def get_filter_values(mol):
"""
calculate the values, for a given molecule, that are used to filter
return as a dictionary
"""
assert isinstance(mol, Chem.Mol)
values = {}
values["MW"] = desc.CalcExactMolWt(mol)
values["logP"] = crip.MolLogP(mol)
values["HBA"] = lip.NumHAcceptors(mol)
values["HBD"] = lip.NumHDonors(mol)
values["tPSA"] = desc.CalcTPSA(mol)
values["rot_bonds"] = lip.NumRotatableBonds(mol)
values["rigid_bonds"] = mol.GetNumBonds() - values["rot_bonds"] # assume mutual exclusion
values["num_rings"] = lip.RingCount(mol)
values["num_hetero_atoms"] = lip.NumHeteroatoms(mol)
values["charge"] = rdmolops.GetFormalCharge(mol) # trusting this charge calculation method
values["num_carbons"], values["num_charges"], values["max_ring_size"] = get_atom_props(mol)
try:
values["hc_ratio"] = float(values["num_hetero_atoms"]) / float(values["num_carbons"])
except ZeroDivisionError:
values["hc_ratio"] = 100000000 # if there are zero carbons
values["fc"] = len(list(Brics.FindBRICSBonds(mol))) # how many BRICS bonds, related to complexity
values["is_good"] = True # default to true, but not yet observed
atoms = [atom.GetSymbol() for atom in mol.GetAtoms()] # get all the atoms, and make the list unique (only types)
atoms = set(atoms)
atoms = list(atoms)
values["atoms"] = atoms
values["num_chiral_centers"] = len(Chem.FindMolChiralCenters(mol, includeUnassigned=True))
values["rejections"] = [] # empty list to store the reasons for rejection
return values
def get_descriptors(mol, write=False):
# Make a copy of the molecule dataframe
desc = [
Lipinski.NumAromaticHeterocycles(mol),
Lipinski.NumAromaticRings(mol),
Lipinski.NumHDonors(mol),
Lipinski.RingCount(mol),
Lipinski.NHOHCount(mol),
Lipinski.NumHeteroatoms(mol),
Lipinski.NumAliphaticCarbocycles(mol),
Lipinski.NumSaturatedCarbocycles(mol),
Lipinski.NumAliphaticHeterocycles(mol),
Lipinski.NumHAcceptors(mol),
Lipinski.NumSaturatedHeterocycles(mol),
Lipinski.NumAliphaticRings(mol),
Descriptors.NumRadicalElectrons(mol),
Descriptors.MaxPartialCharge(mol),
Descriptors.NumValenceElectrons(mol),
Lipinski.FractionCSP3(mol),
Descriptors.MaxAbsPartialCharge(mol),
Lipinski.NumAromaticCarbocycles(mol),
Lipinski.NumSaturatedRings(mol),
Lipinski.NumRotatableBonds(mol)
]
desc = [0 if i != i else i for i in desc]
return desc
def PhyChem(smiles):
""" Calculating the 19D physicochemical descriptors for each molecules,
the value has been normalized with Gaussian distribution.
Arguments:
smiles (list): list of SMILES strings.
Returns:
props (ndarray): m X 19 matrix as normalized PhysChem descriptors.
