Automated generation and evaluation of specific MHC binding predictive tools: ARB matrix applications

Huynh Hoa Bui, John Sidney, Bjoern Peters, Muthuraman Sathiamurthy, Asabe Sinichi, Kelly Anne Purton, Bianca R. Mothé, Francis V. Chisari, David Watkins, Alessandro Sette

Research output: Contribution to journalArticle

181 Citations (Scopus)

Abstract

Prediction of which peptides can bind major histocompatibility complex (MHC) molecules is commonly used to assist in the identification of T cell epitopes. However, because of the large numbers of different MHC molecules of interest, each associated with different predictive tools, tool generation and evaluation can be a very resource intensive task. A methodology commonly used to predict MHC binding affinity is the matrix or linear coefficients method. Herein, we described Average Relative Binding (ARB) matrix methods that directly predict IC50 values allowing combination of searches involving different peptide sizes and alleles into a single global prediction. A computer program was developed to automate the generation and evaluation of ARB predictive tools. Using an in-house MHC binding database, we generated a total of 85 and 13 MHC class I and class II matrices, respectively. Results from the automated evaluation of tool efficiency are presented. We anticipate that this automation framework will be generally applicable to the generation and evaluation of large numbers of MHC predictive methods and tools, and will be of value to centralize and rationalize the process of evaluation of MHC predictions. MHC binding predictions based on ARB matrices were made available at http://epitope.liai.org:8080/matrix web server.

Original languageEnglish
Pages (from-to)304-314
Number of pages11
JournalImmunogenetics
Volume57
Issue number5
DOIs
StatePublished - Jun 1 2005
Externally publishedYes

Fingerprint

Major Histocompatibility Complex
Peptides
T-Lymphocyte Epitopes
Automation
Inhibitory Concentration 50
Epitopes
Software
Alleles
Databases

Keywords

  • Automated tool evaluation
  • Binding prediction
  • Computer algorithms
  • MHC
  • Web server

ASJC Scopus subject areas

  • Immunology
  • Genetics

Cite this

Bui, H. H., Sidney, J., Peters, B., Sathiamurthy, M., Sinichi, A., Purton, K. A., ... Sette, A. (2005). Automated generation and evaluation of specific MHC binding predictive tools: ARB matrix applications. Immunogenetics, 57(5), 304-314. https://doi.org/10.1007/s00251-005-0798-y

Automated generation and evaluation of specific MHC binding predictive tools : ARB matrix applications. / Bui, Huynh Hoa; Sidney, John; Peters, Bjoern; Sathiamurthy, Muthuraman; Sinichi, Asabe; Purton, Kelly Anne; Mothé, Bianca R.; Chisari, Francis V.; Watkins, David; Sette, Alessandro.

In: Immunogenetics, Vol. 57, No. 5, 01.06.2005, p. 304-314.

Research output: Contribution to journalArticle

Bui, HH, Sidney, J, Peters, B, Sathiamurthy, M, Sinichi, A, Purton, KA, Mothé, BR, Chisari, FV, Watkins, D & Sette, A 2005, 'Automated generation and evaluation of specific MHC binding predictive tools: ARB matrix applications', Immunogenetics, vol. 57, no. 5, pp. 304-314. https://doi.org/10.1007/s00251-005-0798-y
Bui, Huynh Hoa ; Sidney, John ; Peters, Bjoern ; Sathiamurthy, Muthuraman ; Sinichi, Asabe ; Purton, Kelly Anne ; Mothé, Bianca R. ; Chisari, Francis V. ; Watkins, David ; Sette, Alessandro. / Automated generation and evaluation of specific MHC binding predictive tools : ARB matrix applications. In: Immunogenetics. 2005 ; Vol. 57, No. 5. pp. 304-314.
@article{baf7ee9470ef4cebada5ac8ef7097d67,
title = "Automated generation and evaluation of specific MHC binding predictive tools: ARB matrix applications",
abstract = "Prediction of which peptides can bind major histocompatibility complex (MHC) molecules is commonly used to assist in the identification of T cell epitopes. However, because of the large numbers of different MHC molecules of interest, each associated with different predictive tools, tool generation and evaluation can be a very resource intensive task. A methodology commonly used to predict MHC binding affinity is the matrix or linear coefficients method. Herein, we described Average Relative Binding (ARB) matrix methods that directly predict IC50 values allowing combination of searches involving different peptide sizes and alleles into a single global prediction. A computer program was developed to automate the generation and evaluation of ARB predictive tools. Using an in-house MHC binding database, we generated a total of 85 and 13 MHC class I and class II matrices, respectively. Results from the automated evaluation of tool efficiency are presented. We anticipate that this automation framework will be generally applicable to the generation and evaluation of large numbers of MHC predictive methods and tools, and will be of value to centralize and rationalize the process of evaluation of MHC predictions. MHC binding predictions based on ARB matrices were made available at http://epitope.liai.org:8080/matrix web server.",
keywords = "Automated tool evaluation, Binding prediction, Computer algorithms, MHC, Web server",
author = "Bui, {Huynh Hoa} and John Sidney and Bjoern Peters and Muthuraman Sathiamurthy and Asabe Sinichi and Purton, {Kelly Anne} and Moth{\'e}, {Bianca R.} and Chisari, {Francis V.} and David Watkins and Alessandro Sette",
year = "2005",
month = "6",
day = "1",
doi = "10.1007/s00251-005-0798-y",
language = "English",
volume = "57",
pages = "304--314",
journal = "Immunogenetics",
issn = "0093-7711",
publisher = "Springer Verlag",
number = "5",

