def run_model(parameters_dict):
# Extracting search parameters
explicit_search_parameters_dict = _extract_explicit_search_parameters(
parameters_dict)
# Extracting IO parameters
explicit_IO_parameters_dict = _extract_explicit_IO_parameters(
parameters_dict)
# Building objective function
evaluation_strategy = _parse_objective_function_strategy(
parameters_dict,
explicit_IO_parameters_dict=explicit_IO_parameters_dict)
# Building action space
action_spaces, action_spaces_parameters = _parse_action_space(
parameters_dict)
# Building mutation strategy
mutation_strategy = _parse_mutation_parameters(
explicit_search_parameters=explicit_search_parameters_dict,
evaluation_strategy=evaluation_strategy,
action_spaces=action_spaces,
action_spaces_parameters=action_spaces_parameters)
# Building stop criterion strategy
stop_criterion_strategy = _parse_stop_criterion_strategy(
explicit_search_parameters_dict=explicit_search_parameters_dict,
explicit_IO_parameters_dict=explicit_IO_parameters_dict)
# Building instance
pop_alg = _build_instance(
evaluation_strategy=evaluation_strategy,
mutation_strategy=mutation_strategy,
stop_criterion_strategy=stop_criterion_strategy,
explicit_search_parameters_dict=explicit_search_parameters_dict,
explicit_IO_parameters_dict=explicit_IO_parameters_dict)
# GuacaMol special case
if evaluation_strategy == "guacamol":
model_generator = ChemPopAlgGoalDirectedGenerator(
pop_alg=pop_alg,
guacamol_init_top_100=explicit_search_parameters_dict[
"guacamol_init_top_100"],
init_pop_path=explicit_IO_parameters_dict["smiles_list_init_path"],
output_save_path=explicit_IO_parameters_dict["model_path"])
assess_goal_directed_generation(
model_generator,
json_output_file=join(explicit_IO_parameters_dict["model_path"],
"output_GuacaMol.json"),
benchmark_version='v2')
else:
pop_alg.run()
def main():
population_size = 100 ### each generation for each mol in population, one oracle call.
max_children = 10
generations_num = int(max_oracle_num / population_size / max_children)
parser = argparse.ArgumentParser()
parser.add_argument(
'--pickle_directory',
help=
'Directory containing pickle files with the distribution statistics',
default=None)
parser.add_argument('--seed', type=int, default=0)
parser.add_argument('--n_jobs', type=int, default=-1)
parser.add_argument('--generations', type=int, default=generations_num)
parser.add_argument('--population_size', type=int, default=population_size)
parser.add_argument('--num_sims', type=int, default=40)
parser.add_argument('--max_children', type=int,
default=max_children) ### 25 -> 5
parser.add_argument('--max_atoms', type=int, default=60)
parser.add_argument('--init_smiles', type=str, default='CC')
parser.add_argument('--output_dir', type=str, default=None)
parser.add_argument('--patience', type=int, default=5)
parser.add_argument('--suite', default='v3')
args = parser.parse_args()
if args.output_dir is None:
args.output_dir = os.path.dirname(os.path.realpath(__file__))
if args.pickle_directory is None:
args.pickle_directory = os.path.dirname(os.path.realpath(__file__))
np.random.seed(args.seed)
setup_default_logger()
# save command line args
with open(os.path.join(args.output_dir, 'goal_directed_params.json'),
'w') as jf:
json.dump(vars(args), jf, sort_keys=True, indent=4)
optimiser = GB_MCTS_Generator(pickle_directory=args.pickle_directory,
n_jobs=args.n_jobs,
num_sims=args.num_sims,
max_children=args.max_children,
init_smiles=args.init_smiles,
max_atoms=args.max_atoms,
patience=args.patience,
generations=args.generations,
population_size=args.population_size)
json_file_path = os.path.join(args.output_dir,
'goal_directed_results.json')
assess_goal_directed_generation(optimiser,
json_output_file=json_file_path,
benchmark_version=args.suite)
def entry_point():
parser = argparse.ArgumentParser()
parser.add_argument('--smiles_file', type=str)
parser.add_argument('--db_fname', type=str)
