Gesellschaft für Informatik e.V.

Lecture Notes in Informatics

German Conference on Bioinformatics GCB 2007 September 26 - 28, 2007, Potsdam, Germany P-115, 123-134 (2007).

Gesellschaft für Informatik, Bonn


Claudia Falter (ed.), Alexander Schliep (ed.), Joachim Selbig (ed.), Martin Vingron (ed.), Dirk Walther (ed.)

Copyright © Gesellschaft für Informatik, Bonn


Supervised posteriors for DNA -motif classification

Jan Grau , Jens Keilwagen , Alexander Kel , Ivo Grosse and Stefan Posch


Markov models have been proposed for the classification of DNA-motifs using generative approaches for parameter learning. Here, we propose to apply the discriminative paradigm for this problem and study two different priors to facilitate parameter estimation using the maximum supervised posterior. Considering seven sets of eukaryotic transcription factor binding sites we find this approach to be superior employing area under the ROC curve and false positive rate as performance criterion, and better in general using sensitivity. In addition, we discuss potential reasons for the improved performance.

Full Text: PDF

Gesellschaft für Informatik, Bonn
ISBN 978-3-88579-209-3

Last changed 04.10.2013 18:15:27