def reproduce(seed,
samples_path=None,
metrics_path=None,
n_jobs=1,
device='cpu',
verbose=False,
samples=30000):
train = moses.get_dataset('train')
model = CombinatorialGenerator(n_jobs=n_jobs)
if verbose:
print("Training...")
model.fit(train)
if verbose:
print(f"Sampling for seed {seed}")
seeds = list(range((seed - 1) * samples, seed * samples))
samples = mapper(n_jobs)(model.generate_one, seeds)
if samples_path is not None:
with open(samples_path, 'w') as f:
f.write('SMILES\n')
for sample in samples:
f.write(sample + '\n')
if verbose:
print(f"Computing metrics for seed {seed}")
metrics = moses.get_all_metrics(samples, n_jobs=n_jobs, device=device)
if metrics_path is not None:
with open(metrics_path, 'w') as f:
for key, value in metrics.items():
f.write("%s,%f\n" % (key, value))
return samples, metrics
def reproduce(seed, samples_path=None, metrics_path=None,
n_jobs=1, device='cpu', verbose=False,
samples=30000):
data = moses.get_dataset('train')[:100000]
if verbose:
print("Training...")
model = HMM(n_jobs=n_jobs, seed=seed, verbose=verbose)
model.fit(data)
np.random.seed(seed)
if verbose:
print(f"Sampling for seed {seed}")
np.random.seed(seed)
samples = [model.generate_one()
for _ in range(samples)]
if samples_path is not None:
with open(samples_path, 'w') as f:
f.write('SMILES\n')
for sample in samples:
f.write(sample+'\n')
if verbose:
print(f"Computing metrics for seed {seed}")
metrics = moses.get_all_metrics(
samples, n_jobs=n_jobs, device=device)
if metrics_path is not None:
with open(samples_path, 'w') as f:
for key, value in metrics.items():
f.write("%s,%f\n" % (key, value))
return samples, metrics
def download_moses():
script_dir = os.path.dirname(os.path.realpath(__file__))
print('>>> Loading data from moses')
train = moses.get_dataset('train')
test = moses.get_dataset('test')
test_scaffolds = moses.get_dataset('test_scaffolds')
train = pd.DataFrame(train).rename(columns={0: 'smiles'})
test = pd.DataFrame(test).rename(columns={0: 'smiles'})
scaf = pd.DataFrame(test_scaffolds).rename(columns={0: 'smiles'})
print(scaf.head())
print('>>> Saving data to csv files in ./data')
train.to_csv(os.path.join(script_dir, '../data/moses_train.csv'))
test.to_csv(os.path.join(script_dir, '../data/moses_test.csv'))
scaf.to_csv(os.path.join(script_dir, '../data/moses_test_scaffolds.csv'))
def reproduce(seed, samples_path=None, metrics_path=None,
n_jobs=1, device='cpu', verbose=False,
samples=30000):
data = moses.get_dataset('train')
model = NGram(10, verbose=verbose)
model.fit(data)
np.random.seed(seed)
smiles = model.generate(samples, l_smooth=0.01)
metrics = moses.get_all_metrics(smiles, n_jobs=n_jobs, device=device)
if samples_path is not None:
with open(samples_path, 'w') as out:
out.write('SMILES\n')
for s in smiles:
out.write(s+'\n')
if metrics_path is not None:
with open(metrics_path, 'w') as out:
for key, value in metrics.items():
out.write("%s,%f\n" % (key, value))
return smiles, metrics
def setUp(self):
self.train = moses.get_dataset('train')
import moses
train = moses.get_dataset('train')
default='images/',
help='Store images in this folder')
return parser
if __name__ == "__main__":
disable_rdkit_log()
parser = get_parser()
config, unknown = parser.parse_known_args()
if len(unknown) != 0:
raise ValueError("Unknown argument " + unknown[0])
os.makedirs(config.img_folder, exist_ok=True)
generated = OrderedDict(
{'MOSES': pd.DataFrame({'SMILES': get_dataset('test')})})
models = pd.read_csv(config.config)
for path, name in zip(models['path'], models['name']):
generated[name] = pd.read_csv(path)
metrics = {'weight': weight, 'logP': logP, 'SA': SA, 'QED': QED}
for s in generated.values():
s['ROMol'] = mapper(config.n_jobs)(get_mol, s['SMILES'])
distributions = OrderedDict()
for metric_name, metric_fn in metrics.items():
distributions[metric_name] = OrderedDict()
for _set, _molecules in generated.items():
distributions[metric_name][_set] = mapper(config.n_jobs)(
metric_fn, _molecules['ROMol'].dropna().values)
import moses
from rdkit import Chem
from rdkit.Chem import Draw
import numpy as np
from tqdm import tqdm
train = moses.get_dataset('train')
test = moses.get_dataset('test')
dataset = np.hstack([train, test]) #sumar los dos arrays que tenemos
#test_scaffolds = moses.get_dataset('test_scaffolds')
print("Number of molecules to train: ", len(train), "Number of molecules to test: ", len(test))
smiles_train = train[0]
def image_molecule(smiles, title = "molecule.png"):
mol_train = Chem.MolFromSmiles(smiles)
Draw.MolToFile(mol_train, title)
return title
def smiles_number_to_smiles_string(input_molecule, dict):
smile_char = [dict_number_to_char[number] for number in smile ]
smile_string = "".join(smile_char)
return smile_string
molecule1 = image_molecule(smiles_train)