You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Traceback (most recent call last):
File "./chemprop/scaffold_split.py", line 70, in <module>
create_crossval_splits()
File "./chemprop/scaffold_split.py", line 64, in create_crossval_splits
fold_indices = split_indices(all_indices, num_folds=5, data=data)
File "./chemprop/scaffold_split.py", line 24, in split_indices
scaffold_to_indices = scaffold_to_smiles(data.mols(), use_indices=True)
File "./chemprop/chemprop/data/scaffold.py", line 41, in scaffold_to_smiles
scaffold = generate_scaffold(mol)
File "./chemprop/chemprop/data/scaffold.py", line 24, in generate_scaffold
scaffold = MurckoScaffold.MurckoScaffoldSmiles(mol=mol, includeChirality=include_chirality)
File "/home/.conda/envs/chemprop/lib/python3.9/site-packages/rdkit/Chem/Scaffolds/MurckoScaffold.py", line 109, in MurckoScaffoldSmiles
scaffold = GetScaffoldForMol(mol)
File "/home/.conda/envs/chemprop/lib/python3.9/site-packages/rdkit/Chem/Scaffolds/MurckoScaffold.py", line 73, in GetScaffoldForMol
res = Chem.MurckoDecompose(mol)
Boost.Python.ArgumentError: Python argument types in
rdkit.Chem.rdmolops.MurckoDecompose(list)
did not match C++ signature:
MurckoDecompose(RDKit::ROMol mol)
There was a similar issue: #98
Do I use it correctly or is it a bug?
Thank you!
The text was updated successfully, but these errors were encountered:
Thanks for reporting, this is another bug that must have been missed when we introduced multiple molecules input. I will look into and correct it shortly, but for your script, it should be sufficient to do:
Hello,
I have an issue with
scaffold_to_smiles
function. The ChemProp version is from 31 March 2021.I use it in a similar way like in https://github.com/chemprop/chemprop/blob/master/scripts/create_crossval_splits.py
and call it this way (
data
isMoleculeDataset
here) :and I get an error:
There was a similar issue: #98
Do I use it correctly or is it a bug?
Thank you!
The text was updated successfully, but these errors were encountered: