gms | German Medical Science

51. Jahrestagung der Deutschen Gesellschaft für Medizinische Informatik, Biometrie und Epidemiologie

Deutsche Gesellschaft für Medizinische Informatik, Biometrie und Epidemiologie e. V. (gmds)

10. - 14.09.2006, Leipzig

Nonparametric Discrimination with Kernel Estimators in Microarray Analysis

Meeting Abstract

Search Medline for

  • Florian Pedross - Medizinische Universität Innsbruck, Innsbruck
  • Oliver Wrulich - Medizinische Universität Innsbruck, Innsbruck
  • Karl-Peter Pfeiffer - Medizinische Universität Innsbruck, Innsbruck

Deutsche Gesellschaft für Medizinische Informatik, Biometrie und Epidemiologie e.V. (gmds). 51. Jahrestagung der Deutschen Gesellschaft für Medizinische Informatik, Biometrie und Epidemiologie. Leipzig, 10.-14.09.2006. Düsseldorf, Köln: German Medical Science; 2006. Doc06gmds225

The electronic version of this article is the complete one and can be found online at: http://www.egms.de/en/meetings/gmds2006/06gmds385.shtml

Published: September 1, 2006

© 2006 Pedross et al.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by-nc-nd/3.0/deed.en). You are free: to Share – to copy, distribute and transmit the work, provided the original author and source are credited.


Outline

Text

In recent years rapid advances have been made in bioinformatics. Especially sequencing of the human genome provides a considerable amount of information in disease research. Gene expression levels of two different data sets, gained by microarray analysis, are investigated. The first microarray analysis concerns different leukemia types and the second pertains to prostate carcinoma patients in comparison to healthy persons. We try to find a good discrimination between the different findings. Statistical techniques, that can handle with situations, where the number of variables beats by far the number of experiments, are needed. We use nonparametric predictive discriminant analysis with kernel estimators. For reducing the error adaptive kernel estimators will be applied. In addition we will introduce a boosting algorithm for kernel density estimators, which re-weights the data using a log -odds ratio based on the leave-one-out estimator. Boosting is justified because it can be shown that the bias can be reduced considerably. Different resampling techniques are tried to minimize misclassification rates.