# this little trick saves duplicated code
def _NumMatches(mol, smarts):
return len(mol.GetSubstructMatches(smarts, uniquify=1))
NumHDonors = lambda x: rdMolDescriptors.CalcNumHBD(x)
NumHDonors.__doc__ = "Number of Hydrogen Bond Donors"
NumHDonors.version = "1.0.0"
_HDonors = lambda x, y=HDonorSmarts: x.GetSubstructMatches(y, uniquify=1)
NumHAcceptors = lambda x: rdMolDescriptors.CalcNumHBA(x)
NumHAcceptors.__doc__ = "Number of Hydrogen Bond Acceptors"
NumHAcceptors.version = "2.0.0"
_HAcceptors = lambda x, y=HAcceptorSmarts: x.GetSubstructMatches(y, uniquify=1)
NumHeteroatoms = lambda x: rdMolDescriptors.CalcNumHeteroatoms(x)
NumHeteroatoms.__doc__ = "Number of Heteroatoms"
NumHeteroatoms.version = "1.0.0"
_Heteroatoms = lambda x, y=HeteroatomSmarts: x.GetSubstructMatches(y,
uniquify=1)
NumRotatableBonds = lambda x: rdMolDescriptors.CalcNumRotatableBonds(x)
NumRotatableBonds.__doc__ = "Number of Rotatable Bonds"
NumRotatableBonds.version = "1.0.0"
_RotatableBonds = lambda x, y=RotatableBondSmarts: x.GetSubstructMatches(
y, uniquify=1)
NOCount = lambda x: rdMolDescriptors.CalcNumLipinskiHBA(x)
NOCount.__doc__ = "Number of Nitrogens and Oxygens"
NOCount.version = "1.0.0"
NHOHCount = lambda x: rdMolDescriptors.CalcNumLipinskiHBD(x)
NHOHCount.__doc__ = "Number of NHs or OHs"
NHOHCount.version = "2.0.0"
def get_global_features(self, mol):
u = []
# Now get some specific features
fdefName = os.path.join(RDConfig.RDDataDir, 'BaseFeatures.fdef')
factory = ChemicalFeatures.BuildFeatureFactory(fdefName)
feats = factory.GetFeaturesForMol(mol)
# First get some basic features
natoms = mol.GetNumAtoms()
nbonds = mol.GetNumBonds()
mw = Descriptors.ExactMolWt(mol)
HeavyAtomMolWt = Descriptors.HeavyAtomMolWt(mol)
NumValenceElectrons = Descriptors.NumValenceElectrons(mol)
''' # These four descriptors are producing the value of infinity for refcode_csd = YOLJUF (CCOP(=O)(Cc1ccc(cc1)NC(=S)NP(OC(C)C)(OC(C)C)[S])OCC\t\n)
MaxAbsPartialCharge = Descriptors.MaxAbsPartialCharge(mol)
MaxPartialCharge = Descriptors.MaxPartialCharge(mol)
MinAbsPartialCharge = Descriptors.MinAbsPartialCharge(mol)
MinPartialCharge = Descriptors.MinPartialCharge(mol)
'''
# FpDensityMorgan1 = Descriptors.FpDensityMorgan1(mol)
# FpDensityMorgan2 = Descriptors.FpDensityMorgan2(mol)
# FpDensityMorgan3 = Descriptors.FpDensityMorgan3(mol)
# Get some features using chemical feature factory
nbrAcceptor = 0
nbrDonor = 0
nbrHydrophobe = 0
nbrLumpedHydrophobe = 0
nbrPosIonizable = 0
nbrNegIonizable = 0
for j in range(len(feats)):
#print(feats[j].GetFamily(), feats[j].GetType())
if ('Acceptor' == (feats[j].GetFamily())):
nbrAcceptor = nbrAcceptor + 1
elif ('Donor' == (feats[j].GetFamily())):
nbrDonor = nbrDonor + 1
elif ('Hydrophobe' == (feats[j].GetFamily())):
nbrHydrophobe = nbrHydrophobe + 1
elif ('LumpedHydrophobe' == (feats[j].GetFamily())):
nbrLumpedHydrophobe = nbrLumpedHydrophobe + 1
elif ('PosIonizable' == (feats[j].GetFamily())):
nbrPosIonizable = nbrPosIonizable + 1
elif ('NegIonizable' == (feats[j].GetFamily())):
nbrNegIonizable = nbrNegIonizable + 1
else:
pass
#print(feats[j].GetFamily())
# Now get some features using rdMolDescriptors
moreGlobalFeatures = [rdm.CalcNumRotatableBonds(mol), rdm.CalcChi0n(mol), rdm.CalcChi0v(mol), \
