CBTOPE2: An improved method for predicting of conformational B-cell epitopes in an antigen from its primary sequence

Abstract

In 2009, our group pioneered a novel method CBTOPE for predicting conformational B-cell epitopes in a protein from its amino acid sequence, which received extensive citations from the scientific community. In a recent study, Cia et al. (2023) evaluated the performance of conformational B-cell epitope prediction methods on a well-curated dataset, revealing that most approaches, including CBTOPE, exhibited poor performance. One plausible cause of this diminished performance is that available methods were trained on datasets that are both limited in size and outdated in content. In this study, we present an enhanced version of CBTOPE, trained, tested, and evaluated using the well-curated dataset from Cai et al. (2023). Initially, we developed machine learning-based models using binary profiles, achieving a maximum AUC of 0.58 on the validation dataset. The performance of our method improved significantly from an AUC of 0.58 to 0.63 when incorporating evolutionary information in the form of a Position-Specific Scoring Matrix (PSSM) profile. Furthermore, the performance increased from an AUC of 0.63 to 0.64 when we integrated both the PSSM profile and relative solvent accessibility (RSA). All models were trained, tested, and optimized on the training dataset using five-fold cross-validation. The final performance of our models was assessed using a validation or independent dataset that was not used during hyperparameter optimization. To facilitate scientific community working in the field of subunit vaccine, we develop a standalone software and web server CBTOPE2 (https://webs.iiitd.edu.in/raghava/cbtope2/).