John Kevin Cava

4th Year CS PhD @ASU @ASUBiodesign | Machine Learning for Molecular Dynamics | Scientific ML | Proteins | Structural Biology

[Abhishek Singharoy @abhisekhsingha1]

Out in @CellSystemsCP, Method to find peptide binders from human proteome in 7 seconds !
@EricWil39327976's best work :)
🙏@diegochowell

Access: https://t.co/chkgVbsmIP

Release: https://t.co/QXqBX6FsvR

Paper: https://t.co/xHNsKx4fEi

@ASUBiodesign @MayoClinic @MountSinaiNYC

[John Kevin Cava @john_kevin_cava]

To internship or not to internship next summer? 🤔

[John Kevin Cava @john_kevin_cava]

Happy to present "Latent Sequence Generation of Steered Molecular Dynamics" as a poster in the #Physics4ML workshop at #ICLR2023 https://t.co/CQr1ienFCA

[Kevin K. Yang 楊凱筌 @KevinKaichuang]

Use a VAE to predict atomic coordinates from coarse-grained coordinates (backmapping) for any protein system.

@SoojungYang2 @RGBLabMIT

https://t.co/cQoLhxCUII

[John Kevin Cava @john_kevin_cava]

@m2saxon Might as well add "doing a NLP tutorial video" 😛

[John Kevin Cava @john_kevin_cava]

Extremely excited to be in person at #NeurIPS2022 . I will be here until Dec 3rd. Anyone interested in SciML, applications to Molecular Biology, DM me and lets have a chat!

[Nicholas Ho @eigenNick]

Procrastinated a bit much on making this tweet, but I'm happy to say that our paper on using RL + MD to learn pathways was accepted to @workshopmlsb! Happy to talk about it, what worked, what didn't, and the next steps!

[John Kevin Cava @john_kevin_cava]

Happy to announce that our paper on learning free energy pathways has been accepted to MLSB at NeurIPS 2022! @workshopmlsb

[John Kevin Cava @john_kevin_cava]

Learning Free Energy Pathways through Reinforcement Learning of Adaptive Steered Molecular Dynamics https://t.co/3VoZjkw7tQ

[MLSB (in San Diego + Copenhagen) @workshopmlsb]

The MLSB 2022 Call for Papers is up on our website! This year, we're looking for 4-5 page short papers.

Submission deadline is Thursday, September 22nd, 2022 AoE.

Check out the website (https://t.co/JbgU0dpYuw) for more info and come to New Orleans in December!

[John Kevin Cava @john_kevin_cava]

Years after being told my interests don't line up with planning, I literally can't believe I am doing planning for Molecular Dynamics. 🤣

[AI at Meta @AIatMeta]

Learn more about Meta AI’s newest inverse protein folding model: ESM-IF1, developed by Meta researchers and team @chloehsu0 @adamlerer @BrianHie @TomSercu @robert_verkuil @jason_liu2 and @ebetica Check it out: 👇

[Pavan Turaga @pturaga1]

Thanksgiving update. #ML4Molecules workshop paper @NeurIPSConf By @john_kevin_cava @JhnVant @Ankita1Shukla @abhisekhsingha1 Nicholas Ho, and Ross Maciejewski. “Towards Conditional Generation of Minimal Action Potential Pathways for Molecular Dynamics". Happy thanksgiving !!

[Sergey Ovchinnikov @sokrypton]

End-to-end learning of multiple sequence alignments with differentiable Smith-Waterman
https://t.co/4KKHCc3OZ0
A fun collaboration with Samantha Petti, Nicholas Bhattacharya, @proteinrosh, @JustasDauparas, @countablyfinite, @keitokiddo, @srush_nlp & @pkoo562 (1/8)

[Ting Chen @tingchenai]

Have you wondered why object detection, unlike classification, has so many sophisticated algorithms?

With Pix2Seq (https://t.co/ygsG3aAIbG), we simply cast object detection as a language modeling task conditioned on pixels!

(with @srbhsxn, Lala Li, @fleet_dj, @geoffreyhinton)

[Andrew White 🐦‍⬛ @andrewwhite01]

Sequence vs Graph, which representation is better? Obviously GNNs can predict per-node, while sequences can't. But what about per-graph properties? We can now bijectively encode graphs as sequences, so it's past time that we answer this for AI in chemistry.

[Abhishek Singharoy @abhisekhsingha1]

Many thanks to our members @JhnVant @EricWil39327976 @john_kevin_cava @eigenNick @ChitrakGupta2 @17Dsarkar @mrinal1989 @sumit15_ @estreitwieser @FathimaTDoole @ChunKitChan17 who work 24x7 to build a Research program !! Onto mid-tenure review with @ASU_SMS :)

[Stat.ML Papers @StatMLPapers]

Inverse design of 3d molecular structures with conditional generative neural networks. (arXiv:2109.04824v1 [cs.LG]) https://t.co/jQwp8lMYmW

[Li Li @leeley18]

Physics computation itself acts as a regularizer while training the model embedded in it. Our results serve as proof-of-principle to smear the boundary between physics computation and ML. We are glad to share our work with you on @PhysRevLett #openaccess https://t.co/yQLKGvMF88

[Chaitanya K. Joshi @chaitjo]

AlphaFold2 seems to be:

- 3D equivariant Transformer which "builds physical & geometric notions into the architecture": https://t.co/fyRwn09zWD (@FabianFuchsML)

- Iteratively predict 'distograms' which are used to update the underlying message-passing graph for the Transformer.