def get_descriptors(mols=None):
table = pd.DataFrame()
i = 0
print('Computing descriptors for {} molecules'.format(len(mols)))
for mol in mols:
if mol:
table.loc[i, 'Smiles'] = Chem.MolToSmiles(mol, True)
table.loc[i, 'MolWt'] = Descriptors.MolWt(mol)
table.loc[i, 'LogP'] = Descriptors.MolLogP(mol)
table.loc[i, 'NumHAcceptors'] = Descriptors.NumHAcceptors(mol)
table.loc[i, 'NumHDonors'] = Descriptors.NumHDonors(mol)
table.loc[i, 'NumHeteroatoms'] = Descriptors.NumHeteroatoms(mol)
table.loc[i,
'NumRotableBonds'] = Descriptors.NumRotatableBonds(mol)
try:
AllChem.EmbedMolecule(mol, useRandomCoords=True)
AllChem.MMFFOptimizeMolecule(mol, mmffVariant='MMFF94s')
table.loc[i, 'TPSA'] = Descriptors.TPSA(mol)
table.loc[i, 'PMI1'] = Descriptors3D.PMI1(mol)
table.loc[i, 'PMI2'] = Descriptors3D.PMI2(mol)
table.loc[i, 'PMI3'] = Descriptors3D.PMI3(mol)
table.loc[i, 'PBF'] = rdMolDescriptors.CalcPBF(mol)
table.loc[i, 'NPR1'] = rdMolDescriptors.CalcNPR1(mol)
table.loc[i, 'NPR2'] = rdMolDescriptors.CalcNPR2(mol)
table.loc[i, 'ISF'] = Descriptors3D.InertialShapeFactor(mol)
i = i + 1
except Exception:
i = i + 1
continue
table.to_csv('Descriptors.csv')
print('Computed descriptors in file Descriptors.csv')
return (plot_NPR(table=table))
def testGithub2037(self):
m = Chem.AddHs(Chem.MolFromSmiles("CCCCCCC"))
cids = AllChem.EmbedMultipleConfs(m, 10)
# start with defaults (which does not cache results):
npr1s = []
npr2s = []
for cid in cids:
npr1s.append(rdMD.CalcNPR1(m, confId=cid))
npr2s.append(rdMD.CalcNPR2(m, confId=cid))
for i in range(1, len(npr1s)):
self.assertNotAlmostEqual(npr1s[0], npr1s[i])
self.assertNotAlmostEqual(npr2s[0], npr2s[i])
# now ensure that we can cache:
npr1s = []
npr2s = []
for cid in cids:
npr1s.append(rdMD.CalcNPR1(m, confId=cid, force=False))
npr2s.append(rdMD.CalcNPR2(m, confId=cid, force=False))
for i in range(1, len(npr1s)):
self.assertAlmostEqual(npr1s[0], npr1s[i])
self.assertAlmostEqual(npr2s[0], npr2s[i])
def calculate_scalar_descriptors(molecule, symbols):
features = list()
features.append(rdMD.CalcAsphericity(molecule))
features += list(rdMD.CalcCrippenDescriptors(molecule))
features.append(rdMD.CalcExactMolWt(molecule))
features.append(rdMD.CalcEccentricity(molecule))
features.append(rdMD.CalcFractionCSP3(molecule))
features.append(rdMD.CalcLabuteASA(molecule))
features.append(rdMD.CalcNPR1(molecule))
features.append(rdMD.CalcNPR2(molecule))
features.append(rdMD.CalcHallKierAlpha(molecule))
# elemental distribution
symbols = np.array(symbols)
features.append(np.sum(symbols == 'H'))
features.append(np.sum(symbols == 'C'))
features.append(np.sum(symbols == 'N'))
features.append(np.sum(symbols == 'O'))
features.append(np.sum(symbols == 'F'))
# ring features
features.append(rdMD.CalcNumAliphaticCarbocycles(molecule))
features.append(rdMD.CalcNumAliphaticHeterocycles(molecule))
features.append(rdMD.CalcNumAromaticCarbocycles(molecule))
features.append(rdMD.CalcNumAromaticHeterocycles(molecule))
features.append(rdMD.CalcNumSaturatedCarbocycles(molecule))
features.append(rdMD.CalcNumSaturatedHeterocycles(molecule))
features.append(rdMD.CalcNumSpiroAtoms(
molecule)) # atom shared between rings with one bond
features.append(rdMD.CalcNumBridgeheadAtoms(
molecule)) # atom shared between rings with at least two bonds
# other counts
features.append(rdMD.CalcNumAmideBonds(molecule))
features.append(rdMD.CalcNumHBA(molecule)) # number of hydrogen acceptors
features.append(rdMD.CalcNumHBD(molecule)) # number of hydrogen donors
return np.array(features)
def main(args):
print(rdBase.rdkitVersion)
input_filename = os.path.basename(args[1]).split('.')[0]
result_file = "output_" + input_filename
print(result_file)
try:
with open(result_file, 'a') as output:
header = ['smiles', 'cid', 'npr1', 'npr2']
output.write((' '.join(header)) + '\n')
with open(args[1]) as f:
for line in f:
try:
smiles, cid = line.strip().split(None, 1)
mol = C.MolFromSmiles(smiles)
mol = C.AddHs(mol)
AllChem.EmbedMolecule(mol,
useExpTorsionAnglePrefs=True,
useBasicKnowledge=True)
except Exception as e:
continue
try:
npr1 = round(CD.CalcNPR1(mol), 4)
npr2 = round(CD.CalcNPR2(mol), 4)
except Exception as e:
print("Failed molecules:" + cid)
record_error(input_filename, smiles, cid)
continue
a = [smiles, cid, npr1, npr2]
a = map(str, a)
#print (' '.join(a))
output.write((' '.join(a)) + '\n')
#print (' '.join(a))
f.close()
output.close()
except IOError as err:
print(err)
PMI3 = lambda *x, **y: rdMolDescriptors.CalcPMI3(*x, **y)
PMI3.version = rdMolDescriptors._CalcPMI3_version
PMI3.__doc__ = """ Third (largest) principal moment of inertia
**Arguments**
- inMol: a molecule
- confId: (optional) the conformation ID to use
- useAtomicMasses: (optional) toggles use of atomic masses in the
calculation. Defaults to True
"""
NPR1 = lambda *x, **y: rdMolDescriptors.CalcNPR1(*x, **y)
NPR1.version = rdMolDescriptors._CalcNPR1_version
NPR1.__doc__ = """ Normalized principal moments ratio 1 (=I1/I3)
from Sauer and Schwarz JCIM 43:987-1003 (2003)
https://doi.org/10.1021/ci025599w
**Arguments**
- inMol: a molecule
- confId: (optional) the conformation ID to use
- useAtomicMasses: (optional) toggles use of atomic masses in the
calculation. Defaults to True
