start = time.time()
mcts.search(state, num_simulations)
end = time.time()
logger.info("--done--")
logger.info("num valid: %d" % num_valid)
best = mcts.get_best_sequence()
generated_text = ''.join(best[0])
logger.info("best generated text: %s" % generated_text)
decoded = DeepSMILESLanguageModelUtils.decode(generated_text,
start='<s>',
end='</s>')
smiles = DeepSMILESLanguageModelUtils.sanitize(decoded)
logger.info("best SMILES: %s, J: %s (%s seconds)" %
(smiles, scorer.score(smiles), str((end - start))))
log_top_best(all_smiles, 5, logger)
logger.info("writing dataset...")
name = 'molexit-%d' % n
dataset = '../models/molexit/%s.txt' % name
with open(dataset, 'w') as f:
for smi in list(
reversed(sorted(all_smiles.items(),
key=lambda kv: kv[1][0])))[:keep_top_n]:
dsmi = smiles_to_deepsmiles(smi[0].strip())
tok = DeepSMILESTokenizer(dsmi)
tokens = tok.get_tokens()
f.write(' '.join([t.value for t in tokens]))
f.write("\n")
start = time.time()
mcts.search(state, num_simulations)
end = time.time()
logger.info("--done--")
logger.info("num valid: %d" % num_valid)
best = mcts.get_best_sequence()
generated_text = ''.join(best[0])
logger.info("best generated text: %s" % generated_text)
decoded = DeepSMILESLanguageModelUtils.decode(generated_text,
start='<s>',
end='</s>')
smiles = DeepSMILESLanguageModelUtils.sanitize(decoded)
logger.info("best SMILES: %s, J: %s (%s seconds)" %
(smiles, distance_scorer.score(smiles), str((end - start))))
log_top_best(all_smiles, 5, logger)
logger.info("writing dataset...")
name = 'molexit-%d' % n
dataset = '../models/molexit/%s.txt' % name
with open(dataset, 'w') as f:
for smi in list(
reversed(sorted(all_smiles.items(),
key=lambda kv: kv[1][0])))[:keep_top_n]:
dsmi = smiles_to_deepsmiles(smi[0].strip())
tok = DeepSMILESTokenizer(dsmi)
tokens = tok.get_tokens()
f.write(' '.join([t.value for t in tokens]))
f.write("\n")
generated = lm.generate(num_chars=100, text_seed='<s>')
decoded = DeepSMILESLanguageModelUtils.decode(generated,
start='<s>',
end='</s>')
sanitized = DeepSMILESLanguageModelUtils.sanitize(decoded)
num_valid += 1
# synthetic accessibility score is a number between 1 (easy to make) and 10 (very difficult to make)
sascore = sascorer.calculateScore(
Chem.MolFromSmiles(sanitized)) / 10.
# cycle score, squashed between 0 and 1
cyclescore = cycle_scorer.score(sanitized)
cyclescore = cyclescore / (1 + cyclescore)
distance_score = distance_scorer.score(sanitized)
score = (0.75 *
distance_score) + (0.15 *
(1 - sascore)) + (0.10 *
(1 - cyclescore))
all_smiles[sanitized] = (score, generated)
if current_best_score is None or beats_current(score):
current_best_score = score
current_best_smiles = sanitized
except Exception as e:
pass
if (i + 1) % 50000 == 0:
t.cancel()
end = time.time()
logger.info("--done--")
logger.info("num simulations: %s" % simulations)
logger.info("num valid (in this iteration): %d" % num_valid)
logger.info("num unique (over all iterations): %s" % len(all_smiles))
logger.info("num unique (in this iteration): %s" % len(seen))
best = mcts.get_best_sequence()
generated_text = ''.join(best[0])
logger.info("best generated text: %s" % generated_text)
decoded = DeepSMILESLanguageModelUtils.decode(generated_text, start='<s>', end='</s>')
smiles = DeepSMILESLanguageModelUtils.sanitize(decoded)
logger.info("best SMILES: %s, J: %s (%s seconds)" % (smiles, distance_scorer.score(smiles), str((end - start))))
log_top_best(all_smiles, 5, logger)
logger.info("writing dataset...")
name = 'molexit-%d' % n
dataset = '../models/molexit/%s.txt' % name
dataset_scores = []
with open(dataset, 'w') as f:
for smi in list(reversed(sorted(all_smiles.items(), key=lambda kv: kv[1][0])))[:keep_top_n]:
dsmi = smiles_to_deepsmiles(smi[0].strip())
tok = DeepSMILESTokenizer(dsmi)
tokens = tok.get_tokens()
f.write(' '.join([t.value for t in tokens]))
f.write("\n")
dataset_scores.append(smi[1][0])
logger.info("beginning search...")
start = time.time()
mcts.search(state, num_simulations)
end = time.time()
logger.info("--done--")
logger.info("num valid: %d" % num_valid)
best = mcts.get_best_sequence()
generated_text = ''.join(best[0])
logger.info("best generated text: %s" % generated_text)
decoded = DeepSMILESLanguageModelUtils.decode(generated_text,
start='<s>',
end='</s>')
smiles = DeepSMILESLanguageModelUtils.sanitize(decoded)
best_score = distance_scorer.score(smiles)
logger.info("best SMILES: %s, J: %s (%s seconds)" %
(smiles, best_score, str((end - start))))
log_top_best(all_smiles, 5, logger)
logger.info("writing dataset...")
name = 'molexit-%d' % n
dataset = '../models/molexit/%s.txt' % name
with open(dataset, 'w') as f:
for smi in list(
reversed(sorted(all_smiles.items(),
key=lambda kv: kv[1][0])))[:keep_top_n]:
dsmi = smiles_to_deepsmiles(smi[0].strip())
tok = DeepSMILESTokenizer(dsmi)
tokens = tok.get_tokens()