def decode_test():
wrong = 0
for tot, s in enumerate(sys.stdin):
s = s.split()[0]
tree = MolTree(s)
tree.recover()
cur_mol = copy_edit_mol(tree.nodes[0].mol)
global_amap = [{}] + [{} for node in tree.nodes]
global_amap[1] = {
atom.GetIdx(): atom.GetIdx()
for atom in cur_mol.GetAtoms()
}
dfs_assemble(cur_mol, global_amap, [], tree.nodes[0], None)
cur_mol = cur_mol.GetMol()
cur_mol = Chem.MolFromSmiles(Chem.MolToSmiles(cur_mol))
set_atommap(cur_mol)
dec_smiles = Chem.MolToSmiles(cur_mol)
gold_smiles = Chem.MolToSmiles(Chem.MolFromSmiles(s))
if gold_smiles != dec_smiles:
print gold_smiles, dec_smiles
wrong += 1
print wrong, tot + 1
def __getitem__(self, item):
smiles = self.data[item]
mol_tree = MolTree(smiles)
if mol_tree.mol is None:
return None
mol_tree.recover()
mol_tree.assemble()
return mol_tree
def __getitem__(self, idx):
smiles = self.data[idx]
mol_tree = MolTree(smiles)
#print(len(smiles))
mol_tree.recover()
mol_tree.assemble()
return mol_tree
def count():
cnt, n = 0, 0
for s in sys.stdin:
s = s.split()[0]
tree = MolTree(s)
tree.recover()
tree.assemble()
for node in tree.nodes:
cnt += len(node.cands)
n += len(tree.nodes)
def optimize(self, smiles, sim_cutoff, lr=2.0, num_iter=20):
mol_tree = MolTree(smiles)
mol_tree.recover()
_, tree_vec, mol_vec = self.encode([mol_tree])
mol = Chem.MolFromSmiles(smiles)
fp1 = AllChem.GetMorganFingerprint(mol, 2)
tree_mean = self.T_mean(tree_vec)
# Following Mueller et al.
tree_log_var = -torch.abs(self.T_var(tree_vec))
mol_mean = self.G_mean(mol_vec)
# Following Mueller et al.
mol_log_var = -torch.abs(self.G_var(mol_vec))
mean = torch.cat([tree_mean, mol_mean], dim=1)
log_var = torch.cat([tree_log_var, mol_log_var], dim=1)
cur_vec = create_var(mean.data, True)
visited = []
for _ in xrange(num_iter):
prop_val = self.propNN(cur_vec).squeeze()
grad = torch.autograd.grad(prop_val, cur_vec)[0]
cur_vec = cur_vec.data + lr * grad.data
cur_vec = create_var(cur_vec, True)
visited.append(cur_vec)
l, r = 0, num_iter - 1
while l < r - 1:
mid = (l + r) / 2
new_vec = visited[mid]
tree_vec, mol_vec = torch.chunk(new_vec, 2, dim=1)
new_smiles = self.decode(tree_vec, mol_vec, prob_decode=False)
if new_smiles is None:
r = mid - 1
continue
new_mol = Chem.MolFromSmiles(new_smiles)
fp2 = AllChem.GetMorganFingerprint(new_mol, 2)
sim = DataStructs.TanimotoSimilarity(fp1, fp2)
if sim < sim_cutoff:
r = mid - 1
else:
l = mid
tree_vec, mol_vec = torch.chunk(visited[l], 2, dim=1)
new_smiles = self.decode(tree_vec, mol_vec, prob_decode=False)
if new_smiles is None:
return smiles, 1.0
new_mol = Chem.MolFromSmiles(new_smiles)
fp2 = AllChem.GetMorganFingerprint(new_mol, 2)
sim = DataStructs.TanimotoSimilarity(fp1, fp2)
if sim >= sim_cutoff:
return new_smiles, sim
else:
return smiles, 1.0
def enum_test():
for s in sys.stdin:
s = s.split()[0]
tree = MolTree(s)
tree.recover()
tree.assemble()
for node in tree.nodes:
if node.label not in node.cands:
print tree.smiles
print node.smiles, [x.smiles for x in node.neighbors]
print node.label, len(node.cands)
def tensorize(smiles, assm=True):
mol_tree = MolTree(smiles)
mol_tree.recover()
if assm:
mol_tree.assemble()
for node in mol_tree.nodes:
if node.label not in node.cands:
node.cands.append(node.label)
del mol_tree.mol
for node in mol_tree.nodes:
del node.mol
return mol_tree
def reconstruct(self, smiles, prob_decode=False):
mol_tree = MolTree(smiles)
mol_tree.recover()
_,tree_vec,mol_vec = self.encode([mol_tree])
tree_mean = self.T_mean(tree_vec)
tree_log_var = -torch.abs(self.T_var(tree_vec)) #Following Mueller et al.
