(
grad.cid2pmap_dict.keys()), len(grad.data))
grad.hill_climb(max_i=20000)
grad.save_energies(grad.gc.comm, "gradient_cid2prm")
grad.verify_results("gradient1")
elif False:
# Run the gradient ascent algorithm, where the starting point is Alberty's table from (Mathematica 2006)
grad.load_nist_data(nist, alberty, skip_missing_reactions=True)
print "Training %d compounds using %d reactions: " % (len(
grad.cid2pmap_dict.keys()), len(grad.data))
grad.cid2pmap_dict = alberty.cid2pmap_dict
grad.hill_climb(max_i=20000)
grad.save_energies(grad.gc.comm, "gradient_cid2prm")
grad.verify_results("gradient2")
elif False:
# Run the gradient ascent algorithm, where the starting point is Alberty's table from (Mathematica 2006)
# Use DETERMINISTIC gradient ascent
grad.load_nist_data(nist,
alberty,
skip_missing_reactions=True,
T_range=(24 + 273.15, 40 + 273.15))
print "Training %d compounds using %d reactions: " % (len(
grad.cid2pmap_dict.keys()), len(grad.data))
grad.cid2pmap_dict = alberty.cid2pmap_dict
grad.deterministic_hill_climb(max_i=200)
grad.save_energies(grad.gc.comm, "gradient_cid2prm")
grad.verify_results("gradient_deterministic")
elif False:
# Run the gradient ascent algorithm, where the starting point arbitrary (predict all of the NIST compounds)
grad = GradientAscent(gc)
grad.load_nist_data(nist, skip_missing_reactions=False)
print "Training %d compounds using %d reactions: " % (len(
grad.cid2pmap_dict.keys()), len(grad.data))
grad.hill_climb(max_i=20000)
grad.save_energies(grad.gc.comm, "gradient_cid2prm")
grad.verify_results("gradient3")
elif False: # Use Alberty's table from (Mathematica 2006) to calculate the dG0 of all possible reactions in KEGG
grad = GradientAscent(gc)
grad.cid2pmap_dict = alberty.cid2pmap_dict
(pH, I, T) = (7, 0, 300)
counter = 0
for rid in grad.kegg.get_all_rids():
sparse_reaction = grad.kegg.rid2sparse_reaction(rid)
try:
dG0 = grad.reaction_to_dG0(sparse_reaction, pH, I, T)
print "R%05d: dG0_r = %.2f [kJ/mol]" % (rid, dG0)
counter += 1
except MissingCompoundFormationEnergy as e:
#print "R%05d: missing formation energy of C%05d" % (rid, e.cid)
pass
print "Managed to calculate the dG0 of %d reactions" % counter
elif False:
util._mkdir("../res/nist/fig")
csv_writer = csv.writer(open("../res/nist/pseudoisomers.csv", "w"))
cid_set = set()
for row in nist.data:
sparce_reaction = row['sparse']
cid_set.update(sparce_reaction.keys())
html_writer.write("<table border=1>\n")
for cid in sorted(list(cid_set)):
html_writer.write(" <tr><td>C%05d</td><td>%s</td><td>" %
(cid, grad.kegg.cid2name(cid)))
try:
mol = grad.kegg.cid2mol(cid)
img_fname = '../res/nist/fig/C%05d.png' % cid
html_writer.embed_img(img_fname, "C%05d" % cid)
mol.draw(show=False, filename=img_fname)
except AssertionError as e:
html_writer.write("WARNING: cannot draw C%05d - %s" %
(cid, str(e)))
except KeggParseException as e:
html_writer.write("WARNING: cannot draw C%05d - %s" %
(cid, str(e)))
html_writer.write("</td><td>")
if (cid in alberty.cid2pmap_dict):
for (nH, z) in alberty.cid2pmap_dict[cid].keys():
html_writer.write("(nH=%d, z=%d)<br>" % (nH, z))
csv_writer.writerow((cid, nH, z))
else:
