NovaAtom-Lite
NovaAtom-Lite is a drug discovery & molecules tool, first public in 2026. Geodesic Intelligence all-atom structure predictor for proteins, DNA, RNA and small-molecule ligands, with pLDDT, PAE and ipTM confidence; strongest on antibody–antigen and protein–ligand interfaces, available through the Geodesic API and the NovaDDE web platform.
| Category | Drug discovery & molecules |
|---|---|
| Task | All-atom biomolecular structure prediction (protein, DNA, RNA, ligands, metals/ions), with cyclic/covalent bonds and contact/pocket hints |
| Website | www.geodesiclab.com/models/novaatom |
| Released | 2026-11-10 (source) |
| License | Proprietary (Proprietary; weights and code not released; free plan (100 credits/week) on NovaDDE, paid Plus/Pro tiers and API) |
| What this allows | Unknown No confirmed terms from a primary source; ask the authors before using it in a product. What do these mean? |
| License source | www.geodesiclab.com/pricing · checked 2026-11-11 |
| Pricing | No-cost tier + paid plans |
| Tags | #co-folding#all-atom#antibody#proprietary |
| Last checked | · links verified |
Can I use NovaAtom-Lite commercially?
Unclear. We could not confirm the terms from a primary source; check with the authors before commercial use.
- License: Proprietary (Proprietary; weights and code not released; free plan (100 credits/week) on NovaDDE, paid Plus/Pro tiers and API)
- Source: www.geodesiclab.com/pricing · license checked 2026-11-11
What the license types mean · not legal advice.
Specs
| Task | All-atom biomolecular structure prediction (protein, DNA, RNA, ligands, metals/ions), with cyclic/covalent bonds and contact/pocket hints |
|---|---|
| Molecular representation | Pairformer trunk with recycling plus atom-level diffusion; reads sequence, MSAs and optional templates |
| Open weights | Not released (API and NovaDDE web platform only) |
| Interface | — |
Compare with…
Pick 1–3 other Drug discovery & molecules tools to compare side by side with NovaAtom-Lite.
Related
Deep learning toolkit for drug discovery, materials and biology.
Open-source cheminformatics and machine learning toolkit.
Message passing neural networks for molecular property prediction.