def _validate(self, vals, tol=1e-2, show=False):
for smi, ans in vals:
mol = Chem.MolFromSmiles(smi)
types = AtomTypes.TypeAtoms(mol)
if show: # pragma: nocover
print(types)
self.assertEqual(len(ans), len(types), 'bad type len for smiles: %s' % (smi))
lens = [len(x) for x in types]
self.assertEqual(max(lens), 1, 'atom matched multiple types for smiles: %s' % (smi))
for a, b in zip(ans, [x[0] for x in types]):
self.assertEqual(a, b, 'bad type for SMILES: %s' % (smi))
def _validate(self,vals,tol=1e-2,show=0):
for smi,ans in vals:
mol = Chem.MolFromSmiles(smi)
types = AtomTypes.TypeAtoms(mol)
if show: print types
assert len(ans)==len(types),'bad type len for smiles: %s'%(smi)
lens = [len(x) for x in types]
assert max(lens)==1,'atom matched multiple types for smiles: %s'%(smi)
types = [x[0] for x in types]
for a,b in zip(ans,types):
assert a==b,'bad type for SMILES: %s'%(smi)
def _exampleCode():
""" Example code for calculating E-state fingerprints """
from rdkit import Chem
smis = ['CC', 'CCC', 'c1[nH]cnc1CC(N)C(O)=O', 'NCCc1ccc(O)c(O)c1']
for smi in smis:
m = Chem.MolFromSmiles(smi)
print(smi, Chem.MolToSmiles(m))
types = AtomTypes.TypeAtoms(m)
for i in range(m.GetNumAtoms()):
print('%d %4s: %s' % (i + 1, m.GetAtomWithIdx(i).GetSymbol(), str(types[i])))
es = EStateIndices(m)
counts, sums = FingerprintMol(m)
for i in range(len(AtomTypes.esPatterns)):
if counts[i]:
name, _ = AtomTypes.esPatterns[i]
print('%6s, % 2d, % 5.4f' % (name, counts[i], sums[i]))
for i in range(len(es)):
print('% 2d, % 5.4f' % (i + 1, es[i]))
print('--------')
def finger_print(chunk):
"""
Create a dictionary with the e-state fingerprint for the molecule in mol (rdkit mol)
Input:
mol; rdkit mol object
name; structure name
e_opt; energy gap (target)
"""
if AtomTypes.esPatterns is None:
AtomTypes.BuildPatts()
name_list = [name for name, _ in AtomTypes.esPatterns]
df = pd.DataFrame(columns=['name', 'smiles'] + name_list)
for row_index, row in chunk.iterrows():
name = (row["name"])
smiles = (row["smiles"])
mol = Chem.MolFromSmiles(smiles)
try:
types = AtomTypes.TypeAtoms(mol)
es = EStateIndices(mol)
counts, sums = Fingerprinter.FingerprintMol(mol)
if AtomTypes.esPatterns is None:
AtomTypes.BuildPatts()
name_list = [name for name, _ in AtomTypes.esPatterns]
data = {'name': name, 'smiles': smiles}
data2 = {k: v for k, v in zip(name_list, sums)}
data.update(data2)
df = df.append(data, ignore_index=True)
except AttributeError:
print(i, formula)
continue
return df
def finger_print(mol, name, e_opt):
"""
Create a dictionary with the e-state fingerprint for the molecule in mol (rdkit mol)
Input:
mol; rdkit mol object
name; structure name
e_opt; energy gap (target)
"""
types = AtomTypes.TypeAtoms(mol)
es = EStateIndices(mol)
counts, sums = Fingerprinter.FingerprintMol(mol)
if AtomTypes.esPatterns is None:
AtomTypes.BuildPatts()
name_list = [name for name, _ in AtomTypes.esPatterns]
data = {'name': name, 'E_opt': e_opt}
data2 = {k: v for k, v in zip(name_list, sums)}
data.update(data2)
return data
nPatts = len(AtomTypes.esPatterns)
counts = numpy.zeros(nPatts,numpy.int)
sums = numpy.zeros(nPatts,numpy.float)
for i,(name,pattern) in enumerate(AtomTypes.esPatterns):
matches = mol.GetSubstructMatches(pattern,uniquify=1)
counts[i] = len(matches)
for match in matches:
sums[i] += esIndices[match[0]]
return counts,sums
if __name__ == '__main__':
from rdkit import Chem
smis = ['CC','CCC','c1[nH]cnc1CC(N)C(O)=O','NCCc1ccc(O)c(O)c1']
for smi in smis:
m = Chem.MolFromSmiles(smi)
print smi,Chem.MolToSmiles(m)
types = AtomTypes.TypeAtoms(m)
for i in range(m.GetNumAtoms()):
print '%d %4s: %s'%(i+1,m.GetAtomWithIdx(i).GetSymbol(),str(types[i]))
es = EStateIndices(m)
counts,sums = FingerprintMol(m)
for i in range(len(AtomTypes.esPatterns)):
if counts[i]:
name,patt = AtomTypes.esPatterns[i]
print '%6s, % 2d, % 5.4f'%(name,counts[i],sums[i])
for i in range(len(es)):
print '% 2d, % 5.4f'%(i+1,es[i])
print '--------'