m is the No. of samples
"""
props = []
for smile in smiles:
mol = Chem.MolFromSmiles(smile)
try:
MW = desc.MolWt(mol)
LOGP = Crippen.MolLogP(mol)
HBA = Lipinski.NumHAcceptors(mol)
HBD = Lipinski.NumHDonors(mol)
rotable = Lipinski.NumRotatableBonds(mol)
amide = AllChem.CalcNumAmideBonds(mol)
bridge = AllChem.CalcNumBridgeheadAtoms(mol)
heteroA = Lipinski.NumHeteroatoms(mol)
heavy = Lipinski.HeavyAtomCount(mol)
spiro = AllChem.CalcNumSpiroAtoms(mol)
FCSP3 = AllChem.CalcFractionCSP3(mol)
ring = Lipinski.RingCount(mol)
Aliphatic = AllChem.CalcNumAliphaticRings(mol)
aromatic = AllChem.CalcNumAromaticRings(mol)
saturated = AllChem.CalcNumSaturatedRings(mol)
heteroR = AllChem.CalcNumHeterocycles(mol)
TPSA = MolSurf.TPSA(mol)
valence = desc.NumValenceElectrons(mol)
mr = Crippen.MolMR(mol)
# charge = AllChem.ComputeGasteigerCharges(mol)
prop = [
MW, LOGP, HBA, HBD, rotable, amide, bridge, heteroA, heavy,
spiro, FCSP3, ring, Aliphatic, aromatic, saturated, heteroR,
TPSA, valence, mr
]
except Exception:
print(smile)
prop = [0] * 19
props.append(prop)
props = np.array(props)
props = Scaler().fit_transform(props)
return props
def __init__(self, *args, **kwargs):
if len(args) > 2:
super(Compound, self).__init__(*args, **kwargs)
return
mol_as_RDmol = args[0] if len(args) > 0 else None
if not mol_as_RDmol:
mol_as_RDmol = kwargs['mol_as_RDmol'] if 'mol_as_RDmol' in kwargs else None
if not mol_as_RDmol:
raise RuntimeError("No RDMol specified")
description = args[1] if len(args) > 1 else None
if not description:
description = kwargs['description'] if 'description' in kwargs else ''
new_kwargs = dict()
new_kwargs['unique_id'] = self._generate_id()
new_kwargs['smiles'] = Chem.MolToSmiles(mol_as_RDmol, isomericSmiles=True, canonical=True)
new_kwargs['inchi'] = Chem.MolToInchi(mol_as_RDmol)
new_kwargs['inchi_key'] = Chem.InchiToInchiKey(new_kwargs['inchi'])
new_kwargs['mol_weight_exact'] = Descriptors.ExactMolWt(mol_as_RDmol)
new_kwargs['heavy_atoms_count'] = Lipinski.HeavyAtomCount(mol_as_RDmol)
new_kwargs['ring_count'] = Lipinski.RingCount(mol_as_RDmol)
new_kwargs['mol'] = mol_as_RDmol
super(Compound, self).__init__(description=description, **new_kwargs)
## logP
org_logp = [Descriptors.MolLogP(mol) for mol in tqdm(org_mols)]
## Bertz TC
org_tcs = [BertzCT(mol) for mol in tqdm(org_mols)]
## TPSA
org_tpsa = [Descriptors.TPSA(mol) for mol in org_mols]
## QED
org_qed = []
for mol in org_mols:
try:
org_qed.append(Descriptors.qed(mol))
except OverflowError:
pass
## number of rings
org_rings1 = [Lipinski.RingCount(mol) for mol in tqdm(org_mols)]
org_rings2 = [Lipinski.NumAliphaticRings(mol) for mol in tqdm(org_mols)]
org_rings3 = [Lipinski.NumAromaticRings(mol) for mol in tqdm(org_mols)]
## SA score
org_SA = []
for mol in tqdm(org_mols):
try:
org_SA.append(sascorer.calculateScore(mol))
