DeepChem Minutes 6/2/2022

DeepChem Minutes

India/Asia/Pacific Call

Date: June 2nd, 2022

Attendees: Bharath, Ashish, Zaky

Summary:

Bharath has been working with GSoC students to review their PRs and get first code changes merged in.

Zaky has been busy with other work but should have more time to contribute.

Ashish has found a tutorial on red blood cell counting that he has been working through.

Americas/Europe/Africa/Middle East

Date: June 3rd, 2022

Attendees: Bharath, Tony, Arun

Summary:

Bharath gave the same update as at the previous call.

Aryan worked on the helper functions for DMPNN featurizer and made a PR regarding the same.

Abhishek worked with GSOC student to discuss details around the plan for GSOC, she proposed a couple of PRs building on top of her previous work. She is getting started with initial PRs.

Tony looked into some of the CI problems to identify why some of the tests are constantly failing. The rl.A2C implementation seems to be bugged, it will need some attention. He is going to look into some of the other bugs to see if there’s some easy fixes. Besides that, he met with Shai and Peter on the ferminet project which has shown good early progress.

Arun worked on debugging CI errors - there were new failures due to tensorboard.

DeepChem Bioinformatics Call

Date: June 6th, 2022

Attendees: Bharath, Saurav, Paulina, Stanley, Ashish

Summary:

Bharath was busy with other work and didn’t do too much on the deepbio end.

Paulina brought up the need to expand DeepChem’s design language to reflect new efforts such as DeepBio / DeepPhysics / DeepScience. She also reminded everyone of Arun’s discussion on adding datasets for DeepBio. She will add a comment to this and we talked about renaming MolNet.

Ashish went through the deepchem tutorials and explored a little bit about the github resource he found for cell classification & counting for blood cells.

Bharath shared https://www.science.org/content/blog-post/computational-happiness-delayed

and https://www.biorxiv.org/content/10.1101/2021.11.10.468064v1.full

Ashish mentioned https://pubs.acs.org/doi/10.1021/acs.jmedchem.2c00487.

We discussed https://moalquraishi.wordpress.com/2021/07/25/the-alphafold2-method-paper-a-fount-of-good-ideas/#more-1384.

Saurav shared https://www.biorxiv.org/content/10.1101/840173v1.

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.