Diffusion AI designs working enzymes from scratch: 13 of 69 designs cut peptide bonds
bravo_abad · x · 2026-10-15
David Baker's lab published a Nature paper on de novo design of cysteine proteases using generative AI.
- Peptide bonds can have half-lives of hundreds of years in neutral water, making enzyme design a demanding test
- The team borrowed catalytic atom geometry from natural enzymes, used RFdiffusion2-MI diffusion model to build new enzyme structures, with ProteinMPNN jointly designing enzyme-substrate pairs
- After computational filtering, 13 of 69 tested designs cut their target peptide, spanning three distinct protein scaffolds
Related event: Baker Lab Publishes Two Nature Papers on De Novo AI-Designed Proteases(6 posts)→
More from Research
- SubQ open-sources Decision LCR, a 72K–115K-token benchmark for decision models — ryanallred · 2026-10-16
- Interpretability debate: 'features' as fundamental neural network units may be wrong — MoonL88537 · 2026-10-16
- FOMO-Dex adds force-aware compliance to dexterous teleoperation for contact-rich robot tasks — HaozhiQ · 2026-10-16
- New mech interp hypothesis: neural networks generalize from the very first training step — burny_tech · 2026-10-16
- Princeton launches research initiative on keeping autonomous AI systems aligned with human intent — LakeBrenden · 2026-10-16
- OrganicHAR at UbiComp 2026: Discovering Activities Sensors Can Actually Distinguish — mynkgoel · 2026-10-16