parser.add_argument('--selection_size', type=int, default=10)
parser.add_argument('--radius', type=int, default=3)
parser.add_argument('--replacements', type=int, default=1000)
parser.add_argument('--min_size', type=int, default=0)
parser.add_argument('--max_size', type=int, default=10)
parser.add_argument('--min_inc', type=int, default=-7)
parser.add_argument('--max_inc', type=int, default=7)
parser.add_argument('--generations', type=int, default=1000)
parser.add_argument('--ncpu', type=int, default=1)
parser.add_argument('--seed', type=int, default=42)
parser.add_argument('--output_dir', type=str, default=None)
parser.add_argument('--suite', default='v2')
args = parser.parse_args()
np.random.seed(args.seed)
setup_default_logger()
if args.output_dir is None:
args.output_dir = os.path.dirname(os.path.realpath(__file__))
# save command line args
with open(os.path.join(args.output_dir, 'goal_directed_params.json'),
'w') as jf:
json.dump(vars(args), jf, sort_keys=True, indent=4)
optimiser = CREM_Generator(smi_file=args.smiles_file,
selection_size=args.selection_size,
db_fname=args.db_fname,
radius=args.radius,
min_size=args.min_size,
max_size=args.max_size,
min_inc=args.min_inc,
max_inc=args.max_inc,
replacements=args.replacements,
generations=args.generations,
ncpu=args.ncpu,
random_start=True,
output_dir=args.output_dir)
json_file_path = os.path.join(args.output_dir,
'goal_directed_results.json')
assess_goal_directed_generation(optimiser,
json_output_file=json_file_path,
benchmark_version=args.suite)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--n_jobs', type=int, default=-1)
parser.add_argument('--episode_size', type=int, default=8192)
parser.add_argument('--batch_size', type=int, default=1024)
parser.add_argument('--entropy_weight', type=int, default=1)
parser.add_argument('--kl_div_weight', type=int, default=10)
parser.add_argument('--output_dir', default=None)
parser.add_argument('--clip_param', type=int, default=0.2)
parser.add_argument('--num_epochs', type=int, default=20)
parser.add_argument('--model_path', default=None)
parser.add_argument('--seed', type=int, default=42)
parser.add_argument('--suite', default='v3')
args = parser.parse_args()
np.random.seed(args.seed)
setup_default_logger()
if args.output_dir is None:
args.output_dir = os.path.dirname(os.path.realpath(__file__))
if args.model_path is None:
dir_path = os.path.dirname(os.path.realpath(__file__))
args.model_path = os.path.join(dir_path, 'pretrained_model',
'model_final_0.473.pt')
# save command line args
with open(os.path.join(args.output_dir, 'goal_directed_params.json'),
'w') as jf:
json.dump(vars(args), jf, sort_keys=True, indent=4)
optimiser = PPODirectedGenerator(pretrained_model_path=args.model_path,
num_epochs=args.num_epochs,
episode_size=args.episode_size,
batch_size=args.batch_size,
entropy_weight=args.entropy_weight,
kl_div_weight=args.kl_div_weight,
clip_param=args.clip_param)
json_file_path = os.path.join(args.output_dir,
'goal_directed_results.json')
assess_goal_directed_generation(optimiser,
json_output_file=json_file_path,
benchmark_version=args.suite)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--pickle_directory', help='Directory containing pickle files with the distribution statistics',
default=None)
parser.add_argument('--seed', type=int, default=0)
parser.add_argument('--n_jobs', type=int, default=-1)
parser.add_argument('--generations', type=int, default=1000)
parser.add_argument('--population_size', type=int, default=100)
parser.add_argument('--num_sims', type=int, default=40)
parser.add_argument('--max_children', type=int, default=25)
parser.add_argument('--max_atoms', type=int, default=60)
parser.add_argument('--init_smiles', type=str, default='CC')
parser.add_argument('--random_start', type=bool, default=False)
parser.add_argument('--output_dir', type=str, default=None)
parser.add_argument('--patience', type=int, default=5)
