BioEmu2
Foundation model for biomolecular structure and dynamics: structure prediction, equilibrium ensemble sampling and time-lagged trajectory generation for proteins, nucleic acids and ligands.
| Category | Protein structure & design |
|---|---|
| GitHub | microsoft/bioemu2 |
| First public | 2026-10-20 (source) |
| Code license | MIT |
| Weights license | code and bioemu2-preview weights MIT (README and Hugging Face model card) |
| What this allows | Permissive (commercial OK) Use, modify and ship it inside closed-source commercial products; keep the license text and copyright notices. What do these mean? |
| License source | github.com/microsoft/bioemu2#license · checked 2026-10-20 |
| Pricing | Open source |
| Tags | #dynamics#ensembles#generative#structure-prediction |
| Last checked | · links verified |
Can I use BioEmu2 commercially?
Yes. The recorded license is permissive, so closed-source commercial use is allowed if you keep the notices.
- Code: MIT
- Weights: code and bioemu2-preview weights MIT (README and Hugging Face model card)
- Source: github.com/microsoft/bioemu2#license · license checked 2026-10-20
What the license types mean · not legal advice.
Specs
| Task | Structure prediction, equilibrium sampling, trajectory propagation, steering |
|---|---|
| Modalities | Proteins, nucleic acids, ligands and other chemical components |
| MSA required | — |
| Open weights | Yes (bioemu2-preview, Hugging Face) |
| GPU need | Linux + NVIDIA GPU (compute capability 7.0+) |
| GitHub stars | 249 |
| Interface | Package, CLI |
Compare with…
Pick 1–3 other Protein structure & design tools to compare side by side with BioEmu2.
Related
DeepMind's open-source protein structure prediction model (monomer and multimer).
Structure prediction of proteins, nucleic acids, ligands and their complexes; hosted web server plus open code, weights on request for non-commercial use.
Open biomolecular interaction models (Boltz-1, Boltz-2) for complex structure and binding-affinity prediction.