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 extract(x, from_smiles):
if from_smiles:
mol = Chem.MolFromSmiles(x)
else:
mol = x
if (mol is None) or (len(mol.GetAtoms()) == 0):
if include_3D:
return [0] * 29
else:
return [0] * 24
else:
logP = Crippen.MolLogP(mol)
refractivity = Crippen.MolMR(mol)
weight = Descriptors.MolWt(mol)
exact_weight = Descriptors.ExactMolWt(mol)
heavy_weight = Descriptors.HeavyAtomMolWt(mol)
heavy_count = Lipinski.HeavyAtomCount(mol)
nhoh_count = Lipinski.NHOHCount(mol)
no_count = Lipinski.NOCount(mol)
hacceptor_count = Lipinski.NumHAcceptors(mol)
hdonor_count = Lipinski.NumHDonors(mol)
hetero_count = Lipinski.NumHeteroatoms(mol)
rotatable_bond_count = Lipinski.NumRotatableBonds(mol)
valance_electron_count = Descriptors.NumValenceElectrons(mol)
amide_bond_count = rdMolDescriptors.CalcNumAmideBonds(mol)
aliphatic_ring_count = Lipinski.NumAliphaticRings(mol)
aromatic_ring_count = Lipinski.NumAromaticRings(mol)
saturated_ring_count = Lipinski.NumSaturatedRings(mol)
aliphatic_cycle_count = Lipinski.NumAliphaticCarbocycles(mol)
aliphaticHetero_cycle_count = Lipinski.NumAliphaticHeterocycles(
mol)
aromatic_cycle_count = Lipinski.NumAromaticCarbocycles(mol)
aromaticHetero_cycle_count = Lipinski.NumAromaticHeterocycles(mol)
saturated_cycle_count = Lipinski.NumSaturatedCarbocycles(mol)
saturatedHetero_cycle_count = Lipinski.NumSaturatedHeterocycles(
mol)
tpsa = rdMolDescriptors.CalcTPSA(mol)
if include_3D:
mol_3D = Chem.AddHs(mol)
AllChem.EmbedMolecule(mol_3D)
AllChem.MMFFOptimizeMolecule(mol_3D)
eccentricity = rdMolDescriptors.CalcEccentricity(mol_3D)
asphericity = rdMolDescriptors.CalcAsphericity(mol_3D)
spherocity = rdMolDescriptors.CalcSpherocityIndex(mol_3D)
inertial = rdMolDescriptors.CalcInertialShapeFactor(mol_3D)
gyration = rdMolDescriptors.CalcRadiusOfGyration(mol_3D)
return [
logP, refractivity, weight, exact_weight, heavy_weight,
heavy_count, nhoh_count, no_count, hacceptor_count,
hdonor_count, hetero_count, rotatable_bond_count,
valance_electron_count, amide_bond_count,
aliphatic_ring_count, aromatic_ring_count,
saturated_ring_count, aliphatic_cycle_count,
aliphaticHetero_cycle_count, aromatic_cycle_count,
aromaticHetero_cycle_count, saturated_cycle_count,
saturatedHetero_cycle_count, tpsa, eccentricity,
asphericity, spherocity, inertial, gyration
]
else:
return [
logP, refractivity, weight, exact_weight, heavy_weight,
heavy_count, nhoh_count, no_count, hacceptor_count,
hdonor_count, hetero_count, rotatable_bond_count,
valance_electron_count, amide_bond_count,
aliphatic_ring_count, aromatic_ring_count,
saturated_ring_count, aliphatic_cycle_count,
aliphaticHetero_cycle_count, aromatic_cycle_count,
aromaticHetero_cycle_count, saturated_cycle_count,
saturatedHetero_cycle_count, tpsa
]
https://doi.org/10.1002/9783527618279.ch37
Definition:
pm2 / (pm1*pm3)
**Arguments**
- inMol: a molecule
- confId: (optional) the conformation ID to use
- useAtomicMasses: (optional) toggles use of atomic masses in the
calculation. Defaults to True
"""
Eccentricity = lambda *x, **y: rdMolDescriptors.CalcEccentricity(*x, **y)
Eccentricity.version = rdMolDescriptors._CalcEccentricity_version
Eccentricity.__doc__ = """ molecular eccentricity
from Todeschini and Consoni "Descriptors from Molecular Geometry"
Handbook of Chemoinformatics
https://doi.org/10.1002/9783527618279.ch37
Definition:
sqrt(pm3**2 -pm1**2) / pm3**2
**Arguments**
- inMol: a molecule
- confId: (optional) the conformation ID to use
'CF', 'CCF', 'CCCF', 'CCCCF', 'CCCCCF', 'CCCCCCF', 'CS', 'CCS', 'CCCS',
'CCCCS', 'CCCCCS', 'CCCCCCS', 'CN', 'CCN', 'CCCN', 'CCCCN', 'CCCCCN',
'CCCCCCN'
]
for smi in A:
m = Chem.MolFromSmiles(smi)
m = localopt(m, 100)
#r=get3D(m,True)
print smi
print "---------"
r = rdMD.CalcWHIM(m)
print "Ei:" + str(r[0]) + "," + str(r[1]) + "," + str(r[2]) + "\n"
print "Gi:" + str(r[5]) + "," + str(r[6]) + "," + str(r[7]) + "\n"
print "SI:" + str(rdMD.CalcSpherocityIndex(m))
print "AS:" + str(rdMD.CalcAsphericity(m))
print "EX:" + str(rdMD.CalcEccentricity(m))
for item in r:
thefile.write("%.3f," % item)
thefile.write("\n")
#m.SetProp("smi", smi)
#writer.write(m)
thefile = open('testBPA.txt', 'w')
writer = Chem.SDWriter('3DBPAmol.sdf')
B = [
'CN(C)CC(Br)c1ccccc1', 'CN(C)CC(Br)c1ccc(F)cc1', 'CN(C)CC(Br)c1ccc(Cl)cc1',
'CN(C)CC(Br)c1ccc(Cl)cc1', 'CN(C)CC(Br)c1ccc(I)cc1',
'CN(C)CC(Br)c1ccc(C)cc1', 'CN(C)CC(Br)c1cccc(F)c1',
'CN(C)CC(Br)c1cccc(Cl)c1', 'CN(C)CC(Br)c1cccc(Br)c1',
'CN(C)CC(Br)c1cccc(I)c1', 'CN(C)CC(Br)c1cccc(C)c1',
'CN(C)CC(Br)c1ccc(F)c(Cl)c1', 'CN(C)CC(Br)c1ccc(F)c(Br)c1',