Mol-1
Mol-1 is a protein structure & design tool whose code is published by molence on GitHub, first public in 2026. Molence Bio's open all-atom structure prediction model, derived from Protenix, for protein, nucleic acid, ligand and ion complexes, tuned for antibody–antigen, protein–ligand and peptide accuracy, with fine-tuning code.
| Category | Protein structure & design |
|---|---|
| Developer (GitHub) | molence |
| Input | Protein, DNA, RNA, ligand, ion, covalent bonds and modifications |
| Task | All-atom biomolecular complex structure prediction (AlphaFold 3-style co-folding) |
| Interface | CLI (mol pred), Python package, Web (Molence Lab) |
| GitHub | molence/Mol-1 |
| Released | 2026-10-27 (source) |
| Code license | Apache-2.0 |
| Weights license | the 2.2 GB mol-1-base checkpoint is a public download, with no separate weights license stated |
| 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/molence/Mol-1#license · checked 2026-10-28 |
| Pricing | Open source |
| Tags | #structure#co-folding#antibody |
| Last checked | · links verified |
Can I use Mol-1 commercially?
Yes. The recorded license is permissive, so closed-source commercial use is allowed if you keep the notices.
- Code: Apache-2.0
- Weights: the 2.2 GB mol-1-base checkpoint is a public download, with no separate weights license stated
- Source: github.com/molence/Mol-1#license · license checked 2026-10-28
What the license types mean · not legal advice.
Specs
| Task | All-atom biomolecular complex structure prediction (AlphaFold 3-style co-folding) |
|---|---|
| Modalities | Protein, DNA, RNA, ligand, ion, covalent bonds and modifications |
| MSA required | Yes (ColabFold MMseqs2 protein MSA; optional HMMER templates and RNA MSA) |
| Open weights | Yes (mol-1-base checkpoint, 2.2 GB) |
| GPU need | — |
| GitHub stars | 136 |
| Interface | CLI (mol pred), Python package, Web (Molence Lab) |
Compare with…
Pick 1–3 other Protein structure & design tools to compare side by side with Mol-1.
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.