Ankur Parikh's Avatar

Ankur Parikh

@ankur-parikh.bsky.social

Staff Research Scientist at Google DeepMind. ML for Biology and Chemistry (Previously NLP). Former adjunct assistant prof at NYU. All opinions my own. https://scholar.google.com/citations?user=bRpjhycAAAAJ&hl=en&oi=ao

3,257 Followers  |  411 Following  |  10 Posts  |  Joined: 15.11.2024  |  1.8778

Latest posts by ankur-parikh.bsky.social on Bluesky

Here’s the updated Computational Biology Starter Pack! Let me know if you'd like to be included.

go.bsky.app/QVPoZXp

24.11.2024 16:33 β€” πŸ‘ 175    πŸ” 77    πŸ’¬ 81    πŸ“Œ 5

i would like to be added if possible!

25.11.2024 01:59 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

New starter pack! go.bsky.app/GZ4hZzu

28.10.2024 09:43 β€” πŸ‘ 42    πŸ” 17    πŸ’¬ 6    πŸ“Œ 5

thanks!

21.11.2024 16:05 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

could I be added? Thanks :)

21.11.2024 16:00 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Preview
Out-of-Distribution Validation for Bioactivity Prediction in Drug... Recent advances in machine learning for materials science have significantly improved the prediction of novel materials. Building on these methods, we have adapted them for drug discovery...

We translated a validation strategy in Materials to Small molecules.

A key problem in cross-validation is splitting of data. Here we propose a step-forward CV. People are used to scaffold splits, time splits etc. but these all have limitations.

21.11.2024 02:04 β€” πŸ‘ 17    πŸ” 3    πŸ’¬ 1    πŸ“Œ 0
Preview
Language model-guided anticipation and discovery of unknown metabolites Despite decades of study, large parts of the mammalian metabolome remain unexplored. Mass spectrometry-based metabolomics routinely detects thousands of small molecule-associated peaks within human ti...

Thrilled to share our approach for language model-guided discovery of unknown mammalian metabolites: DeepMet. We’ve now used this approach to discover ~50 new human and mouse metabolites! www.biorxiv.org/content/10.1...

19.11.2024 15:40 β€” πŸ‘ 12    πŸ” 4    πŸ’¬ 0    πŸ“Œ 0

Two BioML starter packs now:

Pack 1: go.bsky.app/2VWBcCd
Pack 2: go.bsky.app/Bw84Hmc

DM if you want to be included (or nominate people who should be!)

18.11.2024 17:09 β€” πŸ‘ 119    πŸ” 56    πŸ’¬ 10    πŸ“Œ 11

A starter pack for anyone interested in AI & drug discovery :)

go.bsky.app/AgYHc8j

15.11.2024 00:29 β€” πŸ‘ 53    πŸ” 15    πŸ’¬ 29    πŸ“Œ 2

thanks!

19.11.2024 13:43 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

hi! i would like to be added if possible

17.11.2024 19:40 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

thanks!

17.11.2024 18:53 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

hi! could you add me :)

17.11.2024 18:51 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

I'm making a list of AI for Science researchers on bluesky β€” let me know if I missed you / if you'd like to join!

go.bsky.app/AcP9Lix

10.11.2024 00:11 β€” πŸ‘ 246    πŸ” 90    πŸ’¬ 160    πŸ“Œ 5

This pack is now up to 67 people, broadly in AI and advanced data for science. Follow along, and forward me others who should be there! πŸ¦‹πŸ¦‹

go.bsky.app/JeFdryY

16.11.2024 16:32 β€” πŸ‘ 45    πŸ” 15    πŸ’¬ 22    πŸ“Œ 0

We got an πŸ₯‚ Outstanding Paper Award!! Cannot be more grateful πŸ₯Ή This is super validating for our long pursuit of computational work on QUD.

Congrats to the amazing @yatingwu.bsky.social, Ritika Mangla, Alex Dimakis, @gregdnlp.bsky.social

15.11.2024 13:12 β€” πŸ‘ 60    πŸ” 9    πŸ’¬ 1    πŸ“Œ 0

thanks!

16.11.2024 04:20 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

would like to be added :)

16.11.2024 04:08 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Evo, a 7-billion-parameter genomic foundation model, learns biological complexity from individual nucleotides to whole genomes.

Evo, a 7-billion-parameter genomic foundation model, learns biological complexity from individual nucleotides to whole genomes.

Pretraining a genomic foundation model across prokaryotic life.

Pretraining a genomic foundation model across prokaryotic life.

Fine-tuning on CRISPR-Cas sequences enables generative design of protein-RNA complexes.

Fine-tuning on CRISPR-Cas sequences enables generative design of protein-RNA complexes.

Fig. 4. Fine-tuning on IS200/IS605 sequences enables generative design of transposable biological systems.

Fig. 4. Fine-tuning on IS200/IS605 sequences enables generative design of transposable biological systems.

Evo: A genomic language model of prokaryote genomes generates functional cas9 proteins and transposons.

@brianhiestand.bsky.social

www.science.org/doi/10.1126/...

14.11.2024 20:53 β€” πŸ‘ 59    πŸ” 27    πŸ’¬ 0    πŸ“Œ 1

would like to be on this list as well!

16.11.2024 00:50 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

@ankur-parikh is following 19 prominent accounts