Combining dissimilarity based classifiers for cancer prediction using gene expression profiles

Manuel Martín-Merino,Ángela Blanco,Javier De Las Rivas

doi:10.1186/1471-2105-8-s8-s3

Abstract

Presentacion oral, parte del suplemento: Highlights from the Third International Society for Computational Biology (ISCB) Student Council Symposium at the Fifteenth Annual International Conference on Intelligent Systems for Molecular Biology (ISMB) Vienna, Austria. 21 July 2007.

Highlights

DNA Microarrays allow us to monitor the expression level of thousands of genes simultaneously across a collection of related samples
Common Support Vector Machines (SVM) algorithms rely on the use of the Euclidean distance which does not reflect accurately the proximities among the sample profiles [1]
This feature favors the misclassification of cancer samples which is a serious drawback in our application

Summary

Background

DNA Microarrays allow us to monitor the expression level of thousands of genes simultaneously across a collection of related samples. Support Vector Machines (SVM) have been applied to identify cancer samples considering the gene expression levels with encouraging results This kind of techniques are able to deal with high dimensional and noisy data which is an important requirement in our practical problem. Common SVM algorithms rely on the use of the Euclidean distance which does not reflect accurately the proximities among the sample profiles [1] This feature favors the misclassification of cancer samples (false negative errors) which is a serious drawback in our application. To avoid the bias introduced by resampling techniques, we propose a combination strategy that builds the diversity of classifiers considering a set of dissimilarities that reflect different features of the data. Our method is able to work directly from a dissimilarity matrix

Experimental results

Method

Conclusion