Applicability Domains Enhance Application of PPARγ Agonist Classifiers Trained by Drug-like Compounds to Environmental Chemicals

被引：26

作者：

Wang, Zhongyu ^{[1
]}

Chen, Jingwen ^{[1
]}

Hong, Huixiao ^{[2
]}

机构：

[1] Dalian Univ Technol, Sch Environm Sci & Technol, Key Lab Ind Ecol & Environm Engn MOE, Dalian 116024, Peoples R China

[2] US FDA, Natl Ctr Toxicol Res, Jefferson, AR 72079 USA

来源：

CHEMICAL RESEARCH IN TOXICOLOGY | 2020年 / 33卷 / 06期

基金：

中国国家自然科学基金; 国家重点研发计划;

关键词：

NUCLEAR RECEPTORS PPAR-GAMMA-1; OUTCOME PATHWAY FRAMEWORK; PREDICTION; MODE; ADIPOGENESIS; ACTIVATION; DATABASE; LIGANDS; QSAR;

D O I：

10.1021/acs.chemrestox.9b00498

中图分类号：

R914 [药物化学];

学科分类号：

100701 ;

摘要：

Peroxisome proliferator activator receptor gamma (PPAR gamma) agonist activity of chemicals is an indicator of concerned health conditions such as fatty liver and obesity. In silico screening PPAR gamma agonists based on quantitative structure-activity relationship (QSAR) models could serve as an efficient and pragmatic strategy. Owing to the broad research interests in discovery of PPAR gamma-targeted drugs, a large amount of PPAR gamma agonist activity data has been produced in the field of medicinal chemistry, facilitating development of robust QSAR models. In this study, random forest classifiers were developed based on the binary-category data transformed from the heterogeneous PPAR gamma agonist activity data of drug-like compounds. Coupling with applicability domains, capability of the established classifiers for predicting environmental chemicals was evaluated using two external data sets. Our results demonstrated that applicability domains could enhance application of the developed classifiers to predict environmental PPAR gamma agonists.

引用

页码：1382 / 1388

页数：7