A discriminative framework for detecting remote protein homologies

J Comput Biol. 2000 Feb-Apr;7(1-2):95-114. doi: 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.

Publication types

  • Research Support, U.S. Gov't, Non-P.H.S.

MeSH terms

  • Biometry
  • Databases, Factual
  • GTP-Binding Proteins / genetics
  • Markov Chains
  • Models, Statistical
  • Proteins / genetics*
  • Sequence Alignment / statistics & numerical data*
  • Sequence Analysis, Protein / statistics & numerical data*

Substances

  • Proteins
  • GTP-Binding Proteins