POPI

Predicting immunogenicity of MHC class I binding peptides by mining informative physicochemical properties

Chun Wei Tung, Shinn Ying Ho

Research output: Contribution to journalArticle

72 Citations (Scopus)

Abstract

Motivation: Both modeling of antigen-processing pathway including major histocompatibility complex (MHC) binding and immunogenicity prediction of those MHC-binding peptides are essential to develop a computer-aided system of peptide-based vaccine design that is one goal of immunoinformatics. Numerous studies have dealt with modeling the immunogenic pathway but not the intractable problem of immunogenicity prediction due to complex effects of many intrinsic and extrinsic factors. Moderate affinity of the MHC-peptide complex is essential to induce immune responses, but the relationship between the affinity and peptide immunogenicity is too weak to use for predicting immunogenicity. This study focuses on mining informative physicochemical properties from known experimental immunogenicity data to understand immune responses and predict immunogenicity of MHC-binding peptides accurately. Results: This study proposes a computational method to mine a feature set of informative physicochemical properties from MHC class I binding peptides to design a support vector machine (SVM) based system (named POPI) for the prediction of peptide immunogenicity. High performance of POPI arises mainly from an inheritable bi-objective genetic algorithm, which aims to automatically determine the best number m out of 531 physicochemical properties, identify these m properties and tune SVM parameters simultaneously. The dataset consisting of 428 human MHC class I binding peptides belonging to four classes of immunogenicity was established from MHCPEP, a database of MHC-binding peptides (Brusic et al, 1998). POPI, utilizing the m = 23 selected properties, performs well with the accuracy of 64.72% using leave-one-out cross-validation, compared with two sequence alignment-based prediction methods ALIGN (54.91%) and PSI-BLAST (53.23%). POPI is the first computational system for prediction of peptide immunogenicity based on physicochemical properties.

Original languageEnglish
Pages (from-to)942-949
Number of pages8
JournalBioinformatics
Volume23
Issue number8
DOIs
Publication statusPublished - Apr 15 2007
Externally publishedYes

Fingerprint

Major Histocompatibility Complex
Peptides
Mining
Prediction
Immune Response
Affine transformation
Support vector machines
Pathway
Support Vector Machine
Class
Intrinsic Factor
Subunit Vaccines
Sequence Alignment
Computer Systems
Antigen Presentation
Vaccines
Vaccine
Antigens
Computational methods
Modeling

ASJC Scopus subject areas

  • Statistics and Probability
  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Computational Theory and Mathematics
  • Computational Mathematics

Cite this

POPI : Predicting immunogenicity of MHC class I binding peptides by mining informative physicochemical properties. / Tung, Chun Wei; Ho, Shinn Ying.

In: Bioinformatics, Vol. 23, No. 8, 15.04.2007, p. 942-949.

Research output: Contribution to journalArticle

@article{3a93cadfe8ff45f99a38cbb2fe656b6c,
title = "POPI: Predicting immunogenicity of MHC class I binding peptides by mining informative physicochemical properties",
abstract = "Motivation: Both modeling of antigen-processing pathway including major histocompatibility complex (MHC) binding and immunogenicity prediction of those MHC-binding peptides are essential to develop a computer-aided system of peptide-based vaccine design that is one goal of immunoinformatics. Numerous studies have dealt with modeling the immunogenic pathway but not the intractable problem of immunogenicity prediction due to complex effects of many intrinsic and extrinsic factors. Moderate affinity of the MHC-peptide complex is essential to induce immune responses, but the relationship between the affinity and peptide immunogenicity is too weak to use for predicting immunogenicity. This study focuses on mining informative physicochemical properties from known experimental immunogenicity data to understand immune responses and predict immunogenicity of MHC-binding peptides accurately. Results: This study proposes a computational method to mine a feature set of informative physicochemical properties from MHC class I binding peptides to design a support vector machine (SVM) based system (named POPI) for the prediction of peptide immunogenicity. High performance of POPI arises mainly from an inheritable bi-objective genetic algorithm, which aims to automatically determine the best number m out of 531 physicochemical properties, identify these m properties and tune SVM parameters simultaneously. The dataset consisting of 428 human MHC class I binding peptides belonging to four classes of immunogenicity was established from MHCPEP, a database of MHC-binding peptides (Brusic et al, 1998). POPI, utilizing the m = 23 selected properties, performs well with the accuracy of 64.72{\%} using leave-one-out cross-validation, compared with two sequence alignment-based prediction methods ALIGN (54.91{\%}) and PSI-BLAST (53.23{\%}). POPI is the first computational system for prediction of peptide immunogenicity based on physicochemical properties.",
author = "Tung, {Chun Wei} and Ho, {Shinn Ying}",
year = "2007",
month = "4",
day = "15",
doi = "10.1093/bioinformatics/btm061",
language = "English",
volume = "23",
pages = "942--949",
journal = "Bioinformatics",
issn = "1367-4803",
publisher = "Oxford University Press",
number = "8",

