7 datasets found

The dataset used for testing the performance of the deep generative model.

The MOSES dataset is a benchmarking platform for molecular generation models. It contains a large collection of molecules with their 3D conformers calculated by RDKit.

The GEOM-DRUGS dataset contains 27M conformations for 300k molecules, and it serves as a standard benchmark for the machine learning-based 3D molecular generators.

The Uni-Mol dataset contains 208M conformations for 12M molecules and 3.2M spatial structures of protein pockets.

The GFlowNet dataset is a dataset of molecules used for molecular docking and generation. It contains 300,000 molecules with their corresponding properties and structures.

The ZINC250K dataset is a large dataset of molecules used for molecular design and generation. It contains 250,000 molecules with their corresponding properties and structures.

The MOSES dataset is a large dataset of molecules, and the HIV dataset is a subset of the MOSES dataset containing 41127 molecules.