Efficient remote homology detection

Antolin Janssen, E. Tsivtsivadze, J. Boberg, T.M.H. Dijkstra, T. Heskes

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

3 Downloads (Pure)

Abstract

We propose an effcient multi-class classiffcation algorithm for remote homology detection (RHD). Unlike methods that treat RHD as a set of binary classiffcation tasks, our algorithm solves a single multiclass classiffcation problem by incorporating information about classwise correlations among the proteins using joint kernel functions. Furthermore,the proposed method leads to notable reduction in computational time compared to binary classiffcation algorithms. We evaluate our method on the Structural Classiffcation of Proteins database and show that performance is better or comparable to several state-of-theartalgorithms for protein classiffcation and remote homology detection.
Original languageEnglish
Title of host publicationProceedings of the Pattern Recognition in Bioinformatics, 22 - 24 September 2010, Nijmegen, The Netherlands
Publication statusPublished - 2010

Fingerprint Dive into the research topics of 'Efficient remote homology detection'. Together they form a unique fingerprint.

Cite this