Date: July 15th, 2021
Attendees: Bharath, Ashwin, Vignesh, Arun, Alana
Summary: Bharath has mainly been working with GSoC work and has submitted everyone’s evaluations.
Ashwin has been working with getting the new reaction transformer to process the USPTO dataset and has mostly gotten this functional.
Vignesh has been working on the JaxModel evaluation method. There’s one small blocker with random number handling in Haiku which becomes important for dropout and is working on uncertainty.
Arun has made a PR improving the documentation for contributions and is now working on a tutorial for lattice convolutions
Alana has been working on the tokenizer/BertFeaturizer and is working on it in parallel with the FASTALoader.
Date: July 16th, 2021
Attendees: Bharath, Peter, Atreya, Seyone
Summary: Bharath gave the same update as in the last meeting.
Atreya just sent out his PR for the first MAT layer PR and added some more documentation in a separate PR.
Peter has worked on a PR to do some cleanup in the metrics class where there was some undocumented behavior. Peter has also worked on a second PR to fix some of the CI failures caused by the latest pandas version.
Seyone will try to work on the CI issues with RobertaFeaturizer this weekend and hopes to get that unblocked.
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.