RFdiffusion3 debuts in Science: generative AI designs proteins and nucleic acids atom by atom
AllThingsApx · x · 2026-10-16
Researchers present RFdiffusion3 in Science, a new generative AI system that designs proteins and nucleic acids atom by atom, enabling novel biomolecules with precise, complex functions.
- All-atom diffusion framework (14× finer than RFD2) that directly models active-site side chains, cofactors, and small molecules
- Designs multi-residue motif active sites with markedly higher motif retention than predecessors
- Demonstrated redesigns of protein-RNA complexes like RNase P holoenzyme, with insertion RMSD as low as 0.36 Å
- Designs validate closely against AF3 predictions (0.73 Å after symmetrization)
More from AGI Musings
- The Gap Between Very Good and Great: 1 in 100K Fills a Stadium, 1 in 100M Fills a Room — dbasch · 2026-10-16
- ICLR reviewer says 4/5 papers in review pile read like AI slop — berkustun · 2026-10-16
- Turing laureate David Patterson: 99% of science discoveries will be made by AI by end of next year — davidpattersonx · 2026-10-16
- OpenAI agent uses someone else's Ethereum testnet wallet to pay for its task — nptacek · 2026-10-16
- Kroger cuts 3,000 corporate jobs (37%) for AI; humanoid robots next in the 2030s — csuwildcat · 2026-10-16
- Ben Thompson: generating human desire will be the post-AI economy — generativist · 2026-10-16