Pocket2Mol
E(3)-equivariant graph neural network that samples drug-like molecules atom by atom inside 3D protein pockets.
| Category | Drug discovery & molecules |
|---|---|
| GitHub | pengxingang/Pocket2Mol |
| First public | 2022-05-15 (source) |
| Paper | https://arxiv.org/abs/2205.07249 · arXiv preprint (2022) |
| License | MIT |
| Pricing | Open source |
| Tags | #drug-discovery |
| Last checked | 2026-10-16 |
Specs
| Task | Pocket-conditioned molecule generation |
|---|---|
| Molecular representation | 3D atoms (pocket-conditioned) |
| Open weights | Yes |
| GitHub stars | 413 |
| Interface | — |
Specs come from each project's README, paper or official page · Pocket2Mol README · Pocket2Mol paper. “—” means we couldn't verify it.
Compare with…
Pick 1–3 other Drug discovery & molecules tools to compare side by side with Pocket2Mol.
Related
Deep learning toolkit for drug discovery, materials and biology.
Drug discovery & moleculesOpen source#ml#molecules
Open-source cheminformatics and machine learning toolkit.
Drug discovery & moleculesOpen source#cheminformatics
Message passing neural networks for molecular property prediction.
Drug discovery & moleculesOpen source#property-prediction#gnn