KekulizeException: Can't kekulize mol.

[RudrajitDawn]

Hi, I am trying to execute the scripts/preprocess.py and getting this error.

"""
Traceback (most recent call last):
File "/usr/lib/python3.7/multiprocessing/pool.py", line 121, in worker
result = (True, func(*args, **kwds))
File "/usr/lib/python3.7/multiprocessing/pool.py", line 44, in mapstar
return list(map(*args))
File "", line 28, in tensorize_pair
mol_tree0 = tensorize(smiles_pair[0], assm=False)
File "", line 12, in tensorize
mol_tree = MolTree(smiles)
File "", line 95, in init
cmol = get_clique_mol(self.mol, c)
File "", line 68, in get_clique_mol
smiles = Chem.MolFragmentToSmiles(mol, atoms, kekuleSmiles=True)
rdkit.Chem.rdchem.KekulizeException: Can't kekulize mol. Unkekulized atoms: 1 2 3 4 26
"""

The above exception was the direct cause of the following exception:

KekulizeException Traceback (most recent call last)
in ()
48 data = [line.strip("\r\n ").split()[:2] for line in f]
49
---> 50 all_data = pool.map(tensorize_pair, data)
51 num_splits = len(data) / 10000
52

1 frames
/usr/lib/python3.7/multiprocessing/pool.py in get(self, timeout)
655 return self._value
656 else:
--> 657 raise self._value
658
659 def _set(self, i, obj):

KekulizeException: Can't kekulize mol. Unkekulized atoms: 1 2 3 4 26

[xinyangATK]

Have you solved it? I have also met this problem and I skip these molecules but failed in another error:

Original Traceback (most recent call last):
  File "/home/ubuntu/anaconda3/envs/lxy/lib/python3.9/site-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop
    data = fetcher.fetch(index)
  File "/home/ubuntu/anaconda3/envs/lxy/lib/python3.9/site-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/home/ubuntu/anaconda3/envs/lxy/lib/python3.9/site-packages/torch/utils/data/_utils/fetch.py", line 49, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/mnt/507aa612-08ac-464f-84b1-98511af354c1/LXY/iclr19-graph2graph/fast_jtnn/datautils.py", line 93, in __getitem__
    return tensorize(batch0, self.vocab, assm=False), tensorize(batch1, self.vocab, assm=self.y_assm)
  File "/mnt/507aa612-08ac-464f-84b1-98511af354c1/LXY/iclr19-graph2graph/fast_jtnn/datautils.py", line 109, in tensorize
    set_batch_nodeID(tree_batch, vocab)
  File "/mnt/507aa612-08ac-464f-84b1-98511af354c1/LXY/iclr19-graph2graph/fast_jtnn/datautils.py", line 136, in set_batch_nodeID
    node.wid = vocab.get_index(node.smiles)
  File "/mnt/507aa612-08ac-464f-84b1-98511af354c1/LXY/iclr19-graph2graph/fast_jtnn/mol_tree.py", line 18, in get_index
    return self.vmap[smiles]
KeyError: 'C1=CNN=C1'

Does this KetError mean that I should re-generate vocab of QED dataset?

[RudrajitDawn]

I made some working version of the code here: graph2graph_molecule

[xinyangATK]

I made some working version of the code here: graph2graph_molecule

Are you just replace the code

all_data = pool.map(tensorize_pair, data)

with

process_map(tensorize_pair, data, max_workers=16, chunksize=1)

This way indeed works for the former problem, but I still have the problem with KeyError that I mentioned above

[RudrajitDawn]

You can create a new issue with the new problem. I think the key should be in the "vocab.txt" . So, if it is not there, it may be manually added or the vocabulary can be extracted from list of SMILES strings using "mol_tree.py"

[zkysfls]

Have you solved it? I have also met this problem and I skip these molecules but failed in another error:

Original Traceback (most recent call last):
  File "/home/ubuntu/anaconda3/envs/lxy/lib/python3.9/site-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop
    data = fetcher.fetch(index)
  File "/home/ubuntu/anaconda3/envs/lxy/lib/python3.9/site-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/home/ubuntu/anaconda3/envs/lxy/lib/python3.9/site-packages/torch/utils/data/_utils/fetch.py", line 49, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/mnt/507aa612-08ac-464f-84b1-98511af354c1/LXY/iclr19-graph2graph/fast_jtnn/datautils.py", line 93, in __getitem__
    return tensorize(batch0, self.vocab, assm=False), tensorize(batch1, self.vocab, assm=self.y_assm)
  File "/mnt/507aa612-08ac-464f-84b1-98511af354c1/LXY/iclr19-graph2graph/fast_jtnn/datautils.py", line 109, in tensorize
    set_batch_nodeID(tree_batch, vocab)
  File "/mnt/507aa612-08ac-464f-84b1-98511af354c1/LXY/iclr19-graph2graph/fast_jtnn/datautils.py", line 136, in set_batch_nodeID
    node.wid = vocab.get_index(node.smiles)
  File "/mnt/507aa612-08ac-464f-84b1-98511af354c1/LXY/iclr19-graph2graph/fast_jtnn/mol_tree.py", line 18, in get_index
    return self.vmap[smiles]
KeyError: 'C1=CNN=C1'

Does this KetError mean that I should re-generate vocab of QED dataset?

Hi! I want to know have you solved this problem?

[RudrajitDawn]

I forgot whether I solved it or not.