Supplementary data for the thesis "Development and Validation of Explainable Machine-Learning Prediction Systems: A Study of Biomedical and Clinical Data"

The files contain the dataset for the thesis "Development and Validation of Explainable Machine-Learning Prediction Systems: A Study of Biomedical and Clinical Data".

Chapter 3 includes a patient dataset with CDI (Clostridioides difficile infection) admissions from 2009-2014 in Hong Kong.

Chapter 4 includes a list of protein structure data derived from UniProt (www.uniprot.org) (release 2021_03) and their corresponding enzyme functions. The protein structure data file can be downloaded from the open-source database Protein Data Bank (www.rcsb.org). Additionally, a list of AlphaFold 2 predicted structures is also included, and the structural data can be downloaded from www.alphafold.com.

Chapter 5 contains a list of PDB structures derived from UniProt (release 2023_01).

该数据集包含了论文《可解释机器学习预测系统的开发与验证：基于生物医学和临床数据的实证研究》的附件。第三章包含了一组2009至2014年间香港地区艰难梭菌感染（Clostridioides difficile infection，简称CDI）患者数据集。第四章收录了源自UniProt（www.uniprot.org）数据库（2021_03版）的蛋白质结构数据及其相应的酶功能列表。蛋白质结构数据文件可从开源数据库蛋白质数据银行（www.rcsb.org）下载。此外，还包括了AlphaFold 2预测的结构列表，且结构数据可从www.alphafold.com下载。第五章则包含了一组源自UniProt（2023_01版）的PDB结构数据。