mol_mean = self.G_mean(mol_vec)
mol_log_var = -torch.abs(self.G_var(mol_vec)) #Following Mueller et al.
epsilon = create_var(torch.randn(1, self.latent_size / 2), False)
tree_vec = tree_mean + torch.exp(tree_log_var / 2) * epsilon
epsilon = create_var(torch.randn(1, self.latent_size / 2), False)
mol_vec = mol_mean + torch.exp(mol_log_var / 2) * epsilon
return self.decode(tree_vec, mol_vec, prob_decode)
def reconstruct1(self, smiles, prob_decode=False):
mol_tree = MolTree(smiles)
mol_tree.recover()
# print("tree olusturuldu")
_, tree_vec, mol_vec = self.encode([mol_tree])
# print("encode edildi")
tree_mean = self.T_mean(tree_vec)
tree_log_var = -torch.abs(self.T_var(tree_vec)) # Following Mueller et al.
mol_mean = self.G_mean(mol_vec)
mol_log_var = -torch.abs(self.G_var(mol_vec)) # Following Mueller et al.
epsilon = create_var(torch.randn(1, (int)(self.latent_size / 2)), False)
tree_vec = tree_mean + torch.exp(tree_log_var / 2) * epsilon
epsilon = create_var(torch.randn(1, (int)(self.latent_size / 2)), False)
mol_vec = mol_mean + torch.exp(mol_log_var / 2) * epsilon
return tree_vec,mol_vec,prob_decode
def recon_eval(self, smiles):
mol_tree = MolTree(smiles)
mol_tree.recover()
_,tree_vec,mol_vec = self.encode([mol_tree])
tree_mean = self.T_mean(tree_vec)
tree_log_var = -torch.abs(self.T_var(tree_vec)) #Following Mueller et al.
mol_mean = self.G_mean(mol_vec)
mol_log_var = -torch.abs(self.G_var(mol_vec)) #Following Mueller et al.
all_smiles = []
for i in range(10):
epsilon = create_var(torch.randn(1, (int)(self.latent_size / 2)), False)
tree_vec = tree_mean + torch.exp(tree_log_var / 2) * epsilon
epsilon = create_var(torch.randn(1, (int)(self.latent_size / 2)), False)
mol_vec = mol_mean + torch.exp(mol_log_var / 2) * epsilon
for j in range(10):
new_smiles = self.decode(tree_vec, mol_vec, prob_decode=True)
all_smiles.append(new_smiles)
return all_smiles
def reconstruct(self, smiles, prob_decode=False,DataFrame=None):
mol_tree = MolTree(smiles)
mol_tree.recover()
#print("tree olusturuldu")
_,tree_vec,mol_vec = self.encode([mol_tree])
#print("encode edildi")
tree_mean = self.T_mean(tree_vec)
tree_log_var = -torch.abs(self.T_var(tree_vec)) #Following Mueller et al.
mol_mean = self.G_mean(mol_vec)
mol_log_var = -torch.abs(self.G_var(mol_vec)) #Following Mueller et al.
epsilon = create_var(torch.randn(1, (int)(self.latent_size / 2)), False)
tree_vec = tree_mean + torch.exp(tree_log_var / 2) * epsilon
epsilon = create_var(torch.randn(1, (int)(self.latent_size / 2)), False)
mol_vec = mol_mean + torch.exp(mol_log_var / 2) * epsilon
thethird=torch.cat((tree_vec, mol_vec), 1)
#print(thethird.to('cpu').data.numpy())
DataFrame.loc[smiles]=thethird.to('cpu').data.numpy()[0]
return self.decode(tree_vec, mol_vec, prob_decode)
def __getitem__(self, idx):
smiles = self.data[idx]
mol_tree = MolTree(smiles)
mol_tree.recover()
mol_tree.assemble()
return mol_tree, self.prop_data[idx]
