VaxiJen: a server for prediction of protective antigens, tumour antigens and subunit vaccines

Irini A. Doytchinova, Darren R. Flower

Research output: Contribution to journalArticle

Abstract

Background - Vaccine development in the post-genomic era often begins with the in silico screening of genome information, with the most probable protective antigens being predicted rather than requiring causative microorganisms to be grown. Despite the obvious advantages of this approach – such as speed and cost efficiency – its success remains dependent on the accuracy of antigen prediction. Most approaches use sequence alignment to identify antigens. This is problematic for several reasons. Some proteins lack obvious sequence similarity, although they may share similar structures and biological properties. The antigenicity of a sequence may be encoded in a subtle and recondite manner not amendable to direct identification by sequence alignment. The discovery of truly novel antigens will be frustrated by their lack of similarity to antigens of known provenance. To overcome the limitations of alignment-dependent methods, we propose a new alignment-free approach for antigen prediction, which is based on auto cross covariance (ACC) transformation of protein sequences into uniform vectors of principal amino acid properties.
Results - Bacterial, viral and tumour protein datasets were used to derive models for prediction of whole protein antigenicity. Every set consisted of 100 known antigens and 100 non-antigens. The derived models were tested by internal leave-one-out cross-validation and external validation using test sets. An additional five training sets for each class of antigens were used to test the stability of the discrimination between antigens and non-antigens. The models performed well in both validations showing prediction accuracy of 70% to 89%. The models were implemented in a server, which we call VaxiJen.
Conclusion - VaxiJen is the first server for alignment-independent prediction of protective antigens. It was developed to allow antigen classification solely based on the physicochemical properties of proteins without recourse to sequence alignment. The server can be used on its own or in combination with alignment-based prediction methods.
Original languageEnglish
Article number4
Number of pages7
JournalBMC Bioinformatics
Volume8
DOIs
Publication statusPublished - 5 Jan 2007

Fingerprint

Cancer Vaccines
Subunit Vaccines
Vaccines
Vaccine
Neoplasm Antigens
Antigens
Tumors
Tumor
Servers
Server
Sequence Alignment
Prediction
Alignment
Protein
Proteins
Cost Efficiency
Provenance
Dependent
Microorganisms
Protein Sequence

Bibliographical note

© 2007 Doytchinova and Flower; 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.

Keywords

  • VaxiJen
  • vaccines
  • tumour antigens

Cite this

@article{0b2aa13f3a884c1e9fa06749e04847a5,
title = "VaxiJen: a server for prediction of protective antigens, tumour antigens and subunit vaccines",
abstract = "Background - Vaccine development in the post-genomic era often begins with the in silico screening of genome information, with the most probable protective antigens being predicted rather than requiring causative microorganisms to be grown. Despite the obvious advantages of this approach – such as speed and cost efficiency – its success remains dependent on the accuracy of antigen prediction. Most approaches use sequence alignment to identify antigens. This is problematic for several reasons. Some proteins lack obvious sequence similarity, although they may share similar structures and biological properties. The antigenicity of a sequence may be encoded in a subtle and recondite manner not amendable to direct identification by sequence alignment. The discovery of truly novel antigens will be frustrated by their lack of similarity to antigens of known provenance. To overcome the limitations of alignment-dependent methods, we propose a new alignment-free approach for antigen prediction, which is based on auto cross covariance (ACC) transformation of protein sequences into uniform vectors of principal amino acid properties.Results - Bacterial, viral and tumour protein datasets were used to derive models for prediction of whole protein antigenicity. Every set consisted of 100 known antigens and 100 non-antigens. The derived models were tested by internal leave-one-out cross-validation and external validation using test sets. An additional five training sets for each class of antigens were used to test the stability of the discrimination between antigens and non-antigens. The models performed well in both validations showing prediction accuracy of 70{\%} to 89{\%}. The models were implemented in a server, which we call VaxiJen.Conclusion - VaxiJen is the first server for alignment-independent prediction of protective antigens. It was developed to allow antigen classification solely based on the physicochemical properties of proteins without recourse to sequence alignment. The server can be used on its own or in combination with alignment-based prediction methods.",
keywords = "VaxiJen, vaccines, tumour antigens",
author = "Doytchinova, {Irini A.} and Flower, {Darren R.}",
note = "{\circledC} 2007 Doytchinova and Flower; 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 = "2007",
month = "1",
day = "5",
doi = "10.1186/1471-2105-8-4",
language = "English",
volume = "8",
journal = "BMC Bioinformatics",
issn = "1471-2105",
publisher = "BioMed Central",

}

VaxiJen : a server for prediction of protective antigens, tumour antigens and subunit vaccines. / Doytchinova, Irini A.; Flower, Darren R.

