Closed mufeili closed 3 years ago
@rbharath Thank you for the review. I think you can go ahead and merge it. For the follow-up PRs, do we now have an overview of all the datasets and their statistics, including the new ones in MoleculeNet v2?
Also copy @miaecle in case you have bandwidth to take a look.
@mufeili The list of datasets on https://deepchem.readthedocs.io/en/latest/api_reference/moleculenet.html is probably pretty representative of MoleculeNet v2 (although we might have a few more datasets trickling in before we made the cut). We don't have a nice table with statistics though (which would be nice to have!)
Going to go ahead and merge this in (please still free to comment @miaecle if you have bandwidth!)
@rbharath This PR is for a submission of GCN with MolGraphConv featurization on BACE. It includes:
It depends on PR #2328 in DeepChem for a bug fix.
We also need to fix a warning related to DGL in DeepChem.