args = parser.parse_args()
if args.output_dir is None:
args.output_dir = os.path.dirname(os.path.realpath(__file__))
if args.pickle_directory is None:
args.pickle_directory = os.path.dirname(os.path.realpath(__file__))
np.random.seed(args.seed)
setup_default_logger()
# save command line args
with open(os.path.join(args.output_dir, 'goal_directed_params.json'), 'w') as jf:
json.dump(vars(args), jf, sort_keys=True, indent=4)
optimiser = GB_MCTS_Generator(pickle_directory=args.pickle_directory,
n_jobs=args.n_jobs,
random_start=args.random_start,
num_sims=args.num_sims,
max_children=args.max_children,
init_smiles=args.init_smiles,
max_atoms=args.max_atoms,
patience=args.patience,
generations=args.generations,
population_size=args.population_size)
json_file_path = os.path.join(args.output_dir, 'goal_directed_results.json')
assess_goal_directed_generation(optimiser, json_output_file=json_file_path)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--smiles_file', default='data/guacamol_v1_all.smiles')
parser.add_argument('--seed', type=int, default=42)
parser.add_argument('--population_size', type=int, default=100)
parser.add_argument('--n_mutations', type=int, default=200)
parser.add_argument('--gene_size', type=int, default=300)
parser.add_argument('--generations', type=int, default=1000)
parser.add_argument('--n_jobs', type=int, default=-1)
parser.add_argument('--random_start', action='store_true')
parser.add_argument('--output_dir', type=str, default=None)
parser.add_argument('--patience', type=int, default=5)
parser.add_argument('--suite', default='v1')
args = parser.parse_args()
np.random.seed(args.seed)
setup_default_logger()
if args.output_dir is None:
args.output_dir = os.path.dirname(os.path.realpath(__file__))
# save command line args
with open(os.path.join(args.output_dir, 'goal_directed_params.json'),
'w') as jf:
json.dump(vars(args), jf, sort_keys=True, indent=4)
optimiser = ChemGEGenerator(smi_file=args.smiles_file,
population_size=args.population_size,
n_mutations=args.n_mutations,
gene_size=args.gene_size,
generations=args.generations,
n_jobs=args.n_jobs,
random_start=args.random_start,
patience=args.patience)
json_file_path = os.path.join(args.output_dir,
'goal_directed_results.json')
assess_goal_directed_generation(optimiser,
json_output_file=json_file_path,
benchmark_version=args.suite)
from guacamol.assess_goal_directed_generation import assess_goal_directed_generation
from generative_playground.molecules.guacamol_utils import MyGoalDirectedGenerator
my_gen = MyGoalDirectedGenerator('trivial')
assess_goal_directed_generation(goal_directed_molecule_generator=my_gen,
benchmark_version='trivial')
parser.add_argument('--n_jobs', type=int, default=-1)
parser.add_argument('--suite', default='v3')
args = parser.parse_args()
if args.output_dir is None:
args.output_dir = os.path.dirname(os.path.realpath(__file__))
if args.model_path is None:
dir_path = os.path.dirname(os.path.realpath(__file__))
args.model_path = os.path.join(dir_path, 'pretrained_model',
'model_final_0.473.pt')
optimizer = SmilesRnnDirectedGenerator(
pretrained_model_path=args.model_path,
n_epochs=args.n_epochs,
mols_to_sample=args.mols_to_sample,
keep_top=args.keep_top,
optimize_n_epochs=args.optimize_n_epochs,
max_len=args.max_len,
optimize_batch_size=args.optimize_batch_size,
number_final_samples=args.benchmark_num_samples,
random_start=args.random_start,
smi_file=args.smiles_file,
n_jobs=args.n_jobs)
json_file_path = os.path.join(args.output_dir,
'goal_directed_results.json')
assess_goal_directed_generation(optimizer,
json_output_file=json_file_path,
benchmark_version=args.suite)
import argparse
import os
from guacamol.assess_goal_directed_generation import assess_goal_directed_generation
from guacamol.utils.helpers import setup_default_logger
from .chembl_file_reader import ChemblFileReader
