def __init__(self, num_iterations, keep_top_n, time_per_iteration_minutes):
self.num_iterations = num_iterations
self.keep_top_n = keep_top_n
self.time_per_iteration_minutes = time_per_iteration_minutes
self.lm = None
env = os.environ.copy()
env["PATH"] = "/Users/luis/kenlm/build/bin:" + env["PATH"]
self.lm_trainer = KenLMTrainer(env)
self.converter = Converter(rings=True, branches=True)
class DeepSmilesEncoder(FunctionApplier):
def __init__(self, astype=Series, branches=True, rings=True):
super().__init__(self.encode)
self.encoder = DeepSmilesConverter(branches, rings)
def encode(self, smiles):
k = self.function_kwargs
return self.encoder.encode(smiles)
logger.info("TanimotoScorer(abilify, radius=6)")
logger.info("num_iterations = 100")
logger.info("simulations_per_iteration = 50000")
logger.info("keep_top_n = 5000")
logger.info("loading language model...")
vocab = get_arpa_vocab(
'../resources/zinc12_fragments_deepsmiles_klm_10gram_200502.arpa')
lm = KenLMDeepSMILESLanguageModel(
'../resources/zinc12_fragments_deepsmiles_klm_10gram_200502.klm', vocab)
abilify = "Clc4cccc(N3CCN(CCCCOc2ccc1c(NC(=O)CC1)c2)CC3)c4Cl"
scorer = TanimotoScorer(abilify, radius=6)
converter = Converter(rings=True, branches=True)
env = os.environ.copy()
env["PATH"] = "/Users/luis/kenlm/build/bin:" + env["PATH"]
lm_trainer = KenLMTrainer(env)
def log_best(j, all_best, n_valid, lggr):
if j % 1000 == 0:
lggr.info("--iteration: %d--" % j)
lggr.info("num valid: %d" % n_valid)
log_top_best(all_best, 5, lggr)
def smiles_to_deepsmiles(smiles):
canonical = pybel.readstring(
"smi", smiles).write("can").strip() # TODO do we need to canonicalize?
def __init__(self, astype=Series, branches=True, rings=True):
super().__init__(self.encode)
self.encoder = DeepSmilesConverter(branches, rings)
from rdkit import Chem
from rdkit.Chem import AllChem
from deepsmiles import Converter
f = open('ms-nmr.txt')
f1 = open('ms-m-ir-nmr.txt', 'w')
# alcohol, ether, carbonyl
for line in f:
if '[' in line:
smi = Converter(rings=True, branches=True).decode(line.split('],')[1])
mol = Chem.MolFromSmiles(smi)
mol = AllChem.AddHs(mol)
# print(smi,mol.HasSubstructMatch(Chem.MolFromSmarts('[$(C[OX2H1]);!$([CX3](=O)[OX2H1])]')))
print(smi, mol.HasSubstructMatch(Chem.MolFromSmarts('[$(c[OX2H1])]')))
# print(smi,mol.HasSubstructMatch(Chem.MolFromSmarts('[$(C[OX2H1])&(c[OX2H1])]')))
o = 1 if mol.HasSubstructMatch(Chem.MolFromSmarts(
'[$(C[OX2H1])]')) == True or mol.HasSubstructMatch(
Chem.MolFromSmarts('[$(c[OX2H1])]')) == True else 0
e = 1 if mol.HasSubstructMatch(Chem.MolFromSmarts(
'[o]([c])[c]')) == True or mol.HasSubstructMatch(
Chem.MolFromSmarts('[O]([C])[C]')) == True else 0
carb = 1 if mol.HasSubstructMatch(
Chem.MolFromSmarts(
'[$([CX3]=[OX1]),$([CX3+]-[OX1-])]')) == True else 0
atoms = mol.GetAtoms()
l = [a.GetSymbol() for a in atoms]
cs = l.count('C')
hs = l.count('H')
os = l.count('O')
#print(line,cs,hs,os)
l1 = str(line.split(']')[0]) + ', ' + str(
[cs, hs, os, o, e, carb]).split('[')[1] + line.split(']')[1]
class ChemgramsGoalDirectedGenerator(GoalDirectedGenerator):
def __init__(self, num_iterations, keep_top_n, time_per_iteration_minutes):
self.num_iterations = num_iterations
self.keep_top_n = keep_top_n
self.time_per_iteration_minutes = time_per_iteration_minutes
self.lm = None
env = os.environ.copy()
env["PATH"] = "/Users/luis/kenlm/build/bin:" + env["PATH"]
self.lm_trainer = KenLMTrainer(env)
self.converter = Converter(rings=True, branches=True)
def generate_optimized_molecules(self,
scoring_function,
number_molecules,
starting_population=None):
self.new_model_dir()
vocab = get_arpa_vocab(
'../resources/chembl_25_deepsmiles_klm_10gram_200503.arpa')
self.lm = KenLMDeepSMILESLanguageModel(
'../resources/chembl_25_deepsmiles_klm_10gram_200503.klm', vocab)
print("generating %s samples..." % number_molecules)
smiles_and_scores = []
TIME_PER_ITERATION = self.time_per_iteration_minutes * 60 # in seconds
found = False
for n in range(1, self.num_iterations + 1):
print("iteration %s" % n)
num_valid = 0
start = time.time()
elapsed = time.time() - start
while elapsed < TIME_PER_ITERATION:
try:
generated = self.lm.generate(num_chars=100,
text_seed='<s>')
decoded = DeepSMILESLanguageModelUtils.decode(generated,
start='<s>',
end='</s>')
smiles = DeepSMILESLanguageModelUtils.sanitize(decoded)
score = scoring_function.score(smiles)
num_valid += 1
smiles_and_scores.append((smiles, score))
if score == 1.0:
found = True
break
except Exception:
pass
elapsed = time.time() - start
print("num valid: %s" % num_valid)
if found:
break
self.retrain(n, self.keep_top_n, smiles_and_scores)
return [
pair[0] for pair in list(
reversed(sorted(smiles_and_scores, key=lambda p: p[1])))
[:number_molecules]
]
def new_model_dir(self):
print(
"deleting any existing molexit directory, and creating a new one..."
)
path = Path("../models/molexit/")
if os.path.exists(path) and os.path.isdir(path):
shutil.rmtree(path)
path.mkdir(parents=True, exist_ok=True)
def retrain(self, n, keep_top_n, smiles_and_scores):
print("writing dataset...")
name = 'molexit-%d' % n
dataset = '../models/molexit/%s.txt' % name
dataset_scores = []
with open(dataset, 'w') as f:
for smi, score in list(
reversed(sorted(smiles_and_scores,
key=lambda p: p[1])))[:keep_top_n]:
dsmi = self.converter.encode(
pybel.readstring("smi", smi.strip()).write("can").strip())
tok = DeepSMILESTokenizer(dsmi)
tokens = tok.get_tokens()
f.write(' '.join([t.value for t in tokens]))
f.write("\n")
dataset_scores.append(score)
print('dataset: size: %s, mean score: %s, max score: %s' %
(len(dataset_scores), np.mean(dataset_scores),
np.max(dataset_scores)))
print('training new LM...')
self.lm_trainer.train(10, dataset, '../models/molexit', name)
vocab = get_arpa_vocab('../models/molexit/%s.arpa' % name)
self.lm = KenLMDeepSMILESLanguageModel(
'../models/molexit/%s.klm' % name, vocab)