Remote homology detection based on oligomer distances
Open Access
- 12 July 2006
- journal article
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 22 (18) , 2224-2231
Abstract
Motivation: Remote homology detection is among the most intensively researched problems in bioinformatics. Currently discriminative approaches, especially kernel-based methods, provide the most accurate results. However, kernel methods also show several drawbacks: in many cases prediction of new sequences is computationally expensive, often kernels lack an interpretable model for analysis of characteristic sequence features, and finally most approaches make use of so-called hyperparameters which complicate the application of methods across different datasets.Keywords
This publication has 20 references indexed in Scilit:
- Application of latent semantic analysis to protein remote homology detectionBioinformatics, 2005
- Semi-supervised protein classification using cluster kernelsBioinformatics, 2005
- Protein homology detection using string alignment kernelsBioinformatics, 2004
- Mismatch string kernels for discriminative protein classificationBioinformatics, 2004
- Sequence comparisons using multiple sequences detect three times as many remote homologues as pairwise methodsJournal of Molecular Biology, 1998
- SCOP: A structural classification of proteins database for the investigation of sequences and structuresJournal of Molecular Biology, 1995
- Hidden Markov Models in Computational BiologyJournal of Molecular Biology, 1994
- Basic Local Alignment Search ToolJournal of Molecular Biology, 1990
- Basic local alignment search toolJournal of Molecular Biology, 1990
- Identification of common molecular subsequencesJournal of Molecular Biology, 1981