DeepChem Minutes 7/22/2021

DeepChem Minutes

India/Asia/Pacific Call

Date: July 22nd, 2021

Attendees: Bharath, Ashwin, Peter, Alana

Summary:

Bharath has mainly been working with GSoC work and has submitted everyone’s evaluations.

Ashwin has been working on updating the reaction split transformer to respond to PRs and hopes to get it done by today. Ashwin is planning to work on the tokenizer for the USPTO dataset.

Alana is working towards tokenizing FASTA files with BERT tokenizer and is debugging some of the issues that have cropped up.

Peter put up a PR making a fix to the metric handling for defaults.

Americas/Europe/Africa/Middle East

India/Asia/Pacific Call

Date: July 23rd, 2021

Attendees: Bharath, Seyone, Vignesh, David

Summary:

Bharath gave the same update as in the last meeting.

Seyone has been working on figuring out how to get RobertaFeaturizer merged into DeepChem. He’s made progress on the mypy error but still has a couple of issues.

Vignesh has been working on the evaluation code for JaxModel. The PR is now ready for review again.

David has been working to get his tutorial for protein melting point modeling up and running. He still has a couple errors with KerasModel.

Atreya has a large PR up for molecular attention transformer layers up. He has a second PR coming through for the remaining layers and then will start on the PR for the MAT model itself.

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.