Gene selection for cancer classification through ensemble of methods

Authors:
Artur Wilinski;Stanislaw Osowski;Krzysztof Siwek
Affiliations:
Warsaw University of Life Sciences, Warsaw, Poland;Military University of Technology and Warsaw University of Technology, Warsaw, Poland;Warsaw University of Technology, Warsaw, Poland
Venue:
ICANNGA'09 Proceedings of the 9th international conference on Adaptive and natural computing algorithms
Year:
2009

Citing 4
Cited 1

Pattern classification: a unified view of statistical and neural approaches

Pattern classification: a unified view of statistical and neural approaches
Gene Selection for Cancer Classification using Support Vector Machines

Machine Learning
An introduction to variable and feature selection

The Journal of Machine Learning Research
Gene extraction for cancer diagnosis by support vector machines-An improvement

Artificial Intelligence in Medicine

A Survey on Filter Techniques for Feature Selection in Gene Expression Microarray Analysis

IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.