Provides users a support vector machines (SVM) prediction model using Bayes Feature Extraction (BFE) to predict linear B-cell epitopes of diverse lengths (12- to 20-mers). Bayesb is based on the report that linear B-cell epitopes and non-epitope sequences have distinctive residue composition and position-specific propensity patterns which could be used for epitope discrimination in silico. It aims to discriminating epitopes from non-epitopes in benchmark datasets and annotated antigenic proteins.
Singapore Immunology Network, Biopolis, Singapore; Data Mining Department, Institute for Infocomm Research, Singapore; Department of Biochemistry, Yong Loo Lin School of Medicine, National University of Singapore, Singapore
Bayesb funding source(s)
Supported by a joint council research grant from the Joint Council Office (JCO) of A *STAR Singapore.