A two-stage classifier for identification of protein-protein interface residues

Changhui Yan, Drena Dobbs, Vasant Honavar

Research output: Contribution to journalArticle

107 Citations (Scopus)

Abstract

Motivation: The ability to identify protein-protein interaction sites and to detect specific amino acid residues that contribute to the specificity and affinity of protein interactions has important implications for problems ranging from rational drug design to analysis of metabolic and signal transduction networks. Results: We have developed a two-stage method consisting of a support vector machine (SVM) and a Bayesian classifier for predicting surface residues of a protein that participate in protein-protein interactions. This approach exploits the fact that interface residues tend to form clusters in the primary amino acid sequence. Our results show that the proposed two-stage classifier outperforms previously published sequence-based methods for predicting interface residues. We also present results obtained using the two-stage classifier on an independent test set of seven CAPRI (Critical Assessment of PRedicted Interactions) targets. The success of the predictions is validated by examining the predictions in the context of the three-dimensional structures of protein complexes.

Original languageEnglish (US)
Pages (from-to)i371-i378
JournalBioinformatics
Volume20
Issue numberSUPPL. 1
DOIs
StatePublished - Dec 1 2004

Fingerprint

Classifiers
Classifier
Proteins
Protein
Protein-protein Interaction
Bayesian Classifier
Drug Design
Signal Transduction
Prediction
Test Set
Amino Acid Sequence
Independent Set
Amino acids
Interaction
Specificity
Affine transformation
Amino Acids
Support Vector Machine
Signal transduction
Tend

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Computational Theory and Mathematics
  • Computational Mathematics

Cite this

Yan, Changhui ; Dobbs, Drena ; Honavar, Vasant. / A two-stage classifier for identification of protein-protein interface residues. In: Bioinformatics. 2004 ; Vol. 20, No. SUPPL. 1. pp. i371-i378.
@article{adcf0376732f42b48a0a73fec62c612c,
title = "A two-stage classifier for identification of protein-protein interface residues",
abstract = "Motivation: The ability to identify protein-protein interaction sites and to detect specific amino acid residues that contribute to the specificity and affinity of protein interactions has important implications for problems ranging from rational drug design to analysis of metabolic and signal transduction networks. Results: We have developed a two-stage method consisting of a support vector machine (SVM) and a Bayesian classifier for predicting surface residues of a protein that participate in protein-protein interactions. This approach exploits the fact that interface residues tend to form clusters in the primary amino acid sequence. Our results show that the proposed two-stage classifier outperforms previously published sequence-based methods for predicting interface residues. We also present results obtained using the two-stage classifier on an independent test set of seven CAPRI (Critical Assessment of PRedicted Interactions) targets. The success of the predictions is validated by examining the predictions in the context of the three-dimensional structures of protein complexes.",
author = "Changhui Yan and Drena Dobbs and Vasant Honavar",
year = "2004",
month = "12",
day = "1",
doi = "10.1093/bioinformatics/bth920",
language = "English (US)",
volume = "20",
pages = "i371--i378",
journal = "Bioinformatics",
issn = "1367-4803",
publisher = "Oxford University Press",
number = "SUPPL. 1",

}

A two-stage classifier for identification of protein-protein interface residues. / Yan, Changhui; Dobbs, Drena; Honavar, Vasant.

In: Bioinformatics, Vol. 20, No. SUPPL. 1, 01.12.2004, p. i371-i378.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A two-stage classifier for identification of protein-protein interface residues

AU - Yan, Changhui

AU - Dobbs, Drena

AU - Honavar, Vasant

PY - 2004/12/1

Y1 - 2004/12/1

N2 - Motivation: The ability to identify protein-protein interaction sites and to detect specific amino acid residues that contribute to the specificity and affinity of protein interactions has important implications for problems ranging from rational drug design to analysis of metabolic and signal transduction networks. Results: We have developed a two-stage method consisting of a support vector machine (SVM) and a Bayesian classifier for predicting surface residues of a protein that participate in protein-protein interactions. This approach exploits the fact that interface residues tend to form clusters in the primary amino acid sequence. Our results show that the proposed two-stage classifier outperforms previously published sequence-based methods for predicting interface residues. We also present results obtained using the two-stage classifier on an independent test set of seven CAPRI (Critical Assessment of PRedicted Interactions) targets. The success of the predictions is validated by examining the predictions in the context of the three-dimensional structures of protein complexes.

AB - Motivation: The ability to identify protein-protein interaction sites and to detect specific amino acid residues that contribute to the specificity and affinity of protein interactions has important implications for problems ranging from rational drug design to analysis of metabolic and signal transduction networks. Results: We have developed a two-stage method consisting of a support vector machine (SVM) and a Bayesian classifier for predicting surface residues of a protein that participate in protein-protein interactions. This approach exploits the fact that interface residues tend to form clusters in the primary amino acid sequence. Our results show that the proposed two-stage classifier outperforms previously published sequence-based methods for predicting interface residues. We also present results obtained using the two-stage classifier on an independent test set of seven CAPRI (Critical Assessment of PRedicted Interactions) targets. The success of the predictions is validated by examining the predictions in the context of the three-dimensional structures of protein complexes.

UR - http://www.scopus.com/inward/record.url?scp=13244292990&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=13244292990&partnerID=8YFLogxK

U2 - 10.1093/bioinformatics/bth920

DO - 10.1093/bioinformatics/bth920

M3 - Article

C2 - 15262822

AN - SCOPUS:13244292990

VL - 20

SP - i371-i378

JO - Bioinformatics

JF - Bioinformatics

SN - 1367-4803

IS - SUPPL. 1

ER -