An improved deep learning model for immunogenic B epitope prediction

Abstract

The recognition of B epitopes by B cells of the immune system initiates an immune response that leads to the production of antibodies to combat bacterial and viral infections. Computational methods for predicting the epitopes on antigens have shown promising results in the development of subunit vaccines and therapeutics. Recently, the use of protein language models (pLMs) for epitope prediction has led to a substantial increase in prediction accuracy. However, further improvements in precision are necessary for practical applications. Here, we develop and evaluate a series of models using different combinations of features and feature fusion techniques on a curated independent test set. Our results show that the models that use protein embeddings along with structural features are better at predicting both linear and conformational B epitopes when compared to a baseline model that uses only protein embeddings as features. Additionally, we show that the embeddings of ESM-2, an evolutionary scale model, likely capture T-B reciprocity.