Effective Clustering Algorithms for Gene Expression Data

TL;DR

This paper proposes a hybrid clustering algorithm combining K-Means with CCIA to improve gene expression data analysis, addressing the challenge of specifying the number of clusters and demonstrating superior performance over traditional methods.

Contribution

It introduces a novel hybrid clustering approach that overcomes K-Means limitations in gene expression data analysis, with improved accuracy and cluster quality.

Findings

The proposed method outperforms traditional K-Means clustering.

It achieves higher Silhouette Coefficient scores.

The algorithm effectively identifies co-expressed gene groups.

Abstract

Microarrays are made it possible to simultaneously monitor the expression profiles of thousands of genes under various experimental conditions. Identification of co-expressed genes and coherent patterns is the central goal in microarray or gene expression data analysis and is an important task in Bioinformatics research. In this paper, K-Means algorithm hybridised with Cluster Centre Initialization Algorithm (CCIA) is proposed Gene Expression Data. The proposed algorithm overcomes the drawbacks of specifying the number of clusters in the K-Means methods. Experimental analysis shows that the proposed method performs well on gene Expression Data when compare with the traditional K- Means clustering and Silhouette Coefficients cluster measure.