COMP6v2 Release

COmprehensive Machine-learning Potential (COMP6) Benchmark Suite version 2.0 The COMP6v2 data is an extension of the COMP6 benchmark found in the following repository: https://github.com/isayev/COMP6 COMP6v2 is a data set of density functional properties for molecules containing H, C, N, O, S, F, and Cl. It is available at the following levels of theory: wB97X/631Gd (data used to train model in the ANI-2x paper) wB97MD3BJ/def2TZVPP wB97MV/def2TZVPP B973c/def2mTZVP You will notice that COMP6v1 is split into subsets: ANI-MD DrugBank GDB07to09 GDB10to13 Tripeptides s66x8 As we are releasing multiple levels of theory here, each h5 file is a combination of all subsets. The sample data loader script provides an example of how to access the contents of the data sets using h5py. View the supplementary information for more information on the formatting and contents of the data sets. Details on the generation of this data can be found in the ANI-2x paper.综合机器学习势能（Comprehensive Machine-learning Potential，COMP6）基准套件v2.0 COMP6v2数据集是下述仓库中COMP6基准套件的扩展版本：https://github.com/isayev/COMP6 COMP6v2是包含H、C、N、O、S、F、Cl元素的分子的密度泛函性质数据集。该数据集提供以下理论水平下的数据： - wB97X/6-31Gd（用于训练ANI-2x论文中模型的数据集） - wB97M-D3BJ/def2-TZVPP - wB97MV/def2-TZVPP - B973c/def2-mTZVP 需注意，COMP6v1被划分为以下子集： - ANI-MD - DrugBank - GDB07至GDB09 - GDB10至GDB13 - 三肽 - s66x8 由于本次发布涵盖多种理论水平的数据，每个h5文件均为所有子集的整合。 附带的示例数据加载脚本演示了如何使用h5py库访问数据集内容。如需了解数据集格式与内容的更多细节，请查阅补充材料。关于该数据集生成的详细信息，请参阅ANI-2x相关论文。