A Discriminative Framework for Detecting Remote Protein Homologies
- 1 February 2000
- journal article
- research article
- Published by Mary Ann Liebert Inc in Journal of Computational Biology
- Vol. 7 (1-2) , 95-114
- https://doi.org/10.1089/10665270050081405
Abstract
A new method for detecting remote protein homologies is introduced and shown to perform well in classifying protein domains by SCOP superfamily. The method is a variant of support vector machines using a new kernel function. The kernel function is derived from a generative statistical model for a protein family, in this case a hidden Markov model. This general approach of combining generative models like HMMs with discriminative methods such as support vector machines may have applications in other areas of biosequence analysis as well.Keywords
This publication has 20 references indexed in Scilit:
- Position-based sequence weightsPublished by Elsevier ,2004
- Comprehensive assessment of automatic structural alignment against a manual standard, the scop classification of proteinsProtein Science, 1998
- Methods and Statistics for Combining Motif Match ScoresJournal of Computational Biology, 1998
- Gapped BLAST and PSI-BLAST: a new generation of protein database search programsNucleic Acids Research, 1997
- [27] Local alignment statisticsPublished by Elsevier ,1996
- Prediction of protein folding class using global description of amino acid sequence.Proceedings of the National Academy of Sciences, 1995
- Maximum Discrimination Hidden Markov Models of Sequence ConsensusJournal of Computational Biology, 1995
- Hidden Markov models of biological primary sequence information.Proceedings of the National Academy of Sciences, 1994
- Basic Local Alignment Search ToolJournal of Molecular Biology, 1990
- Profile analysis: detection of distantly related proteins.Proceedings of the National Academy of Sciences, 1987