dmlc--dgl
9df8cd3242
* Update * Update * Update * Update * Update
31 行
750 B
Python
31 行
750 B
Python
# pylint: disable=C0111, C0103, E1101, W0611, W0612
|
|
import copy
|
|
|
|
import rdkit.Chem as Chem
|
|
|
|
|
|
def get_slots(smiles):
|
|
mol = Chem.MolFromSmiles(smiles)
|
|
return [(atom.GetSymbol(), atom.GetFormalCharge(), atom.GetTotalNumHs())
|
|
for atom in mol.GetAtoms()]
|
|
|
|
|
|
class Vocab(object):
|
|
|
|
def __init__(self, smiles_list):
|
|
self.vocab = smiles_list
|
|
self.vmap = {x: i for i, x in enumerate(self.vocab)}
|
|
self.slots = [get_slots(smiles) for smiles in self.vocab]
|
|
|
|
def get_index(self, smiles):
|
|
return self.vmap[smiles]
|
|
|
|
def get_smiles(self, idx):
|
|
return self.vocab[idx]
|
|
|
|
def get_slots(self, idx):
|
|
return copy.deepcopy(self.slots[idx])
|
|
|
|
def size(self):
|
|
return len(self.vocab)
|