GEOM Dataset

GEOM is a dataset with over 30 million molecular conformations annotated by energy and statistical weight for over 430,000 molecules. Approximately 130,000 molecules are from the QM9 dataset, while 300,000 are drug-like molecules with experimental binding data for various targets.

GEOM数据集包含超3000万条带有能量与统计权重注释的分子构象（molecular conformations），共覆盖超43万种分子。其中约13万种分子源自QM9数据集，另有30万种为类药分子，且附带针对多种靶点的实验结合数据。