DeepChem Minutes 12/2/2021

DeepChem Minutes

India/Asia/Pacific Call

Date: December 2nd, 2021

Attendees: Bharath


No one else attended the call, so the meeting adjourned early.

Americas/Europe/Africa/Middle East

Date: December 3rd, 2021

Attendees: Bharath, Tony


Bharath this week was working with Arun on getting the release out the door.

Tony is working on improving the documentation, adding a section for developers to install from source. He’s also working to add top_k to the metrics for use in downstream protein modeling.

Sai has been working on the MolGAN tutorial. The first cut of the tutorial rejected many compounds from tox21 due to them being too large. Sai started looking at QM9 as a target instead but has some overfitting issues with the models.

David is working on the sparse matrix one hot featurizer. David thinks there may be potential integration issues with DiskDataset that may have to be figured out in a next step.

Joining the DeepChem Developer Calls

As a quick reminder to anyone reading along, the DeepChem developer calls are open to the public! If you’re interested in attending either or both of the calls, please send an email to, where X=bharath, Y=ramsundar.