def __getitem__(self, idx):
batch_data = self.data[idx]
tree1_batch = [dpair[0] for dpair in batch_data]
tree2_batch = [dpair[1] for dpair in batch_data]
x_batch = MolTree.tensorize(tree1_batch, self.vocab, self.avocab, target=False, add_target=self.add_target)
y_batch = MolTree.tensorize(tree2_batch, self.vocab, self.avocab, target=True, add_target=self.add_target)
return x_batch, y_batch, tree1_batch, tree2_batch
def predict(smiles, lr, vocab, avocab, reselect, ori_smiles, iternum, output):
mol = Chem.MolFromSmiles(smiles)
atomnum = mol.GetNumAtoms()
tree = get_tree(smiles)
score1 = penalized_logp(smiles)
try:
xbatch = MolTree.tensorize([tree], vocab, avocab, target=False)
new_smiles, sim, reselect, score11, score2 = model.test(xbatch, tree, lr=lr, reselect_num=reselect)
except:
ori_sim = similarity(smiles, ori_smiles)
return score1, score1, atomnum, smiles, 1.0, ori_sim, 0
if smiles == new_smiles:
s = "iter: %d sim: 0.00 ori_sim: 0.00 imp: 0.00 cannot decode\n" % (iternum)
ori_sim = similarity(smiles, ori_smiles)
else:
ori_sim = similarity(new_smiles, ori_smiles)
if reselect == 0:
s = "iter: %d sim: %.2f ori_sim: %.4f imp: %.2f decode molecule %s\n" % (iternum, sim, ori_sim, score2-score1, new_smiles)
elif reselect == 1:
s = "iter: %d sim: %.2f ori_sim: %.4f imp: %.2f decode molecule %s reselect\n" % (iternum, sim, ori_sim, score2-score1, new_smiles)
output.write(s)
print(s)
return score1, score2, atomnum, new_smiles, sim, ori_sim, reselect
def predict(smiles,
lr,
vocab,
avocab,
reselect,
ori_smiles,
iternum,
output,
prop="logp",
sim_type="binary"):
mol = Chem.MolFromSmiles(smiles)
atomnum = mol.GetNumAtoms()
tree = get_tree(smiles)
score1 = get_prop(smiles, prop=prop)
try:
xbatch = MolTree.tensorize([tree], vocab, avocab, target=False)
new_smiles, sim, reselect, score11, score2 = model.test(
xbatch, tree, reselect_num=reselect, prop=prop, sim_type=sim_type)
except Exception as e:
print(e)
print("cannot process molecule %s at iteration %d" % (smiles, iternum))
return score1, score1, atomnum, smiles, 1.0, 0.0, 0
#except:
# ori_sim = similarity(smiles, ori_smiles)
# return score1, score1, atomnum, smiles, 1.0, ori_sim, 0
if smiles == new_smiles:
s = "iter: %d sim: 0.00 ori_sim: 0.00 imp: 0.00 cannot decode\n" % (
iternum)
ori_sim = similarity(smiles, ori_smiles, sim_type=sim_type)
else:
ori_sim = similarity(new_smiles, ori_smiles, sim_type=sim_type)
if reselect == 0:
s = "iter: %d sim: %.2f ori_sim: %.4f prop1: %.2f prop2: %.2f imp: %.2f decode molecule %s\n" % (
iternum, sim, ori_sim, score1, score2, score2 - score1,
new_smiles)
elif reselect == 1:
s = "iter: %d sim: %.2f ori_sim: %.4f prop1: %.2f prop2: %.2f imp: %.2f decode molecule %s reselect\n" % (
iternum, sim, ori_sim, score1, score2, score2 - score1,
new_smiles)
output.write(s)
print(s)
return score1, score2, atomnum, new_smiles, sim, ori_sim, reselect
def predict(smiles, model, vocab, avocab, reselect, ori_smiles, iternum, prop="logp"):
mol = Chem.MolFromSmiles(smiles)
atomnum1 = mol.GetNumAtoms()
tree = get_tree(smiles)
score1 = get_prop(smiles, prop=prop)
try:
xbatch = MolTree.tensorize([tree], vocab, avocab, target=False)
new_smiles, sim, reselect, score11, score2 = model.test(xbatch, tree, reselect_num=reselect, prop=prop)
except:
ori_sim = similarity(smiles, ori_smiles, "binary")
result = [smiles, smiles, 1.0, ori_sim, score1, score1, atomnum1, atomnum1]
return result
if smiles == new_smiles:
ori_sim = similarity(smiles, ori_smiles, "binary")
else:
ori_sim = similarity(new_smiles, ori_smiles, "binary")
atomnum2 = Chem.MolFromSmiles(new_smiles).GetNumAtoms()
result = [smiles, new_smiles, sim, ori_sim, score1, score2, atomnum1, atomnum2]
return result
