def main():
args = get_arguments()
data_train, data_test, charset = load_dataset(args.data)
model = MoleculeVAE()
if os.path.isfile(args.model):
model.load(charset, args.model, latent_rep_size=args.latent_dim)
else:
model.create(charset, latent_rep_size=args.latent_dim)
checkpointer = ModelCheckpoint(filepath=args.model,
verbose=1,
save_best_only=True)
reduce_lr = ReduceLROnPlateau(monitor='val_loss',
factor=0.2,
patience=3,
min_lr=0.0001)
model.autoencoder.fit(data_train,
data_train,
shuffle=True,
nb_epoch=args.epochs,
batch_size=args.batch_size,
callbacks=[checkpointer, reduce_lr],
validation_data=(data_test, data_test))
def visualize_model(args):
model = MoleculeVAE()
data, charset = load_dataset(args.data, split=False)
if os.path.isfile(args.model):
model.load(charset, args.model)
else:
raise ValueError("Model file %s doesn't exist" % args.model)
plot(model.autoencoder, to_file=args.outfile)
def autoencoder(args, model):
latent_dim = args.latent_dim
data, charset = load_dataset(args.data, split=False)
if os.path.isfile(args.model):
model.load(charset, args.model, latent_rep_size=latent_dim)
else:
raise ValueError("Model file %s doesn't exist" % args.model)
sampled = model.autoencoder.predict(data[0].reshape(
1, 120, len(charset))).argmax(axis=2)[0]
mol = decode_smiles_from_indexes(map(from_one_hot_array, data[0]), charset)
sampled = decode_smiles_from_indexes(sampled, charset)
print(mol)
print(sampled)
def main():
args = get_arguments()
model = MoleculeVAE()
data, data_test, charset = load_dataset(args.data)
if os.path.isfile(args.model):
model.load(charset, args.model, latent_rep_size=args.latent_dim)
else:
raise ValueError("Model file %s doesn't exist" % args.model)
if not args.visualize:
x_latent = model.encoder.predict(data)
np.savetxt(sys.stdout, x_latent, delimiter='\t')
else:
visualize_latent_rep(args, model, data)
def encoder(args, model):
latent_dim = args.latent_dim
data, charset = load_dataset(args.data, split=False)
if os.path.isfile(args.model):
model.load(charset, args.model, latent_rep_size=latent_dim)
else:
raise ValueError("Model file %s doesn't exist" % args.model)
x_latent = model.encoder.predict(data)
if args.save_h5:
h5f = h5py.File(args.save_h5, 'w')
h5f.create_dataset('charset', data=charset)
h5f.create_dataset('latent_vectors', data=x_latent)
h5f.close()
else:
np.savetxt(sys.stdout, x_latent, delimiter='\t')
def main():
args = get_arguments()
model = MoleculeVAE()
data, charset = load_dataset('data/all_smiles_120_one_hot.h5', split=False)
if os.path.isfile(args.model):
model.load(charset, args.model)
else:
raise ValueError("Model file %s doesn't exist" % args.model)
sampled = model.autoencoder.predict(data[100].reshape(
1, 120, len(charset))).argmax(axis=2)[0]
mol = decode_smiles_from_indexes(map(from_one_hot_array, data[100]),
charset)
sampled = decode_smiles_from_indexes(sampled, charset)
print(mol)
print(sampled)
def main():
args = get_arguments()
model = MoleculeVAE()
data, data_test, charset = load_dataset(args.data)
if os.path.isfile(args.model):
model.load(charset, args.model, latent_rep_size=args.latent_dim)
else:
raise ValueError("Model file %s doesn't exist" % args.model)
x_latent = model.encoder.predict(data)
if not args.visualize:
if not args.save_h5:
np.savetxt(sys.stdout, x_latent, delimiter='\t')
else:
h5f = h5py.File(args.save_h5, 'w')
h5f.create_dataset('charset', data=charset)
h5f.create_dataset('latent_vectors', data=x_latent)
h5f.close()
else:
visualize_latent_rep(args, model, x_latent)
