BcePred: Prediction of Continuous B-Cell Epitopes in Antigenic Sequences Using Physico-chemical Properties

Welcome to the official repository for BcePred, a web server for predicting continuous B-cell epitopes in antigenic protein sequences. This resource is designed to support researchers in vaccine design, immunoinformatics, and computational immunology. Web Server: https://webs.iiitd.edu.in/raghava/bcepred/ Citation Saha, S., & Raghava, G. P. S. (2004). BcePred: Prediction of continuous B-cell epitopes in antigenic sequences using physico-chemical properties. In G. Nicosia, V. Cutello, P. J. Bentley, & J. Timmis (Eds.), Artificial Immune Systems, Third International Conference (ICARIS 2004), Lecture Notes in Computer Science, Vol. 3239, pp. 197–204. Springer-Verlag Berlin Heidelberg. https://link.springer.com/chapter/10.1007/978-3-540-30220-9_16 About the Tool BcePred is a web-based server for predicting continuous (linear) B-cell epitopes in antigenic protein sequences using physico-chemical properties of amino acids. It provides a systematic, benchmarked evaluation of seven residue property scales commonly used in existing epitope prediction methods — and introduces a combined multi-property approach that outperforms any single property. The tool integrates data from: Bcipep database (experimentally validated B-cell epitopes) SWISS-PROT database (non-epitope random peptide sequences) Key Features Dataset 1,029 non-redundant continuous B-cell epitopes from the Bcipep database 1,029 non-epitopes (random peptides of equal length, derived from SWISS-PROT) Coverage across diverse pathogenic groups: viruses, bacteria, protozoa, and fungi