Uncertainty Estimation in SARS-CoV-2 B-cell Epitope Prediction for Vaccine Development

TL;DR

This paper introduces a calibrated uncertainty estimation method for deep learning-based B-cell epitope prediction, improving reliability in identifying vaccine candidates against SARS-CoV-2.

Contribution

It presents a novel uncertainty estimation approach using MC-DropWeights for more trustworthy epitope predictions in vaccine development.

Findings

More reliable epitope predictions for SARS-CoV-2

Enhanced confidence in vaccine candidate identification

Improved accuracy over standard methods

Abstract

B-cell epitopes play a key role in stimulating B-cells, triggering the primary immune response which results in antibody production as well as the establishment of long-term immunity in the form of memory cells. Consequently, being able to accurately predict appropriate linear B-cell epitope regions would pave the way for the development of new protein-based vaccines. Knowing how much confidence there is in a prediction is also essential for gaining clinicians' trust in the technology. In this article, we propose a calibrated uncertainty estimation in deep learning to approximate variational Bayesian inference using MC-DropWeights to predict epitope regions using the data from the immune epitope database. Having applied this onto SARS-CoV-2, it can more reliably predict B-cell epitopes than standard methods. This will be able to identify safe and effective vaccine candidates against Covid-19.