Title: Comparison of methods for the selection of genomic biomarkers

Authors: Dan Lin; Abel Tilahun; Jose Cortinas Abrahantes; Ziv Shkedy; Geert Molenberghs; Hinrich W.H. Gohlmann; Willem Talloen; Luc Bijnens

Addresses: I-Biostat, Universiteit Hasselt, 3590, Diepenbeek, Belgium ' Department of Biostatistics, Harvard School of Public Health, 02138, Boston, MA, USA ' Scientific Assessment Support Unit, European Food Safety Authority, 43100, Parma, Italy ' I-Biostat, Universiteit Hasselt, 3590, Diepenbeek, Belgium ' I-Biostat, Universiteit Hasselt, 3590, Diepenbeek, Belgium; 3000, Katholieke Universiteit Leuven, Belgium ' Janssen Pharmaceutical Companies of Johnson and Johnson, 2340, Beerse, Belgium ' Janssen Pharmaceutical Companies of Johnson and Johnson, 2340, Beerse, Belgium ' Janssen Pharmaceutical Companies of Johnson and Johnson, 2340, Beerse, Belgium

Abstract: In recent years, a lot of attention is placed on the selection and evaluation of biomarkers in microarray experiments. Two sets of biomarkers are of importance, namely therapeutic and prognostic. The therapeutic biomarkers would give us information on the response of the genes to treatment in relation to the response of the clinical outcome to the same treatments, whereas the prognostic biomarkers enable us to predict the clinical outcome irrespective of treatments and other confounding factors. In this paper, we use different methods that allow for both linear and non-linear associations to select prognostic markers for depression, the response.

Keywords: prognostics biomarkers; microarray experiments; linear associations; nonlinear associations; genomic biomarkers; biomarker selection; clinical outcomes; depression; depressed patients; gene expression; bioinformatics; genetic biomarkers.

DOI: 10.1504/IJDMB.2013.054691

International Journal of Data Mining and Bioinformatics, 2013 Vol.8 No.1, pp.24 - 41

Received: 21 Apr 2010
Accepted: 22 May 2011

Published online: 20 Oct 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article