Chemprop vs DeepChem
Chemprop: Message passing neural networks for molecular property prediction. DeepChem: Deep learning toolkit for drug discovery, materials and biology.
Facts below come from each project's own website, repository and paper. We don't publish benchmark claims here; see the papers for evaluations.
| Field | Chemprop | DeepChem |
|---|---|---|
| Task | Property prediction | ML toolkit: molecular property prediction, generative chemistry, materials and bio models |
| Molecular representation | Molecular graph (message passing NN) | SMILES, molecular graphs, fingerprints (built-in featurizers) |
| Open weights | Yes (Halicin model checkpoints on Zenodo) | — |
| License | MIT | MIT |
| Pricing | Open source | Open source |
| Released | 2019-02-07 | 2016-01-29 |
| Paper | Link | — |
| GitHub | GitHub | GitHub |
| GitHub stars | 2,505 | 7,060 |
| Interface | Colab, Web | Package, Docker |
License and commercial use
| Field | Chemprop | DeepChem |
|---|---|---|
| Code license | MIT | MIT |
| Weights license | — | — |
| Commercial use | Permissive (commercial OK) | Permissive (commercial OK) |
| Answer | Yes. The recorded license is permissive, so closed-source commercial use is allowed if you keep the notices. Details | Yes. The recorded license is permissive, so closed-source commercial use is allowed if you keep the notices. Details |
Add more Drug discovery & molecules tools to this comparison →