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_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 __init__(self, max_logP=6.35584, maxMW=360, min_tpsa=40, max_tpsa=90, max_hbd=0) -> None:
super().__init__()
self.logP_gauss = MinGaussianModifier(max_logP, 1)
self.molW_gauss = MinGaussianModifier(maxMW, 60)
self.tpsa_maxgauss = MaxGaussianModifier(min_tpsa, 20)
self.tpsa_mingauss = MinGaussianModifier(max_tpsa, 30)
self.hbd_gauss = MinGaussianModifier(max_hbd, 2.0)
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 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 similarity_cns_mpo(smiles, molecule_name, max_logP=5.0) -> GoalDirectedBenchmark:
benchmark_name = f'{molecule_name}'
os_tf = TanimotoScoringFunction(smiles, fp_type='FCFP4')
os_ap = TanimotoScoringFunction(smiles, fp_type='AP')
anti_fp = TanimotoScoringFunction(smiles, fp_type='ECFP6',
score_modifier=MinGaussianModifier(mu=0.70, sigma=0.1))
t_cns = ArithmeticMeanScoringFunction([os_tf, os_ap, anti_fp, CNS_MPO_ScoringFunction(max_logP=max_logP)])
specification = uniform_specification(1, 10, 100)
return GoalDirectedBenchmark(name=benchmark_name,
objective=t_cns,
contribution_specification=specification)
def test_min_gaussian_function():
mu = -1.223
sigma = 0.334
f = MinGaussianModifier(mu=mu, sigma=sigma)
assert f(mu) == 1.0
low_value = -np.inf
large_value = np.inf
assert f(low_value) == 1.0
assert f(large_value) == 0.0
full_gaussian = partial(gaussian, mu=mu, sig=sigma)
min_gaussian_lambda = lambda x: 1.0 if x < mu else full_gaussian(x)
min_gaussian = np.vectorize(min_gaussian_lambda)
assert f(scalar_value) == min_gaussian(scalar_value)
assert np.allclose(f(value_array), min_gaussian(value_array))
