Support Vector Based T-Score for Gene Ranking

  • Piyushkumar A. Mundra
  • Jagath C. Rajapakse
Conference paper

DOI: 10.1007/978-3-540-88436-1_13

Part of the Lecture Notes in Computer Science book series (LNCS, volume 5265)
Cite this paper as:
Mundra P.A., Rajapakse J.C. (2008) Support Vector Based T-Score for Gene Ranking. In: Chetty M., Ngom A., Ahmad S. (eds) Pattern Recognition in Bioinformatics. PRIB 2008. Lecture Notes in Computer Science, vol 5265. Springer, Berlin, Heidelberg

Abstract

T-score between classes and gene expressions is widely used for gene ranking in microarray gene expression data analysis. We propose to use only support vector points for computation of t-scores for gene ranking. The proposed method uses backward elimination of features, similar to Support Vector Machine Recursive Feature Elimination (SVM-RFE) formulation, but achieves better results than SVM-RFE and t-score based feature selection on three benchmark cancer datasets.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Piyushkumar A. Mundra
    • 1
  • Jagath C. Rajapakse
    • 1
    • 2
    • 3
  1. 1.Bioinformatics Research Center, School of Computer EngineeringNanyang Technological UniversitySingapore
  2. 2.Singapore-MIT AllianceSingapore
  3. 3.Department of Biological EngineeringMassachusetts Institute of TechnologyUSA

Personalised recommendations