Prediction of Drug-Drug Interactions Based on Multi-layer Feature Selection and Data Balance

作     者：YUE Kejuan ZOU Beiji WANG Lei LI Xiao ZENG Min WEI Faran 

作者机构：School of Information Science and Engineering Central South University Center for Ophthalmic Imaging Research Central South university School of Information Science and Engineering Hunan First Normal University 

出 版 物：《Chinese Journal of Electronics》 (电子学报(英文))

年 卷 期：2017年第26卷第3期

页      面：585-590页

核心收录：

学科分类：1007[医学-药学(可授医学、理学学位)] 1006[医学-中西医结合] 100706[医学-药理学] 100602[医学-中西医结合临床] 10[医学] 

基　　金：supported by the National Natural Science Foundation of China(No.61573380,No.61672542) the Scientific Research Fund of Hunan Provincial Education Department(No.13C143) 

主　　题：Adverse event reports Drug-drug interactions(DDIs) Feature selection Data balance 

摘      要：Drug-drug interactions(DDIs)occur when two drugs react with each other,which may cause unexpected side effects and even death of the *** that use adverse event reports to predict unexpected DDIs are limited by two critical yet challenging *** is the difficulty of selecting discriminative features from numerous redundant and irrelevant adverse events for *** other is the data imbalance,i.e.,the drug pairs causing adverse effects are far less than those not causing adverse effects,which leads to poor accuracy of DDIs *** propose a multi-layer feature selection method to select discriminative adverse events and apply an over-sampling technique to make the data *** experimental results show that the validation accuracy of positive DDIs on the Canada Vigilance Adverse Reaction Online Database increases to two times,and 110 DDIs are identified on the drug interactions checker of *** in USA.