MoleculeNet is a large scale benchmark for molecular machine learning. MoleculeNet curates multiple public datasets, establishes metrics for evaluation, and offers high quality open-source implementations of multiple previously proposed molecular featurization and learning algorithms (released as part of the DeepChem open source library). MoleculeNet benchmarks demonstrate that learnable representations are powerful tools for molecular machine learning and broadly offer the best performance.
Variants: MoleculeNet
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Molecular Property Prediction | Uni-Mol | Galactica: A Large Language Model … | 2022-11-16 |
| Molecular Property Prediction | GAL 30B | Galactica: A Large Language Model … | 2022-11-16 |
| Molecular Property Prediction | GAL 6.7B | Galactica: A Large Language Model … | 2022-11-16 |
| Molecular Property Prediction | GAL 1.3B | Galactica: A Large Language Model … | 2022-11-16 |
| Molecular Property Prediction | GAL 125M | Galactica: A Large Language Model … | 2022-11-16 |
Recent papers with results on this dataset: