MaSIF
Geometric deep learning on protein molecular surfaces to predict interaction sites, ligand pockets and binding partners.
| Category | Protein structure & design |
|---|---|
| GitHub | LPDI-EPFL/masif |
| First public | 2019-03-14 (source) |
| Paper | https://doi.org/10.1038/s41592-019-0666-6 · Nature Methods (2020) |
| License | Apache-2.0 |
| Pricing | Open source |
| Tags | #protein-surface#molecular-surface#geometric-deep-learning |
| Last checked | 2026-10-16 |
Specs
| Task | Interaction site and binder search |
|---|---|
| Modalities | Protein surface (structure) |
| MSA required | No |
| Open weights | Yes |
| GPU need | CPU or GPU (TensorFlow) |
| GitHub stars | 783 |
| Interface | — |
Specs come from each project's README, paper or official page · MaSIF README · MaSIF paper. “—” means we couldn't verify it.
Compare with…
Pick 1–3 other Protein structure & design tools to compare side by side with MaSIF.
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