I'll be in Seoul next week for ICML 2026! 🇰🇷 Message me if you'd like to meet up for food, coffee, or drinks! Would love to talk all things proteins, small molecules, and biology in general 🧬

I also recently discussed the Bits to Binders competition with my co-organizers and Ron Green on the KUNGFU.AI Hidden Layers podcast! It was a very fun conversation 🤠🧬 (links below)

Clay Kosonocky@kosonocky.bsky.social · 3mo ago

I’ve been asked a few times how I got started running a worldwide protein design competition. The short answer is that I never intended to start this project at all: it just sort of happened. The more correct answer requires me to tell the origin story of the BioML Society [1/2]

I’ve been asked a few times how I got started running a worldwide protein design competition. The short answer is that I never intended to start this project at all: it just sort of happened. The more correct answer requires me to tell the origin story of the BioML Society [1/2]

Have you wondered what the wet lab success rates are for current AI-driven protein design models? Look no further! In our new review, @kevinkaichuang.bsky.social @avapamini.bsky.social, @sarahalamdari.bsky.social, and I report wet lab success rates for *over 200* different protein design tasks 🧬💻

Huge shoutout to Twist for making the competition possible!

Twist Bioscience@twistbioscience.com · 5mo ago

AI-designed proteins are advancing fast, but how do they perform in real biological systems? Bits to Binders found out…

Amazing work from Clay @kosonocky.bsky.social, Alex Abel and LEAH labs, and all the collaborators and participants in the Bits2Binders AI CAR-T therapy protein design competition. The results are in! bsky.app/profile/koso...

Clay Kosonocky@kosonocky.bsky.social · 5mo ago

The results are finally in! 🏆💻🧬 I'm thrilled to announce that the manuscript for the Bits to Binders protein design competition is out on bioRxiv! Here's a summary of our findings, including some simple criteria that nearly *double* success rates when applied as a filter 🧵

Results from an impressive world-wide binder design competition.

Clay Kosonocky@kosonocky.bsky.social · 5mo ago

The results are finally in! 🏆💻🧬 I'm thrilled to announce that the manuscript for the Bits to Binders protein design competition is out on bioRxiv! Here's a summary of our findings, including some simple criteria that nearly *double* success rates when applied as a filter 🧵

The results are finally in! 🏆💻🧬 I'm thrilled to announce that the manuscript for the Bits to Binders protein design competition is out on bioRxiv! Here's a summary of our findings, including some simple criteria that nearly *double* success rates when applied as a filter 🧵

🚨The Bits to Binders Competition has concluded!🧬 One year ago we gathered scientists from around the world to design and submit protein binders that cause immune cells to target and eliminate CD20+ tumors Spoiler: They work!

For better or worse, I've subconsciously adopted a policy of "AI/fake/bot unless proven innocent" w/ regards to internet content from anyone I don't know personally

Some recent used bookstore acquisitions of mine Part of a few themes I'm trying to understand: - cultures & life via classic lit - basics of philosophy & history - modern political climate & trajectory - how can we make cities better? - what will the future look like?

Effect of SMILES representation on structure prediction, now with a large sample size!

Clay Kosonocky@kosonocky.bsky.social · last yr.

And we see it more clearly in these plots. Ideally if there were no effect, the experimental conditions (plots 2 & 3) would be as tight with the y=x as the 1st plot. But we can see that some ligands just don't behave as well

PSA: Digging into Chai-1 and found out that it gives different protein-ligand structures & confidences depending on the SMILES canonicalization used May also be the case with AF3 & Boltz-1, but haven't verified As to what this means... see the rest of the thread 🧵

The DNA for the Bits to Binders competition has just arrived from @twistbio.bsky.social! It is now being handed off to LEAH Labs where they will begin testing the 12,000 binders in a few days 👀 Stay tuned!

This year I've read 30 books so far. Here are the ~10 that I found the most valuable 🧵 1) One Hundred Years of Solitude (1967) by Gabriel Garcia Marquez Fantastic novel that I think everybody should read once. Captures the feeling of human life that feels instinctually correct

Unparalleled levels of productivity this week

@ddelalamo.bsky.social Just looked at the data. We fine-tuned ProteinMPNN on AlphaFold structures from each class of temperature in the HotProtein dataset. We found no change in performance on FireProtDB ddG or dTM. Work done w/ Phillip Woolley at UT Austin

Diego del Alamo@delalamo.xyz · 2y ago

Did you likewise see similar performance on FirProt?

Legend

Last year I made an intro Protein + ML project to teach BioML Society members about protein embeddings. Here it is! Hope you all enjoy Should get you familiar extracting embeddings for proteins, visualizing them, and using them for property prediction

"open-source and commercially available" 😎

Gabriele Corso@gcorso.bsky.social · 2y ago

Thrilled to announce Boltz-1, the first open-source and commercially available model to achieve AlphaFold3-level accuracy on biomolecular structure prediction! An exciting collaboration with Jeremy, Saro, and an amazing team at MIT and Genesis Therapeutics. A thread!

Hi new followers. Y'all might find this protein design resource list useful. Lots of great papers + available tools here! github.com/kosonocky/bi...

Has anybody been curating a list of the most seminal papers in the BioML space? Mainly interested in work that expands our ability to do and understand new things rather than improve upon benchmarks

I tried to make a bioml starter pack. DM if you want me to add or remove you? go.bsky.app/2VWBcCd

Kevin K. Yang 楊凱筌@kevinkaichuang.bsky.social · 2y ago

Anybody have a bioml starter pack?