except (OverflowError, ZeroDivisionError):
pass
## NP-likeness
fscore = npscorer.readNPModel()
org_NP = [npscorer.scoreMol(mol, fscore) for mol in tqdm(org_mols)]
## % sp3 carbons
org_sp3 = [Lipinski.FractionCSP3(mol) for mol in org_mols]
def calc_rdkit(mol):
descriptors = pd.Series(
np.array([
Crippen.MolLogP(mol),
Crippen.MolMR(mol),
Descriptors.FpDensityMorgan1(mol),
Descriptors.FpDensityMorgan2(mol),
Descriptors.FpDensityMorgan3(mol),
Descriptors.FractionCSP3(mol),
Descriptors.HeavyAtomMolWt(mol),
Descriptors.MaxAbsPartialCharge(mol),
Descriptors.MaxPartialCharge(mol),
Descriptors.MinAbsPartialCharge(mol),
Descriptors.MinPartialCharge(mol),
Descriptors.MolWt(mol),
Descriptors.NumRadicalElectrons(mol),
Descriptors.NumValenceElectrons(mol),
EState.EState.MaxAbsEStateIndex(mol),
EState.EState.MaxEStateIndex(mol),
EState.EState.MinAbsEStateIndex(mol),
EState.EState.MinEStateIndex(mol),
EState.EState_VSA.EState_VSA1(mol),
EState.EState_VSA.EState_VSA10(mol),
EState.EState_VSA.EState_VSA11(mol),
EState.EState_VSA.EState_VSA2(mol),
EState.EState_VSA.EState_VSA3(mol),
EState.EState_VSA.EState_VSA4(mol),
EState.EState_VSA.EState_VSA5(mol),
EState.EState_VSA.EState_VSA6(mol),
EState.EState_VSA.EState_VSA7(mol),
EState.EState_VSA.EState_VSA8(mol),
EState.EState_VSA.EState_VSA9(mol),
Fragments.fr_Al_COO(mol),
Fragments.fr_Al_OH(mol),
Fragments.fr_Al_OH_noTert(mol),
Fragments.fr_aldehyde(mol),
Fragments.fr_alkyl_carbamate(mol),
Fragments.fr_alkyl_halide(mol),
Fragments.fr_allylic_oxid(mol),
Fragments.fr_amide(mol),
Fragments.fr_amidine(mol),
Fragments.fr_aniline(mol),
Fragments.fr_Ar_COO(mol),
Fragments.fr_Ar_N(mol),
Fragments.fr_Ar_NH(mol),
Fragments.fr_Ar_OH(mol),
Fragments.fr_ArN(mol),
Fragments.fr_aryl_methyl(mol),
Fragments.fr_azide(mol),
Fragments.fr_azo(mol),
Fragments.fr_barbitur(mol),
Fragments.fr_benzene(mol),
Fragments.fr_benzodiazepine(mol),
Fragments.fr_bicyclic(mol),
Fragments.fr_C_O(mol),
Fragments.fr_C_O_noCOO(mol),
Fragments.fr_C_S(mol),
Fragments.fr_COO(mol),
Fragments.fr_COO2(mol),
Fragments.fr_diazo(mol),
Fragments.fr_dihydropyridine(mol),
Fragments.fr_epoxide(mol),
Fragments.fr_ester(mol),
Fragments.fr_ether(mol),
Fragments.fr_furan(mol),
Fragments.fr_guanido(mol),
Fragments.fr_halogen(mol),
Fragments.fr_hdrzine(mol),
Fragments.fr_hdrzone(mol),
Fragments.fr_HOCCN(mol),
Fragments.fr_imidazole(mol),
Fragments.fr_imide(mol),
Fragments.fr_Imine(mol),
Fragments.fr_isocyan(mol),
Fragments.fr_isothiocyan(mol),
Fragments.fr_ketone(mol),
Fragments.fr_ketone_Topliss(mol),
Fragments.fr_lactam(mol),
Fragments.fr_lactone(mol),
Fragments.fr_methoxy(mol),
Fragments.fr_morpholine(mol),
Fragments.fr_N_O(mol),
Fragments.fr_Ndealkylation1(mol),
Fragments.fr_Ndealkylation2(mol),
Fragments.fr_NH0(mol),
Fragments.fr_NH1(mol),
Fragments.fr_NH2(mol),
Fragments.fr_Nhpyrrole(mol),
Fragments.fr_nitrile(mol),
