You are here: TUCS > PUBLICATIONS > Publication Search > Efficient Remote Homology Dete...
Efficient Remote Homology Detection
Antolin Janssen, Evgeni Tsivtsivadze, Jorma Boberg, Tjeerd M.H. Dijkstra, Tom Heskes, Efficient Remote Homology Detection. In: Supplementary Proceedings of Pattern Recognition in Bioinformatics, 5th IAPR International Conference, PRIB 2010 Nijmegen, The Netherlands, September 22-24, 2010, 2010.
Abstract:
We propose an effcient multi-class classication algorithm
for remote homology detection (RHD). Unlike methods that treat RHD
as a set of binary classication tasks, our algorithm solves a single multiclass
classication 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 classication algorithms. We evaluate
our method on the Structural Classication of Proteins database and
show that performance is better or comparable to several state-of-theart
algorithms for protein classication and remote homology detection.
BibTeX entry:
@INPROCEEDINGS{inpJaTsBoDiHe10a,
title = {Efficient Remote Homology Detection},
booktitle = {Supplementary Proceedings of Pattern Recognition in Bioinformatics, 5th IAPR International Conference, PRIB 2010 Nijmegen, The Netherlands, September 22-24, 2010},
author = {Janssen, Antolin and Tsivtsivadze, Evgeni and Boberg, Jorma and Dijkstra, Tjeerd M.H. and Heskes, Tom},
year = {2010},
}
Belongs to TUCS Research Unit(s): Turku BioNLP Group