RFdiffusion: diffusion models design new proteins that work in the lab
Result confirmed
Importance: major (4 of 5)The takeaway
David Baker’s lab (Nature, July 2023) fine-tuned RoseTTAFold as a diffusion model to generate new protein backbones for binders, symmetric assemblies and metal-binding sites.
Status
- Claim
Result confirmed
- Our reporting
- High confidence
- Verification
- Peer-reviewed
- Importance
- Major (4 of 5)
- Last verified
- 29 September 2026
Your AI and this story
- GPT-6 AstraIn its training data
- Claude Opus 5.5In its training data
- Gemini 4 HydrogenIn its training data
- Grok 4.7In its training data
It happened before the cutoffs of all four assistants, so it can be in their training data.
Key facts
- Nature, 11 Jul 2023; code released free and open-source in 2023
- Designs: protein binders, symmetric oligomers, enzyme active-site scaffolds, metal-binding proteins
- Successors: RFdiffusion2 (Nature Methods, Jan 2026: scaffolds for all 41 benchmark active sites vs 16 before) and RFdiffusion3 (open-sourced Dec 2025)
- Part of the work recognised by the 2024 Nobel Prize in Chemistry (Baker)
What happened
By adapting image-generation-style diffusion to protein structures, the Baker lab made protein design largely a matter of generating and filtering candidates on computers.
Why it matters
It became the workhorse of AI protein design, underlying AI antivenoms, antibodies and enzymes.
Sources
3 sources from 3 sites. Numbers match the chips in the text.
3 sources: 3 primary
Primary
- De novo design of protein structure and function with RFdiffusion (Nature)nature.com, paper
- Baker Lab: RFdiffusion now free and open sourcebakerlab.org, official
- IPD: RFdiffusion3 now availableipd.uw.edu, official
Changes
- Filed