}

TY - JOUR

T1 - Automated generation and evaluation of specific MHC binding predictive tools

T2 - ARB matrix applications

AU - Bui, Huynh Hoa

AU - Sidney, John

AU - Peters, Bjoern

AU - Sathiamurthy, Muthuraman

AU - Sinichi, Asabe

AU - Purton, Kelly Anne

AU - Mothé, Bianca R.

AU - Chisari, Francis V.

AU - Watkins, David

AU - Sette, Alessandro

PY - 2005/6/1

Y1 - 2005/6/1

N2 - Prediction of which peptides can bind major histocompatibility complex (MHC) molecules is commonly used to assist in the identification of T cell epitopes. However, because of the large numbers of different MHC molecules of interest, each associated with different predictive tools, tool generation and evaluation can be a very resource intensive task. A methodology commonly used to predict MHC binding affinity is the matrix or linear coefficients method. Herein, we described Average Relative Binding (ARB) matrix methods that directly predict IC50 values allowing combination of searches involving different peptide sizes and alleles into a single global prediction. A computer program was developed to automate the generation and evaluation of ARB predictive tools. Using an in-house MHC binding database, we generated a total of 85 and 13 MHC class I and class II matrices, respectively. Results from the automated evaluation of tool efficiency are presented. We anticipate that this automation framework will be generally applicable to the generation and evaluation of large numbers of MHC predictive methods and tools, and will be of value to centralize and rationalize the process of evaluation of MHC predictions. MHC binding predictions based on ARB matrices were made available at http://epitope.liai.org:8080/matrix web server.

AB - Prediction of which peptides can bind major histocompatibility complex (MHC) molecules is commonly used to assist in the identification of T cell epitopes. However, because of the large numbers of different MHC molecules of interest, each associated with different predictive tools, tool generation and evaluation can be a very resource intensive task. A methodology commonly used to predict MHC binding affinity is the matrix or linear coefficients method. Herein, we described Average Relative Binding (ARB) matrix methods that directly predict IC50 values allowing combination of searches involving different peptide sizes and alleles into a single global prediction. A computer program was developed to automate the generation and evaluation of ARB predictive tools. Using an in-house MHC binding database, we generated a total of 85 and 13 MHC class I and class II matrices, respectively. Results from the automated evaluation of tool efficiency are presented. We anticipate that this automation framework will be generally applicable to the generation and evaluation of large numbers of MHC predictive methods and tools, and will be of value to centralize and rationalize the process of evaluation of MHC predictions. MHC binding predictions based on ARB matrices were made available at http://epitope.liai.org:8080/matrix web server.

KW - Automated tool evaluation

KW - Binding prediction

KW - Computer algorithms

KW - MHC

KW - Web server

UR - http://www.scopus.com/inward/record.url?scp=21344466799&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=21344466799&partnerID=8YFLogxK

U2 - 10.1007/s00251-005-0798-y

DO - 10.1007/s00251-005-0798-y

M3 - Article

C2 - 15868141

AN - SCOPUS:21344466799

VL - 57

SP - 304

EP - 314

JO - Immunogenetics

JF - Immunogenetics

SN - 0093-7711

IS - 5

ER -