A Novel Soft Clustering Approach for Gene Expression Data

作     者：E.Kavitha R.Tamilarasan Arunadevi Baladhandapani M.K.Jayanthi Kannan 

作者机构：A Constituent College of Anna UniversityUniversity College of EngineeringVillupuram605103India A Constituent College of Anna UniversityUniversity College of EngineeringPattukkottai614701India Department of Electronics and Communication EngineeringDr.N.G.P Institute of TechnologyCoimbatore641048India Department of Computer Science EngineeringFaculty of Engineering and TechnologyJAIN(Deemed to be University)Bangalore562112India 

出 版 物：《Computer Systems Science & Engineering》 (计算机系统科学与工程（英文）)

年 卷 期：2022年第43卷第12期

页      面：871-886页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Reinforcement membership centroid threshold statistics bioinformatics gene expression data 

摘      要：Gene expression data represents a condition matrix where each rowrepresents the gene and the column shows the condition. Micro array used todetect gene expression in lab for thousands of gene at a time. Genes encode proteins which in turn will dictate the cell function. The production of messengerRNA along with processing the same are the two main stages involved in the process of gene expression. The biological networks complexity added with thevolume of data containing imprecision and outliers increases the challenges indealing with them. Clustering methods are hence essential to identify the patternspresent in massive gene data. Many techniques involve hierarchical, partitioning,grid based, density based, model based and soft clustering approaches for dealingwith the gene expression data. Understanding the gene regulation and other usefulinformation from this data can be possible only through effective clustering algorithms. Though many methods are discussed in the literature, we concentrate onproviding a soft clustering approach for analyzing the gene expression data. Thepopulation elements are grouped based on the fuzziness principle and a degree ofmembership is assigned to all the elements. An improved Fuzzy clustering byLocal Approximation of Memberships (FLAME) is proposed in this workwhich overcomes the limitations of the other approaches while dealing with thenon-linear relationships and provide better segregation of biological functions.