def load_jtnn():
# Load configs & data
model_path = 'data/jtnn/model'
conf = json.load(open('data/jtnn/config.json', 'r'))
vocab = [t.strip() for t in open('data/jtnn/vocab.dat')]
vocab = Vocab(vocab)
labels = [l.strip() for l in open('data/jtnn/labels.dat')]
n_classes = len(labels)
# Load JTNN VAE model
hidden_size = conf['hidden_size']
latent_size = conf['latent_size']
depth = conf['depth']
model = JTNNVAE(vocab, hidden_size, latent_size, depth, n_classes)
saves = sorted(os.listdir(model_path))
path = os.path.join(model_path, saves[-1])
model.load_state_dict(torch.load(path))
model = model.cuda()
return model, labels
smiles = f.readlines()
for i in xrange(len(smiles)):
smiles[i] = smiles[i].strip()
vocab = [x.strip("\r\n ") for x in open(opts.vocab_path)]
vocab = Vocab(vocab)
batch_size = 100
hidden_size = int(opts.hidden_size)
latent_size = int(opts.latent_size)
depth = int(opts.depth)
model = JTNNVAE(vocab, hidden_size, latent_size, depth)
model.load_state_dict(torch.load(opts.model_path))
model = model.cuda()
smiles_rdkit = []
for i in xrange(len(smiles)):
smiles_rdkit.append(
MolToSmiles(MolFromSmiles(smiles[i]), isomericSmiles=True))
logP_values = []
for i in xrange(len(smiles)):
logP_values.append(Descriptors.MolLogP(MolFromSmiles(smiles_rdkit[i])))
SA_scores = []
for i in xrange(len(smiles)):
SA_scores.append(-sascorer.calculateScore(MolFromSmiles(smiles_rdkit[i])))
cycle_scores = []