DeepChem Minutes
India/Asia/Pacific Call
Date: March 17th, 2022
Attendees: Bharath, Peter, Alana
Summary:
Bharath has been mainly working with students this week.
Peter has been working on OpenMM mainly.
Americas/Europe/Africa/Middle East
Date: March 18th, 2022
Attendees: Bharath, Princy, Aryan, Tony, Arun, Abhishek, Neeraj
Summary:
Bharath gave the same update as at the last call.
Aryan is working on D-MPNN for DeepChem.
Princy has addressed review comments on her PR.
Tony tried to resubmit his PR for sequence utilities, but it looks like the CI isn’t running.
Arun has been working on diffusion models and score-based models and has been implementing a paper on crystal diffusional variational autoencoders. Arun also discussed migrating DeepChem’s code base to follow 4-space instead of 2-space indent. Bharath suggested putting up a forum post to take the discussion further. The forum post can be found here.
Abhishek this week tried training a few DeepChem pytorch models and tried a few models in a distributed setting with 8 or 16 GPUs. There are some issues with distributed training processing that he’s working on figuring out.
Stanley is interested in the new bioinformatics working group meetings and looking forward to the discussion on protein modeling.
Neeraj is interested in working on pytorch porting.
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 X.Y@gmail.com, where X=bharath, Y=ramsundar.