from .optimizer import BestFromChemblOptimizer
if __name__ == '__main__':
setup_default_logger()
parser = argparse.ArgumentParser(description='Goal-directed benchmark for best molecules from SMILES file',
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('--smiles_file', default='data/guacamol_v1_all.smiles')
parser.add_argument('--output_dir', default=None, help='Output directory')
args = parser.parse_args()
if args.output_dir is None:
args.output_dir = os.path.dirname(os.path.realpath(__file__))
smiles_reader = ChemblFileReader(args.smiles_file)
optimizer = BestFromChemblOptimizer(smiles_reader=smiles_reader)
json_file_path = os.path.join(args.output_dir, 'goal_directed_results.json')
assess_goal_directed_generation(optimizer, json_output_file=json_file_path)
def run_model(parameters_dict):
# Extracting search parameters
explicit_search_parameters_dict = _extract_explicit_search_parameters(
parameters_dict)
# Extracting IO parameters
explicit_IO_parameters_dict = _extract_explicit_IO_parameters(
parameters_dict)
# Building objective function
evaluation_strategy = _parse_objective_function_strategy(
parameters_dict,
explicit_IO_parameters_dict=explicit_IO_parameters_dict,
explicit_search_parameters_dict=explicit_search_parameters_dict)
# Building action space
action_spaces, action_spaces_parameters, explicit_action_space_parameters = _parse_action_space(
parameters_dict)
# Building mutation strategy
mutation_strategy = _parse_mutation_parameters(
explicit_search_parameters=explicit_search_parameters_dict,
evaluation_strategy=evaluation_strategy,
action_spaces=action_spaces,
action_spaces_parameters=action_spaces_parameters,
search_space_parameters=explicit_action_space_parameters)
# Building stop criterion strategy
stop_criterion_strategy = _parse_stop_criterion_strategy(
explicit_search_parameters_dict=explicit_search_parameters_dict,
explicit_IO_parameters_dict=explicit_IO_parameters_dict)
# Building instance
pop_alg = _build_instance(
evaluation_strategy=evaluation_strategy,
mutation_strategy=mutation_strategy,
stop_criterion_strategy=stop_criterion_strategy,
explicit_search_parameters_dict=explicit_search_parameters_dict,
explicit_IO_parameters_dict=explicit_IO_parameters_dict)
# GuacaMol special case
if is_or_contains_undefined_GuacaMol_evaluation_strategy(
evaluation_strategy):
model_generator = ChemPopAlgGoalDirectedGenerator(
pop_alg=pop_alg,
guacamol_init_top_100=explicit_search_parameters_dict[
"guacamol_init_top_100"],
init_pop_path=explicit_IO_parameters_dict["smiles_list_init_path"],
output_save_path=explicit_IO_parameters_dict["model_path"])
# Extracting proper set of benchmarks
benchmark_parameter = get_GuacaMol_benchmark_parameter(
evaluation_strategy)
benchmark_key = benchmark_parameter.split("_")[1]
assess_goal_directed_generation(
model_generator,
json_output_file=join(explicit_IO_parameters_dict["model_path"],
"output_GuacaMol.json"),
benchmark_version=benchmark_key)
else:
pop_alg.run()
return pop_alg
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--smiles_file', default='data/guacamol_v1_all.smi')
parser.add_argument('--seed', type=int, default=24)
parser.add_argument('--output_dir', type=str, default=None)
parser.add_argument('--suite', default='v2')
parser.add_argument('--generations', type=int, default=1000)
parser.add_argument('--population', type=int, default=100)
parser.add_argument('--selection_size', type=int, default=200)
parser.add_argument('--selection_method', type=str, default='linear')
parser.add_argument('--derive_size', type=int, default=100)
parser.add_argument('--brics_fragment_db',
type=str,
default='deriver_goal/chembl.db')
parser.add_argument('--selfies_proportion', type=float, default=0)
parser.add_argument('--brics_proportion', type=float, default=0)
parser.add_argument('--selfies_gb_proportion', type=float, default=0)
parser.add_argument('--smiles_gb_proportion', type=float, default=0)
