Prediction of promiscuous peptides that bind HLA class I molecules

Vladimir Brusic, Nikolai Petrovsky, Guanglan Zhang, Vladimir B. Bajic

Research output: Contribution to journalArticle

83 Citations (Scopus)

Abstract

Promiscuous T-cell epitopes make ideal targets for vaccine development. We report here a computational system, MULTIPRED, for the prediction of peptide binding to the HLA-A2 supertype. It combines a novel representation of peptide/MHC interactions with a hidden Markov model as the prediction algorithm. MULTIPRED is both sensitive and specific, and demonstrates high accuracy of peptide-binding predictions for HLA-A*0201, *0204, and *0205 alleles, good accuracy for *0206 allele, and marginal accuracy for *0203 allele. MULTIPRED replaces earlier requirements for individual prediction models for each HLA allelic variant and simplifies computational aspects of peptide-binding prediction. Preliminary testing indicates that MULTIPRED can predict peptide binding to HLA-A2 supertype molecules with high accuracy, including those allelic variants for which no experimental binding data are currently available.

Original languageEnglish
Pages (from-to)280-285
Number of pages6
JournalImmunology and Cell Biology
Volume80
Issue number3
DOIs
Publication statusPublished - 2002
Externally publishedYes

Fingerprint

Peptides
Molecules
HLA-A2 Antigen
Alleles
T-Lymphocyte Epitopes
Hidden Markov models
Vaccines
Testing

Keywords

  • Hidden Markov models
  • HLA allele
  • Immunoinformatics
  • Peptide binding
  • Predictive modelling

ASJC Scopus subject areas

  • Immunology
  • Clinical Biochemistry
  • Cell Biology

Cite this

Prediction of promiscuous peptides that bind HLA class I molecules. / Brusic, Vladimir; Petrovsky, Nikolai; Zhang, Guanglan; Bajic, Vladimir B.

In: Immunology and Cell Biology, Vol. 80, No. 3, 2002, p. 280-285.

Research output: Contribution to journalArticle

Brusic, Vladimir ; Petrovsky, Nikolai ; Zhang, Guanglan ; Bajic, Vladimir B. / Prediction of promiscuous peptides that bind HLA class I molecules. In: Immunology and Cell Biology. 2002 ; Vol. 80, No. 3. pp. 280-285.
@article{95b608ab0ab34c089a366644d90d5699,
title = "Prediction of promiscuous peptides that bind HLA class I molecules",
abstract = "Promiscuous T-cell epitopes make ideal targets for vaccine development. We report here a computational system, MULTIPRED, for the prediction of peptide binding to the HLA-A2 supertype. It combines a novel representation of peptide/MHC interactions with a hidden Markov model as the prediction algorithm. MULTIPRED is both sensitive and specific, and demonstrates high accuracy of peptide-binding predictions for HLA-A*0201, *0204, and *0205 alleles, good accuracy for *0206 allele, and marginal accuracy for *0203 allele. MULTIPRED replaces earlier requirements for individual prediction models for each HLA allelic variant and simplifies computational aspects of peptide-binding prediction. Preliminary testing indicates that MULTIPRED can predict peptide binding to HLA-A2 supertype molecules with high accuracy, including those allelic variants for which no experimental binding data are currently available.",
keywords = "Hidden Markov models, HLA allele, Immunoinformatics, Peptide binding, Predictive modelling",
author = "Vladimir Brusic and Nikolai Petrovsky and Guanglan Zhang and Bajic, {Vladimir B.}",
year = "2002",
doi = "10.1046/j.1440-1711.2002.01088.x",
language = "English",
volume = "80",
pages = "280--285",
journal = "Immunology and Cell Biology",
issn = "0818-9641",
publisher = "Nature Publishing Group",
number = "3",

}

TY - JOUR

T1 - Prediction of promiscuous peptides that bind HLA class I molecules

AU - Brusic, Vladimir

AU - Petrovsky, Nikolai

AU - Zhang, Guanglan

AU - Bajic, Vladimir B.

PY - 2002

Y1 - 2002

N2 - Promiscuous T-cell epitopes make ideal targets for vaccine development. We report here a computational system, MULTIPRED, for the prediction of peptide binding to the HLA-A2 supertype. It combines a novel representation of peptide/MHC interactions with a hidden Markov model as the prediction algorithm. MULTIPRED is both sensitive and specific, and demonstrates high accuracy of peptide-binding predictions for HLA-A*0201, *0204, and *0205 alleles, good accuracy for *0206 allele, and marginal accuracy for *0203 allele. MULTIPRED replaces earlier requirements for individual prediction models for each HLA allelic variant and simplifies computational aspects of peptide-binding prediction. Preliminary testing indicates that MULTIPRED can predict peptide binding to HLA-A2 supertype molecules with high accuracy, including those allelic variants for which no experimental binding data are currently available.

AB - Promiscuous T-cell epitopes make ideal targets for vaccine development. We report here a computational system, MULTIPRED, for the prediction of peptide binding to the HLA-A2 supertype. It combines a novel representation of peptide/MHC interactions with a hidden Markov model as the prediction algorithm. MULTIPRED is both sensitive and specific, and demonstrates high accuracy of peptide-binding predictions for HLA-A*0201, *0204, and *0205 alleles, good accuracy for *0206 allele, and marginal accuracy for *0203 allele. MULTIPRED replaces earlier requirements for individual prediction models for each HLA allelic variant and simplifies computational aspects of peptide-binding prediction. Preliminary testing indicates that MULTIPRED can predict peptide binding to HLA-A2 supertype molecules with high accuracy, including those allelic variants for which no experimental binding data are currently available.

KW - Hidden Markov models

KW - HLA allele

KW - Immunoinformatics

KW - Peptide binding

KW - Predictive modelling

UR - http://www.scopus.com/inward/record.url?scp=0035989339&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035989339&partnerID=8YFLogxK

U2 - 10.1046/j.1440-1711.2002.01088.x

DO - 10.1046/j.1440-1711.2002.01088.x

M3 - Article

VL - 80

SP - 280

EP - 285

JO - Immunology and Cell Biology

JF - Immunology and Cell Biology

SN - 0818-9641

IS - 3

ER -