DeepChem Minutes
India/Asia/Pacific Call
Date: November 4th, 2021
Attendees: Bharath, Peter
Summary:
Bharath worked with Arun this week on moving the release closer to getting out the door. They decided to upgrade the dc.dock to using the Python vina backend.
Peter was working on OpenMM this week and doesn’t have much to report.
Bharath mentioned TensorFlow 2.7 has come out
Americas/Europe/Africa/Middle East
Date: November 5th, 2021
Attendees: Bharath, Arun, Delora, Tony, Sai
Summary:
Delora is finishing a postdoc with a background in chemistry and mathematics and is working to enter the AI drug discovery space and is interested to connect with DeepChem.
Bharath gave the same update as at the last meeting.
Arun has been working on fixing the DeepChem docking infrastructure. He’s been shifting dc.dock to use the Python Autodock Vina framework instead of the executable.
Tony has been working on implementing the multiple sequence alignment featurizer in DeepChem porting it from PNet. Tony plans to work on some small PRs to gain experience.
Delora has put up an issue #2739 raising an issue trying to fix a bug in the ChemBERTa tutorial PR. Delora has been working on a new small tutorial adding improved masking for ChemBERTa.
Sai has been working on a new tutorial for MolGAN but was running into an issue where the SMILES weren’t being featurized for QM9 and asked if we could look at a smaller dataset. Bharath suggested Tox21/Lip
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.