def make_monomer(length):
"""make an alkyl chain with two phenyl end caps
>>> length = 7
>>> ap_monomer = AlkylPhenylPolymer.make_monomer(length)
>>> ap_monomer.get_num_atoms() == 6 * 2 + length
True
>>> display(Draw.MolToImage(mol_with_atom_index(ap_monomer.to_rdkit_mol()),
... size=(700, 300)))
"""
alkane = init_building_block(smiles='F' + 'C' * length + 'F',
functional_groups=[stk.FluoroFactory()])
benzene = init_building_block(smiles='FC1=CC=CC=C1',
functional_groups=[stk.FluoroFactory()])
alkyl_phenyl = stk.ConstructedMolecule(
topology_graph=stk.polymer.Linear(
building_blocks=(alkane, benzene),
repeating_unit='BAB',
num_repeating_units=1,
optimizer=stk.MCHammer(),
))
return stk.BuildingBlock.init_from_molecule(alkyl_phenyl)
hydrogen=stk.H(5),
atom=stk.C(1),
bonders=(stk.S(0), ),
deleters=(stk.H(5), ),
),
stk.Thiol(
sulfur=stk.S(4),
hydrogen=stk.H(12),
atom=stk.C(3),
bonders=(stk.S(4), ),
deleters=(stk.H(12), ),
),
),
),
lambda: CaseData(
factory=stk.FluoroFactory(),
molecule=stk.BuildingBlock('FCC(F)CCF'),
functional_groups=(
stk.Fluoro(
fluorine=stk.F(0),
atom=stk.C(1),
bonders=(stk.C(1), ),
deleters=(stk.F(0), ),
),
stk.Fluoro(
fluorine=stk.F(3),
atom=stk.C(2),
bonders=(stk.C(2), ),
deleters=(stk.F(3), ),
),
stk.Fluoro(
55,
56,
57,
58,
59,
31,
62,
63,
),
stk.BuildingBlock(
smiles=('Br[C+]1[C+]2[N+][C+2]C2(Br)[C+](I)[C+'
'](I)[C+](Br)[C+]1Br'),
functional_groups=[
stk.BromoFactory(),
stk.IodoFactory(),
stk.FluoroFactory(),
],
): (0, 1, 18, 50, 51),
stk.BuildingBlock(
smiles=('Br[C+]1[C+]2[S][C+2]C2(Br)[C+](I)[C+]'
'(I)[C+](Br)[C+]1Br'),
functional_groups=[
stk.BromoFactory(),
stk.IodoFactory(),
stk.FluoroFactory(),
],
): (2, 16, 34, 49),
stk.BuildingBlock(
smiles=('Br[C+]1[C+]2[S][O]C2(Br)[C+](I)[C+](I'
')[C+](Br)[C+]1Br'),
functional_groups=[
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--mongodb_uri',
help='The MongoDB URI for the database to connect to.',
default='mongodb://localhost:27017/')
args = parser.parse_args()
logging.basicConfig(level=logging.INFO)
# Use a random seed to get reproducible results.
random_seed = 4
generator = np.random.RandomState(random_seed)
logger.info('Making building blocks.')
# Load the building block databases.
fluoros = tuple(
get_building_blocks(
path=pathlib.Path(__file__).parent / 'fluoros.txt',
functional_group_factory=stk.FluoroFactory(),
))
bromos = tuple(
get_building_blocks(
path=pathlib.Path(__file__).parent / 'bromos.txt',
functional_group_factory=stk.BromoFactory(),
))
initial_population = tuple(get_initial_population(fluoros, bromos))
# Write the initial population.
for i, record in enumerate(initial_population):
write(record.get_molecule(), f'initial_{i}.mol')
client = pymongo.MongoClient(args.mongodb_uri)
db = stk.ConstructedMoleculeMongoDb(client)
fitness_db = stk.ValueMongoDb(client, 'fitness_values')
# Plot selections.
generation_selector = stk.Best(
num_batches=25,
duplicate_molecules=False,
)
stk.SelectionPlotter('generation_selection', generation_selector)
mutation_selector = stk.Roulette(
num_batches=5,
random_seed=generator.randint(0, 1000),
)
stk.SelectionPlotter('mutation_selection', mutation_selector)
crossover_selector = stk.Roulette(
num_batches=3,
batch_size=2,
random_seed=generator.randint(0, 1000),
)
stk.SelectionPlotter('crossover_selection', crossover_selector)
fitness_calculator = stk.PropertyVector(
property_functions=(
get_num_rotatable_bonds,
get_complexity,
get_num_bad_rings,
),
input_database=fitness_db,
output_database=fitness_db,
)