}

TY - JOUR

T1 - POPI

T2 - Predicting immunogenicity of MHC class I binding peptides by mining informative physicochemical properties

AU - Tung, Chun Wei

AU - Ho, Shinn Ying

PY - 2007/4/15

Y1 - 2007/4/15

N2 - Motivation: Both modeling of antigen-processing pathway including major histocompatibility complex (MHC) binding and immunogenicity prediction of those MHC-binding peptides are essential to develop a computer-aided system of peptide-based vaccine design that is one goal of immunoinformatics. Numerous studies have dealt with modeling the immunogenic pathway but not the intractable problem of immunogenicity prediction due to complex effects of many intrinsic and extrinsic factors. Moderate affinity of the MHC-peptide complex is essential to induce immune responses, but the relationship between the affinity and peptide immunogenicity is too weak to use for predicting immunogenicity. This study focuses on mining informative physicochemical properties from known experimental immunogenicity data to understand immune responses and predict immunogenicity of MHC-binding peptides accurately. Results: This study proposes a computational method to mine a feature set of informative physicochemical properties from MHC class I binding peptides to design a support vector machine (SVM) based system (named POPI) for the prediction of peptide immunogenicity. High performance of POPI arises mainly from an inheritable bi-objective genetic algorithm, which aims to automatically determine the best number m out of 531 physicochemical properties, identify these m properties and tune SVM parameters simultaneously. The dataset consisting of 428 human MHC class I binding peptides belonging to four classes of immunogenicity was established from MHCPEP, a database of MHC-binding peptides (Brusic et al, 1998). POPI, utilizing the m = 23 selected properties, performs well with the accuracy of 64.72% using leave-one-out cross-validation, compared with two sequence alignment-based prediction methods ALIGN (54.91%) and PSI-BLAST (53.23%). POPI is the first computational system for prediction of peptide immunogenicity based on physicochemical properties.

AB - Motivation: Both modeling of antigen-processing pathway including major histocompatibility complex (MHC) binding and immunogenicity prediction of those MHC-binding peptides are essential to develop a computer-aided system of peptide-based vaccine design that is one goal of immunoinformatics. Numerous studies have dealt with modeling the immunogenic pathway but not the intractable problem of immunogenicity prediction due to complex effects of many intrinsic and extrinsic factors. Moderate affinity of the MHC-peptide complex is essential to induce immune responses, but the relationship between the affinity and peptide immunogenicity is too weak to use for predicting immunogenicity. This study focuses on mining informative physicochemical properties from known experimental immunogenicity data to understand immune responses and predict immunogenicity of MHC-binding peptides accurately. Results: This study proposes a computational method to mine a feature set of informative physicochemical properties from MHC class I binding peptides to design a support vector machine (SVM) based system (named POPI) for the prediction of peptide immunogenicity. High performance of POPI arises mainly from an inheritable bi-objective genetic algorithm, which aims to automatically determine the best number m out of 531 physicochemical properties, identify these m properties and tune SVM parameters simultaneously. The dataset consisting of 428 human MHC class I binding peptides belonging to four classes of immunogenicity was established from MHCPEP, a database of MHC-binding peptides (Brusic et al, 1998). POPI, utilizing the m = 23 selected properties, performs well with the accuracy of 64.72% using leave-one-out cross-validation, compared with two sequence alignment-based prediction methods ALIGN (54.91%) and PSI-BLAST (53.23%). POPI is the first computational system for prediction of peptide immunogenicity based on physicochemical properties.

UR - http://www.scopus.com/inward/record.url?scp=34249687092&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34249687092&partnerID=8YFLogxK

U2 - 10.1093/bioinformatics/btm061

DO - 10.1093/bioinformatics/btm061

M3 - Article

VL - 23

SP - 942

EP - 949

JO - Bioinformatics

JF - Bioinformatics

SN - 1367-4803

IS - 8

ER -