def main():
decoded_file = GRAMMAR_WEIGHTS.split(".")[0] + "_decRes.txt"
priors_file = GRAMMAR_WEIGHTS.split(".")[0] + "_priorsRes.txt"
generation_file = GRAMMAR_WEIGHTS.split(".")[0] + "_generationRes.txt"
grammar_model = molecule_vae.Qm9GrammarModel(GRAMMAR_WEIGHTS)
XTE = readStr_qm9()
XTE = XTE[0:5000]
# rember to comment and uncomment the line in the #moelcule_vae file
decoded_result = reconstruction(grammar_model, XTE)
save_decoded_results(XTE, decoded_result, decoded_file)
# decoded_priors = prior(grammar_model)
# save_decoded_priors(decoded_priors, priors_file)
decoded_generation = generation(grammar_model)
save_decoded_priors(decoded_generation, generation_file)
def main():
from att_model_proxy import AttMolProxy as ProxyModel
from att_model_proxy import cmd_args
# takes the model and calculate the decode results
model = ProxyModel()
# update where to save
decoded_file = cmd_args.save_dir + '/decoded_results.txt'
# reading smiles test set
if cmd_args.smiles_file == 'qm9':
smiles_list = readStr_qm9()
elif cmd_args.smiles_file == 'zinc':
smiles_list = read_zinc()
XTE = smiles_list[0:nb_smiles]
decoded_result = reconstruct(model, XTE)
decoded_result = np.array(decoded_result)
save_decoded_results(XTE, decoded_result, decoded_file)
def main():
torch.manual_seed(0)
lg = rdkit.RDLogger.logger()
lg.setLevel(rdkit.RDLogger.CRITICAL)
parser = OptionParser()
parser.add_option("-t", "--test", dest="test_path")
parser.add_option("-v", "--vocab", dest="vocab_path")
parser.add_option("-m", "--model", dest="model_path")
parser.add_option("-w", "--hidden", dest="hidden_size", default=200)
parser.add_option("-l", "--latent", dest="latent_size", default=56)
parser.add_option("-d", "--depth", dest="depth", default=3)
opts, args = parser.parse_args()
vocab = [x.strip("\r\n ") for x in open(opts.vocab_path)]
vocab = Vocab(vocab)
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()
dataset_name = opts.test_path
result_file = dataset_name + "_decoded_results.txt"
priors_file = dataset_name + "_decoded_priors.txt"
generation_fie = dataset_name + "_generation.txt"
# read dataset
if dataset_name == "zinc":
XTE = read_zinc()
else:
D = readStr_qm9()
# fix problem about molecule with '.' inside
XTE = []
for mol in D:
if "." not in mol:
XTE.append(mol)
# reconstruction
XTE = XTE[0:5000]
XTE = filter(lambda x: len(x) > 1,
XTE) #needed for removing smiles with only a char.
decoded_result = reconstruction(model, XTE, 20, 1)
save_decoded_results(XTE, decoded_result, result_file)
# prior
# decoded_priors_witherrors = model.sample_prior_eval(True, 1000, 10)
# decoded_priors = []
# for i in decoded_priors_witherrors:
# decoded_priors.append(sanitize(i))
# save_decoded_priors(decoded_priors, priors_file)
# generation
generation_witherrors = model.sample_prior_eval(True, 20000, 1)
generation = []
for i in generation_witherrors:
generation.append(sanitize(i))
save_decoded_priors(generation, generation_fie)