def GetMolInput(dissociation):
mols = [
] # a list of pairs of Molecule objects and stoichiometric coefficients
while mols == []:
print 'KEGG ID or SMILES (or Enter to quit):',
s_input = raw_input()
if not s_input:
return []
elif re.findall('C\d\d\d\d\d', s_input) != []:
try:
cid = int(s_input[1:])
mols = [(GetMostAbundantMol(cid, dissociation), 1)]
print "Compound:", mols[0][0].ToInChI()
except ValueError:
print 'syntax error: KEGG compound ID is bad (%s), please try again' % s_input
elif re.findall('R\d\d\d\d\d', s_input) != []:
try:
rid = int(s_input[1:])
reaction = Kegg.getInstance().rid2reaction(rid)
print "Reaction:", str(reaction)
for cid, coeff in reaction.iteritems():
mols += [(GetMostAbundantMol(cid, dissociation), coeff)]
except ValueError:
print 'syntax error: KEGG reaction ID is bad (%s), please try again' % s_input
else:
try:
mols = [(Molecule.FromSmiles(s_input), 1)]
print "Compound:", mols[0][0].ToInChI()
except Exception:
print 'unable to parse SMILES string, please try again'
return mols
def CreateEmptyGroupDecomposition(self):
emptymol = Molecule.FromSmiles("")
decomposition = self.Decompose(emptymol,
ignore_protonations=True,
strict=False)
for i, (group, _node_sets) in enumerate(decomposition.groups):
decomposition.groups[i] = (group, [])
return decomposition
def GetMol(self, nH=None, nMg=0):
from toolbox.molecule import Molecule
if nH is None:
nH = self.min_nH
if (nH, nMg) not in self.mol_dict:
return None
s, mol = self.mol_dict[nH, nMg]
if mol is None:
mol = Molecule.FromSmiles(s)
self.mol_dict[nH, nMg] = (s, mol)
return mol
def test_dissociation_table(diss,
group_decomposer,
id,
ignore_missing_smiles=False):
if diss is None:
logging.warning('%s: does not appear in the dissociation table' % id)
return
nH, nMg = diss.GetMostAbundantPseudoisomer(pH=default_pH,
I=default_I,
pMg=14,
T=default_T)
if nMg != 0:
logging.warning('%s: default species has nMg = %d' % (id, nMg))
return
smiles = diss.GetSmiles(nH=nH, nMg=0)
if not smiles:
if not ignore_missing_smiles:
logging.warning(
'%s: no SMILES in the dissociation table for nH = %d' %
(id, nH))
return
logging.debug('%s: nH = %d, smiles = %s' % (id, nH, smiles))
mol = Molecule.FromSmiles(smiles)
try:
decomposition = group_decomposer.Decompose(mol,
ignore_protonations=False,
strict=True)
except GroupDecompositionError:
return
groupvec = decomposition.AsVector()
logging.debug("%s: decomposition = %s" % (id, groupvec))
gc_nH = decomposition.Hydrogens()
if nH != gc_nH:
logging.warning(
'%s: nH doesn\'t match: explicit = %d, decomposition = %d' %
(id, nH, gc_nH))
import unittest
from pygibbs.groups_data import GroupsData
from pygibbs import group_decomposition
from toolbox.molecule import Molecule
import logging
PHOSPHATE = Molecule.FromSmiles('[O-]P([O-])(=O)O')
ATP = Molecule.FromSmiles(
'C1=NC2=C(C(=N1)N)N=CN2C3C(C(C(O3)COP(=O)([O-])OP(=O)([O-])OP(=O)([O-])O)O)O'
)
A4P = Molecule.FromSmiles(
'C1=NC2=C(C(=N1)N)N=CN2C3C(C(C(O3)COP(=O)([O-])OP(=O)([O-])OP(=O)([O-])OP(=O)([O-])O)O)O'
)
class GroupsDecompositionTest(unittest.TestCase):
"""Tests for GroupsDecomposition"""
def setUp(self):
self.groups_decomposer = group_decomposition.GroupDecomposer.FromGroupsFile(
open('../data/thermodynamics/groups_species.csv', 'r'))
def testFindPhosphateChains(self):
ps = group_decomposition.GroupDecomposer.FindPhosphateChains(
PHOSPHATE, ignore_protonations=False)
for unused_grp, l in ps:
self.assertTrue(not l)
mk_ps_dict = lambda ps: dict((key, l) for key, l in ps)
mk_ps_string = lambda ps: ', '.join(
["%s x %d" % (str(key), len(l)) for key, l in ps if l != []])
sum_conc = 0
for Ka_subset in itertools.combinations(Ka_list, i+1): # all choices of i values from the Ka list
sum_conc += np.prod(Ka_subset)
relative_conc.append(sum_conc)
Ka_i = relative_conc[i+1] / relative_conc[i]
transformed_pKas.append(-np.log10(Ka_i))
return transformed_pKas
if __name__ == "__main__":
diss_table_example = [4.0, 4.0, 4.0]
new_diss_table = _TransformMultiples(diss_table_example)
print diss_table_example
print new_diss_table
from toolbox.molecule import Molecule
compound_list = [('glycine', 'C(=O)(O)CN'),
('CO2', 'O=C=O'),
('ATP', 'Nc1ncnc2n(cnc12)C1OC(COP([O-])(=O)OP([O-])(=O)OP(O)([O-])=O)C(O)C1O'),
('3-Ketoarabinitol', 'OCC(O)C(C(O)CO)=O')]
for name, smiles in compound_list:
diss_table1, major_ms = GetDissociationConstants(smiles, transform_multiples=False)
diss_table2, major_ms = GetDissociationConstants(smiles, transform_multiples=True)
m = Molecule.FromSmiles(major_ms)
print name, m.ToInChI()
for i in xrange(len(diss_table1)):
print "%.2f %.2f" % (diss_table1[i][0], diss_table2[i][0])
logging.error(e)
continue
return
atp = 'C1=NC2=C(C(=N1)N)N=CN2C3C(C(C(O3)COP(=O)(O)OP(=O)(O)OP(=O)(O)O)O)O'
coa = 'C1C=CN(C=C1C(=O)N)C2C(C(C(O2)COP(=O)(O)OP(=O)(O)OCC3C(C(C(O3)N4C=NC5=C4N=CN=C5N)O)O)O)O'
glucose = 'C(C1C(C(C(C(O1)O)O)O)O)O'
mgatp = 'C([C@@H]1[C@H]([C@H]([C@H](n2cnc3c(N)[nH+]cnc23)O1)O)O)OP(=O)([O-])OP(=O)([O-])OP(=O)([O-])[O-].[Mg+2].[Mg+2]'
#smiless = [
# ('ATP', atp),
# ('CoA', coa), ('Glucose', glucose), ('MgAtp', mgatp),
# ]
smiless = [('ATP', atp)]
mols = [(name, Molecule.FromSmiles(s)) for name, s in smiless]
for name, mol in mols:
print name
decomposition = decomposer.Decompose(mol)
print decomposition.ToTableString()
print 'Group count', decomposition.group_count
print 'Net charge', decomposition.net_charge
print 'Hydrogens', decomposition.hydrogens
print 'Magnesiums', decomposition.magnesiums
print 'Group Vector:'
print decomposition.AsVector()
print 'Pseudoisomer Vectors:'
for v in decomposition.PseudoisomerVectors():
def main():
mol = Molecule.FromSmiles('C(O)(=O)C(=O)O')
emp = EnzymeMarketplace()
print emp.React(mol)