parser.add_argument('--mutation_rate', type=float, default=0.5)
parser.add_argument('--enable_scanner', action='store_true', default=False)
parser.add_argument('--enable_filter', action='store_true', default=False)
parser.add_argument('--delayed_filtering', type=float, default=0)
parser.add_argument('--patience', type=int, default=5)
parser.add_argument('--temperature', type=float, default=1)
parser.add_argument('--temp_decay', type=float, default=0.95)
parser.add_argument('--start_task', type=int, default=0)
parser.add_argument('--random_start', action='store_true', default=False)
parser.add_argument('--derive_population',
action='store_true',
default=False)
parser.add_argument('--counterscreen', action='store_true', default=False)
args = parser.parse_args()
#assert os.path.exists('data/guacamol_v1_all.smiles')
try:
os.remove('deriver_goal/all_output_smiles.smi')
os.remove('deriver_goal/mean_scores_by_generation.txt')
os.remove('deriver_goal/best_scores_by_generation.txt')
os.remove('deriver_goal/worst_scores_by_generation.txt')
os.remove('deriver_goal/selected_output_smiles.smi')
os.remove('deriver_goal/top_100_output_smiles.smi')
except FileNotFoundError:
pass
np.random.seed(args.seed)
random.seed = args.seed
# turn off the millions of lines of useless text
logging.basicConfig(format='%(levelname)s : %(message)s',
level=logging.CRITICAL)
if args.output_dir is None:
args.output_dir = os.path.dirname(os.path.realpath(__file__))
# save command line args
with open(os.path.join(args.output_dir, 'goal_directed_params.json'),
'w') as jf:
json.dump(vars(args), jf, sort_keys=True, indent=4)
optimiser = DeriverGenerator(
smi_file=args.smiles_file,
generations=args.generations,
population=args.population,
selection_size=args.selection_size,
selection_method=args.selection_method,
derive_size=args.derive_size,
brics_fragment_db=args.brics_fragment_db,
selfies_proportion=args.selfies_proportion,
brics_proportion=args.brics_proportion,
selfies_gb_proportion=args.selfies_gb_proportion,
smiles_gb_proportion=args.smiles_gb_proportion,
mutation_rate=args.mutation_rate,
enable_scanner=args.enable_scanner,
enable_filter=args.enable_filter,
delayed_filtering=args.delayed_filtering,
patience=args.patience,
temperature=args.temperature,
temp_decay=args.temp_decay,
start_task=args.start_task,
random_start=args.random_start,
derive_population=args.derive_population,
counterscreen=args.counterscreen)
json_file_path = os.path.join(args.output_dir,
'goal_directed_results.json')
assess_goal_directed_generation(optimiser,
json_output_file=json_file_path,
benchmark_version=args.suite)
iterations = 100
balance = 1.0
version = "v2"
accumulate_rewards = False
json_file = "guacamol/json_results/first_nn_trial.json"
# neural net
hidden_size = 256
num_layers = 2
biderectional = False
file = "deep_likeliness/saved_parameters/deep_scorer_network.pth"
neural_net = RNNEncoder(hidden_size=hidden_size,
num_layers=num_layers,
bidirectional=biderectional)
neural_net.load_state_dict(torch.load(file))
model = SynergeticMolGDG(
neural_network=neural_net,
mutation_rate=mutation_rate,
n_walkers=n_walkers,
balance=balance,
iterations=iterations,
accumulate_rewards=accumulate_rewards,
n_cpu=n_cpu,
)
assess_goal_directed_generation(model,
json_output_file=json_file,
benchmark_version=version)
all_smiles.add(smiles)
if self.best_score < score:
self.best_score = score
self.best_smiles = smiles
return score
mcts = LanguageModelMCTSWithPUCTTerminating(self.lm,
width,
max_depth,
eval_function,
cpuct=c,
terminating_symbol='</s>')
mcts.search(["<s>"], num_simulations)
return [self.best_smiles]
if __name__ == '__main__':
setup_default_logger()
generator = ChemgramsMCTSGoalDirectedGenerator()
json_file_path = os.path.join('../models',
'goal_directed_learning_results.json')
assess_goal_directed_generation(generator,
json_output_file=json_file_path,
benchmark_version='v2')
