def main(config):
set_seed(config.seed)
train = read_smiles_csv(config.train_load)
vocab = CharVocab.from_data(train)
torch.save(vocab, config.vocab_save)
torch.save(config, config.config_save)
device = torch.device(config.device)
# condition mode
if config.conditional:
fps = read_fps_csv(config.train_load)
fps = fps_to_list(fps)
fps = [torch.tensor(f, dtype=torch.float, device=device) for f in fps]
# fingerprints length
fps_len = len(fps[0])
else:
fps = None
fps_len = 0
with Pool(config.n_jobs) as pool:
reward_func = MetricsReward(train, config.n_ref_subsample,
config.rollouts, pool,
config.addition_rewards)
model = ORGAN(vocab, config, fps_len, reward_func)
model = model.to(device)
trainer = ORGANTrainer(config)
trainer.fit(model, train, fps)
torch.save(model.state_dict(), config.model_save)
def __init__(self, config):
model_config = torch.load(config.config_load)
model_vocab = torch.load(config.vocab_load)
model_state = torch.load(config.model_load)
self.config = config
device = torch.device(config.device)
self.model = ORGAN(model_vocab, model_config)
self.model.load_state_dict(model_state)
self.model = self.model.to(device)
self.model.eval()
def main(config):
set_seed(config.seed)
model_config = torch.load(config.config_load)
model_vocab = torch.load(config.vocab_load)
model_state = torch.load(config.model_load)
device = torch.device(config.device)
model = ORGAN(model_vocab, model_config)
model.load_state_dict(model_state)
model = model.to(device)
model.eval()
samples = []
n = config.n_samples
with tqdm.tqdm(total=config.n_samples, desc='Generating samples') as T:
while n > 0:
current_samples = model.sample(min(n, config.n_batch), config.max_len)
samples.extend(current_samples)
n -= len(current_samples)
T.update(len(current_samples))
samples = pd.DataFrame(samples, columns=['SMILES'])
samples.to_csv(config.gen_save, index=False)
def main(config):
set_seed(config.seed)
train = read_smiles_csv(config.train_load)
vocab = CharVocab.from_data(train)
device = torch.device(config.device)
with Pool(config.n_jobs) as pool:
reward_func = MetricsReward(train, config.n_ref_subsample,
config.rollouts, pool,
config.addition_rewards)
model = ORGAN(vocab, config, reward_func)
model = model.to(device)
trainer = ORGANTrainer(config)
trainer.fit(model, train)
torch.save(model.state_dict(), config.model_save)
torch.save(config, config.config_save)
torch.save(vocab, config.vocab_save)
class OrganGenerator(DistributionMatchingGenerator):
def __init__(self, config):
model_config = torch.load(config.config_load)
model_vocab = torch.load(config.vocab_load)
model_state = torch.load(config.model_load)
self.config = config
device = torch.device(config.device)
self.model = ORGAN(model_vocab, model_config)
self.model.load_state_dict(model_state)
self.model = self.model.to(device)
self.model.eval()
def generate(self, number_samples: int) -> List[str]:
samples = []
n = number_samples
with tqdm.tqdm(total=number_samples, desc='Generating samples') as T:
while n > 0:
current_samples = self.model.sample(
min(n, self.config.n_batch), self.config.max_len)
samples.extend(current_samples)
n -= len(current_samples)
T.update(len(current_samples))
return samples
def main(config):
set_seed(config.seed)
model_config = torch.load(config.config_load)
model_vocab = torch.load(config.vocab_load)
model_state = torch.load(config.model_load)
device = torch.device(config.device)
# condition mode
if config.conditional:
print('Conditional generation')
# target fingerprints
fps_center = read_fps_csv(config.condition_load)
fps_center = fps_to_list(list(set(fps_center)))
fps_center = [
torch.tensor(f, dtype=torch.float, device=device)
for f in fps_center
]
# target fingerprints length
fps_len = len(fps_center[0])
# target fingerprints number
fps_num = len(fps_center)
else:
fps_center = [None]
fps_len = 0
fps_num = 1
model = ORGAN(model_vocab, model_config, fps_len)
model.load_state_dict(model_state)
model = model.to(device)
model.eval()
# sample numbers
gen_samples = []
n = config.n_samples
with tqdm.tqdm(total=config.n_samples, desc='Generating samples') as T:
for i in range(fps_num):
samples = []
while n > 0:
fps = fps_center[i]
if config.conditional:
fps = fps_center[i].unsqueeze(0)
current_samples = model.sample(fps, config.conditional,
min(n, config.n_batch),
config.max_len)
samples.extend(current_samples)
n -= len(current_samples)
T.update(len(current_samples))
gen_samples.extend(samples)
df = pd.DataFrame(gen_samples, columns=['SMILES'])
df.to_csv(config.gen_save, index=False)
# tanimoto similarity score and summary
if config.conditional:
calculate_score(config.gen_save, config.condition_load,
config.n_samples)