Additive method for the prediction of protein-peptide binding affinity. Application to the MHC class I molecule HLA-A*0201

Irini A. Doytchinova, Martin J. Blythe, Darren R. Flower

Research output: Contribution to journalArticle

Abstract

A method has been developed for prediction of binding affinities between proteins and peptides. We exemplify the method through its application to binding predictions of peptides with affinity to major histocompatibility complex class I molecule HLA-A*0201. The method is named “additive” because it is based on the assumption that the binding affinity of a peptide could be presented as a sum of the contributions of the amino acids at each position and the interactions between them. The amino acid contributions and the contributions of the interactions between adjacent side chains and every second side chain were derived using a partial least squares (PLS) statistical methodology using a training set of 420 experimental IC50 values. The predictive power of the method was assessed using rigorous cross-validation and using an independent test set of 89 peptides. The mean value of the residuals between the experimental and predicted pIC50 values was 0.508 for this test set. The additive method was implemented in a program for rapid T-cell epitope search. It is universal and can be applied to any peptide−protein interaction where binding data is known.
Original languageEnglish
Pages (from-to)263-272
Number of pages10
JournalJournal of Proteome Research
Volume1
Issue number3
DOIs
Publication statusPublished - May 2002

Fingerprint

Protein Binding
Peptides
Molecules
Proteins
Amino Acids
T-Lymphocyte Epitopes
Major Histocompatibility Complex
Least-Squares Analysis
Inhibitory Concentration 50
HLA-A*02:01 antigen

Keywords

  • qsar
  • pls
  • free-wilson
  • mhc
  • hla-a*0201

Cite this

Doytchinova, Irini A. ; Blythe, Martin J. ; Flower, Darren R. / Additive method for the prediction of protein-peptide binding affinity. Application to the MHC class I molecule HLA-A*0201. In: Journal of Proteome Research. 2002 ; Vol. 1, No. 3. pp. 263-272.
@article{6a6e3186df8341ae9e2beaf8633264f9,
title = "Additive method for the prediction of protein-peptide binding affinity. Application to the MHC class I molecule HLA-A*0201",
abstract = "A method has been developed for prediction of binding affinities between proteins and peptides. We exemplify the method through its application to binding predictions of peptides with affinity to major histocompatibility complex class I molecule HLA-A*0201. The method is named “additive” because it is based on the assumption that the binding affinity of a peptide could be presented as a sum of the contributions of the amino acids at each position and the interactions between them. The amino acid contributions and the contributions of the interactions between adjacent side chains and every second side chain were derived using a partial least squares (PLS) statistical methodology using a training set of 420 experimental IC50 values. The predictive power of the method was assessed using rigorous cross-validation and using an independent test set of 89 peptides. The mean value of the residuals between the experimental and predicted pIC50 values was 0.508 for this test set. The additive method was implemented in a program for rapid T-cell epitope search. It is universal and can be applied to any peptide−protein interaction where binding data is known.",
keywords = "qsar, pls, free-wilson, mhc, hla-a*0201",
author = "Doytchinova, {Irini A.} and Blythe, {Martin J.} and Flower, {Darren R.}",
year = "2002",
month = "5",
doi = "10.1021/pr015513z",
language = "English",
volume = "1",
pages = "263--272",
journal = "Journal of Proteome Research",
issn = "1535-3893",
publisher = "American Chemical Society",
number = "3",

}

Additive method for the prediction of protein-peptide binding affinity. Application to the MHC class I molecule HLA-A*0201. / Doytchinova, Irini A.; Blythe, Martin J.; Flower, Darren R.

In: Journal of Proteome Research, Vol. 1, No. 3, 05.2002, p. 263-272.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Additive method for the prediction of protein-peptide binding affinity. Application to the MHC class I molecule HLA-A*0201

AU - Doytchinova, Irini A.

AU - Blythe, Martin J.

AU - Flower, Darren R.

PY - 2002/5

Y1 - 2002/5

N2 - A method has been developed for prediction of binding affinities between proteins and peptides. We exemplify the method through its application to binding predictions of peptides with affinity to major histocompatibility complex class I molecule HLA-A*0201. The method is named “additive” because it is based on the assumption that the binding affinity of a peptide could be presented as a sum of the contributions of the amino acids at each position and the interactions between them. The amino acid contributions and the contributions of the interactions between adjacent side chains and every second side chain were derived using a partial least squares (PLS) statistical methodology using a training set of 420 experimental IC50 values. The predictive power of the method was assessed using rigorous cross-validation and using an independent test set of 89 peptides. The mean value of the residuals between the experimental and predicted pIC50 values was 0.508 for this test set. The additive method was implemented in a program for rapid T-cell epitope search. It is universal and can be applied to any peptide−protein interaction where binding data is known.

AB - A method has been developed for prediction of binding affinities between proteins and peptides. We exemplify the method through its application to binding predictions of peptides with affinity to major histocompatibility complex class I molecule HLA-A*0201. The method is named “additive” because it is based on the assumption that the binding affinity of a peptide could be presented as a sum of the contributions of the amino acids at each position and the interactions between them. The amino acid contributions and the contributions of the interactions between adjacent side chains and every second side chain were derived using a partial least squares (PLS) statistical methodology using a training set of 420 experimental IC50 values. The predictive power of the method was assessed using rigorous cross-validation and using an independent test set of 89 peptides. The mean value of the residuals between the experimental and predicted pIC50 values was 0.508 for this test set. The additive method was implemented in a program for rapid T-cell epitope search. It is universal and can be applied to any peptide−protein interaction where binding data is known.

KW - qsar

KW - pls

KW - free-wilson

KW - mhc

KW - hla-a0201

UR - http://pubs.acs.org/doi/pdf/10.1021/pr015513z

U2 - 10.1021/pr015513z

DO - 10.1021/pr015513z

M3 - Article

VL - 1

SP - 263

EP - 272

JO - Journal of Proteome Research

JF - Journal of Proteome Research

SN - 1535-3893

IS - 3

ER -