RFdiffusion
A-UW Baker Lab
Protein DesignDe Novo GenerationBinder Designopen
Updated 1 month agoNextIn take
RFdiffusion changed what is possible in protein design — designing binders that actually work in the lab at double-digit success rates. Pair it with ProteinMPNN for the full design pipeline.
Specifications
| Architecture | Denoising diffusion on RoseTTAFold frames for protein backbone generation |
| Parameters | ~300M |
| Training Data | PDB structures — trained to reverse the noising process on known backbones |
| License | BSD license. Fully open weights and code. |
| Hardware | 1x A100 40GB, CPU-feasible for small designs |
| Inference Cost | Self-hosted — ~$0.01/design on cloud GPU |
| API Available | No |
| Weights Available | Yes |
Benchmark Performance
| Benchmark | Score |
|---|---|
| ProteinGym | N/A (generative) |
When to Use This
- +De novo protein binder design
- +Scaffold generation for therapeutic protein engineering
When NOT to Use This
- −Structure prediction of natural proteins — use Boltz or AF3
- −Sequence design — pair with ProteinMPNN downstream
Production Readiness
pilot
Known Users
- Baker Lab and collaborators
- Multiple biotech companies including Generate Biomedicines
Grade Rationale
A-
The most impactful protein design tool released in the last five years. Experimentally validated de novo binders with success rates that were unthinkable before diffusion models. A- because generative design is inherently harder to benchmark than prediction.
Sources
Update History
2026-02-20Initial entry