the "the first evidence " is incorrect. We removed it from the paper.

David M. Sabatini, William F. DeGrado, Jeremy Wohlwend, Gabriele Corso, Regina Barzilay, Tommi Jaakkola

Arash Vahdat, Shamayeeta Ray, Jonathan T. Goldstein, Andrew Savinov, Jacob A. Hambalek, Anshika Gupta, Diego A. Taquiri-Diaz, Yaotian Zhang, A. Katherine Hatstat, Angelika Arada, Nam Hyeong Kim, Ethel Tackie-Yarboi, Dylan Boselli, Lee Schnaider, Chang C. Liu, Gene-Wei Li, Denes Hnisz,

Huge thanks to @aihealthmit.bsky.social
This is an awesome team: Felix Faltings, MinGyu Choi, Yuxin Xie, Eunsu Hur, Timothy O’Donnell, Anton Bushuiev, Talip Uçar, Saro Passaro, Weian Mao, Mateo Reveiz, Roman Bushuiev, Tomáš Pluskal, Josef Sivic, Karsten Kreis,

And join us for live presentations, demos, and discussions:
MIT (Cambridge) – Thursday, October 30th luma.com/7474iho2
London – Thursday, November 6th luma.com/l2zgvfwt

🚀 Model & code: github.com/HannesStark/...
🤗 Join our fast-growing Slack community: boltz.bio/join-slack
🧠 Blog post: boltz.bio/boltzgen
📄 Full manuscript: hannes-stark.com/assets/boltz...

Everything is integrated in one easy to use end-to-end pipeline! Just type up your design specification and try it out!

This results in a design specification language for various constraints – including covalent bonds, structure groups, binding sites, secondary structures and design masks – that steer the diffusion process towards specific design objectives during inference.

With this we train a model with the standard AF3 / Boltz-2 scalable architecture that has proven state-of-the-art for folding. Injecting conditioning inputs allows us to control the designed binder in various ways

Due to a purely geometry-based encoding of designed residues this unified boils down to supervising with the same diffusion loss for structure prediction and design.

BoltzGen’s success stems from its unification of design and structure prediction. A purely geometry-based representation of designed residues enables scalable training on both tasks. As a result, unlike any previous design model, BoltzGen matches the performance of SOTA folding

We have more campaigns where the validation goes beyond binding: we test 6 BoltzGen designs against each of 3 diversely structured peptides. We obtain nM binders against two and uM against the third. For every target, at least on design neutralizes its antimicrobial activity.

For peptides, we e.g., succeed for designing linear and disulfide-bonded peptides against crucial metabolic pathway targets and disordered proteins. When testing 5 designs, we have one success, posing the first evidence of de-novo peptides binding disordered proteins.

We go after targets that require generalization. E.g. we tested 15 nanobodies against each of 9 targets selected for their dissimilarity to any protein with an existing bound structure. For 6 of 9 targets we obtain nM binders. The same 67% success rate holds for miniproteins 🤗