Microbiome Data Representation by Joint Nonnegative Matrix Factorization with Laplacian Regularization

作     者：Jiang, Xingpeng Hu, Xiaohua Xu, Weiwei 

作者机构：Cent China Normal Univ Sch Comp Sci Wuhan Hubei Peoples R China Drexel Univ Coll Comp & Informat Philadelphia PA 19104 USA Wuhan Univ Int Sch Software Wuhan Hubei Peoples R China 

出 版 物：《IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS》 (IEEE/ACM Trans. Comput. BioL. Bioinf.)

年 卷 期：2017年第14卷第2期

页      面：353-359页

核心收录：

学科分类：0710[理学-生物学] 0808[工学-电气工程] 08[工学] 0714[理学-统计学（可授理学、经济学学位）] 0701[理学-数学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：US National Science Foundation (NSF) [IIP 1160960, NNS IIP 1332024, NSF CCF 0905291, NSFC 90920005, NSFC 61170189] China National 12-5 plan [2012BAK24B01] International Cooperation Project of Hubei Province [2014BHE0017] CCNU MOE [CCNU15ZD003] 

主　　题：Human microbiome nonnegative matrix factorization multi-view clustering data integration data representation 

摘      要：Microbiome datasets are often comprised of different representations or views which provide complementary information to understand microbial communities, such as metabolic pathways, taxonomic assignments, and gene families. Data integration methods including approaches based on nonnegative matrix factorization (NMF) combine multi-view data to create a comprehensive view of a given microbiome study by integrating multi-view information. In this paper, we proposed a novel variant of NMF which called Laplacian regularized joint non-negative matrix factorization (LJ-NMF) for integrating functional and phylogenetic profiles from HMP. We compare the performance of this method to other variants of NMF. The experimental results indicate that the proposed method offers an efficient framework for microbiome data analysis.