Drug repositioning based on comprehensive similarity measures and Bi-Random walk algorithm

• DOI: 10.1093/bioinformatics/btw228
• Publication Date: 2016-05-06T03:04:47Z
• Authors: Huimin Luo; Jianxin Wang; Min Li; Junwei Luo; Xiaoqing Peng; Fang-Xiang Wu; Yi Pan
• Keywords: Similarity (geometry); Drug repositioning; Drug Development

Drug repositioning, which aims to identify new indications for existing drugs, offers a promising alternative reduce the total time and cost of traditional drug development. Many computational strategies repositioning have been proposed, are based on similarities among drugs diseases. Current studies typically use either only drug-related properties (e.g. chemical structures) or disease-related phenotypes) calculate disease similarity, respectively, while not taking into account influence known drug-disease association information similarity measures.In this article, assumption that similar normally associated with diseases vice versa, we propose novel method named MBiRW, utilizes some comprehensive measures Bi-Random walk (BiRW) algorithm potential given drug. By integrating features associations, firstly developed Then network constructed, they incorporated heterogeneous interactions. Based network, BiRW is adopted predict associations. Computational experiment results from various datasets demonstrate proposed approach has reliable prediction performance outperforms several recent approaches. Moreover, case five selected further confirm superior our discover practically.http://github.com//bioinfomaticsCSU/MBiRW CONTACT: [e-mail] data available at Bioinformatics online.