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 test_geometric_mean_scoring_function():
# define a scoring function returning the geometric mean from two mock functions
# and assert that it returns the correct values.
mock_values_1 = [0.232, 0.665, 0.0, 1.0, 0.993]
mock_values_2 = [0.010, 0.335, 0.8, 0.3, 0.847]
mock_1 = MockScoringFunction(mock_values_1)
mock_2 = MockScoringFunction(mock_values_2)
scoring_function = GeometricMeanScoringFunction(scoring_functions=[mock_1, mock_2])
smiles = ['CC'] * 5
scores = scoring_function.score_list(smiles)
expected = [sqrt(v1 * v2) for v1, v2 in zip(mock_values_1, mock_values_2)]
assert scores == expected
def median_tadalafil_sildenafil() -> GoalDirectedBenchmark:
# median mol between tadalafil and sildenafil
m1 = TanimotoScoringFunction('O=C1N(CC(N2C1CC3=C(C2C4=CC5=C(OCO5)C=C4)NC6=C3C=CC=C6)=O)C', fp_type='ECFP6')
m2 = TanimotoScoringFunction('CCCC1=NN(C2=C1N=C(NC2=O)C3=C(C=CC(=C3)S(=O)(=O)N4CCN(CC4)C)OCC)C', fp_type='ECFP6')
median = GeometricMeanScoringFunction([m1, m2])
specification = uniform_specification(1, 10, 100)
return GoalDirectedBenchmark(name='Median molecules 2',
objective=median,
contribution_specification=specification)
def zaleplon_with_other_formula() -> GoalDirectedBenchmark:
# zaleplon_with_other_formula with other formula
zaleplon = TanimotoScoringFunction('O=C(C)N(CC)C1=CC=CC(C2=CC=NC3=C(C=NN23)C#N)=C1',
fp_type='ECFP4')
formula = IsomerScoringFunction('C19H17N3O2')
specification = uniform_specification(1, 10, 100)
return GoalDirectedBenchmark(name='Zaleplon MPO',
objective=GeometricMeanScoringFunction([zaleplon, formula]),
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 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 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)
