def calc(smi, name):
m = Chem.MolFromSmiles(smi)
if m is not None:
try:
hba = rdMolDescriptors.CalcNumHBA(m)
hbd = rdMolDescriptors.CalcNumHBD(m)
nrings = rdMolDescriptors.CalcNumRings(m)
rtb = rdMolDescriptors.CalcNumRotatableBonds(m)
psa = rdMolDescriptors.CalcTPSA(m)
logp, mr = rdMolDescriptors.CalcCrippenDescriptors(m)
mw = rdMolDescriptors._CalcMolWt(m)
csp3 = rdMolDescriptors.CalcFractionCSP3(m)
hac = m.GetNumHeavyAtoms()
if hac == 0:
fmf = 0
else:
fmf = GetScaffoldForMol(m).GetNumHeavyAtoms() / hac
qed = QED.qed(m)
nrings_fused = fused_ring_count(m)
n_unique_hba_hbd_atoms = count_hbd_hba_atoms(m)
max_ring_size = len(max(m.GetRingInfo().AtomRings(), key=len, default=()))
n_chiral_centers = len(FindMolChiralCenters(m, includeUnassigned=True))
fcsp3_bm = rdMolDescriptors.CalcFractionCSP3(GetScaffoldForMol(m))
return name, hba, hbd, hba + hbd, nrings, rtb, round(psa, 2), round(logp, 2), round(mr, 2), round(mw, 2), \
round(csp3, 3), round(fmf, 3), round(qed, 3), hac, nrings_fused, n_unique_hba_hbd_atoms, \
max_ring_size, n_chiral_centers, round(fcsp3_bm, 3)
except:
sys.stderr.write(f'molecule {name} was omitted due to an error in calculation of some descriptors\n')
return None
else:
sys.stderr.write('smiles %s cannot be parsed (%s)' % (smi, name))
return None
def calc(smi, name):
m = Chem.MolFromSmiles(smi)
if m is not None:
try:
hba = rdMolDescriptors.CalcNumHBA(m)
hbd = rdMolDescriptors.CalcNumHBD(m)
nrings = rdMolDescriptors.CalcNumRings(m)
rtb = rdMolDescriptors.CalcNumRotatableBonds(m)
psa = rdMolDescriptors.CalcTPSA(m)
logp, mr = rdMolDescriptors.CalcCrippenDescriptors(m)
mw = rdMolDescriptors._CalcMolWt(m)
csp3 = rdMolDescriptors.CalcFractionCSP3(m)
hac = m.GetNumHeavyAtoms()
if hac == 0:
fmf = 0
else:
fmf = GetScaffoldForMol(m).GetNumHeavyAtoms() / hac
qed = QED.qed(m)
nrings_fused = fused_ring_count(m)
return name, hba, hbd, hba + hbd, nrings, rtb, round(psa, 2), round(logp, 2), round(mr, 2), round(mw, 2), \
round(csp3, 3), round(fmf, 3), round(qed, 3), hac, nrings_fused
except:
sys.stderr.write(
f'molecule {name} was omitted due to an error in calculation of some descriptors\n'
)
return None
else:
sys.stderr.write('smiles %s cannot be parsed (%s)' % (smi, name))
return None
def _calculateDescriptors(mol):
df = pd.DataFrame(index=[0])
df["SlogP"] = rdMolDescriptors.CalcCrippenDescriptors(mol)[0]
df["SMR"] = rdMolDescriptors.CalcCrippenDescriptors(mol)[1]
df["LabuteASA"] = rdMolDescriptors.CalcLabuteASA(mol)
df["TPSA"] = Descriptors.TPSA(mol)
df["AMW"] = Descriptors.MolWt(mol)
df["ExactMW"] = rdMolDescriptors.CalcExactMolWt(mol)
df["NumLipinskiHBA"] = rdMolDescriptors.CalcNumLipinskiHBA(mol)
df["NumLipinskiHBD"] = rdMolDescriptors.CalcNumLipinskiHBD(mol)
df["NumRotatableBonds"] = rdMolDescriptors.CalcNumRotatableBonds(mol)
df["NumHBD"] = rdMolDescriptors.CalcNumHBD(mol)
df["NumHBA"] = rdMolDescriptors.CalcNumHBA(mol)
df["NumAmideBonds"] = rdMolDescriptors.CalcNumAmideBonds(mol)
df["NumHeteroAtoms"] = rdMolDescriptors.CalcNumHeteroatoms(mol)
df["NumHeavyAtoms"] = Chem.rdchem.Mol.GetNumHeavyAtoms(mol)
df["NumAtoms"] = Chem.rdchem.Mol.GetNumAtoms(mol)
df["NumRings"] = rdMolDescriptors.CalcNumRings(mol)
df["NumAromaticRings"] = rdMolDescriptors.CalcNumAromaticRings(mol)
df["NumSaturatedRings"] = rdMolDescriptors.CalcNumSaturatedRings(mol)