In: BMC Bioinformatics, Vol. 8, 4, 05.01.2007.

Research output: Contribution to journalArticle

TY - JOUR

T1 - VaxiJen

T2 - a server for prediction of protective antigens, tumour antigens and subunit vaccines

AU - Doytchinova, Irini A.

AU - Flower, Darren R.

N1 - © 2007 Doytchinova and Flower; 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 - 2007/1/5

Y1 - 2007/1/5

N2 - Background - Vaccine development in the post-genomic era often begins with the in silico screening of genome information, with the most probable protective antigens being predicted rather than requiring causative microorganisms to be grown. Despite the obvious advantages of this approach – such as speed and cost efficiency – its success remains dependent on the accuracy of antigen prediction. Most approaches use sequence alignment to identify antigens. This is problematic for several reasons. Some proteins lack obvious sequence similarity, although they may share similar structures and biological properties. The antigenicity of a sequence may be encoded in a subtle and recondite manner not amendable to direct identification by sequence alignment. The discovery of truly novel antigens will be frustrated by their lack of similarity to antigens of known provenance. To overcome the limitations of alignment-dependent methods, we propose a new alignment-free approach for antigen prediction, which is based on auto cross covariance (ACC) transformation of protein sequences into uniform vectors of principal amino acid properties.Results - Bacterial, viral and tumour protein datasets were used to derive models for prediction of whole protein antigenicity. Every set consisted of 100 known antigens and 100 non-antigens. The derived models were tested by internal leave-one-out cross-validation and external validation using test sets. An additional five training sets for each class of antigens were used to test the stability of the discrimination between antigens and non-antigens. The models performed well in both validations showing prediction accuracy of 70% to 89%. The models were implemented in a server, which we call VaxiJen.Conclusion - VaxiJen is the first server for alignment-independent prediction of protective antigens. It was developed to allow antigen classification solely based on the physicochemical properties of proteins without recourse to sequence alignment. The server can be used on its own or in combination with alignment-based prediction methods.

AB - Background - Vaccine development in the post-genomic era often begins with the in silico screening of genome information, with the most probable protective antigens being predicted rather than requiring causative microorganisms to be grown. Despite the obvious advantages of this approach – such as speed and cost efficiency – its success remains dependent on the accuracy of antigen prediction. Most approaches use sequence alignment to identify antigens. This is problematic for several reasons. Some proteins lack obvious sequence similarity, although they may share similar structures and biological properties. The antigenicity of a sequence may be encoded in a subtle and recondite manner not amendable to direct identification by sequence alignment. The discovery of truly novel antigens will be frustrated by their lack of similarity to antigens of known provenance. To overcome the limitations of alignment-dependent methods, we propose a new alignment-free approach for antigen prediction, which is based on auto cross covariance (ACC) transformation of protein sequences into uniform vectors of principal amino acid properties.Results - Bacterial, viral and tumour protein datasets were used to derive models for prediction of whole protein antigenicity. Every set consisted of 100 known antigens and 100 non-antigens. The derived models were tested by internal leave-one-out cross-validation and external validation using test sets. An additional five training sets for each class of antigens were used to test the stability of the discrimination between antigens and non-antigens. The models performed well in both validations showing prediction accuracy of 70% to 89%. The models were implemented in a server, which we call VaxiJen.Conclusion - VaxiJen is the first server for alignment-independent prediction of protective antigens. It was developed to allow antigen classification solely based on the physicochemical properties of proteins without recourse to sequence alignment. The server can be used on its own or in combination with alignment-based prediction methods.

KW - VaxiJen

KW - vaccines

KW - tumour antigens

U2 - 10.1186/1471-2105-8-4

DO - 10.1186/1471-2105-8-4

M3 - Article

C2 - 17207271

VL - 8

JO - BMC Bioinformatics

JF - BMC Bioinformatics

SN - 1471-2105

M1 - 4

ER -