PEPITO: improved discontinuous B-cell epitope prediction using multiple distance thresholds and half sphere exposure

Area of Science:

• Computational immunology
• Bioinformatics
• Structural biology

Background:

• Accurate prediction of B-cell epitopes is crucial for vaccine design and immunotherapy.
• Most B-cell epitopes are discontinuous, posing a challenge for existing prediction methods that often focus on linear epitopes.
• Predicting discontinuous epitopes remains difficult even with available antigen tertiary structure information.

Purpose of the Study:

• To develop and evaluate a novel computational method for predicting discontinuous B-cell epitopes.
• To improve the accuracy of B-cell epitope prediction, particularly for discontinuous epitopes.
• To provide a new tool for researchers in immunology and drug discovery.

Main Methods:

• The PEPITO predictor utilizes a combination of amino-acid propensity scores and half sphere exposure values at multiple distances.
• The method incorporates information about the local and global structural context of amino acids.
• Performance was evaluated using standard metrics such as the Area Under the Curve (AUC).

Main Results:

• PEPITO achieved state-of-the-art performance, with an AUC of 75.4 on the Discotope dataset.
• Benchmarking on the Epitome dataset showed PEPITO outperforming the Discotope predictor, achieving AUCs of 68.3 and 66.0, respectively.
• The results demonstrate the effectiveness of the combined feature approach for discontinuous epitope prediction.

Conclusions:

• PEPITO represents a significant advancement in the computational prediction of discontinuous B-cell epitopes.
• The predictor's performance highlights the utility of integrating structural and sequence-based features.
• PEPITO is available as part of the SCRATCH suite, facilitating its use in immunological research.