nH = grad.kegg.cid2num_hydrogens(cid)
z = grad.kegg.cid2charge(cid)
html_writer.write("unknown pseudoisomers<br>")
html_writer.write("(nH=%d, z=%d)" % (nH, z))
csv_writer.writerow((cid, nH, z))
html_writer.write("</td></tr>\n")
html_writer.write("</table>\n")
html_writer.close()
def AnalyzeConcentrationGradient(pathway_file,
output_prefix,
thermo,
conc_range,
cids=[],
pH=None):
compound_names = ','.join([thermo.kegg.cid2name(cid) for cid in cids])
pathway_list = KeggFile2PathwayList(pathway_file)
pathway_names = [entry for (entry, _) in pathway_list]
html_writer = HtmlWriter('%s.html' % output_prefix)
# run once just to make sure that the pathways are all working:
logging.info("testing all pathways with default concentrations")
data = GetAllOBDs(pathway_list,
html_writer,
thermo,
pH=pH,
section_prefix="test",
balance_water=True,
override_bounds={})
csv_output = csv.writer(open('%s.csv' % output_prefix, 'w'))
csv_output.writerow(['pH', '[' + compound_names + ']'] + pathway_names)
conc_vec = 10**(-ParseConcentrationRange(conc_range)
) # logarithmic scale between 10mM and 1nM
override_bounds = {}
obd_mat = []
for conc in conc_vec.flat:
for cid in cids:
override_bounds[cid] = (conc, conc)
logging.info("[%s] = %.1e M" % (compound_names, conc))
data = GetAllOBDs(pathway_list,
html_writer=None,
thermo=thermo,
pH=pH,
section_prefix="",
balance_water=True,
override_bounds=override_bounds)
obds = [d['OBD'] for d in data]
obd_mat.append(obds)
csv_output.writerow([data[0]['pH'], conc] + obds)
obd_mat = np.matrix(
obd_mat) # rows are pathways and columns are concentrations
fig = plt.figure(figsize=(6, 6), dpi=90)
colormap = color.ColorMap(pathway_names)
for i, name in enumerate(pathway_names):
plt.plot(conc_vec,
obd_mat[:, i],
'-',
color=colormap[name],
figure=fig)
plt.title("OBD vs. [%s]" % (compound_names), figure=fig)
plt.xscale('log')
plt.ylim(ymin=0)
plt.xlabel('[%s] (in M)' % compound_names, figure=fig)
plt.ylabel('Optimized Distributed Bottleneck [kJ/mol]', figure=fig)
plt.legend(pathway_names)
html_writer.write('<h2>Summary figure</h1>\n')
html_writer.embed_matplotlib_figure(fig)
html_writer.close()
if __name__ == "__main__":
kegg = Kegg.getInstance()
graph = {}
for rid in kegg.get_all_rids():
r = kegg.rid2reaction(rid)
for cid1 in r.sparse.keys():
for cid2 in r.sparse.keys():
if r.sparse[cid1] * r.sparse[cid2] < 0:
graph.setdefault(cid1, set()).add(cid2)
queue = [355]
cofactors = set([1,2,3,4,5,6,7,8,9,10,11,13,14,20,28,30])
html_writer = HtmlWriter('../res/kegg_bfs.html')
for i in xrange(3):
next_queue = set()
cofactors.update(queue)
while queue:
cid = queue.pop(0)
next_queue.update(graph[cid])
queue = list(next_queue.difference(cofactors))
for cid in queue:
try:
html_writer.write(kegg.cid2mol(cid).ToSVG())
html_writer.write(kegg.cid2name(cid))
except (KeggParseException, OpenBabelError):
html_writer.write(kegg.cid2name(cid))
def WriteUniqueReactionReport(self, unique_sparse_reactions,
unique_nist_row_representatives,
unique_data_mat, full_data_mat,
cid2nH_nMg=None):
total_std = full_data_mat[2:4, :].std(1)
fig = plt.figure()
plt.plot(unique_data_mat[2, :].T, unique_data_mat[3, :].T, '.')