fitness_normalizer = stk.NormalizerSequence(
fitness_normalizers=(
# Prevent division by 0 error in DivideByMean, by ensuring
# a value of each property to be at least 1.
stk.Add((1, 1, 1)),
stk.DivideByMean(),
# Obviously, because all coefficients are equal, the
# Multiply normalizer does not need to be here. However,
# it's here to show that you can easily change the relative
# importance of each component of the fitness value, by
# changing the values of the coefficients.
stk.Multiply((1, 1, 1)),
stk.Sum(),
stk.Power(-1),
), )
ea = stk.EvolutionaryAlgorithm(
num_processes=1,
initial_population=initial_population,
fitness_calculator=fitness_calculator,
mutator=stk.RandomMutator(
mutators=(
stk.RandomBuildingBlock(
building_blocks=fluoros,
is_replaceable=is_fluoro,
random_seed=generator.randint(0, 1000),
),
stk.SimilarBuildingBlock(
building_blocks=fluoros,
is_replaceable=is_fluoro,
random_seed=generator.randint(0, 1000),
),
stk.RandomBuildingBlock(
building_blocks=bromos,
is_replaceable=is_bromo,
random_seed=generator.randint(0, 1000),
),
stk.SimilarBuildingBlock(
building_blocks=bromos,
is_replaceable=is_bromo,
random_seed=generator.randint(0, 1000),
),
),
random_seed=generator.randint(0, 1000),
),
crosser=stk.GeneticRecombination(get_gene=get_functional_group_type, ),
generation_selector=generation_selector,
mutation_selector=mutation_selector,
crossover_selector=crossover_selector,
fitness_normalizer=fitness_normalizer,
)
logger.info('Starting EA.')
generations = []
for generation in ea.get_generations(50):
for record in generation.get_molecule_records():
db.put(record.get_molecule())
generations.append(generation)
# Write the final population.
for i, record in enumerate(generation.get_molecule_records()):
write(record.get_molecule(), f'final_{i}.mol')
logger.info('Making fitness plot.')
# Normalize the fitness values across the entire EA before
# plotting the fitness values.
generations = tuple(
normalize_generations(
fitness_calculator=fitness_calculator,
fitness_normalizer=fitness_normalizer,
generations=generations,
))
fitness_progress = stk.ProgressPlotter(
generations=generations,
get_property=lambda record: record.get_fitness_value(),
y_label='Fitness Value',
)
fitness_progress.write('fitness_progress.png')
fitness_progress.get_plot_data().to_csv('fitness_progress.csv')
logger.info('Making rotatable bonds plot.')
rotatable_bonds_progress = stk.ProgressPlotter(
generations=generations,
get_property=lambda record: get_num_rotatable_bonds(record.
get_molecule()),
y_label='Number of Rotatable Bonds',
)
rotatable_bonds_progress.write('rotatable_bonds_progress.png')
def main():
parser = argparse.ArgumentParser()
parser.add_argument(
'--mongodb_uri',
help='The MongoDB URI for the database to connect to.',
default='mongodb://localhost:27017/',
)
args = parser.parse_args()
logging.basicConfig(level=logging.INFO)
# Use a random seed to get reproducible results.
random_seed = 4
generator = np.random.RandomState(random_seed)
logger.info('Making building blocks.')
# Load the building block databases.
fluoros = tuple(
get_building_blocks(
path=pathlib.Path(__file__).parent / 'fluoros.txt',
functional_group_factory=stk.FluoroFactory(),
))
bromos = tuple(
get_building_blocks(
path=pathlib.Path(__file__).parent / 'bromos.txt',
functional_group_factory=stk.BromoFactory(),
))
initial_population = tuple(get_initial_population(fluoros, bromos))
# Write the initial population.
for i, record in enumerate(initial_population):
write(record.get_molecule(), f'initial_{i}.mol')
client = pymongo.MongoClient(args.mongodb_uri)
db = stk.ConstructedMoleculeMongoDb(client)
ea = stk.EvolutionaryAlgorithm(
initial_population=initial_population,
fitness_calculator=stk.FitnessFunction(get_fitness_value),
mutator=stk.RandomMutator(
mutators=(
stk.RandomBuildingBlock(
building_blocks=fluoros,
is_replaceable=is_fluoro,
random_seed=generator.randint(0, 1000),
),
stk.SimilarBuildingBlock(
building_blocks=fluoros,
is_replaceable=is_fluoro,
random_seed=generator.randint(0, 1000),
),
stk.RandomBuildingBlock(
building_blocks=bromos,
is_replaceable=is_bromo,
random_seed=generator.randint(0, 1000),
),
stk.SimilarBuildingBlock(
building_blocks=bromos,
is_replaceable=is_bromo,
random_seed=generator.randint(0, 1000),
),
),
random_seed=generator.randint(0, 1000),
),
crosser=stk.GeneticRecombination(get_gene=get_functional_group_type, ),
generation_selector=stk.Best(
num_batches=25,
duplicate_molecules=False,
),
mutation_selector=stk.Roulette(
num_batches=5,
random_seed=generator.randint(0, 1000),
),
crossover_selector=stk.Roulette(
num_batches=3,
batch_size=2,
random_seed=generator.randint(0, 1000),
),
)
logger.info('Starting EA.')
generations = []
for generation in ea.get_generations(50):
for record in generation.get_molecule_records():
db.put(record.get_molecule())
generations.append(generation)
# Write the final population.
for i, record in enumerate(generation.get_molecule_records()):
write(record.get_molecule(), f'final_{i}.mol')
logger.info('Making fitness plot.')
fitness_progress = stk.ProgressPlotter(
generations=generations,
get_property=lambda record: record.get_fitness_value(),
y_label='Fitness Value',
)
fitness_progress.write('fitness_progress.png')
logger.info('Making rotatable bonds plot.')
rotatable_bonds_progress = stk.ProgressPlotter(
generations=generations,
get_property=get_num_rotatable_bonds,
y_label='Number of Rotatable Bonds',
)
rotatable_bonds_progress.write('rotatable_bonds_progress.png')
