Inferring potential small molecule–miRNA association based on triple layer heterogeneous network

doi:10.1186/s13321-018-0284-9

	Inferring potential small molecule–miRNA association based on triple layer heterogeneous network
	Qu,Jia 1; Chen,Xing 1; Sun,Ya-Zhou 2,3; Li,Jian-Qiang 2,3; Ming,Zhong 2,3
刊名	Journal of Cheminformatics
	2018-06-26
卷号	10 期号:1
关键词	microRNA Small molecule Association prediction Triple layer heterogeneous network
ISSN号	1758-2946
DOI	10.1186/s13321-018-0284-9
英文摘要	AbstractRecently, many biological experiments have indicated that microRNAs (miRNAs) are a newly discovered small molecule (SM) drug targets that play an important role in the development and progression of human complex diseases. More and more computational models have been developed to identify potential associations between SMs and target miRNAs, which would be a great help for disease therapy and clinical applications for known drugs in the field of medical research. In this study, we proposed a computational model of triple layer heterogeneous network based small molecule–MiRNA association prediction (TLHNSMMA) to uncover potential SM–miRNA associations by integrating integrated SM similarity, integrated miRNA similarity, integrated disease similarity, experimentally verified SM–miRNA associations and miRNA–disease associations into a heterogeneous graph. To evaluate the performance of TLHNSMMA, we implemented global and two types of local leave-one-out cross validation as well as fivefold cross validation to compare TLHNSMMA with one previous classical computational model (SMiR-NBI). As a result, for Dataset 1, TLHNSMMA obtained the AUCs of 0.9859, 0.9845, 0.7645 and 0.9851?±?0.0012, respectively; for Dataset 2, the AUCs are in turn 0.8149, 0.8244, 0.6057 and 0.8168?±?0.0022. As the result of case studies shown, among the top 10, 20 and 50 potential SM-related miRNAs, there were 2, 7 and 14 SM–miRNA associations confirmed by experiments, respectively. Therefore, TLHNSMMA could be effectively applied to the prediction of SM–miRNA associations.
语种	英语
出版者	Springer International Publishing
WOS记录号	BMC:10.1186/S13321-018-0284-9
内容类型	期刊论文
源URL	[http://ir.amss.ac.cn/handle/2S8OKBNM/428]
专题	中国科学院数学与系统科学研究院
通讯作者	Chen,Xing
作者单位	1. 2. 3.
推荐引用方式 GB/T 7714	Qu,Jia,Chen,Xing,Sun,Ya-Zhou,et al. Inferring potential small molecule–miRNA association based on triple layer heterogeneous network[J]. Journal of Cheminformatics,2018,10(1).
APA	Qu,Jia,Chen,Xing,Sun,Ya-Zhou,Li,Jian-Qiang,&Ming,Zhong.(2018).Inferring potential small molecule–miRNA association based on triple layer heterogeneous network.Journal of Cheminformatics,10(1).
MLA	Qu,Jia,et al."Inferring potential small molecule–miRNA association based on triple layer heterogeneous network".Journal of Cheminformatics 10.1(2018).