BepiPred-2.0 is a web server designed for predicting B-cell epitopes from antigen sequences. It is based on a random forest algorithm trained on epitopes annotated from antibody-antigen protein structures, which significantly improves the accuracy of sequence-based epitope prediction compared to previous methods. The server was evaluated on both structural and linear epitope datasets, outperforming other tools in terms of accuracy. BepiPred-2.0 provides a user-friendly interface that supports both computer-savvy and non-expert users, making it a valuable tool for researchers in bioinformatics and immunology. The method's performance is enhanced by using high-quality structural data, and it can be applied to various applications such as vaccine design and therapeutic antibody development.BepiPred-2.0 is a web server designed for predicting B-cell epitopes from antigen sequences. It is based on a random forest algorithm trained on epitopes annotated from antibody-antigen protein structures, which significantly improves the accuracy of sequence-based epitope prediction compared to previous methods. The server was evaluated on both structural and linear epitope datasets, outperforming other tools in terms of accuracy. BepiPred-2.0 provides a user-friendly interface that supports both computer-savvy and non-expert users, making it a valuable tool for researchers in bioinformatics and immunology. The method's performance is enhanced by using high-quality structural data, and it can be applied to various applications such as vaccine design and therapeutic antibody development.