Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
  Learning interpretable SVMs for biological sequence classification

Sonnenburg, S., Rätsch, G., & Schäfer, C. (2005). Learning interpretable SVMs for biological sequence classification. In S. Miyano, J. Mesirov, S. Kasif, S. Istrail, P. Pevzner, & M. Waterman (Eds.), Research in Computational Molecular Biology: 9th Annual International Conference, RECOMB 2005, Cambridge, MA, USA, May 14-18, 2005 (pp. 389-407). Berlin, Germany: Springer.

Item is

Basisdaten

einblenden: ausblenden:
Genre: Konferenzbeitrag

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Sonnenburg, S, Autor           
Rätsch, G1, Autor           
Schäfer, C, Autor
Affiliations:
1Rätsch Group, Friedrich Miescher Laboratory, Max Planck Society, ou_3378052              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: We propose novel algorithms for solving the so-called Support Vector Multiple Kernel Learning problem and show how they can be used to understand the resulting support vector decision function. While classical kernel-based algorithms (such as SVMs) are based on a single kernel, in Multiple Kernel Learning a quadratically-constraint quadratic program is solved in order to find a sparse convex combination of a set of support vector kernels. We show how this problem can be cast into a semi-infinite linear optimization problem which can in turn be solved efficiently using a boosting-like iterative method in combination with standard SVM optimization algorithms. The proposed method is able to deal with thousands of examples while combining hundreds of kernels within reasonable time.

In the second part we show how this technique can be used to understand the obtained decision function in order to extract biologically relevant knowledge about the sequence analysis problem at hand. We consider the problem of splice site identification and combine string kernels at different sequence positions and with various substring (oligomer) lengths. The proposed algorithm computes a sparse weighting over the length and the substring, highlighting which substrings are important for discrimination. Finally, we propose a bootstrap scheme in order to reliably identify a few statistically significant positions, which can then be used for further analysis such as consensus finding.

Details

einblenden:
ausblenden:
Sprache(n):
 Datum: 2005
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: DOI: 10.1007/11415770_30
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: 9th Annual International Conference on Research in Computational Molecular Biology (RECOMB 2005)
Veranstaltungsort: Cambridge, MA, USA
Start-/Enddatum: 2005-05-14 - 2005-05-18

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: Research in Computational Molecular Biology: 9th Annual International Conference, RECOMB 2005, Cambridge, MA, USA, May 14-18, 2005
Genre der Quelle: Konferenzband
 Urheber:
Miyano, S, Herausgeber
Mesirov, J, Herausgeber
Kasif, S, Herausgeber
Istrail, S, Herausgeber
Pevzner, PA, Herausgeber
Waterman, M, Herausgeber
Affiliations:
-
Ort, Verlag, Ausgabe: Berlin, Germany : Springer
Seiten: 632 Band / Heft: - Artikelnummer: - Start- / Endseite: 389 - 407 Identifikator: ISBN: 978-3-540-25866-7
DOI: 10.1007/b135594

Quelle 2

einblenden:
ausblenden:
Titel: Lecture Notes in Computer Science
Genre der Quelle: Reihe
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: -
Seiten: - Band / Heft: 3500 Artikelnummer: - Start- / Endseite: - Identifikator: -