ProteinMPNN
AUW Baker Lab
Sequence DesignInverse Foldingopen
Updated 2 months agoNextIn take
ProteinMPNN is the quiet workhorse of the protein design revolution — 2M parameters, runs on a laptop, and has been behind more successful designed proteins than any model 100x its size.
Specifications
| Architecture | Message-passing neural network on protein structure graphs |
| Parameters | ~2M |
| Training Data | PDB structures with sequence-structure pairs |
| License | MIT license. Fully open weights and code. |
| Hardware | Runs on CPU. GPU optional for speed. |
| Inference Cost | Negligible — runs on laptop hardware |
| API Available | No |
| Weights Available | Yes |
Benchmark Performance
| Benchmark | Score |
|---|---|
| ProteinGym | 52% recovery rate |
When to Use This
- +Designing sequences for computationally generated backbones
- +Redesigning natural proteins for improved stability or function
When NOT to Use This
- −Generating new backbone structures — use RFdiffusion first
- −Predicting structure from sequence — this does the reverse
Production Readiness
production
Known Users
- Baker Lab and hundreds of academic groups
- Multiple protein engineering companies
Grade Rationale
A
The gold standard for inverse folding and sequence design. Tiny model, runs anywhere, works reliably, and has been experimentally validated hundreds of times. A because it does one thing and does it better than anything else.
Sources
Update History
2026-02-01Initial entry