def classify(sdf, label, lambdas):
new_filename = "%s_class.sdf" % sdf.split('.sdf')[0]
new_label = label + "_class"
sdm = ForwardSDMolSupplier(sdf,
strictParsing=False,
removeHs=False,
sanitize=False)
sdw = SDWriter(new_filename)
counter = -1
i = 0
for mol in sdm:
print(i)
sys.stdout.flush()
i += 1
counter += 1
if mol is None:
print("%d rdkit couldn't read molecule" % counter, file=sys.stderr)
sys.stderr.flush()
continue
c = None
prop = floatify(mol.GetProp(label))
if prop is None:
print("couldn't convert %s to float or int...skip" %
mol.GetProp(label),
file=sys.stderr)
sys.stderr.flush()
continue
for k, l in lambdas.items():
if l(prop):
c = k
print("hit %s" % k)
sys.stdout.flush()
break
if c is None:
print("%d no prop range matched '%s' ..skip" %
(counter, mol.GetProp(label)),
prop,
type(prop),
file=sys.stderr)
sys.stderr.flush()
sys.stdout.flush()
continue
mol.SetProp(new_label, c)
try:
sdw.write(mol)
except:
print(
"couldn't write mol %d to file, try to build mol from smiles" %
i,
file=sys.stderr)
mol = MolFromSmiles(mol.GetProp("SMILES"))
AllChem.Compute2DCoords(mol)
mol.SetProp(new_label, c)
try:
sdw.write(mol)
except:
print("couldn't write mol %d to file...skip" % i,
file=sys.stderr)
sdw.close()
def extract_substructure_information(self, radii, smi_dict):
self.radii = radii
for akey in smi_dict.keys():
info = {}
mol = MolFromSmiles(smi_dict[akey])
fp = _GetMorganFingerprint(mol, max(radii), bitInfo=info)
mol_id = akey if self.name_field == None else mol.GetProp(
self.name_field)
self.mols_ids.append(mol_id)
substructure_dictionary = {
k: [mol_id]
for k, v in info.items() if v[0][1] in radii
}
self.substructure_dictionary = self._combine_dicts(
substructure_dictionary, self.substructure_dictionary)
self.nb_substructures = len(self.substructure_dictionary.keys())
self.max_radius = max(radii)