df["NumAliphaticRings"] = rdMolDescriptors.CalcNumAliphaticRings(mol)
df["NumAromaticHeterocycles"] = \
rdMolDescriptors.CalcNumAromaticHeterocycles(mol)
df["NumSaturatedHeterocycles"] = \
rdMolDescriptors.CalcNumSaturatedHeterocycles(mol)
df["NumAliphaticHeterocycles"] = \
rdMolDescriptors.CalcNumAliphaticHeterocycles(mol)
df["NumAromaticCarbocycles"] = \
rdMolDescriptors.CalcNumAromaticCarbocycles(mol)
df["NumSaturatedCarbocycles"] = \
rdMolDescriptors.CalcNumSaturatedCarbocycles(mol)
df["NumAliphaticCarbocycles"] = \
rdMolDescriptors.CalcNumAliphaticCarbocycles(mol)
df["FractionCSP3"] = rdMolDescriptors.CalcFractionCSP3(mol)
df["Chi0v"] = rdMolDescriptors.CalcChi0v(mol)
df["Chi1v"] = rdMolDescriptors.CalcChi1v(mol)
df["Chi2v"] = rdMolDescriptors.CalcChi2v(mol)
df["Chi3v"] = rdMolDescriptors.CalcChi3v(mol)
df["Chi4v"] = rdMolDescriptors.CalcChi4v(mol)
df["Chi1n"] = rdMolDescriptors.CalcChi1n(mol)
df["Chi2n"] = rdMolDescriptors.CalcChi2n(mol)
df["Chi3n"] = rdMolDescriptors.CalcChi3n(mol)
df["Chi4n"] = rdMolDescriptors.CalcChi4n(mol)
df["HallKierAlpha"] = rdMolDescriptors.CalcHallKierAlpha(mol)
df["kappa1"] = rdMolDescriptors.CalcKappa1(mol)
df["kappa2"] = rdMolDescriptors.CalcKappa2(mol)
df["kappa3"] = rdMolDescriptors.CalcKappa3(mol)
slogp_VSA = list(map(lambda i: "slogp_VSA" + str(i), list(range(1, 13))))
df = df.assign(**dict(zip(slogp_VSA, rdMolDescriptors.SlogP_VSA_(mol))))
smr_VSA = list(map(lambda i: "smr_VSA" + str(i), list(range(1, 11))))
df = df.assign(**dict(zip(smr_VSA, rdMolDescriptors.SMR_VSA_(mol))))
peoe_VSA = list(map(lambda i: "peoe_VSA" + str(i), list(range(1, 15))))
df = df.assign(**dict(zip(peoe_VSA, rdMolDescriptors.PEOE_VSA_(mol))))
MQNs = list(map(lambda i: "MQN" + str(i), list(range(1, 43))))
df = df.assign(**dict(zip(MQNs, rdMolDescriptors.MQNs_(mol))))
return df
def calculate_properties(self, mol):
"""this method calculates basic properties for the smiles
returns : list of int or float (properties)"""
properties = []
properties.append(mol.GetNumAtoms())
properties.append(desc.CalcCrippenDescriptors(mol)[0])
properties.append(desc.CalcTPSA(mol))
properties.append(desc.CalcNumRotatableBonds(mol))
properties.append(desc.CalcFractionCSP3(mol))
return properties
def calc(smi, name):
m = Chem.MolFromSmiles(smi)
if m is not None:
hba = rdMolDescriptors.CalcNumHBA(m)
hbd = rdMolDescriptors.CalcNumHBD(m)
nrings = rdMolDescriptors.CalcNumRings(m)
rtb = rdMolDescriptors.CalcNumRotatableBonds(m)
psa = rdMolDescriptors.CalcTPSA(m)
logp, mr = rdMolDescriptors.CalcCrippenDescriptors(m)
mw = rdMolDescriptors._CalcMolWt(m)
csp3 = rdMolDescriptors.CalcFractionCSP3(m)
fmf = GetScaffoldForMol(m).GetNumAtoms(onlyHeavy=True) / m.GetNumAtoms(onlyHeavy=True)
return name, hba, hbd, hba + hbd, nrings, rtb, round(psa, 2), round(logp, 2), round(mr, 2), round(mw, 2), \
round(csp3, 3), round(fmf, 3)
else:
sys.stderr.write('smiles %s cannot be parsed (%s)' % (smi, name))
return None
def calculate_properties(self, smiles=None, mol=None, props=[]):
"""this method calculates basic properties for the mol
returns : error (bool)"""
if len(props) == 0:
return True
if mol is None:
mol = Chem.MolFromSmiles(smiles)
if mol is None:
return True
if 'py_formula' in props:
self.data['py_formula'] = desc.CalcMolFormula(mol)