plt.xlabel("$\sigma(\Delta_r G^\circ)$")
plt.ylabel("$\sigma(\Delta_r G^{\'\circ})$")
plt.title('$\sigma_{total}(\Delta_r G^\circ) = %.1f$ kJ/mol, '
'$\sigma_{total}(\Delta_r G^{\'\circ}) = %.1f$ kJ/mol' %
(total_std[0, 0], total_std[1, 0]))
self.html_writer.embed_matplotlib_figure(fig, width=640, height=480)
logging.info('std(dG0_r) = %.1f' % total_std[0, 0])
logging.info('std(dG\'0_r) = %.1f' % total_std[1, 0])
rowdicts = []
for i, reaction in enumerate(unique_sparse_reactions):
logging.debug('Analyzing unique reaction: ' +
str(unique_sparse_reactions[i]))
ddG0 = self.GetDissociation().ReverseTransformReaction(reaction,
pH=7, I=0.1, pMg=10, T=298.15, cid2nH_nMg=cid2nH_nMg)
d = {}
d["_reaction"] = reaction.to_hypertext(show_cids=False)
d["reaction"] = reaction.FullReactionString(show_cids=False) # no hypertext for the CSV output
d["Reference ID"] = unique_nist_row_representatives[i].ref_id
d["EC"] = unique_nist_row_representatives[i].ec
d["E(" + symbol_dr_G0 + ")"] = unique_data_mat[0, i]
d["E(" + symbol_dr_G0_prime + ")"] = unique_data_mat[1, i]
d["E(" + symbol_dr_G0 + ")'"] = unique_data_mat[0, i] + ddG0
d["std(" + symbol_dr_G0 + ")"] = unique_data_mat[2, i]
d["std(" + symbol_dr_G0_prime + ")"] = unique_data_mat[3, i]
d["diff"] = unique_data_mat[2, i] - unique_data_mat[3, i]
d["#observations"] = "%d" % unique_data_mat[4, i]
flag = 0
c_nad = reaction.sparse.get(3, 0)
c_nadh = reaction.sparse.get(4, 0)
c_nadp = reaction.sparse.get(6, 0)
c_nadph = reaction.sparse.get(5, 0)
if c_nad == 1 and c_nadh == -1:
flag = 1
elif c_nad == -1 and c_nadh == 1:
flag = -1
elif c_nadp == 1 and c_nadph == -1:
flag = 2
elif c_nadp == -1 and c_nadph == 1:
flag = -2
d["Arren Flag"] = flag
if d["diff"] > self.std_diff_threshold:
_mkdir('../res/prc_reactions')
link = "prc_reactions/%s.html" % reaction.name
d["analysis"] = '<a href="%s">link</a>' % link
reaction_html_writer = HtmlWriter(os.path.join('../res', link))
self.AnalyzeSingleReaction(reaction,
html_writer=reaction_html_writer)
rowdicts.append(d)
result_headers = ["E(" + symbol_dr_G0 + ")",
"E(" + symbol_dr_G0_prime + ")",
"E(" + symbol_dr_G0 + ")'",
"std(" + symbol_dr_G0 + ")",
"std(" + symbol_dr_G0_prime + ")"]
rowdicts.sort(key=lambda x:x["diff"], reverse=True)
self.html_writer.write_table(rowdicts, ["reaction", "Reference ID"] +
result_headers + ["EC", "#observations", "analysis"],
decimal=1)
csv_writer = csv.DictWriter(open('../res/nist_regression_unique.csv', 'w'),
["_reaction", "Reference ID", "EC", "#observations"]
+ result_headers + ['Arren Flag'],
extrasaction='ignore')
csv_writer.writeheader()
csv_writer.writerows(rowdicts)
def main():
html_writer = HtmlWriter("../res/nist/report.html")
estimators = LoadAllEstimators()
nist = Nist()
nist.T_range = (273.15 + 24, 273.15 + 40)
#nist.override_I = 0.25
#nist.override_pMg = 14.0
#nist.override_T = 298.15
html_writer.write('<p>\n')
html_writer.write("Total number of reaction in NIST: %d</br>\n" %
len(nist.data))
html_writer.write("Total number of reaction in range %.1fK < T < %.1fK: %d</br>\n" % \
(nist.T_range[0], nist.T_range[1], len(nist.SelectRowsFromNist())))
html_writer.write('</p>\n')
reactions = {}
reactions['KEGG'] = []
for reaction in Kegg.getInstance().AllReactions():
try:
reaction.Balance(balance_water=True, exception_if_unknown=True)
reactions['KEGG'].append(reaction)
except (KeggReactionNotBalancedException, KeggParseException,
OpenBabelError):
pass
reactions['FEIST'] = Feist.FromFiles().reactions
reactions['NIST'] = nist.GetUniqueReactionSet()
pairs = []
#pairs += [('hatzi_gc', 'UGC')], ('PGC', 'PRC'), ('alberty', 'PRC')]
for t1, t2 in pairs:
logging.info('Writing the NIST report for %s vs. %s' %
(estimators[t1].name, estimators[t2].name))
html_writer.write('<p><b>%s vs. %s</b> ' %
(estimators[t1].name, estimators[t2].name))
html_writer.insert_toggle(start_here=True)
two_way_comparison(html_writer=html_writer,
thermo1=estimators[t1],
thermo2=estimators[t2],
reaction_list=reactions['FEIST'],
name='%s_vs_%s' % (t1, t2))
html_writer.div_end()
html_writer.write('</p>')
