TY - CHAP
T1 - Building classifier ensembles for B-cell epitope prediction
AU - El-Manzalawy, Yasser
AU - Honavar, Vasant
PY - 2014
Y1 - 2014
N2 - Identification of B-cell epitopes in target antigens is a critical step in epitope-driven vaccine design, immunodiagnostic tests, and antibody production. B-cell epitopes could be linear, i.e., a contiguous amino acid sequence fragment of an antigen, or conformational, i.e., amino acids that are often not contiguous in the primary sequence but appear in close proximity within the folded 3D antigen structure. Numerous computational methods have been proposed for predicting both types of B-cell epitopes. However, the development of tools for reliably predicting B-cell epitopes remains a major challenge in immunoinformatics. Classifier ensembles a promising approach for combining a set of classifiers such that the overall performance of the resulting ensemble is better than the predictive performance of the best individual classifier. In this chapter, we show how to build a classifier ensemble for improved prediction of linear B-cell epitopes. The method can be easily adapted to build classifier ensembles for predicting conformational epitopes.
AB - Identification of B-cell epitopes in target antigens is a critical step in epitope-driven vaccine design, immunodiagnostic tests, and antibody production. B-cell epitopes could be linear, i.e., a contiguous amino acid sequence fragment of an antigen, or conformational, i.e., amino acids that are often not contiguous in the primary sequence but appear in close proximity within the folded 3D antigen structure. Numerous computational methods have been proposed for predicting both types of B-cell epitopes. However, the development of tools for reliably predicting B-cell epitopes remains a major challenge in immunoinformatics. Classifier ensembles a promising approach for combining a set of classifiers such that the overall performance of the resulting ensemble is better than the predictive performance of the best individual classifier. In this chapter, we show how to build a classifier ensemble for improved prediction of linear B-cell epitopes. The method can be easily adapted to build classifier ensembles for predicting conformational epitopes.
UR - http://www.scopus.com/inward/record.url?scp=84934441467&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84934441467&partnerID=8YFLogxK
U2 - 10.1007/978-1-4939-1115-8_15
DO - 10.1007/978-1-4939-1115-8_15
M3 - Chapter
C2 - 25048130
AN - SCOPUS:84934441467
SN - 9781493911141
T3 - Methods in Molecular Biology
SP - 285
EP - 294
BT - Immunoinformatics
PB - Humana Press Inc.
ER -