Logo des Repositoriums
 

PALMA: Perfect alignments using large margin algorithms

dc.contributor.authorRätsch, G.
dc.contributor.authorHepp, B.
dc.contributor.authorSchulze, U.
dc.contributor.authorOng, C. S.
dc.contributor.editorHuson, Daniel
dc.contributor.editorKohlbacher, Oliver
dc.contributor.editorLupas, Andrei
dc.contributor.editorNieselt, Kay
dc.contributor.editorZell, Andreas
dc.date.accessioned2019-08-12T13:06:16Z
dc.date.available2019-08-12T13:06:16Z
dc.date.issued2006
dc.description.abstractDespite many years of research on how to properly align sequences in the presence of sequencing errors, alternative splicing and micro-exons, the correct alignment of mRNA sequences to genomic DNA is still a challenging task. We present a novel approach based on large margin learning that combines kernel based splice site predictions with common sequence alignment techniques. By solving a convex optimization problem, our algorithm – called PALMA – tunes the parameters of the model such that the true alignment scores higher than all other alignments. In an experimental study on the alignments of mRNAs containing artificially generated micro-exons, we show that our algorithm drastically outperforms all other methods: It perfectly aligns all 4358 sequences on an hold-out set, while the best other method misaligns at least 90 of them. Moreover, our algorithm is very robust against noise in the query sequence: when deleting, inserting, or mutating up to 50% of the query sequence, it still aligns 95% of all sequences correctly, while other methods achieve less than 36% accuracy. For datasets, additional results and a stand-alone alignment tool see http://www.fml.mpg.de/raetsch/projects/palma.en
dc.identifier.isbn978-3-88579-177-5
dc.identifier.pissn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/24204
dc.language.isoen
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartofGerman Conference on Bioinformatics
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) - Proceedings, Volume P-83
dc.titlePALMA: Perfect alignments using large margin algorithmsen
dc.typeText/Conference Paper
gi.citation.endPage113
gi.citation.publisherPlaceBonn
gi.citation.startPage104
gi.conference.dateSeptember 19-22, 2006
gi.conference.locationTübingen
gi.conference.sessiontitleRegular Research Papers

Dateien

Originalbündel
1 - 1 von 1
Lade...
Vorschaubild
Name:
104.pdf
Größe:
511.96 KB
Format:
Adobe Portable Document Format