IrwinLab/LSD_mPro_Fink_2023_noncovalent_Screen2_ZINC22

该数据集包含三个配置：docking_results、invitro_results和poses_top500k。docking_results配置包含smiles、zincid、tranche和score等字段，主要用于训练，数据大小为77272380574字节，共有878517250个示例。invitro_results配置包含zincid、ID、vendorid、Smile等字段，同样用于训练，数据大小为27747字节，共有140个示例。poses_top500k配置包含Name、Protonation、Long_Name等字段，用于训练，数据大小为1990496511字节，共有499990个示例。

The dataset consists of three configurations: docking_results, invitro_results, and poses_top500k. The docking_results configuration includes fields such as smiles, zincid, tranche, and score, primarily for training, with a data size of 77272380574 bytes and a total of 878517250 examples. The invitro_results configuration includes fields like zincid, ID, vendorid, Smile, etc., also for training, with a data size of 27747 bytes and 140 examples. The poses_top500k configuration contains fields such as Name, Protonation, Long_Name, etc., for training, with a data size of 1990496511 bytes and 499990 examples.