modelforge curated dataset: tmQM

Curated tmQM Dataset: Pd, Zn, Fe, Cu, Ni, Pt, Ir, Rh, Cr, Ag subset restricted to C, H, P, S, O, N, F, Cl, Br, version "subset_PdZnFeCuNiPtIrRhCrAg_CHPSONFClBr_v0": This provides a curated hdf5 file for the tmQM dataset (release 13Aug2024) designed to be compatible with modelforge, an infrastructure to implement and train NNPs. This datafile includes a subset of the original dataset (60637 unique molecules of the 108541 total), limited to those with metal centers of type Pd, Zn, Fe, Cu, Ni, Pt, Ir, Rh, Cr, or Ag and whose non-metal centers only sample from the following elements (C, H, P, S, O, N, F, Cl, Br). Note, only a single configuration per unique molecule is provided. Note: this has a bug where S is exlcuded and Se included instead. Use, v1 of this. When applicable, the units of properties are provided in the datafile, encoded as strings compatible with the openff-units package. For more information about the structure of the data file, please see the following: https://github.com/choderalab/modelforge/wiki/Dataset-and-curation#curation-module精选tmQM数据集： 以Pd、Zn、Fe、Cu、Ni、Pt、Ir、Rh、Cr、Ag为金属中心，且非金属元素仅包含C、H、P、S、O、N、F、Cl、Br的子集，版本标识为「subset_PdZnFeCuNiPtIrRhCrAg_CHPSONFClBr_v0」： 本文件为适配modelforge（一款用于实现与训练神经网络势（Neural Network Potentials, NNPs）的基础设施）的精选HDF5格式数据文件，基于2024年8月13日发布的tmQM数据集构建。该数据文件源自原始tmQM数据集的子集：原始数据集共计108541个分子，本子集包含其中60637个独特分子，且仅包含指定的金属中心（Pd、Zn、Fe、Cu、Ni、Pt、Ir、Rh、Cr、Ag），非金属原子仅取自C、H、P、S、O、N、F、Cl、Br元素。需注意，本子集仅为每个独特分子提供单一构型。 注意：该版本存在一处缺陷，将S元素错误排除并替换为Se元素，建议使用该数据集的v1版本。 若适用，数据文件中会以字符串形式标注各属性的单位，其格式兼容openff-units工具包。如需了解数据文件的详细结构，请参阅以下链接： https://github.com/choderalab/modelforge/wiki/Dataset-and-curation#curation-module