if False:
estimators['alberty'].CompareOverKegg(
html_writer,
other=estimators['PRC'],
fig_name='kegg_compare_alberty_vs_nist')
rowdicts = []
rowdict = {'Method': 'Total'}
for db_name, reaction_list in reactions.iteritems():
rowdict[db_name + ' coverage'] = len(reaction_list)
rowdicts.append(rowdict)
for name in ['UGC', 'PGC', 'PRC', 'alberty', 'merged', 'hatzi_gc']:
thermo = estimators[name]
logging.info('Writing the NIST report for %s' % thermo.name)
html_writer.write('<p><b>%s</b> ' % thermo.name)
html_writer.insert_toggle(start_here=True)
num_estimations, rmse = nist.verify_results(html_writer=html_writer,
thermodynamics=thermo,
name=name)
html_writer.div_end()
html_writer.write('N = %d, RMSE = %.1f</p>\n' %
(num_estimations, rmse))
logging.info('N = %d, RMSE = %.1f' % (num_estimations, rmse))
rowdict = {
'Method': thermo.name,
'RMSE (kJ/mol)': "%.1f (N=%d)" % (rmse, num_estimations)
}
for db_name, reaction_list in reactions.iteritems():
n_covered = thermo.CalculateCoverage(reaction_list)
percent = n_covered * 100.0 / len(reaction_list)
rowdict[db_name +
" coverage"] = "%.1f%% (%d)" % (percent, n_covered)
logging.info(db_name + " coverage = %.1f%%" % percent)
rowdicts.append(rowdict)
headers = ['Method', 'RMSE (kJ/mol)'] + \
[db_name + ' coverage' for db_name in reactions.keys()]
html_writer.write_table(rowdicts, headers=headers)
def AnalyzePHGradient(pathway_file, output_prefix, thermo, conc_range):
pathway_list = KeggFile2PathwayList(pathway_file)
pathway_names = [entry for (entry, _) in pathway_list]
html_writer = HtmlWriter('%s.html' % output_prefix)
# run once just to make sure that the pathways are all working:
logging.info("testing all pathways with default pH")
data = GetAllOBDs(pathway_list,
html_writer,
thermo,
pH=None,
section_prefix="test",
balance_water=True,
override_bounds={})
csv_output = csv.writer(open('%s.csv' % output_prefix, 'w'))
csv_output.writerow(['pH'] + pathway_names)
util._mkdir(output_prefix)
shadow_csvs = {}
for d in data:
path = '%s/%s.csv' % (output_prefix, d['entry'])
shadow_csvs[d['entry']] = csv.writer(open(path, 'w'))
shadow_csvs[d['entry']].writerow(['pH'] + d['rids'])
pH_vec = ParseConcentrationRange(conc_range)
obd_mat = []
for pH in pH_vec.flat:
logging.info("pH = %.1f" % (pH))
data = GetAllOBDs(pathway_list,
html_writer=None,
thermo=thermo,
pH=pH,
section_prefix="",
balance_water=True,
override_bounds={})
obds = [d['OBD'] for d in data]
obd_mat.append(obds)
csv_output.writerow([data[0]['pH']] + obds)
for d in data:
if type(d['reaction prices']) != types.FloatType:
prices = list(d['reaction prices'].flat)
shadow_csvs[d['entry']].writerow([pH] + prices)
obd_mat = np.matrix(
obd_mat) # rows are pathways and columns are concentrations
fig = plt.figure(figsize=(6, 6), dpi=90)
colormap = color.ColorMap(pathway_names)
for i, name in enumerate(pathway_names):
plt.plot(pH_vec, obd_mat[:, i], '-', color=colormap[name], figure=fig)
plt.title("OBD vs. pH", figure=fig)
plt.ylim(0, np.max(obd_mat.flat))
plt.xlabel('pH', figure=fig)
plt.ylabel('Optimized Distributed Bottleneck [kJ/mol]', figure=fig)
plt.legend(pathway_names)
html_writer.write('<h2>Summary figure</h1>\n')
html_writer.embed_matplotlib_figure(fig)
html_writer.close()
'--leave_one_out',
action='store_true',
default=False,
help='A flag for running the Leave One Out analysis')
return parser
if __name__ == "__main__":
logger = logging.getLogger('')
logger.setLevel(logging.DEBUG)
parser = MakeOpts()
args = parser.parse_args()
util._mkdir('../res')
db = SqliteDatabase('../res/gibbs.sqlite', 'w')
html_writer = HtmlWriter('../res/ugc.html')
ugc = UnifiedGroupContribution(db,
html_writer,
anchor_all=args.anchor_all_formations)
ugc.LoadGroups(FromDatabase=(not args.recalc_groups))
ugc.LoadObservations(FromDatabase=(not args.recalc_observations))
ugc.LoadGroupVectors(FromDatabase=(not args.recalc_groupvectors))
ugc.LoadData(FromDatabase=(not args.recalc_matrices))
if args.dump:
ugc.SaveDataToMatfile()
sys.exit(0)
if args.train:
ugc.EstimateKeggCids()
sys.exit(0)
