MetalHawk: Enhanced Classification Of Metal Coordination Geometries by Artificial Neural Networks

The data used to train and validate the CSD-NN and PDB-NN models. These neural networks built in Scikit-learn and are trained to recognize the geometry and coordination number of a metal site from the geometric features including distances and angles of the six atoms closest to the metal. The sites are stored as .pdb files composed of all atoms falling within 10 angstroms of the central metal atom and they include both metal complexes deposited in the Cambridge Structural Database (CSD, Version 5.42-5.43) and bioinorganic sites deposited in the Protein Data Bank (PDB), retrieved through the MetalPDB interface (up to the end of 2018). The sites are divided in seven geometry classes: linear (LIN), trigonal planar (TRI), tetrahedral (TET), square planar (SPL), square pyramidal (SQP), trigonal bipyramidal (TBP) and octahedral (OCT). The number of metal sites in each file is the following: CSD_dataset_pdbs.zip - 110K CSD_validation_dataset_pdbs.zip - 1369 PDB_dataset_pdbs.zip file - 2960 PDB_validation_dataset_pdbs.zip - 106 The file images_and_data_analysis.zip contains all data and code required to replicate the figures shown in the paper.本数据集用于训练与验证CSD-NN与PDB-NN模型。这些神经网络基于Scikit-learn构建，旨在通过距中心金属原子最近的六个原子的距离与角度等几何特征，识别金属位点的几何构型与配位数。所有金属位点均以.pdb格式文件存储，每个文件包含中心金属原子10埃范围内的全部原子；这些位点既包括沉积于剑桥晶体结构数据库（Cambridge Structural Database，版本5.42-5.43，简称CSD）中的金属配合物，也包括通过MetalPDB接口检索得到、截至2018年底收录于蛋白质数据银行（Protein Data Bank，简称PDB）中的生物无机位点。所有金属位点被划分为7类几何构型：直线型（LIN）、平面三角形（TRI）、四面体（TET）、平面正方形（SPL）、四方锥（SQP）、三角双锥（TBP）与八面体（OCT）。各压缩文件包含的金属位点数量如下：CSD_dataset_pdbs.zip —— 11万个；CSD_validation_dataset_pdbs.zip —— 1369个；PDB_dataset_pdbs.zip —— 2960个；PDB_validation_dataset_pdbs.zip —— 106个。images_and_data_analysis.zip文件包含了复现论文中所有图表所需的全部数据与代码。