Gene Selection for Cancer Classification through Ensemble of Methods

The paper develops the methods of selection of the most important gene sequence on the basis of the gene expression microarray, corresponding to different types of cancer. Special two stage strategy of selection has been proposed. In the first stage we apply few different methods of assessment of the importance of genes. Each method stresses different aspects of the problem. In the second stage the selected genes are compared and the genes chosen most frequently by all methods of selection are treated as the most important and representative for the particular type of problem. The results of selection are analyzed using PCA and the selected genes form the input to the SVM classifier recognizing the classes of cancer. The numerical experiments confirm the efficiency of the proposed approach.

[1]  Jason Weston,et al.  Gene Selection for Cancer Classification using Support Vector Machines , 2002, Machine Learning.

[2]  Vojislav Kecman,et al.  Gene extraction for cancer diagnosis by support vector machines - An improvement , 2005, Artif. Intell. Medicine.

[3]  G. McLachlan,et al.  Pattern Classification: A Unified View of Statistical and Neural Approaches. , 1998 .

[4]  W. J. Conover,et al.  Practical Nonparametric Statistics , 1972 .

[5]  Yuriy Gusev,et al.  Computational analysis of biological functions and pathways collectively targeted by co-expressed microRNAs in cancer , 2007, BMC Bioinformatics.

[6]  Jürgen Schürmann,et al.  Pattern classification , 2008 .

[7]  Wei Pan,et al.  Linear regression and two-class classification with gene expression data , 2003, Bioinform..

[8]  Jean-Philippe Vert.  Kernel Methods in Genomics and Computational Biology , 2005 .

[9]  J. Stuart Aitken,et al.  Feature selection and classification for microarray data analysis: Evolutionary methods for identifying predictive genes , 2005, BMC Bioinformatics.

[10]  Bernhard Schölkopf,et al.  Learning with kernels , 2001 .

[11]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

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

[13]  Louise C. Showe,et al.  Recursive Cluster Elimination (RCE) for classification and feature selection from gene expression data , 2007, BMC Bioinformatics.