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 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 __init__(self, molecular_formula: str) -> None:
"""
Args:
molecular_formula: target molecular formula
"""
super().__init__()
element_occurrences = parse_molecular_formula(molecular_formula)
total_number_atoms = sum(element_tuple[1] for element_tuple in element_occurrences)
# scoring functions for each element
self.functions = [RdkitScoringFunction(descriptor=AtomCounter(element),
score_modifier=GaussianModifier(mu=n_atoms, sigma=1.0))
for element, n_atoms in element_occurrences]
# scoring functions for the total number of atoms
self.functions.append(RdkitScoringFunction(descriptor=num_atoms,
score_modifier=GaussianModifier(mu=total_number_atoms, sigma=2.0)))
def determine_scoring_functions(
molecular_formula: str) -> List[RdkitScoringFunction]:
element_occurrences = parse_molecular_formula(molecular_formula)
total_number_atoms = sum(element_tuple[1]
for element_tuple in element_occurrences)
# scoring functions for each element
functions = [
RdkitScoringFunction(descriptor=AtomCounter(element),
score_modifier=GaussianModifier(mu=n_atoms,
sigma=1.0))
for element, n_atoms in element_occurrences
]
# scoring functions for the total number of atoms
functions.append(
RdkitScoringFunction(descriptor=num_atoms,
score_modifier=GaussianModifier(
mu=total_number_atoms, sigma=2.0)))
return functions