EPSVR and EPMeta

Prediction of antigenic epitopes using support vector regression and multiple server results

Shide Liang, Dandan Zheng, Daron M. Standley, Bo Yao, Martin Zacharias, Chi Zhang

Research output: Contribution to journalArticle

73 Citations (Scopus)

Abstract

Background: Accurate prediction of antigenic epitopes is important for immunologic research and medical applications, but it is still an open problem in bioinformatics. The case for discontinuous epitopes is even worse - currently there are only a few discontinuous epitope prediction servers available, though discontinuous peptides constitute the majority of all B-cell antigenic epitopes. The small number of structures for antigen-antibody complexes limits the development of reliable discontinuous epitope prediction methods and an unbiased benchmark to evaluate developed methods.Results: In this work, we present two novel server applications for discontinuous epitope prediction: EPSVR and EPMeta, where EPMeta is a meta server. EPSVR, EPMeta, and datasets are available at http://sysbio.unl.edu/services.Conclusion: The server application for discontinuous epitope prediction, EPSVR, uses a Support Vector Regression (SVR) method to integrate six scoring terms. Furthermore, we combined EPSVR with five existing epitope prediction servers to construct EPMeta. All methods were benchmarked by our curated independent test set, in which all antigens had no complex structures with the antibody, and their epitopes were identified by various biochemical experiments. The area under the receiver operating characteristic curve (AUC) of EPSVR was 0.597, higher than that of any other existing single server, and EPMeta had a better performance than any single server - with an AUC of 0.638, significantly higher than PEPITO and Disctope (p-value < 0.05).

Original languageEnglish (US)
Article number381
JournalBMC bioinformatics
Volume11
DOIs
StatePublished - Jul 16 2010

Fingerprint

Epitopes
Support Vector Regression
Servers
Server
Prediction
Single Server
Antibody
Antigens
Area Under Curve
Antibodies
B Cells
Medical Applications
Receiver Operating Characteristic Curve
p-Value
Test Set
Independent Set
B-Lymphocyte Epitopes
Complex Structure
Scoring
Benchmarking

ASJC Scopus subject areas

  • Structural Biology
  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Applied Mathematics

Cite this

EPSVR and EPMeta : Prediction of antigenic epitopes using support vector regression and multiple server results. / Liang, Shide; Zheng, Dandan; Standley, Daron M.; Yao, Bo; Zacharias, Martin; Zhang, Chi.

In: BMC bioinformatics, Vol. 11, 381, 16.07.2010.

Research output: Contribution to journalArticle

@article{6870d82d01994da79848942a8028b902,
title = "EPSVR and EPMeta: Prediction of antigenic epitopes using support vector regression and multiple server results",
abstract = "Background: Accurate prediction of antigenic epitopes is important for immunologic research and medical applications, but it is still an open problem in bioinformatics. The case for discontinuous epitopes is even worse - currently there are only a few discontinuous epitope prediction servers available, though discontinuous peptides constitute the majority of all B-cell antigenic epitopes. The small number of structures for antigen-antibody complexes limits the development of reliable discontinuous epitope prediction methods and an unbiased benchmark to evaluate developed methods.Results: In this work, we present two novel server applications for discontinuous epitope prediction: EPSVR and EPMeta, where EPMeta is a meta server. EPSVR, EPMeta, and datasets are available at http://sysbio.unl.edu/services.Conclusion: The server application for discontinuous epitope prediction, EPSVR, uses a Support Vector Regression (SVR) method to integrate six scoring terms. Furthermore, we combined EPSVR with five existing epitope prediction servers to construct EPMeta. All methods were benchmarked by our curated independent test set, in which all antigens had no complex structures with the antibody, and their epitopes were identified by various biochemical experiments. The area under the receiver operating characteristic curve (AUC) of EPSVR was 0.597, higher than that of any other existing single server, and EPMeta had a better performance than any single server - with an AUC of 0.638, significantly higher than PEPITO and Disctope (p-value < 0.05).",
author = "Shide Liang and Dandan Zheng and Standley, {Daron M.} and Bo Yao and Martin Zacharias and Chi Zhang",
year = "2010",
month = "7",
day = "16",
doi = "10.1186/1471-2105-11-381",
language = "English (US)",
volume = "11",
journal = "BMC Bioinformatics",
issn = "1471-2105",
publisher = "BioMed Central",

}

TY - JOUR

T1 - EPSVR and EPMeta

T2 - Prediction of antigenic epitopes using support vector regression and multiple server results

AU - Liang, Shide

AU - Zheng, Dandan

AU - Standley, Daron M.

AU - Yao, Bo

AU - Zacharias, Martin

AU - Zhang, Chi

PY - 2010/7/16

Y1 - 2010/7/16

N2 - Background: Accurate prediction of antigenic epitopes is important for immunologic research and medical applications, but it is still an open problem in bioinformatics. The case for discontinuous epitopes is even worse - currently there are only a few discontinuous epitope prediction servers available, though discontinuous peptides constitute the majority of all B-cell antigenic epitopes. The small number of structures for antigen-antibody complexes limits the development of reliable discontinuous epitope prediction methods and an unbiased benchmark to evaluate developed methods.Results: In this work, we present two novel server applications for discontinuous epitope prediction: EPSVR and EPMeta, where EPMeta is a meta server. EPSVR, EPMeta, and datasets are available at http://sysbio.unl.edu/services.Conclusion: The server application for discontinuous epitope prediction, EPSVR, uses a Support Vector Regression (SVR) method to integrate six scoring terms. Furthermore, we combined EPSVR with five existing epitope prediction servers to construct EPMeta. All methods were benchmarked by our curated independent test set, in which all antigens had no complex structures with the antibody, and their epitopes were identified by various biochemical experiments. The area under the receiver operating characteristic curve (AUC) of EPSVR was 0.597, higher than that of any other existing single server, and EPMeta had a better performance than any single server - with an AUC of 0.638, significantly higher than PEPITO and Disctope (p-value < 0.05).

AB - Background: Accurate prediction of antigenic epitopes is important for immunologic research and medical applications, but it is still an open problem in bioinformatics. The case for discontinuous epitopes is even worse - currently there are only a few discontinuous epitope prediction servers available, though discontinuous peptides constitute the majority of all B-cell antigenic epitopes. The small number of structures for antigen-antibody complexes limits the development of reliable discontinuous epitope prediction methods and an unbiased benchmark to evaluate developed methods.Results: In this work, we present two novel server applications for discontinuous epitope prediction: EPSVR and EPMeta, where EPMeta is a meta server. EPSVR, EPMeta, and datasets are available at http://sysbio.unl.edu/services.Conclusion: The server application for discontinuous epitope prediction, EPSVR, uses a Support Vector Regression (SVR) method to integrate six scoring terms. Furthermore, we combined EPSVR with five existing epitope prediction servers to construct EPMeta. All methods were benchmarked by our curated independent test set, in which all antigens had no complex structures with the antibody, and their epitopes were identified by various biochemical experiments. The area under the receiver operating characteristic curve (AUC) of EPSVR was 0.597, higher than that of any other existing single server, and EPMeta had a better performance than any single server - with an AUC of 0.638, significantly higher than PEPITO and Disctope (p-value < 0.05).

UR - http://www.scopus.com/inward/record.url?scp=77954543849&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77954543849&partnerID=8YFLogxK

U2 - 10.1186/1471-2105-11-381

DO - 10.1186/1471-2105-11-381

M3 - Article

VL - 11

JO - BMC Bioinformatics

JF - BMC Bioinformatics

SN - 1471-2105

M1 - 381

ER -