def test_arithmetic_mean_scoring_function():
# define a scoring function returning the mean from two mock functions
# and assert that it returns the correct values.
weight_1 = 0.4
weight_2 = 0.6
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 = ArithmeticMeanScoringFunction(
scoring_functions=[mock_1, mock_2], weights=[weight_1, weight_2])
smiles = ['CC'] * 5
scores = scoring_function.score_list(smiles)
expected = [
weight_1 * v1 + weight_2 * v2
for v1, v2 in zip(mock_values_1, mock_values_2)
]
assert scores == expected
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 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 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 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 scaffold_hop() -> GoalDirectedBenchmark:
"""
Keep the decoration, and similarity to start point, but change the scaffold.
"""
smiles = "CCCOc1cc2ncnc(Nc3ccc4ncsc4c3)c2cc1S(=O)(=O)C(C)(C)C"
pharmacophor_sim = TanimotoScoringFunction(
smiles,
fp_type="PHCO",
score_modifier=ClippedScoreModifier(upper_x=0.75))
deco = SMARTSScoringFunction(
"[#6]-[#6]-[#6]-[#8]-[#6]~[#6]~[#6]~[#6]~[#6]-[#7]-c1ccc2ncsc2c1",
inverse=False)
# anti scaffold
scaffold = SMARTSScoringFunction(
"[#7]-c1n[c;h1]nc2[c;h1]c(-[#8])[c;h0][c;h1]c12", inverse=True)
scaffold_hop_obj = ArithmeticMeanScoringFunction(
[pharmacophor_sim, deco, scaffold])
specification = uniform_specification(1, 10, 100)
return GoalDirectedBenchmark(name="Scaffold Hop",
objective=scaffold_hop_obj,
contribution_specification=specification)
def median_molecule() -> GoalDirectedBenchmark:
t_camphor = TanimotoScoringFunction('CC1(C)C2CCC1(C)C(=O)C2',
fp_type='ECFP4')
t_menthol = TanimotoScoringFunction('CC(C)C1CCC(C)CC1O', fp_type='ECFP4')
median = ArithmeticMeanScoringFunction([t_menthol, t_camphor])
specification = uniform_specification(1, 10, 100)
return GoalDirectedBenchmark(name='Median molecules',
objective=median,
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 decoration_hop() -> GoalDirectedBenchmark:
smiles = 'CCCOc1cc2ncnc(Nc3ccc4ncsc4c3)c2cc1S(=O)(=O)C(C)(C)C'
pharmacophor_sim = TanimotoScoringFunction(smiles, fp_type='PHCO',
score_modifier=ClippedScoreModifier(upper_x=0.85))
# change deco
deco1 = SMARTSScoringFunction('CS([#6])(=O)=O', inverse=True)
deco2 = SMARTSScoringFunction('[#7]-c1ccc2ncsc2c1', inverse=True)
# keep scaffold
scaffold = SMARTSScoringFunction('[#7]-c1n[c;h1]nc2[c;h1]c(-[#8])[c;h0][c;h1]c12', inverse=False)
deco_hop1_fn = ArithmeticMeanScoringFunction([pharmacophor_sim, deco1, deco2, scaffold])
specification = uniform_specification(1, 10, 100)
return GoalDirectedBenchmark(name='Deco Hop',
objective=deco_hop1_fn,
contribution_specification=specification)