A dataset of 120,000 geometries from the WS22 database, sampled to 15,000 geometries for each molecule.

A diverse collection of multifidelity QC properties for 9 molecules, calculated at 5 different fidelities.

The dataset is used for testing the proposed TopNets architecture on molecular property prediction tasks.

A dataset of small molecules for benchmarking molecule generation methods. The dataset consists of fingerprints of the molecules, and the goal is to predict the original...