Related Experiment Video
Updated: May 23, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
Published on: October 11, 2018
Gene expression data analysis using multiobjective clustering improved with SVM based ensemble
Anirban Mukhopadhyay1, Ujjwal Maulik, Sanghamitra Bandyopadhyay
1Department of Computer Science and Engineering, University of Kalyani, Kalyani, India. anirban@klyuniv.ac.in
This study introduces a new multiobjective clustering method (MOCSVMEN) for analyzing gene expression data. It improves upon traditional methods by optimizing cluster compactness and separation simultaneously, leading to better identification of co-expressed genes.
Area of Science:
- Bioinformatics
- Computational Biology
- Genomics
Background:
- Microarray technology enables simultaneous monitoring of thousands of gene expression levels across diverse experimental conditions.
- Clustering is a key data mining technique for identifying co-expressed genes in microarray data.
- Traditional clustering methods often optimize a single criterion, limiting their effectiveness on varied datasets.
Purpose of the Study:
- To improve a multiobjective clustering technique for gene expression data analysis.
- To enhance cluster compactness and separation simultaneously using a novel support vector machine classification-based cluster ensemble method.
- To evaluate the performance of the proposed MOCSVMEN algorithm against existing microarray data clustering methods.
Main Methods:
- Development of a multiobjective clustering technique optimizing both cluster compactness and separation.
- Integration of a support vector machine classification-based cluster ensemble approach.
- Comparative performance analysis using two real-life benchmark gene expression datasets.
- Utilized the Biological Homogeneity Index (BHI) for evaluating clustering goodness with respect to functional annotation.
Main Results:
- The proposed MOCSVMEN algorithm demonstrated superior performance compared to several well-established microarray data clustering algorithms.
- The method effectively optimizes cluster compactness and separation simultaneously.
- Performance was validated using benchmark gene expression datasets and the BHI metric.
Conclusions:
- The MOCSVMEN algorithm represents a significant advancement in clustering microarray gene expression data.
- Simultaneous optimization of compactness and separation enhances the identification of biologically relevant gene clusters.
- The approach offers improved accuracy and reliability for analyzing complex genomic datasets.
Related Concept Videos
Cluster Sampling Method
To choose a cluster sample, divide the population into clusters (groups) and then randomly select some of the clusters. All the members from these clusters are in the cluster sample. For example, if you randomly sample four departments from your...
Multi-species Conserved Sequences
Although the genome of each species varies greatly from each other, a few sequences are highly conserved. Such conserved DNA...
RNA-seq
Before the discovery of RNA-seq, microarray-based methods and Sanger sequencing were used for transcriptome analysis. However, while microarray-based...
Multi-input and Multi-variable systems
In the absence of...
Comparing the Survival Analysis of Two or More Groups
DNA Microarrays