rdm.CalcChi1n(mol), rdm.CalcChi1v(mol), rdm.CalcChi2n(mol), rdm.CalcChi2v(mol), \
rdm.CalcChi3n(mol), rdm.CalcChi4n(mol), rdm.CalcChi4v(mol), \
rdm.CalcFractionCSP3(mol), rdm.CalcHallKierAlpha(mol), rdm.CalcKappa1(mol), \
rdm.CalcKappa2(mol), rdm.CalcLabuteASA(mol), \
rdm.CalcNumAliphaticCarbocycles(mol), rdm.CalcNumAliphaticHeterocycles(mol), \
rdm.CalcNumAliphaticRings(mol), rdm.CalcNumAmideBonds(mol), \
rdm.CalcNumAromaticCarbocycles(mol), rdm.CalcNumAromaticHeterocycles(mol), \
rdm.CalcNumAromaticRings(mol), rdm.CalcNumBridgeheadAtoms(mol), rdm.CalcNumHBA(mol), \
rdm.CalcNumHBD(mol), rdm.CalcNumHeteroatoms(mol), rdm.CalcNumHeterocycles(mol), \
rdm.CalcNumLipinskiHBA(mol), rdm.CalcNumLipinskiHBD(mol), rdm.CalcNumRings(mol), \
rdm.CalcNumSaturatedCarbocycles(mol), rdm.CalcNumSaturatedHeterocycles(mol), \
rdm.CalcNumSaturatedRings(mol), rdm.CalcNumSpiroAtoms(mol), rdm.CalcTPSA(mol)]
u = [natoms, nbonds, mw, HeavyAtomMolWt, NumValenceElectrons, \
nbrAcceptor, nbrDonor, nbrHydrophobe, nbrLumpedHydrophobe, \
nbrPosIonizable, nbrNegIonizable]
u = u + moreGlobalFeatures
u = np.array(u).T
# Some of the descriptors produice NAN. We can convert them to 0
# If you are getting outliers in the training or validation set this could be
# Because some important features were set to zero here because it produced NAN
# Removing those features from the feature set might remove the outliers
#u[np.isnan(u)] = 0
#u = torch.tensor(u, dtype=torch.float)
return (u)
def get_molecular_features(dataframe, mol_list):
df = dataframe
for i in range(len(mol_list)):
print("Getting molecular features for molecule: ", i)
mol = mol_list[i]
natoms = mol.GetNumAtoms()
nbonds = mol.GetNumBonds()
mw = Descriptors.ExactMolWt(mol)
df.at[i,"NbrAtoms"] = natoms
df.at[i,"NbrBonds"] = nbonds
df.at[i,"mw"] = mw
df.at[i,'HeavyAtomMolWt'] = Chem.Descriptors.HeavyAtomMolWt(mol)
df.at[i,'NumValenceElectrons'] = Chem.Descriptors.NumValenceElectrons(mol)
''' # These four descriptors are producing the value of infinity for refcode_csd = YOLJUF (CCOP(=O)(Cc1ccc(cc1)NC(=S)NP(OC(C)C)(OC(C)C)[S])OCC\t\n)
df.at[i,'MaxAbsPartialCharge'] = Chem.Descriptors.MaxAbsPartialCharge(mol)
df.at[i,'MaxPartialCharge'] = Chem.Descriptors.MaxPartialCharge(mol)
df.at[i,'MinAbsPartialCharge'] = Chem.Descriptors.MinAbsPartialCharge(mol)
df.at[i,'MinPartialCharge'] = Chem.Descriptors.MinPartialCharge(mol)
'''
df.at[i,'FpDensityMorgan1'] = Chem.Descriptors.FpDensityMorgan1(mol)
df.at[i,'FpDensityMorgan2'] = Chem.Descriptors.FpDensityMorgan2(mol)
df.at[i,'FpDensityMorgan3'] = Chem.Descriptors.FpDensityMorgan3(mol)
#print(natoms, nbonds)
# Now get some specific features
fdefName = os.path.join(RDConfig.RDDataDir,'BaseFeatures.fdef')
factory = ChemicalFeatures.BuildFeatureFactory(fdefName)
feats = factory.GetFeaturesForMol(mol)
#df["Acceptor"] = 0
#df["Aromatic"] = 0
#df["Hydrophobe"] = 0
nbrAcceptor = 0
nbrDonor = 0
nbrHydrophobe = 0
nbrLumpedHydrophobe = 0
nbrPosIonizable = 0
nbrNegIonizable = 0
for j in range(len(feats)):
#print(feats[j].GetFamily(), feats[j].GetType())
if ('Acceptor' == (feats[j].GetFamily())):
nbrAcceptor = nbrAcceptor + 1
elif ('Donor' == (feats[j].GetFamily())):
nbrDonor = nbrDonor + 1
