RESEARCH ARTICLE


Feature Selection Algorithm Based on Mutual Information and Lasso for Microarray Data



Wang Zhongxin1, Sun Gang1, 2, *, Zhang Jing3, Zhao Jia1
1 School of Computer and Information Engineering, Fuyang Teachers College, Fuyang, China
2 School of Computer and Information, Hefei University of Technology, Hefei, China
3 Information & Telecommunication Branch, State Grid Anhui Electric Power Company, Hefei, China


Article Metrics

CrossRef Citations:
0
Total Statistics:

Full-Text HTML Views: 2623
Abstract HTML Views: 792
PDF Downloads: 232
ePub Downloads: 282
Total Views/Downloads: 3929
Unique Statistics:

Full-Text HTML Views: 709
Abstract HTML Views: 429
PDF Downloads: 172
ePub Downloads: 127
Total Views/Downloads: 1437



© Zhongxin et al.; Licensee Bentham Open

open-access license: This is an open access article licensed under the terms of the Creative Commons Attribution-Non-Commercial 4.0 International Public License (CC BY-NC 4.0) (https://creativecommons.org/licenses/by-nc/4.0/legalcode), which permits unrestricted, non-commercial use, distribution and reproduction in any medium, provided the work is properly cited.

* Address correspondence to this authors at the Hefei University of Technology, Tunxi Rd. No. 193, Baohe, Hefei, Anhui, China; Tel: 0551-62902373; Fax: +0551-62902373; E-mail: ahfysungang@163.com


Abstract

With the development of microarray technology, massive microarray data is produced by gene expression experiments, and it provides a new approach for the study of human disease. Due to the characteristics of high dimensionality, much noise and data redundancy for microarray data, it is difficult to my knowledge from microarray data profoundly and accurately,and it also brings enormous difficulty for information genes selection. Therefore, a new feature selection algorithm for high dimensional microarray data is proposed in this paper, which mainly involves two steps. In the first step, mutual information method is used to calculate all genes, and according to the mutual information value, information genes is selected as candidate genes subset and irrelevant genes are filtered. In the second step, an improved method based on Lasso is used to select information genes from candidate genes subset, which aims to remove the redundant genes. Experimental results show that the proposed algorithm can select fewer genes, and it has better classification ability, stable performance and strong generalization ability. It is an effective genes feature selection algorithm.

Keywords: Feature selection, Lasso, Microarray data, Mutual information.