RFdiffusion3, a generative molecular-design system, designs proteins and nucleic acids at atomic resolution, generating protein structures approximately 10 times faster than its predecessor.

The research team includes David Baker. Science and Technology Daily, citing the latest issue of Science, reported that the University of Washington professor and 2024 Nobel Prize in Chemistry laureate participated in developing RFdiffusion3, also called RFD3. The report describes it as a generative AI system for direct atomic-level molecular design.

The design scope extends beyond proteins. RFD3 also covers nucleic acids, including ribonucleic acid (RNA). The source therefore describes molecular-design capabilities broader than protein structure generation alone.

The speed comparison applies specifically to protein-structure generation. The reported rate is approximately ten times that of the predecessor system, not a stated tenfold reduction in total research cost or hardware requirements. The supplied summary does not identify benchmark hardware, absolute runtimes, or experimentally validated success rates, and discusses specialized RNA molecules, biosensors, and biomolecular tools as prospective applications rather than completed outcomes.