Mining gene expression datasets using density-based clustering

Given the recent advancement of microarray technologies, we present a density-based clustering approach for the purpose of co-expressed gene cluster identification. The underlying hypothesis is that a set of co-expressed gene clusters can be used to reveal a common biological function. By addressing the strengths and limitations of previous densitybased clustering approaches, we present a novel clustering algorithm that utilizes a neighborhood defined by k-nearest neighbors. Experimental results indicate that the proposed method identifies biologically meaningful and co-expressed gene clusters. Categories and Subject Descriptors I.5.3 [Pattern Recognition]: Clustering General Terms Algorithms Keywords Density-based Clustering, Gene Expression Analysis, Microarray Analysis

• Type: Conference
• Year: 2004
• Where: CIKM
• Authors: Seokkyung Chung, Jongeun Jun, Dennis McLeod
• Keywords: CIKM 2004, Co-expressed Gene Clusters, Density-based Clustering, Density-based Clustering Approach