Fragments.fr_nitro(mol),
Fragments.fr_nitro_arom(mol),
Fragments.fr_nitro_arom_nonortho(mol),
Fragments.fr_nitroso(mol),
Fragments.fr_oxazole(mol),
Fragments.fr_oxime(mol),
Fragments.fr_para_hydroxylation(mol),
Fragments.fr_phenol(mol),
Fragments.fr_phenol_noOrthoHbond(mol),
Fragments.fr_phos_acid(mol),
Fragments.fr_phos_ester(mol),
Fragments.fr_piperdine(mol),
Fragments.fr_piperzine(mol),
Fragments.fr_priamide(mol),
Fragments.fr_prisulfonamd(mol),
Fragments.fr_pyridine(mol),
Fragments.fr_quatN(mol),
Fragments.fr_SH(mol),
Fragments.fr_sulfide(mol),
Fragments.fr_sulfonamd(mol),
Fragments.fr_sulfone(mol),
Fragments.fr_term_acetylene(mol),
Fragments.fr_tetrazole(mol),
Fragments.fr_thiazole(mol),
Fragments.fr_thiocyan(mol),
Fragments.fr_thiophene(mol),
Fragments.fr_unbrch_alkane(mol),
Fragments.fr_urea(mol),
GraphDescriptors.BalabanJ(mol),
GraphDescriptors.BertzCT(mol),
GraphDescriptors.Chi0(mol),
GraphDescriptors.Chi0n(mol),
GraphDescriptors.Chi0v(mol),
GraphDescriptors.Chi1(mol),
GraphDescriptors.Chi1n(mol),
GraphDescriptors.Chi1v(mol),
GraphDescriptors.Chi2n(mol),
GraphDescriptors.Chi2v(mol),
GraphDescriptors.Chi3n(mol),
GraphDescriptors.Chi3v(mol),
GraphDescriptors.Chi4n(mol),
GraphDescriptors.Chi4v(mol),
GraphDescriptors.HallKierAlpha(mol),
GraphDescriptors.Ipc(mol),
GraphDescriptors.Kappa1(mol),
GraphDescriptors.Kappa2(mol),
GraphDescriptors.Kappa3(mol),
Lipinski.HeavyAtomCount(mol),
Lipinski.NHOHCount(mol),
Lipinski.NOCount(mol),
Lipinski.NumAliphaticCarbocycles(mol),
Lipinski.NumAliphaticHeterocycles(mol),
Lipinski.NumAliphaticRings(mol),
Lipinski.NumAromaticCarbocycles(mol),
Lipinski.NumAromaticHeterocycles(mol),
Lipinski.NumAromaticRings(mol),
Lipinski.NumHAcceptors(mol),
Lipinski.NumHDonors(mol),
Lipinski.NumHeteroatoms(mol),
Lipinski.NumRotatableBonds(mol),
Lipinski.NumSaturatedCarbocycles(mol),
Lipinski.NumSaturatedHeterocycles(mol),
Lipinski.NumSaturatedRings(mol),
Lipinski.RingCount(mol),
MolSurf.LabuteASA(mol),
MolSurf.PEOE_VSA1(mol),
MolSurf.PEOE_VSA10(mol),
MolSurf.PEOE_VSA11(mol),
MolSurf.PEOE_VSA12(mol),
MolSurf.PEOE_VSA13(mol),
MolSurf.PEOE_VSA14(mol),
MolSurf.PEOE_VSA2(mol),
MolSurf.PEOE_VSA3(mol),
MolSurf.PEOE_VSA4(mol),
MolSurf.PEOE_VSA5(mol),
MolSurf.PEOE_VSA6(mol),
MolSurf.PEOE_VSA7(mol),
MolSurf.PEOE_VSA8(mol),
MolSurf.PEOE_VSA9(mol),
MolSurf.SlogP_VSA1(mol),
MolSurf.SlogP_VSA10(mol),
MolSurf.SlogP_VSA11(mol),
MolSurf.SlogP_VSA12(mol),
MolSurf.SlogP_VSA2(mol),
MolSurf.SlogP_VSA3(mol),
MolSurf.SlogP_VSA4(mol),
MolSurf.SlogP_VSA5(mol),
MolSurf.SlogP_VSA6(mol),
MolSurf.SlogP_VSA7(mol),
MolSurf.SlogP_VSA8(mol),
MolSurf.SlogP_VSA9(mol),
MolSurf.SMR_VSA1(mol),
MolSurf.SMR_VSA10(mol),
MolSurf.SMR_VSA2(mol),
MolSurf.SMR_VSA3(mol),
MolSurf.SMR_VSA4(mol),
MolSurf.SMR_VSA5(mol),
MolSurf.SMR_VSA6(mol),
MolSurf.SMR_VSA7(mol),
MolSurf.SMR_VSA8(mol),
MolSurf.SMR_VSA9(mol),
