Prediction of MHC class II-binding peptides using an evolutionary algorithm and artificial neural network

Vladimir Brusic, George Rudy, Margo Honeyman, Jürgen Hammer, Leonard Harrison

Research output: Contribution to journalArticle

238 Citations (Scopus)

Abstract

Motivation: Prediction methods for identifying binding peptides could minimize the number of peptides required to be synthesized and assayed, and thereby facilitate the identification of potential T-cell epitopes. We developed a bioinformatic method for the prediction of peptide binding to MHC class II molecules. Results: Experimental binding data and expert knowledge of anchor positions and binding motifs were combined with an evolutionary algorithm (EA) and an artificial neural network (ANN): binding data extraction→peptide alignment→ANN training and classification. This method, termed PERUN, was implemented for the prediction of peptides that bind to HLA-DR4(B1*0401). The respective positive predictive values of PERUN predictions of high-, moderate-, low- and zero-affinity binders were assessed as 0.8, 0.7, 0.5 and 0.8 by cross-validation, and 1.0, 0.8, 0.3 and 0.7 by experimental binding. This illustrates the synergy between experimentation and computer modeling, and its application to the indentification of potential immunotherapeutic peptides. Availability: Software and data are available from the authors upon request. Contact: vladimir@@@wehi.edu.au.

Original languageEnglish
Pages (from-to)121-130
Number of pages10
JournalBioinformatics
Volume14
Issue number2
Publication statusPublished - 1998
Externally publishedYes

Fingerprint

Evolutionary algorithms
Peptides
Artificial Neural Network
Evolutionary Algorithms
Neural networks
Prediction
HLA-DR4 Antigen
T-Lymphocyte Epitopes
Epitopes
Computational Biology
T-cells
Bioelectric potentials
Bioinformatics
Anchors
Computer Modeling
Software
Synergy
Binders
Cross-validation
Experimentation

ASJC Scopus subject areas

  • Clinical Biochemistry
  • Computer Science Applications
  • Computational Theory and Mathematics

Cite this

Brusic, V., Rudy, G., Honeyman, M., Hammer, J., & Harrison, L. (1998). Prediction of MHC class II-binding peptides using an evolutionary algorithm and artificial neural network. Bioinformatics, 14(2), 121-130.

Prediction of MHC class II-binding peptides using an evolutionary algorithm and artificial neural network. / Brusic, Vladimir; Rudy, George; Honeyman, Margo; Hammer, Jürgen; Harrison, Leonard.

In: Bioinformatics, Vol. 14, No. 2, 1998, p. 121-130.

Research output: Contribution to journalArticle

Brusic, V, Rudy, G, Honeyman, M, Hammer, J & Harrison, L 1998, 'Prediction of MHC class II-binding peptides using an evolutionary algorithm and artificial neural network', Bioinformatics, vol. 14, no. 2, pp. 121-130.
Brusic, Vladimir ; Rudy, George ; Honeyman, Margo ; Hammer, Jürgen ; Harrison, Leonard. / Prediction of MHC class II-binding peptides using an evolutionary algorithm and artificial neural network. In: Bioinformatics. 1998 ; Vol. 14, No. 2. pp. 121-130.
@article{aa12227ad7e649ed8eaec4a00a3c6b4f,
title = "Prediction of MHC class II-binding peptides using an evolutionary algorithm and artificial neural network",
abstract = "Motivation: Prediction methods for identifying binding peptides could minimize the number of peptides required to be synthesized and assayed, and thereby facilitate the identification of potential T-cell epitopes. We developed a bioinformatic method for the prediction of peptide binding to MHC class II molecules. Results: Experimental binding data and expert knowledge of anchor positions and binding motifs were combined with an evolutionary algorithm (EA) and an artificial neural network (ANN): binding data extraction→peptide alignment→ANN training and classification. This method, termed PERUN, was implemented for the prediction of peptides that bind to HLA-DR4(B1*0401). The respective positive predictive values of PERUN predictions of high-, moderate-, low- and zero-affinity binders were assessed as 0.8, 0.7, 0.5 and 0.8 by cross-validation, and 1.0, 0.8, 0.3 and 0.7 by experimental binding. This illustrates the synergy between experimentation and computer modeling, and its application to the indentification of potential immunotherapeutic peptides. Availability: Software and data are available from the authors upon request. Contact: vladimir@@@wehi.edu.au.",
author = "Vladimir Brusic and George Rudy and Margo Honeyman and J{\"u}rgen Hammer and Leonard Harrison",
year = "1998",
language = "English",
volume = "14",
pages = "121--130",
journal = "Bioinformatics",
issn = "1367-4803",
publisher = "Oxford University Press",
number = "2",

}

TY - JOUR

T1 - Prediction of MHC class II-binding peptides using an evolutionary algorithm and artificial neural network

AU - Brusic, Vladimir

AU - Rudy, George

AU - Honeyman, Margo

AU - Hammer, Jürgen

AU - Harrison, Leonard

PY - 1998

Y1 - 1998

N2 - Motivation: Prediction methods for identifying binding peptides could minimize the number of peptides required to be synthesized and assayed, and thereby facilitate the identification of potential T-cell epitopes. We developed a bioinformatic method for the prediction of peptide binding to MHC class II molecules. Results: Experimental binding data and expert knowledge of anchor positions and binding motifs were combined with an evolutionary algorithm (EA) and an artificial neural network (ANN): binding data extraction→peptide alignment→ANN training and classification. This method, termed PERUN, was implemented for the prediction of peptides that bind to HLA-DR4(B1*0401). The respective positive predictive values of PERUN predictions of high-, moderate-, low- and zero-affinity binders were assessed as 0.8, 0.7, 0.5 and 0.8 by cross-validation, and 1.0, 0.8, 0.3 and 0.7 by experimental binding. This illustrates the synergy between experimentation and computer modeling, and its application to the indentification of potential immunotherapeutic peptides. Availability: Software and data are available from the authors upon request. Contact: vladimir@@@wehi.edu.au.

AB - Motivation: Prediction methods for identifying binding peptides could minimize the number of peptides required to be synthesized and assayed, and thereby facilitate the identification of potential T-cell epitopes. We developed a bioinformatic method for the prediction of peptide binding to MHC class II molecules. Results: Experimental binding data and expert knowledge of anchor positions and binding motifs were combined with an evolutionary algorithm (EA) and an artificial neural network (ANN): binding data extraction→peptide alignment→ANN training and classification. This method, termed PERUN, was implemented for the prediction of peptides that bind to HLA-DR4(B1*0401). The respective positive predictive values of PERUN predictions of high-, moderate-, low- and zero-affinity binders were assessed as 0.8, 0.7, 0.5 and 0.8 by cross-validation, and 1.0, 0.8, 0.3 and 0.7 by experimental binding. This illustrates the synergy between experimentation and computer modeling, and its application to the indentification of potential immunotherapeutic peptides. Availability: Software and data are available from the authors upon request. Contact: vladimir@@@wehi.edu.au.

UR - http://www.scopus.com/inward/record.url?scp=0031825709&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031825709&partnerID=8YFLogxK

M3 - Article

C2 - 9545443

AN - SCOPUS:0031825709

VL - 14

SP - 121

EP - 130

JO - Bioinformatics

JF - Bioinformatics

SN - 1367-4803

IS - 2

ER -