Date: January 13th, 2022
Attendees: Bharath, Arun, Peter, Ashwin
Arun and Bharath worked on getting the 2.6.0 release out the door.
Peter put up a PR to get numpy 1.22 working. It took a good bit of work, so Peter hopes that it won’t be repeated for every numpy release. Optimistically, Peter hopes it’s an artifact of the transition to typing.
Ashwin has been mostly busy but is restarting work on the retrosynthesis models. He hopes to get those PRs out soon. He noted he’s having some installation issues with DeepChem. Bharath suggested taking a look at https://deepchem.readthedocs.io/en/latest/get_started/installation.html#from-source-lightweight-guide.
Date: January 14th, 2022
Attendees: Bharath, Tony, Aryan, Isuru, Sai, Abhishek, Atreya
Aryan is a 2nd engineering BTech mechanical engineering student who has been working on deep learning for the last 6 months.
Isuru is an undergrad at Cornell who has started working on deep learning over the last year.
Bharath gave the same update as at the last meeting.
Sai pushed his updates to the MolGAN tutorial.
Tony is working on implementing a multisequence alignment featurizer in DeepChem.
Abhishek worked with one of his students on an initial PyTorch Lightning module. There are some minor mismatches with the TorchModel code that would be good to discuss on the PR.
Atreya has been busy for the last few months but is looking to get back into DeepChem. Atreya mentioned that he wasn’t able to find the DMPNN implementation in the https://github.com/chemprop/chemprop repo any longer. Bharath suggested emailing the authors.
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.