Forecasting the liver toxicity of traditional Chinese medicines using the quantitative structure-activity relationship(QSAR) model
作者单位：Emergency&Critical Care CenterBeijing Anzhen HospitalCapital Medical University Clinical Trial CenterDepartment of PharmacyBeijing 302 Hospital
会议名称：《第三届全国药物代谢动力学青年科学家论坛暨刘昌孝人才奖颁奖大会》
会议日期：2017年
学科分类：1008[医学-中药学(可授医学、理学学位)] 1006[医学-中西医结合] 100602[医学-中西医结合临床] 10[医学]
摘 要：Objective:Hepatotoxicity of traditional Chinese medicines(TCMs) has attracted worldwide concerns;however,data on TCM toxicity are *** major reason lies in that safety evaluation in vitro assays is much costly and time-consuming based on the numerous ingredients in varities of *** study aims to develop a more applicable and optimal tool to evaluate TCM ***:A quantitative structure-activity relationship(QSAR) analysis was performed based on published data and *** and Drug Administration’s Liver Toxicity Knowledge Base(LTKB).Results:Eleven herbal ingredients with proven liver toxicity in the literature were added into the dataset besides chemicals from *** generated QSAR model yielded a sensitivity of 83.8%,a specificity of 70.1% and an accuracy of 80.2%.As a comparison,using the same procedure,another QSAR model was built up on the basis of the identical compounds excluding the 11 herbal *** performance of the two QSAR models was further assessed by the external independent *** the externally tested 20 compounds from TCMs,14 hepatotoxins were all accurately predicted by the QSAR model generated from the dataset containing herbal ingredients;while 4 well-known hepatotoxins were not correctly predicted by the QSAR model generated from the dataset excluding herbal ***:Adding natural hepatotoxins into the dataset makes the QSAR model more applicable for TCM hepatotoxicity assessment,which provides a right direction in the methodology study for TCM safety *** generated QSAR model has the practical value to prioritize the hepatotoxicity risk of TCM compounds.