def sitagliptin_replacement() -> GoalDirectedBenchmark:
# Find a molecule dissimilar to sitagliptin, but with the same properties
smiles = "Fc1cc(c(F)cc1F)CC(N)CC(=O)N3Cc2nnc(n2CC3)C(F)(F)F"
sitagliptin = Chem.MolFromSmiles(smiles)
target_logp = logP(sitagliptin)
target_tpsa = tpsa(sitagliptin)
similarity = TanimotoScoringFunction(smiles,
fp_type="ECFP4",
score_modifier=GaussianModifier(
mu=0, sigma=0.1))
lp = RdkitScoringFunction(descriptor=logP,
score_modifier=GaussianModifier(mu=target_logp,
sigma=0.2))
tp = RdkitScoringFunction(descriptor=tpsa,
score_modifier=GaussianModifier(mu=target_tpsa,
sigma=5))
isomers = IsomerScoringFunction("C16H15F6N5O")
specification = uniform_specification(1, 10, 100)
return GoalDirectedBenchmark(
name="Sitagliptin MPO",
objective=GeometricMeanScoringFunction([similarity, lp, tp, isomers]),
contribution_specification=specification,
)
def score_mol(self, mol: Chem.Mol) -> float:
mw = mol_weight(mol)
lp = logP(mol)
hbd = num_H_donors(mol)
mol_tpsa = tpsa(mol)
o1 = self.tpsa_mingauss(mol_tpsa)
o2 = self.tpsa_maxgauss(mol_tpsa)
o3 = self.hbd_gauss(hbd)
o4 = self.logP_gauss(lp)
o5 = self.molW_gauss(mw)
return 0.2 * (o1 + o2 + o3 + o4 + o5)
def smarts_with_other_target(smarts: str, other_molecule: str) -> ScoringFunction:
smarts_scoring_function = SMARTSScoringFunction(target=smarts)
other_mol = Chem.MolFromSmiles(other_molecule)
target_logp = logP(other_mol)
target_tpsa = tpsa(other_mol)
target_bertz = bertz(other_mol)
lp = RdkitScoringFunction(descriptor=logP,
score_modifier=GaussianModifier(mu=target_logp, sigma=0.2))
tp = RdkitScoringFunction(descriptor=tpsa,
score_modifier=GaussianModifier(mu=target_tpsa, sigma=5))
bz = RdkitScoringFunction(descriptor=bertz,
score_modifier=GaussianModifier(mu=target_bertz, sigma=30))
return GeometricMeanScoringFunction([smarts_scoring_function, lp, tp, bz])
