8 datasets found

The TUDataset is a collection of benchmark datasets for learning with graphs. It contains 14 datasets, each with a different type of graph.

Zinc12K dataset is a subset of ZINC250k containing 12k molecules.

The 3DGCN model predicts molecular properties and biochemical activities based on 3D molecular graph.

The MoleculeNet dataset is a collection of molecular property prediction tasks. It contains 17 datasets, each with a different type of molecular graph.

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

Geom, energy-annotated molecular conformations for property prediction and molecular generation.

The KPGT model is a knowledge-guided pre-training of graph transformer for molecular property prediction.

The PCQM4Mv2 dataset provides a well-defined ML task of predicting the HOMO-LUMO gap of molecules given their 2D molecular graphs. Each molecule has two natural views. The 2D...