Metabolite-Disease Association Prediction Algorithm Combining DeepWalk and Random Forest

作     者：Jiaojiao Tie Xiujuan Lei Yi Pan Jiaojiao Tie;Xiujuan Lei;Yi Pan

作者机构：the School of Computer ScienceShaanxi Normal UniversityXi'an 710119China the the Department of Computer ScienceGeorgia State UniversityAtlanta.GA 30302-3994USA 

出 版 物：《Tsinghua Science and Technology》 (清华大学学报（自然科学版（英文版）)

年 卷 期：2022年第27卷第1期

页      面：58-67页

核心收录：

学科分类：1001[医学-基础医学(可授医学、理学学位)] 100104[医学-病理学与病理生理学] 10[医学] 

主　　题：Deep Walk random forest metabolite-disease associations molecular fingerprint similarity of metabolites 

摘      要：Identifying the association between metabolites and diseases will help us understand the pathogenesis of diseases,which has great significance in diagnosing and treating ***,traditional biometric methods are time consuming and ***,we propose a new metabolite-disease association prediction algorithm based on DeepWalk and random forest(DWRF),which consists of the following key steps:First,the semantic similarity and information entropy similarity of diseases are integrated as the final disease ***,molecular fingerprint similarity and information entropy similarity of metabolites are integrated as the final metabolite ***,DeepWalk is used to extract metabolite features based on the network of metabolite-gene ***,a random forest algorithm is employed to infer metabolite-disease *** experimental results show that DWRF has good performances in terms of the area under the curve value,leave-one-out cross-validation,and five-fold *** studies also indicate that DWRF has a reliable performance in metabolite-disease association prediction.