QM8 dataset is a collection of molecular data used for studying quantum mechanical calculations of electronic spectra and excited state energy of small molecules. The QM8 dataset consists of approximately 7,165 molecules. These molecules are a subset of the GDB-13 database, which contains nearly 1 billion stable and synthetically accessible organic molecules. The subset includes all molecules with up to 23 atoms, including 7 heavy atoms (C, N, O, and S).
Variants: QM8
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Molecular Property Prediction | ChemRL-GEM | ChemRL-GEM: Geometry Enhanced Molecular Representation … | 2021-06-11 |
| Molecular Property Prediction | GROVER (large) | Self-Supervised Graph Transformer on Large-Scale … | 2020-06-18 |
| Molecular Property Prediction | GROVER (base) | Self-Supervised Graph Transformer on Large-Scale … | 2020-06-18 |
| Molecular Property Prediction | PretrainGNN | Strategies for Pre-training Graph Neural … | 2019-05-29 |
| Molecular Property Prediction | D-MPNN | Analyzing Learned Molecular Representations for … | 2019-04-02 |
| Molecular Property Prediction | N-GramXGB | N-Gram Graph: Simple Unsupervised Representation … | 2018-06-24 |
| Molecular Property Prediction | N-GramRF | N-Gram Graph: Simple Unsupervised Representation … | 2018-06-24 |
Recent papers with results on this dataset: