Quantitative prediction of mouse class I MHC peptide binding affinity using support vector machine regression (SVR) models

Wen Liu, Xiangshan Meng, Qiqi Xu, Darren R. Flower, Tongbin Li

Research output: Contribution to journalArticle

Abstract

Background - The binding between peptide epitopes and major histocompatibility complex proteins (MHCs) is an important event in the cellular immune response. Accurate prediction of the binding between short peptides and the MHC molecules has long been a principal challenge for immunoinformatics. Recently, the modeling of MHC-peptide binding has come to emphasize quantitative predictions: instead of categorizing peptides as "binders" or "non-binders" or as "strong binders" and "weak binders", recent methods seek to make predictions about precise binding affinities.
Results - We developed a quantitative support vector machine regression (SVR) approach, called SVRMHC, to model peptide-MHC binding affinities. As a non-linear method, SVRMHC was able to generate models that out-performed existing linear models, such as the "additive method". By adopting a new "11-factor encoding" scheme, SVRMHC takes into account similarities in the physicochemical properties of the amino acids constituting the input peptides. When applied to MHC-peptide binding data for three mouse class I MHC alleles, the SVRMHC models produced more accurate predictions than those produced previously. Furthermore, comparisons based on Receiver Operating Characteristic (ROC) analysis indicated that SVRMHC was able to out-perform several prominent methods in identifying strongly binding peptides.
Conclusion - As a method with demonstrated performance in the quantitative modeling of MHC-peptide binding and in identifying strong binders, SVRMHC is a promising immunoinformatics tool with not inconsiderable future potential.
Original languageEnglish
Pages (from-to)182-194
Number of pages13
JournalBMC Bioinformatics
Volume7
Issue number3
DOIs
Publication statusPublished - 31 Mar 2006

Fingerprint

Peptides
Affine transformation
Support vector machines
Mouse
Support Vector Machine
Regression Model
Binders
Prediction
Major Histocompatibility Complex
Cellular Immunity
ROC Curve
Epitopes
Linear Models
Alleles
Class
MHC binding peptide
Amino Acids
Operating Characteristics
Immune Response
Molecules

Bibliographical note

© 2006 Liu et al; licensee BioMed Central Ltd.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Cite this

Liu, Wen ; Meng, Xiangshan ; Xu, Qiqi ; Flower, Darren R. ; Li, Tongbin. / Quantitative prediction of mouse class I MHC peptide binding affinity using support vector machine regression (SVR) models. In: BMC Bioinformatics. 2006 ; Vol. 7, No. 3. pp. 182-194.
@article{89d751cbaf6147f995bcdcfd1c9e4374,
title = "Quantitative prediction of mouse class I MHC peptide binding affinity using support vector machine regression (SVR) models",
abstract = "Background - The binding between peptide epitopes and major histocompatibility complex proteins (MHCs) is an important event in the cellular immune response. Accurate prediction of the binding between short peptides and the MHC molecules has long been a principal challenge for immunoinformatics. Recently, the modeling of MHC-peptide binding has come to emphasize quantitative predictions: instead of categorizing peptides as {"}binders{"} or {"}non-binders{"} or as {"}strong binders{"} and {"}weak binders{"}, recent methods seek to make predictions about precise binding affinities.Results - We developed a quantitative support vector machine regression (SVR) approach, called SVRMHC, to model peptide-MHC binding affinities. As a non-linear method, SVRMHC was able to generate models that out-performed existing linear models, such as the {"}additive method{"}. By adopting a new {"}11-factor encoding{"} scheme, SVRMHC takes into account similarities in the physicochemical properties of the amino acids constituting the input peptides. When applied to MHC-peptide binding data for three mouse class I MHC alleles, the SVRMHC models produced more accurate predictions than those produced previously. Furthermore, comparisons based on Receiver Operating Characteristic (ROC) analysis indicated that SVRMHC was able to out-perform several prominent methods in identifying strongly binding peptides.Conclusion - As a method with demonstrated performance in the quantitative modeling of MHC-peptide binding and in identifying strong binders, SVRMHC is a promising immunoinformatics tool with not inconsiderable future potential.",
author = "Wen Liu and Xiangshan Meng and Qiqi Xu and Flower, {Darren R.} and Tongbin Li",
note = "{\circledC} 2006 Liu et al; licensee BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.",
year = "2006",
month = "3",
day = "31",
doi = "10.1186/1471-2105-7-182",
language = "English",
volume = "7",
pages = "182--194",
journal = "BMC Bioinformatics",
issn = "1471-2105",
publisher = "BioMed Central",
number = "3",

}

Quantitative prediction of mouse class I MHC peptide binding affinity using support vector machine regression (SVR) models. / Liu, Wen; Meng, Xiangshan; Xu, Qiqi; Flower, Darren R.; Li, Tongbin.

In: BMC Bioinformatics, Vol. 7, No. 3, 31.03.2006, p. 182-194.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Quantitative prediction of mouse class I MHC peptide binding affinity using support vector machine regression (SVR) models

AU - Liu, Wen

AU - Meng, Xiangshan

AU - Xu, Qiqi

AU - Flower, Darren R.

AU - Li, Tongbin

N1 - © 2006 Liu et al; licensee BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

PY - 2006/3/31

Y1 - 2006/3/31

N2 - Background - The binding between peptide epitopes and major histocompatibility complex proteins (MHCs) is an important event in the cellular immune response. Accurate prediction of the binding between short peptides and the MHC molecules has long been a principal challenge for immunoinformatics. Recently, the modeling of MHC-peptide binding has come to emphasize quantitative predictions: instead of categorizing peptides as "binders" or "non-binders" or as "strong binders" and "weak binders", recent methods seek to make predictions about precise binding affinities.Results - We developed a quantitative support vector machine regression (SVR) approach, called SVRMHC, to model peptide-MHC binding affinities. As a non-linear method, SVRMHC was able to generate models that out-performed existing linear models, such as the "additive method". By adopting a new "11-factor encoding" scheme, SVRMHC takes into account similarities in the physicochemical properties of the amino acids constituting the input peptides. When applied to MHC-peptide binding data for three mouse class I MHC alleles, the SVRMHC models produced more accurate predictions than those produced previously. Furthermore, comparisons based on Receiver Operating Characteristic (ROC) analysis indicated that SVRMHC was able to out-perform several prominent methods in identifying strongly binding peptides.Conclusion - As a method with demonstrated performance in the quantitative modeling of MHC-peptide binding and in identifying strong binders, SVRMHC is a promising immunoinformatics tool with not inconsiderable future potential.

AB - Background - The binding between peptide epitopes and major histocompatibility complex proteins (MHCs) is an important event in the cellular immune response. Accurate prediction of the binding between short peptides and the MHC molecules has long been a principal challenge for immunoinformatics. Recently, the modeling of MHC-peptide binding has come to emphasize quantitative predictions: instead of categorizing peptides as "binders" or "non-binders" or as "strong binders" and "weak binders", recent methods seek to make predictions about precise binding affinities.Results - We developed a quantitative support vector machine regression (SVR) approach, called SVRMHC, to model peptide-MHC binding affinities. As a non-linear method, SVRMHC was able to generate models that out-performed existing linear models, such as the "additive method". By adopting a new "11-factor encoding" scheme, SVRMHC takes into account similarities in the physicochemical properties of the amino acids constituting the input peptides. When applied to MHC-peptide binding data for three mouse class I MHC alleles, the SVRMHC models produced more accurate predictions than those produced previously. Furthermore, comparisons based on Receiver Operating Characteristic (ROC) analysis indicated that SVRMHC was able to out-perform several prominent methods in identifying strongly binding peptides.Conclusion - As a method with demonstrated performance in the quantitative modeling of MHC-peptide binding and in identifying strong binders, SVRMHC is a promising immunoinformatics tool with not inconsiderable future potential.

UR - http://www.biomedcentral.com/1471-2105/7/182

U2 - 10.1186/1471-2105-7-182

DO - 10.1186/1471-2105-7-182

M3 - Article

VL - 7

SP - 182

EP - 194

JO - BMC Bioinformatics

JF - BMC Bioinformatics

SN - 1471-2105

IS - 3

ER -