SaProt
Protein language model with a structure-aware vocabulary combining amino acids with Foldseek 3Di tokens.
| Category | Protein structure & design |
|---|---|
| GitHub | westlake-repl/SaProt |
| First public | 2023-10-02 (source) |
| Paper | https://doi.org/10.1101/2023.10.01.560349 · bioRxiv preprint |
| License | MIT |
| Pricing | Open source |
| Tags | #alphafold2#foldseek#predicted-structures |
| Last checked | 2026-10-16 |
Specs
| Task | Embeddings, fitness and property prediction |
|---|---|
| Modalities | Sequence + 3Di structure tokens |
| MSA required | No |
| Open weights | Yes (35M-1.3B) |
| GPU need | GPU recommended |
| GitHub stars | 639 |
| Interface | — |
Specs come from each project's README, paper or official page · SaProt README · SaProt paper. “—” means we couldn't verify it.
Compare with…
Pick 1–3 other Protein structure & design tools to compare side by side with SaProt.
Related
DeepMind's open-source protein structure prediction model (monomer and multimer).
Protein structure & designOpen source#structure#msa
Structure prediction of proteins, nucleic acids, ligands and their complexes; hosted web server plus open code, weights on request for non-commercial use.
Protein structure & designFree (research)#structure#complexes
Open biomolecular interaction models (Boltz-1, Boltz-2) for complex structure and binding-affinity prediction.
Protein structure & designOpen source#structure#affinity