Research Article

Predicting protein structure using hidden Markov models

  1. Kevin Karplus1,*,
  2. Kimmen Sjölander2,
  3. Christian Barrett1,
  4. Melissa Cline2,
  5. David Haussler2,
  6. Richard Hughey1,
  7. Liisa Holm3,
  8. Chris Sander3

Article first published online: 7 DEC 1998

DOI: 10.1002/(SICI)1097-0134(1997)1+<134::AID-PROT18>3.0.CO;2-P

Issue

Proteins: Structure, Function, and Bioinformatics

Proteins: Structure, Function, and Bioinformatics

Supplement: Supplement 1

Volume 29, Issue Supplement 1, pages 134–139, 1997

Additional Information

How to Cite

Karplus, K., Sjölander, K., Barrett, C., Cline, M., Haussler, D., Hughey, R., Holm, L. and Sander, C. (1997), Predicting protein structure using hidden Markov models. Proteins, 29: 134–139. doi: 10.1002/(SICI)1097-0134(1997)1+<134::AID-PROT18>3.0.CO;2-P

Author Information

  1. 1

    Computer Engineering, University of California, Santa Cruz, California

  2. 2

    Computer Science, University of California, Santa Cruz, California

  3. 3

    EBI, United Kingdom

*Computer Engineering Department, Jack Baskin School of Engineering, University of California, Santa Cruz, CA 95064

Publication History

  1. Issue published online: 7 DEC 1998
  2. Article first published online: 7 DEC 1998
  3. Manuscript Accepted: 2 SEP 1997
  4. Manuscript Received: 5 MAY 1997

Funded by

  • NSF. Grant Numbers: CDA-9115268, IRI-9123692, BIR-9408579
  • DOE. Grant Number: 94-12-048216
  • ONR. Grant Number: N00014-91-J-1162
  • NIH. Grant Number: GM17129
  • NFS
  • GAANN graduate fellowships
  • UCSC Division of Natural Sciences

SEARCH

SEARCH BY CITATION

ARTICLE TOOLS

Get PDF (79K)

Keywords:

  • CASP2;
  • fold-recognition;
  • HMM;
  • structure library;
  • remote homology

Abstract

We discuss how methods based on hidden Markov models performed in the fold-recognition section of the CASP2 experiment. Hidden Markov models were built for a representative set of just over 1,000 structures from the Protein Data Bank (PDB). Each CASP2 target sequence was scored against this library of HMMs. In addition, an HMM was built for each of the target sequences and all of the sequences in PDB were scored against that target model, with a good score on both methods indicating a high probability that the target sequence is homologous to the structure. The method worked well in comparison to other methods used at CASP2 for targets of moderate difficulty, where the closest structure in PDB could be aligned to the target with at least 15% residue identity. Proteins, Suppl. 1:134–139, 1997. © 1998 Wiley-Liss, Inc.

Get PDF (79K)