if 'py_em' in props:
self.data['py_em'] = round(desc.CalcExactMolWt(mol), 5)
if 'py_n_Cl_Br' in props:
all_atoms = []
for atom in mol.GetAtoms():
all_atoms.append(atom.GetSymbol())
n_Cl = all_atoms.count('Cl')
n_Br = all_atoms.count('Br')
self.data['py_n_Cl_Br'] = n_Cl + n_Br
if 'py_na' in props:
self.data['py_na'] = mol.GetNumAtoms()
if 'py_mw' in props:
self.data['py_mw'] = desc._CalcMolWt(mol)
if 'py_fsp3' in props:
self.data['py_fsp3'] = desc.CalcFractionCSP3(mol)
if 'py_rb' in props:
self.data['py_rb'] = desc.CalcNumRotatableBonds(mol)
if 'py_tpsa' in props:
self.data['py_tpsa'] = desc.CalcTPSA(mol)
if 'py_clogp' in props:
self.data['py_clogp'] = desc.CalcCrippenDescriptors(mol)[0]
if 'py_nar' in props:
self.data['py_nar'] = desc.CalcNumAromaticRings(mol)
if 'py_nhba' in props:
self.data['py_nhba'] = desc.CalcNumHBA(mol)
if 'py_nhbd' in props:
self.data['py_nhbd'] = desc.CalcNumHBD(mol)
return False
def feature_fp(smiles):
mol = Chem.MolFromSmiles(smiles)
fp = rdMolDescriptors.MQNs_(mol)
fp.append(rdMolDescriptors.CalcNumRotatableBonds(mol))
fp.append(rdMolDescriptors.CalcExactMolWt(mol))
fp.append(rdMolDescriptors.CalcNumRotatableBonds(mol))
fp.append(rdMolDescriptors.CalcFractionCSP3(mol))
fp.append(rdMolDescriptors.CalcNumAliphaticCarbocycles(mol))
fp.append(rdMolDescriptors.CalcNumAliphaticHeterocycles(mol))
fp.append(rdMolDescriptors.CalcNumAliphaticRings((mol)))
fp.append(rdMolDescriptors.CalcNumAromaticCarbocycles(mol))
fp.append(rdMolDescriptors.CalcNumAromaticHeterocycles(mol))
fp.append(rdMolDescriptors.CalcNumAromaticRings(mol))
fp.append(rdMolDescriptors.CalcNumBridgeheadAtoms(mol))
fp.append(rdMolDescriptors.CalcNumRings(mol))
fp.append(rdMolDescriptors.CalcNumAmideBonds(mol))
fp.append(rdMolDescriptors.CalcNumHeterocycles(mol))
fp.append(rdMolDescriptors.CalcNumSpiroAtoms(mol))
fp.append(rdMolDescriptors.CalcTPSA(mol))
return np.array(fp)
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 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)
"num_hba": lambda x: rdMolDesc.CalcNumLipinskiHBA(x),
"slogp": lambda x: round(Crippen.MolLogP(x), 4),
"tpsa": lambda x: round(rdMolDesc.CalcTPSA(x), 4),
"num_rotatable_bond": lambda x: rdMolDesc.CalcNumRotatableBonds(x),
"num_atoms_oxygen": lambda x: len(
[a for a in x.GetAtoms() if a.GetAtomicNum() == 8]
),
"num_atoms_nitrogen": lambda x: len(
[a for a in x.GetAtoms() if a.GetAtomicNum() == 7]
),
"num_atoms_halogen": Fragments.fr_halogen,
"num_atoms_bridgehead": rdMolDesc.CalcNumBridgeheadAtoms,
# custom molecular descriptors
#"ring_size_min": get_min_ring_size,
#"ring_size_max": get_max_ring_size,
"frac_sp3": lambda x: rdMolDesc.CalcFractionCSP3(x),
# HTS filters 1/2 - present in the RDKit Fragments
#"num_aldehyde": Fragments.fr_aldehyde,
#"num_diazo":Fragments.fr_diazo,
#"num_carbonyl": Fragments.fr_C_O, # in Over paper, dicarbonyl compounds are filtered out
#"num_sulfide": Fragments.fr_sulfide, # in Over paper, disulfide compounds are filtered out
#"num_hydrazine": Fragments.fr_hdrzine,
#"num_isocyanate": Fragments.fr_isocyan,
#"num_isothiocyanate": Fragments.fr_isothiocyan,
#"num_quaternary_amine": Fragments.fr_quatN,
# HTS filters 2/2 - not present in the RDKit Fragments
#"num_ab_unsaturated_ketone": lambda x: len(x.GetSubstructMatches(FRAGMENTS['ab_unsaturated_ketone'])), # R=CC=O
