def hard_osimertinib() -> GoalDirectedBenchmark:
smiles = 'COc1cc(N(C)CCN(C)C)c(NC(=O)C=C)cc1Nc2nccc(n2)c3cn(C)c4ccccc34'
modifier = ClippedScoreModifier(upper_x=0.8)
similar_to_osimertinib = TanimotoScoringFunction(smiles,
fp_type='FCFP4',
score_modifier=modifier)
but_not_too_similar = TanimotoScoringFunction(
smiles,
fp_type='ECFP6',
score_modifier=MinGaussianModifier(mu=0.85, sigma=0.1))
tpsa_over_100 = RdkitScoringFunction(descriptor=tpsa,
score_modifier=MaxGaussianModifier(
mu=100, sigma=10))
logP_scoring = RdkitScoringFunction(descriptor=logP,
score_modifier=MinGaussianModifier(
mu=1, sigma=1))
make_osimertinib_great_again = ArithmeticMeanScoringFunction([
similar_to_osimertinib, but_not_too_similar, tpsa_over_100,
logP_scoring
])
specification = uniform_specification(1, 10, 100)
return GoalDirectedBenchmark(name='Osimertinib MPO',
objective=make_osimertinib_great_again,
contribution_specification=specification)
def weird_physchem() -> GoalDirectedBenchmark:
min_bertz = RdkitScoringFunction(descriptor=bertz,
score_modifier=MaxGaussianModifier(
mu=1500, sigma=200))
mol_under_400 = RdkitScoringFunction(descriptor=mol_weight,
score_modifier=MinGaussianModifier(
mu=400, sigma=40))
aroma = RdkitScoringFunction(descriptor=num_aromatic_rings,
score_modifier=MinGaussianModifier(mu=3,
sigma=1))
fluorine = RdkitScoringFunction(descriptor=AtomCounter('F'),
score_modifier=GaussianModifier(mu=6,
sigma=1.0))
opt_weird = ArithmeticMeanScoringFunction(
[min_bertz, mol_under_400, aroma, fluorine])
specification = uniform_specification(1, 10, 100)
return GoalDirectedBenchmark(name='Physchem MPO',
objective=opt_weird,
contribution_specification=specification)
def hard_cobimetinib() -> GoalDirectedBenchmark:
smiles = 'OC1(CN(C1)C(=O)C1=C(NC2=C(F)C=C(I)C=C2)C(F)=C(F)C=C1)C1CCCCN1'
modifier = ClippedScoreModifier(upper_x=0.7)
os_tf = TanimotoScoringFunction(smiles,
fp_type='FCFP4',
score_modifier=modifier)
os_ap = TanimotoScoringFunction(smiles,
fp_type='ECFP6',
score_modifier=MinGaussianModifier(
mu=0.75, sigma=0.1))
rot_b = RdkitScoringFunction(descriptor=num_rotatable_bonds,
score_modifier=MinGaussianModifier(mu=3,
sigma=1))
rings = RdkitScoringFunction(descriptor=num_aromatic_rings,
score_modifier=MaxGaussianModifier(mu=3,
sigma=1))
t_cns = ArithmeticMeanScoringFunction(
[os_tf, os_ap, rot_b, rings,
CNS_MPO_ScoringFunction()])
specification = uniform_specification(1, 10, 100)
return GoalDirectedBenchmark(name='Cobimetinib MPO',
objective=t_cns,
contribution_specification=specification)
def hard_fexofenadine() -> GoalDirectedBenchmark:
"""
make fexofenadine less greasy
:return:
"""
smiles = 'CC(C)(C(=O)O)c1ccc(cc1)C(O)CCCN2CCC(CC2)C(O)(c3ccccc3)c4ccccc4'
modifier = ClippedScoreModifier(upper_x=0.8)
similar_to_fexofenadine = TanimotoScoringFunction(smiles,
fp_type='AP',
score_modifier=modifier)
tpsa_over_90 = RdkitScoringFunction(descriptor=tpsa,
score_modifier=MaxGaussianModifier(
mu=90, sigma=10))
logP_under_4 = RdkitScoringFunction(descriptor=logP,
score_modifier=MinGaussianModifier(
mu=4, sigma=1))
optimize_fexofenadine = ArithmeticMeanScoringFunction(
[similar_to_fexofenadine, tpsa_over_90, logP_under_4])
specification = uniform_specification(1, 10, 100)
return GoalDirectedBenchmark(name='Fexofenadine MPO',
objective=optimize_fexofenadine,
contribution_specification=specification)
def start_pop_ranolazine() -> GoalDirectedBenchmark:
ranolazine = 'COc1ccccc1OCC(O)CN2CCN(CC(=O)Nc3c(C)cccc3C)CC2'
modifier = ClippedScoreModifier(upper_x=0.7)
similar_to_ranolazine = TanimotoScoringFunction(ranolazine,
fp_type='AP',
score_modifier=modifier)
logP_under_4 = RdkitScoringFunction(descriptor=logP,
score_modifier=MaxGaussianModifier(
mu=7, sigma=1))
aroma = RdkitScoringFunction(descriptor=num_aromatic_rings,
score_modifier=MinGaussianModifier(mu=1,
sigma=1))
fluorine = RdkitScoringFunction(descriptor=AtomCounter('F'),
score_modifier=GaussianModifier(mu=1,
sigma=1.0))
optimize_ranolazine = ArithmeticMeanScoringFunction(
[similar_to_ranolazine, logP_under_4, fluorine, aroma])
specification = uniform_specification(1, 10, 100)
return GoalDirectedBenchmark(name='Ranolazine MPO',
objective=optimize_ranolazine,
contribution_specification=specification,
starting_population=[ranolazine])
def ranolazine_mpo() -> GoalDirectedBenchmark:
"""
Make start_pop_ranolazine more polar and add a fluorine
"""
ranolazine = "COc1ccccc1OCC(O)CN2CCN(CC(=O)Nc3c(C)cccc3C)CC2"
