Logo des Repositoriums
 

Supervised posteriors for DNA-motif classification

Kurzanzeige
dc.contributor.authorGrau, Jan
dc.contributor.authorKeilwagen, Jens
dc.contributor.authorKel, Alexander
dc.contributor.authorGrosse, Ivo
dc.contributor.authorPosch, Stefan
dc.contributor.editorFalter, Claudia
dc.contributor.editorSchliep, Alexander
dc.contributor.editorSelbig, Joachim
dc.contributor.editorVingron, Martin
dc.contributor.editorWalther, Dirk
dc.date.accessioned2019-05-15T08:32:28Z
dc.date.available2019-05-15T08:32:28Z
dc.date.issued2007
dc.description.abstractMarkov 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.en
dc.identifier.isbn978-3-88579-209-3
dc.identifier.pissn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/22362
dc.language.isoen
dc.publisherGesellschaft für Informatik e. V.
dc.relation.ispartofGerman conference on bioinformatics – GCB 2007
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) - Proceedings, Volume P-115
dc.titleSupervised posteriors for DNA-motif classificationen
dc.typeText/Conference Paper
gi.citation.endPage134
gi.citation.publisherPlaceBonn
gi.citation.startPage123
gi.conference.dateSeptember 26-28, 2007, Potsdam,
gi.conference.locationPotsdam
gi.conference.sessiontitleRegular Research Papers

Dateien

Originalbündel
1 - 1 von 1
Vorschaubild
Name:
123.pdf
Größe:
833.63 KB
Format:
Adobe Portable Document Format
Herunterladen

Sammlungen

P115 - GCB 2007 - German Conference on Bioinformatics 2007