🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

I am on the academic job market this year! My research advances probabilistic machine learning and its application to biology. I'm looking for faculty positions in stats/CS/applied math and in bio departments. Academic website: eweinstein.github.io

Continuous evolution of user-defined genes at 1 million times the genomic mutation rate - out today in Science, and my first authorship with my new name ✨It is nice to get reacquainted with you, I am Aviv 👋 science.org/doi/10.1126/sc…

Designing proteins is all fun and games, and yes, I believe sequence-based models do it better. 😅 BUT, at the end of the day, it only matters if we can actually have a meaningful impact with the proteins we design. And so I am SUPER EXCITED to show our new collaborative data on

Experimental kcat and KM measurements for hundreds of naturally variants of adenylate kinase. - thermophilic enzymes are not slower than mesophilic! - general kcat/KM predictors are bad and easily beaten by models trained on this specific dataset!

There’s more to life than protein folding. Today, in STAT, I discuss why AlphaFold isn’t the answer to everything — and what it will take to make AI in biology more real.

"Like, make your algorithms better, your models better. You do have enough data — if you were innovative enough on your algorithm side.” endpts.com/isomorphic-lab…

I’m excited to co-host the new #AIxBio conference alongside Žiga Avsec, Noelia Ferruz, Patrick Hsu, Ben Lehner, mary jane, Debora Marks, Tingying Peng, @CarolineUhlerat at Wellcome Genome Campus/ Wellcome Sanger Institute! We’ll focus on modellingz and designing DNA, RNA, proteins, and cells, as well as

What's better than 1 deep mutational scanning (DMS) library? 2! In a new pre-print Brittney Thornton and Rachel F Weissman et al. map the mutational landscape of ISDra2 TnpB protein and reRNA and leverage these datasets to engineer highly active variants (1/9)

Maybe Debora Marks lab can be replaced - I’m excited!

I love ProteinGym but I think it may not be ideal to observe scaling trend. Cuz most of the datasets are highly correlated with number of mutation. I just computed correlation of DMS score to no. mutations for assays with mutation depth ≥ 2 (N=69) and it’s mean 0.378,

1/ We're dedicating $100M to support American scientists facing funding cuts through the Lux Science Helpline, an expansion of our Lux Labs program. To compete in the future, innovation must be funded 🧪💡

Can AI enable safe vaccines at scale that last? Can we anticipate immune response? We tested this .. See cell.com/immunity/fullt… and hms.harvard.edu/news/building-… And big thx to CEPI for funding

Great work Ruben!

We automated systematic reviews using gpt-4.1 and o3-mini ! Our platform (otto-SR) beat humans at all tasks and conducted 12 years of systematic review research in just two days. We also show how otto-SR can be used in the real world to rapidly update clinical guidelines 🧵

Can we re-make proteins to do what we want them to? Maybe only if we learn from evolution intelligently?

Go for the 4th dimension at the same time. (Pun intended)

Amazing that you are doing this!! THANK YOU

RNA, RNA, RNA biorxiv.org/content/10.110… Been a long time goal of Debora Marks.bsky.social to help RNA sequence —> function mapping a million years ago we tried sciencedirect.com/science/articl… Now total refresh for our new world, led by Rohit Arora and Murphy Angelo for seeing this

Save the date! Machine Learning for Drug Discovery (MLDD) is happening soon on Monday 30 June, 2025. MLDD aims to bring together ML for drug discovery experts, innovators, and enthusiasts from the machine learning, biotechnology and drug discovery domains in London, UK to