modifier = ClippedScoreModifier(upper_x=0.7)
similar_to_ranolazine = TanimotoScoringFunction(ranolazine,
fp_type="AP",
score_modifier=modifier)
logP_under_4 = RdkitScoringFunction(descriptor=logP,
score_modifier=MaxGaussianModifier(
mu=7, sigma=1))
tpsa_f = RdkitScoringFunction(descriptor=tpsa,
score_modifier=MaxGaussianModifier(mu=95,
sigma=20))
fluorine = RdkitScoringFunction(descriptor=AtomCounter("F"),
score_modifier=GaussianModifier(mu=1,
sigma=1.0))
optimize_ranolazine = GeometricMeanScoringFunction(
[similar_to_ranolazine, logP_under_4, fluorine, tpsa_f])
specification = uniform_specification(1, 10, 100)
return GoalDirectedBenchmark(
name="Ranolazine MPO",
objective=optimize_ranolazine,
contribution_specification=specification,
starting_population=[ranolazine],
)
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 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])
def similarity_constrained_penalized_logp_cyclebasis(smiles, name, threshold, dataset, fp_type="ECFP4"):
benchmark_name = f"{name} {threshold:.1f} Similarity Constrained Penalized logP"
objective = RdkitScoringFunction(descriptor=lambda mol: _penalized_logp_cyclebasis(mol, dataset))
offset = -objective.score(smiles)
constraint = TanimotoScoringFunction(target=smiles, fp_type=fp_type)
constrained_objective = ThresholdedImprovementScoringFunction(
objective=objective, constraint=constraint, threshold=threshold, offset=offset
)
constrained_objective.corrupt_score = -1000.0
specification = uniform_specification(1)
return GoalDirectedBenchmark(
name=benchmark_name, objective=constrained_objective, contribution_specification=specification
)
def qed_benchmark() -> GoalDirectedBenchmark:
specification = uniform_specification(1, 10, 100)
return GoalDirectedBenchmark(
name="QED",
objective=RdkitScoringFunction(descriptor=qed),
contribution_specification=specification,
)
def pioglitazone_mpo() -> GoalDirectedBenchmark:
# pioglitazone with same mw but less rotatable bonds
smiles = 'O=C1NC(=O)SC1Cc3ccc(OCCc2ncc(cc2)CC)cc3'
pioglitazone = Chem.MolFromSmiles(smiles)
target_molw = mol_weight(pioglitazone)
similarity = TanimotoScoringFunction(smiles, fp_type='ECFP4',
score_modifier=GaussianModifier(mu=0, sigma=0.1))
mw = RdkitScoringFunction(descriptor=mol_weight,
score_modifier=GaussianModifier(mu=target_molw, sigma=10))
rb = RdkitScoringFunction(descriptor=num_rotatable_bonds,
score_modifier=GaussianModifier(mu=2, sigma=0.5))
specification = uniform_specification(1, 10, 100)
return GoalDirectedBenchmark(name='Pioglitazone MPO',
objective=GeometricMeanScoringFunction([similarity, mw, rb]),
contribution_specification=specification)
def tpsa_benchmark(target: float) -> GoalDirectedBenchmark:
benchmark_name = f'TPSA (target: {target})'
objective = RdkitScoringFunction(descriptor=tpsa,
score_modifier=GaussianModifier(mu=target, sigma=20.0))
specification = uniform_specification(1, 10, 100)
return GoalDirectedBenchmark(name=benchmark_name,
objective=objective,
contribution_specification=specification)
def amlodipine_rings() -> GoalDirectedBenchmark:
# amlodipine with 3 rings
amlodipine = TanimotoScoringFunction(r'Clc1ccccc1C2C(=C(/N/C(=C2/C(=O)OCC)COCCN)C)\C(=O)OC', fp_type='ECFP4')
rings = RdkitScoringFunction(descriptor=num_rings,
score_modifier=GaussianModifier(mu=3, sigma=0.5))
specification = uniform_specification(1, 10, 100)
return GoalDirectedBenchmark(name='Amlodipine MPO',
objective=GeometricMeanScoringFunction([amlodipine, rings]),
contribution_specification=specification)
def perindopril_rings() -> GoalDirectedBenchmark:
# perindopril with two aromatic rings
perindopril = TanimotoScoringFunction('O=C(OCC)C(NC(C(=O)N1C(C(=O)O)CC2CCCCC12)C)CCC',
fp_type='ECFP4')
arom_rings = RdkitScoringFunction(descriptor=num_aromatic_rings,
score_modifier=GaussianModifier(mu=2, sigma=0.5))
specification = uniform_specification(1, 10, 100)
return GoalDirectedBenchmark(name='Perindopril MPO',
objective=GeometricMeanScoringFunction([perindopril, arom_rings]),
contribution_specification=specification)
def penalized_logp_cyclebasis(dataset):
benchmark_name = "Penalized logP CycleBasis"
objective = RdkitScoringFunction(descriptor=lambda mol: _penalized_logp_cyclebasis(mol, dataset))
objective.corrupt_score = -1000.0
specification = uniform_specification(1)
return GoalDirectedBenchmark(name=benchmark_name, objective=objective, contribution_specification=specification)