#"num_acyl_halide": lambda x: len(x.GetSubstructMatches(FRAGMENTS['acyl_halide'])), # C(=O)X
#"num_anhydride": lambda x: len(x.GetSubstructMatches(FRAGMENTS['anhydride'])), # CC(=O)OC(=O)C
#"num_peroxide": lambda x: len(x.GetSubstructMatches(FRAGMENTS['peroxide'])), # R-O-O-R'
}
def get_fraction_csp3_(mol: Mol) -> float:
"""Returns fraction of SP3 Carbon atoms"""
return round(rdMolDescriptors.CalcFractionCSP3(mol), round_digs)
def genSmiles(latVecArray, emb, dic, stateMod, decMod, structFlags):
#return array of shape (nParticles, )
out = np.zeros((len(latVecArray), ))
#predict from the vector - states[0] and [1] are reset states for lstm, states[2] is classifier prediction
for vec in range(len(latVecArray)):
#get fragment prediction and states
states = stateMod.predict(latVecArray[vec:vec + 1])
#fragment prediction - add to output - weight this
out[vec] += 2 * states[2]
asciiMat = mu.decodeMatrix(decodeModel=decMod,
stateMatrix=states,
embed=emb,
fwdDict=dic)
smiles = mu.smiles_from_mat(mat=asciiMat, dictMat=dictMat)
# Replace the X -> Cl and Y -> Br dictionary encodings to give (hopefully) valid smiles
sm1 = smiles.replace("X", "Cl")
sm2 = sm1.replace("Y", "Br")
#validity check - add to score if molecule valid then check QED and add to score
if Chem.MolFromSmiles(sm2) != None:
try:
smi = Chem.CanonSmiles(sm2)
mol = Chem.MolFromSmiles(smi)
#add 3 points for a valid molecule
out[vec] += 3
#check for unwanted functionalities - remove 4 points if find any
match = [
mol.HasSubstructMatch(Chem.MolFromSmarts(s))
for s in structFlags
]
if np.any(match): out[vec] += -4
#synthetic accessibility score - this has value between 1 (best) and 10 (worst)
#we remove SAS/10 points from each molecule
out[vec] += -sascorer.calculateScore(mol) / 10
#small penalty for 7 and 8 member rings
if (mol.HasSubstructMatch(Chem.MolFromSmarts('[r7]'))
or mol.HasSubstructMatch(Chem.MolFromSmarts('[r8]'))):
out[vec] += -1
#small penalty for low or high fsp3
if (rdMolDescriptors.CalcFractionCSP3(mol) < 0.2
or rdMolDescriptors.CalcFractionCSP3(mol) > 0.8):
out[vec] += -1
#penalty for low or high heavy atom count
if mol.GetNumHeavyAtoms() < 8 or mol.GetNumHeavyAtoms() > 20:
out[vec] += -2
except:
#if any part of above throws exception, set cost to -3
out[vec] = -3
elif Chem.MolFromSmiles(sm2) == None:
out[vec] = -3
#make output negative to minimise
out = -out
return out
aro = []
aro = np.vstack(
df_all.mols.apply(lambda x: sum(
int(x.GetAtomWithIdx(i).GetIsAromatic())
for i in range(x.GetNumAtoms()))))
df_all['aro'] = aro
# adding new features
# TPSA BAAAAAD
# tpsa = np.vstack(df_all.smiles.apply(lambda x: Descriptors.TPSA(Chem.MolFromSmiles(x))))
# df_all['tpsa'] = pd.DataFrame(tpsa)
# sp3 hybridization
sp3 = np.vstack(
df_all.mols.apply(lambda x: rdMolDescriptors.CalcFractionCSP3(x)))
df_all['sp3'] = sp3
#Drop the 'smiles' column
df_all = df_all.drop(['smiles'], axis=1)
df_all = df_all.drop(['mols'], axis=1)
vals = df_all.values
X_train = vals[:test_idx]
X_test = vals[test_idx:]
print("Train features:", X_train.shape)
print("Train gap:", Y_train.shape)
print("Test features:", X_test.shape)
hd = np.vstack(mols.apply(lambda x: Descriptors.NumHDonors(x)))
df_all['hd'] = hd
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)