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

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.

[1]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[2]  Jianping Li,et al.  A multiple kernel support vector machine scheme for feature selection and rule extraction from gene expression data of cancer tissue , 2007, Artif. Intell. Medicine.

[3]  Li-Yeh Chuang,et al.  A Hybrid BPSO-CGA Approach for Gene Selection and Classification of Microarray Data , 2012, J. Comput. Biol..

[4]  Wang Shu.  Heuristic Breadth-First Search Algorithm for Informative Gene Selection Based on Gene Expression Profiles , 2008 .

[5]  Stefan Arnborg.  Data Mining : Opportunities and Challenges chapter 1: A Survey of Bayesian Data Mining. , 2003 .

[6]  Fillia Makedon,et al.  HykGene: a hybrid approach for selecting marker genes for phenotype classification using microarray gene expression data , 2005, Bioinform..

[7]  Marko Robnik-Sikonja,et al.  Theoretical and Empirical Analysis of ReliefF and RReliefF , 2003, Machine Learning.

[8]  Alfredo Benso,et al.  A cDNA Microarray Gene Expression Data Classifier for Clinical Diagnostics Based on Graph Theory , 2011, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[9]  Pedro Larrañaga,et al.  A review of feature selection techniques in bioinformatics , 2007, Bioinform..

[10]  Weixiang Liu,et al.  An experimental comparison of gene selection by Lasso and Dantzig selector for cancer classification , 2011, Comput. Biol. Medicine.

[11]  Blaise Hanczar,et al.  Improving classification of microarray data using prototype-based feature selection , 2003, SKDD.

[12]  J. Mesirov,et al.  Molecular classification of cancer: class discovery and class prediction by gene expression monitoring. , 1999, Science.

[13]  LarrañagaPedro,et al.  A review of feature selection techniques in bioinformatics , 2007 .