MolSurf.TPSA(mol)
]))
return descriptors
tpsa = [Descriptors.TPSA(mol) for mol in mols]
## QED
qed = []
for mol in tqdm(mols):
try:
qed.append(Descriptors.qed(mol))
except OverflowError:
pass
## % of sp3 carbons
pct_sp3 = [Lipinski.FractionCSP3(mol) for mol in tqdm(mols)]
## % heteroatoms
pct_hetero = [Lipinski.NumHeteroatoms(mol) / mol.GetNumAtoms() for mol in \
tqdm(mols)]
## number of rings
rings = [Lipinski.RingCount(mol) for mol in tqdm(mols)]
## SA score
SA = []
for mol in tqdm(mols):
try:
SA.append(sascorer.calculateScore(mol))
except (OverflowError, ZeroDivisionError):
pass
## NP-likeness
fscore = npscorer.readNPModel()
NP = [npscorer.scoreMol(mol, fscore) for mol in tqdm(mols)]
# add all outcomes to data frame
res = res.append(pd.DataFrame({'outcome': 'Molecular weight',
'value': mws }))
def calculate_metrics(mol):
# calculate chemical descriptors
## % of sp3 carbons
pct_sp3 = Lipinski.FractionCSP3(mol)
## H bond donors/acceptors
h_acceptor = Lipinski.NumHAcceptors(mol)
h_donor = Lipinski.NumHDonors(mol)
## number of rotable bonds
n_bonds = mol.GetNumBonds()
if n_bonds > 0:
rot_bonds = Lipinski.NumRotatableBonds(mol) / n_bonds
else:
rot_bonds = 0
## number of rings, aromatic and aliphatic
n_rings = Lipinski.RingCount(mol)
n_rings_ali = Lipinski.NumAliphaticRings(mol)
n_rings_aro = Lipinski.NumAromaticRings(mol)
## number of stereocentres
Chem.AssignStereochemistry(mol)
n_stereo = CalcNumAtomStereoCenters(mol)
## polarity
tpsa = Chem.CalcTPSA(mol)
## hydrophobicity
logP = Descriptors.MolLogP(mol)
## molecular weight
mw = Descriptors.MolWt(mol)
## in Lipinski space?
Ro5 = in_Ro5(mol)
## % heteroatoms
n_atoms = len(mol.GetAtoms())
pct_hetero = Lipinski.NumHeteroatoms(mol) / n_atoms
## number of each atom
symbols = [atom.GetSymbol() for atom in mol.GetAtoms()]
atom_counts = Counter(symbols)
## Murcko scaffolds
murcko = Chem.MolToSmiles(MurckoScaffold.GetScaffoldForMol(mol))
## NP-likeness
try:
np_score = calculateNPScore(mol, np_mod)
except ValueError:
np_score = None
## synthetic accessibility
try:
sa_score = calculateSAScore(mol, sa_mod)
except ValueError:
sa_score = None
## topological complexity
bertz_idx = BertzCT(mol)
# create dict
metrics = {
'% sp3 carbons': pct_sp3,
'H bond acceptors': h_acceptor,
'H bond donors': h_donor,
'% rotatable bonds': rot_bonds,
'Rings': n_rings,
'Rings, aliphatic': n_rings_ali,
'Rings, aromatic': n_rings_aro,
'Stereocentres': n_stereo,
'Topological polar surface area': tpsa,
'LogP': logP,
'Molecular weight': mw,
'Lipinski rule of 5': Ro5,
'% heteroatoms': pct_hetero,
'Murcko scaffold': murcko,
'NP-likeness score': np_score,
'Synthetic accessibility score': sa_score,
'Bertz topological complexity': bertz_idx
}
# append atom counts
for key in atom_counts.keys():
metrics['Atoms with symbol ' + key] = atom_counts[key]
return (metrics)
