用于样本聚类和网络分析的整合鲁棒结构化NMF模型  

Integrated Robust Structured NMF Model for Sample Clustering and Network Analysis

作　　者：张晓宁 孔祥真[1] 罗传文 刘金星 ZHANG Xiaoning;KONG Xiangzhen;LUO Chuanwen;LIU Jinxing(School of Computer,Qufu Normal University,Rizhao 276826,Shandong,China;School of Information,Beijing Forestry University,Beijing 100083,China)

机构地区：[1]曲阜师范大学计算机学院,山东日照276826 [2]北京林业大学信息学院,北京100083

出　　处：《应用科学学报》2020年第5期825-842,共18页Journal of Applied Sciences

基　　金：国家自然科学基金(No.61872220,No.61702299)资助。

摘　　要：为了更好地保留数据之间的同质性,提出了一种整合鲁棒结构化非负矩阵分解(integrated robust structured non-negative matrix factorization,iRSNMF)模型,并在该模型中引入一个结构化项.将该模型用于癌症样本聚类实验和基因共表达网络分析,以验证其有效性.根据现有文献对相关基因和通路进行生物学解释.实验结果表明,iRSNMF模型聚类性能较好并且能够挖掘到的关键基因更多.用iRSNMF模型获得的基因和通路在癌症的发病机制中起着重要作用,并为癌症诊断、治疗和预后提供了新的思路.In order to preserve the homogeneity among data more effectively,this paper proposes an integrated robust structured non-negative matrix factorization(integrated robust structured non-negative matrix factorization,iRSNMF)model with an induced structured term.We verify the effectiveness of this model by applying it to the clustering experiments of cancer samples and the analysis of gene co-expression network.Reasonable biological explanations of related genes and pathways are given based on existing literature.Experimental results show that the iRSNMF method has excellent clustering performance and more-key genes mining ability.The genes and pathways obtained by the iRSNMF model play an important role in cancer pathogenesis,accordingly,providing a new idea for the diagnosis,treatment and prognosis of cancer.

关 键 词：整合模型 结构化 非负矩阵分解 样本聚类 基因共表达网络分析 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]