Unsupervised selection of informative genes in microarray gene expression data. (2016)

• Record Type: Journal Article
• Authors: Liaghat, Samaneh; Mansoori, Eghbal G.
• Is Part Of: International journal of applied pattern recognition. Volume 3:Number 4(2016)
• Page Start: 351
• Page End: 367
• Publication Date: 2016
• Subjects: DNA microarrays -- gene expression data -- unsupervised gene selection -- Hilbert-Schmidt independence criterion -- HSIC -- bioinformatics -- dependency maximisation -- similarity matrices -- gap statistics -- k-means clustering; Pattern perception -- Periodicals; Pattern recognition systems -- Periodicals; 006.405
• Languages: English
• ISSNs: 2049-887X

Abstract

With respect to DNA microarray has produced massive amounts of gene expression data with high dimension in recent years, gene selection is one of the bottlenecks of gene expression datasets analysis. This paper presents a framework for unsupervised gene selection based on dependency maximisation between the samples similarity matrices of before and after deleting a gene, using a novel estimation of the Hilbert-Schmidt independence criterion (HSIC). The key idea is that elimination of genes which are redundant and/or have much relevancy with other genes does not have much effect on pairwise samples similarity. Also, to deal with diagonally dominant matrices, the dynamic range of matrix values is reduced. Additionally, gap statistic and k-means clustering methods are used to increase the speed of proposed methods. Experimental validation is conducted on several microarray gene expression datasets and the results show that our gene selection scheme works well in practice.