Exploring the Hepatotoxicity of Drugs through Machine Learning and Network Toxicological Methods

作者全名："Tang, Tiantian; Gan, Xiaofeng; Zhou, Li; Pu, Kexue; Wang, Hong; Dai, Weina; Zhou, Bo; Mo, Lingyun; Zhang, Yonghong"

作者地址："[Tang, Tiantian; Gan, Xiaofeng; Wang, Hong; Zhou, Bo; Zhang, Yonghong] Chongqing Med Univ, Coll Pharm, Chongqing Key Res Lab Drug Metab, Chongqing 400016, Peoples R China; [Zhou, Li] Chongqing Med Univ, Collaborat Innovat Ctr Social Risks Governance Hlt, Sch Publ Hlth & Management, Dept Epidemiol, Chongqing 400016, Peoples R China; [Pu, Kexue; Dai, Weina; Zhang, Yonghong] Chongqing Med Univ, Med Data Sci Acad, Coll Med Informat, Chongqing 400016, Peoples R China; [Pu, Kexue; Dai, Weina; Zhang, Yonghong] Chongqing Med Univ, Chongqing Engn Res Ctr Clin Big Data & Drug Evalua, Chongqing 401331, Peoples R China; [Dai, Weina] Fuling Ctr Hosp Chongqing City, Dept Pharm, Chongqing 408000, Peoples R China; [Zhou, Bo] Chongqing Med Univ, Childrens Hosp, Dept Pharm, Key Lab Child Dev & Disorders, Chongqing 400014, Peoples R China; [Mo, Lingyun] Guilin Univ Technol, Coll Environm Sci & Engn, Guangxi Key Lab Theory & Technol Environm Pollut C, Guilin 541004, Peoples R China; [Mo, Lingyun] Minist Nat Resources, Tech Innovat Ctr Mine Geol Environm Restorat Engn, Nanning 530028, Peoples R China"

通信作者："Zhang, YH (通讯作者)，Chongqing Med Univ, Coll Pharm, Chongqing Key Res Lab Drug Metab, Chongqing 400016, Peoples R China."

来源：CURRENT BIOINFORMATICS

ESI学科分类：COMPUTER SCIENCE

WOS号：WOS:001063979200003

JCR分区：Q2

影响因子：2.4

年份：2023

卷号：18

期号：6

开始页：484

结束页：496

文献类型：Article

关键词：Network topological parameters; machine learning; drug-induced liver injury; disease module; mechanism interpretation; adverse drug reactions

摘要："Background: The prediction of the drug-induced liver injury (DILI) of chemicals is still a key issue of the adverse drug reactions (ADRs) that needs to be solved urgently in drug development. The development of a novel method with good predictive capability and strong mechanism interpretation is still a focus topic in exploring the DILI. Objective: With the help of systems biology and network analysis techniques, a class of descriptors that can reflect the influence of drug targets in the pathogenesis of DILI is established. Then a machine learning model with good predictive capability and strong mechanism interpretation is developed between these descriptors and the toxicity of DILI. Methods: After overlapping the DILI disease module and the drug-target network, we developed novel descriptors according to the number of drug genes with different network overlapped distance parameters. The hepatotoxicity of drugs is predicted based on these novel descriptors and the classical molecular descriptors. Then the DILI mechanism interpretations of drugs are carried out with important network topological descriptors in the prediction model. Results: First, we collected targets of drugs and DILI-related genes and developed 5 NT parameters (S, N-ds=0, N-ds=1, N-ds=2, and N-ds>2) based on their relationship with a DILI disease module. Then hepatotoxicity predicting models were established between the above NT parameters combined with molecular descriptors and drugs through the machine learning algorithms. We found that the NT parameters had a significant contribution in the model (ACC(training) (set)=0.71, AUC(training) (set)=0.76; ACC(external) (set)=0.79, AUC(external set)=0.83) developed by these descriptors within the applicability domain, especially for N-ds=2, and N-ds>2. Then, the DILI mechanism of acetaminophen (APAP) and gefitinib are explored based on their risk genes related to ds=2. There are 26 DILI risk genes in the regulation of cell death regulated with two steps by 5 APAP targets, and gefitinib regulated risk gene of CLDN1, EIF2B4, and AMIGO1 with two steps led to DILI which fell in the biological process of response to oxygen-containing compound, indicating that different drugs possibly induced liver injury through regulating different biological functions. Conclusion: A novel method based on network strategies and machine learning algorithms successfully explored the DILI of drugs. The NT parameters had shown advantages in illustrating the DILI mechanism of chemicals according to the relationships between the drug targets and the DILI risk genes in the human interactome. It can provide a novel candidate of molecular descriptors for the predictions of other ADRs or even of the predictions of ADME/T activity."

基金机构：Declared none.

基金资助正文：Declared none.