Identifying significant genes with FM/CM-GA

Authors:
Rommel A. Benites Palomino;Lily R. Liang;Zhao Lu;Vinay Mandal;Deepak Kumar
Affiliations:
Department of Computer Science and Information Technology, University of the District of Columbia, Washington, D.C.;Department of Computer Science and Information Technology, University of the District of Columbia, Washington, D.C;Department of Electrical Engineering, Tuskegee University, Tuskegee, Alabama;Department of Computer Science, Wayne State University, Detroit, MI;Department of Biological and Environmental Sciences, University of the District of Columbia, Washington, D.C.
Venue:
MACMESE'09 Proceedings of the 11th WSEAS international conference on Mathematical and computational methods in science and engineering
Year:
2009

Citing 4
Cited 0

Genetic Algorithms in Search, Optimization and Machine Learning

Genetic Algorithms in Search, Optimization and Machine Learning
Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)

Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)
Applying Data Mining Techniques for Cancer Classification from Gene Expression Data

ICCIT '07 Proceedings of the 2007 International Conference on Convergence Information Technology
Introduction to Genetic Algorithms

Introduction to Genetic Algorithms

Quantified Score

Hi-index	0.00

Visualization

Abstract

Nowadays, there is a dramatic increase of the demand for new algorithms or techniques that is capable to solve complex computing problems on very large datasets. Particularly of great significance in practice are algorithms for finding optimal solution for a given problem with a high number of attributes or variables, such as selecting the most representative human genes from a microarray dataset. In this paper, we propose a new approach, FM/CM-GA, to identify significant genes from microarray datasets. FM/CM-GA combines our innovative FM/CM-test with genetic algorithm and leverages the strengths of each of them. The result is a list of selected genes that contribute significantly to a particular disease. The performance of FM/CM-GA is evaluated by the classification accuracy achieved by using the selected genes as features. Experiments are conducted to demonstrate the superiority of the proposed method over other approaches.