The future of drug design is in AI. Let me introduce our new work, RareFoldGPCR: Agonist Design Beyond Natural Amino Acids. Paper: https://t.co/Xd5UMDI4IF Code: https://t.co/N4JuxIl6o5

This is a rare trait among humans - chimps are probably more rational

The secret to the naked mole-rats’ extraordinarily long life may lie in subtle changes to just four amino acids, researchers report in Science. https://t.co/KtzxnmH3nX

We need to stop scaling with waste. RareFold proves that cutting-edge therapeutic design can and must go hand-in-hand with computational efficiency. Try the new, efficient implementation of RareFold here:

We tackled the silent killer: GPU Waste in protein design. The old way: 25 separate GPUs for a multi-length design campaign. The RareFold way: 1 single GPU handles the entire 25× workload! That’s a 25× reduction in peak hardware demand. 🤯

Try EvoBind here: https://t.co/3kYIKJIABQ Paper:

Check out the pretty logo my great student Diandra Daumiller made for our software EvoBind! It is already quite popular, but I suspect this will make it even more so. (logo description: EvoBind, EB, as a cyclic peptide)

There is also a short video here:

🔹 Key advances: • Supports non-canonical AAs • Designs linear & cyclic peptide agonists • Validated GLP1R activation • Enables pathway-specific (biased) agonism

Thanks! Expanded chemistry means more possible drugs, hopefully it can help with many diseases

Great work (again) from my postdoc @Qiuzhen_Li

Excited to share our new work on the future of functional drug design. RareFoldGPCR: Agonist Design Beyond Natural Amino Acids.

Three days left to apply! Come work with us and change the world with peptide design!

A reminder that there is now *1 week* left until the MLSB deadline on October 1st! Send in your 🧪bio+🤖ML papers, for either 🇺🇸San Diego, 🇩🇰Copenhagen, or ✨both✨!

Thrilled to announce that the first paper from Flemmings PhD was accepted as Poster for NeurIPS2025! In this paper we adapt the HollowNet idea from @RickyTQChen to equivariant MP networks, to get cheap sample likelihoods for CNF-based Boltzmann Generators. Preprint/code soon.

Excited to share an important advance in AI and math. Together with mathematicians from @BrownUniversity, @nyuniversity and @Stanford, we developed a new AI-powered method that has discovered an entirely new family of solutions to several complex equations in fluid dynamics.

Apply here:

We’re hiring a Postdoc in protein design! 📍 2-year position in Stockholm Join us to shape the future of drug design! Work on wet lab validation (cells, affinity) & expand your AI skills.

If you are like us and want to improve the world and have a real impact, apply here: https://t.co/HTHUgihojm More about my lab: https://t.co/iS5NDvy6Xl Email me at patrick.bryant@scilifelab.se if you have any questions.

In the past year, we have: 1. Designed dual GLP1R/GCGR agonists: https://t.co/7FcMTlsjEO 2. HIV inhibitors: https://t.co/4rFCrHvGPm 3. Pioneered structure prediction and design with noncanonical amino acids: