Mining residue contacts in proteins using local structure predictions

Mohammed J. Zaki, Shan Jin, Chris Bystroff

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

In this paper we develop data mining techniques to predict three-dimensional (3-D) contact potentials among protein residues (or amino acids) based on the hierarchical nucleation-propagation model of protein folding. We apply a hybrid approach, using a hidden Markov model to extract folding initiation sites, and then apply association mining to discover contact potentials. The new hybrid approach achieves accuracy results better than those reported previously.

Original languageEnglish
Pages (from-to)789-801
Number of pages13
JournalIEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Volume33
Issue number5
DOIs
Publication statusPublished - 1 Oct 2003
Externally publishedYes

Fingerprint

Protein folding
Data Mining
Protein Folding
Hidden Markov models
Data mining
Amino acids
Nucleation
Association reactions
Proteins
Amino Acids

Keywords

  • Association rules
  • Contact maps
  • Data mining
  • Hidden Markov models
  • Protein structure prediction

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Artificial Intelligence
  • Human-Computer Interaction

Cite this

Mining residue contacts in proteins using local structure predictions. / Zaki, Mohammed J.; Jin, Shan; Bystroff, Chris.

In: IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, Vol. 33, No. 5, 01.10.2003, p. 789-801.

Research output: Contribution to journalArticle

Zaki, Mohammed J. ; Jin, Shan ; Bystroff, Chris. / Mining residue contacts in proteins using local structure predictions. In: IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics. 2003 ; Vol. 33, No. 5. pp. 789-801.
@article{b5f9ca6a4dd8455f950fd8268e306b79,
title = "Mining residue contacts in proteins using local structure predictions",
abstract = "In this paper we develop data mining techniques to predict three-dimensional (3-D) contact potentials among protein residues (or amino acids) based on the hierarchical nucleation-propagation model of protein folding. We apply a hybrid approach, using a hidden Markov model to extract folding initiation sites, and then apply association mining to discover contact potentials. The new hybrid approach achieves accuracy results better than those reported previously.",
keywords = "Association rules, Contact maps, Data mining, Hidden Markov models, Protein structure prediction",
author = "Zaki, {Mohammed J.} and Shan Jin and Chris Bystroff",
year = "2003",
month = "10",
day = "1",
doi = "10.1109/TSMCB.2003.816916",
language = "English",
volume = "33",
pages = "789--801",
journal = "IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics",
issn = "1083-4419",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "5",

}

TY - JOUR

T1 - Mining residue contacts in proteins using local structure predictions

AU - Zaki, Mohammed J.

AU - Jin, Shan

AU - Bystroff, Chris

PY - 2003/10/1

Y1 - 2003/10/1

N2 - In this paper we develop data mining techniques to predict three-dimensional (3-D) contact potentials among protein residues (or amino acids) based on the hierarchical nucleation-propagation model of protein folding. We apply a hybrid approach, using a hidden Markov model to extract folding initiation sites, and then apply association mining to discover contact potentials. The new hybrid approach achieves accuracy results better than those reported previously.

AB - In this paper we develop data mining techniques to predict three-dimensional (3-D) contact potentials among protein residues (or amino acids) based on the hierarchical nucleation-propagation model of protein folding. We apply a hybrid approach, using a hidden Markov model to extract folding initiation sites, and then apply association mining to discover contact potentials. The new hybrid approach achieves accuracy results better than those reported previously.

KW - Association rules

KW - Contact maps

KW - Data mining

KW - Hidden Markov models

KW - Protein structure prediction

UR - http://www.scopus.com/inward/record.url?scp=0141940269&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0141940269&partnerID=8YFLogxK

U2 - 10.1109/TSMCB.2003.816916

DO - 10.1109/TSMCB.2003.816916

M3 - Article

VL - 33

SP - 789

EP - 801

JO - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

JF - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

SN - 1083-4419

IS - 5

ER -