elif ('Hydrophobe' == (feats[j].GetFamily())):
nbrHydrophobe = nbrHydrophobe + 1
elif ('LumpedHydrophobe' == (feats[j].GetFamily())):
nbrLumpedHydrophobe = nbrLumpedHydrophobe + 1
elif ('PosIonizable' == (feats[j].GetFamily())):
nbrPosIonizable = nbrPosIonizable + 1
elif ('NegIonizable' == (feats[j].GetFamily())):
nbrNegIonizable = nbrNegIonizable + 1
else:
pass#print(feats[j].GetFamily())
df.at[i,"Acceptor"] = nbrAcceptor
df.at[i,"Donor"] = nbrDonor
df.at[i,"Hydrophobe"] = nbrHydrophobe
df.at[i,"LumpedHydrophobe"] = nbrLumpedHydrophobe
df.at[i,"PosIonizable"] = nbrPosIonizable
df.at[i,"NegIonizable"] = nbrNegIonizable
# We can also get some more molecular features using rdMolDescriptors
df.at[i,"NumRotatableBonds"] = rdMolDescriptors.CalcNumRotatableBonds(mol)
df.at[i,"CalcChi0n"] = rdMolDescriptors.CalcChi0n(mol)
df.at[i,"CalcChi0v"] = rdMolDescriptors.CalcChi0v(mol)
df.at[i,"CalcChi1n"] = rdMolDescriptors.CalcChi1n(mol)
df.at[i,"CalcChi1v"] = rdMolDescriptors.CalcChi1v(mol)
df.at[i,"CalcChi2n"] = rdMolDescriptors.CalcChi2n(mol)
df.at[i,"CalcChi2v"] = rdMolDescriptors.CalcChi2v(mol)
df.at[i,"CalcChi3n"] = rdMolDescriptors.CalcChi3n(mol)
df.at[i,"CalcChi3v"] = rdMolDescriptors.CalcChi3v(mol)
df.at[i,"CalcChi4n"] = rdMolDescriptors.CalcChi4n(mol)
df.at[i,"CalcChi4v"] = rdMolDescriptors.CalcChi4v(mol)
df.at[i,"CalcFractionCSP3"] = rdMolDescriptors.CalcFractionCSP3(mol)
df.at[i,"CalcHallKierAlpha"] = rdMolDescriptors.CalcHallKierAlpha(mol)
df.at[i,"CalcKappa1"] = rdMolDescriptors.CalcKappa1(mol)
df.at[i,"CalcKappa2"] = rdMolDescriptors.CalcKappa2(mol)
#df.at[i,"CalcKappa3"] = rdMolDescriptors.CalcKappa3(mol)
df.at[i,"CalcLabuteASA"] = rdMolDescriptors.CalcLabuteASA(mol)
df.at[i,"CalcNumAliphaticCarbocycles"] = rdMolDescriptors.CalcNumAliphaticCarbocycles(mol)
df.at[i,"CalcNumAliphaticHeterocycles"] = rdMolDescriptors.CalcNumAliphaticHeterocycles(mol)
df.at[i,"CalcNumAliphaticRings"] = rdMolDescriptors.CalcNumAliphaticRings(mol)
df.at[i,"CalcNumAmideBonds"] = rdMolDescriptors.CalcNumAmideBonds(mol)
df.at[i,"CalcNumAromaticCarbocycles"] = rdMolDescriptors.CalcNumAromaticCarbocycles(mol)
df.at[i,"CalcNumAromaticHeterocycles"] = rdMolDescriptors.CalcNumAromaticHeterocycles(mol)
df.at[i,"CalcNumAromaticRings"] = rdMolDescriptors.CalcNumAromaticRings(mol)
df.at[i,"CalcNumBridgeheadAtoms"] = rdMolDescriptors.CalcNumBridgeheadAtoms(mol)
df.at[i,"CalcNumHBA"] = rdMolDescriptors.CalcNumHBA(mol)
df.at[i,"CalcNumHBD"] = rdMolDescriptors.CalcNumHBD(mol)
df.at[i,"CalcNumHeteroatoms"] = rdMolDescriptors.CalcNumHeteroatoms(mol)
df.at[i,"CalcNumHeterocycles"] = rdMolDescriptors.CalcNumHeterocycles(mol)
df.at[i,"CalcNumLipinskiHBA"] = rdMolDescriptors.CalcNumLipinskiHBA(mol)
df.at[i,"CalcNumLipinskiHBD"] = rdMolDescriptors.CalcNumLipinskiHBD(mol)
df.at[i,"CalcNumRings"] = rdMolDescriptors.CalcNumRings(mol)
df.at[i,"CalcNumSaturatedCarbocycles"] = rdMolDescriptors.CalcNumSaturatedCarbocycles(mol)
df.at[i,"CalcNumSaturatedHeterocycles"] = rdMolDescriptors.CalcNumSaturatedHeterocycles(mol)
df.at[i,"CalcNumSaturatedRings"] = rdMolDescriptors.CalcNumSaturatedRings(mol)
df.at[i,"CalcNumSpiroAtoms"] = rdMolDescriptors.CalcNumSpiroAtoms(mol)
df.at[i,"CalcTPSA"] = rdMolDescriptors.CalcTPSA(mol)
return(df)