Computational epitope mapping of class I fusion proteins using Bayes classification

Abstract

Antibody epitope mapping of viral proteins plays a vital role in understanding immune system mechanisms of protection. In the case of class I viral fusion proteins, recent advances in cryo-electron microscopy and protein stabilization techniques have highlighted the importance of cryptic or alternative conformations that expose epitopes targeted by potent neutralizing antibodies. Thorough epitope mapping of such metastable conformations is difficult, but is critical for understanding sites of vulnerability in class I fusion proteins that occur as transient conformational states during viral attachment and fusion. We introduce a novel method Accelerated class I fusion protein Epitope Mapping (AxIEM) that accounts for fusion protein flexibility to significantly improve out-of-sample prediction of discontinuous antibody epitopes. Harnessing data from previous experimental epitope mapping efforts of several class I fusion proteins, we demonstrate that accuracy of epitope prediction depends on residue environment and allows for the precise prediction of conformation-dependent antibody target residues. We also show that AxIEM can to identify common epitopes and provide structural insights for the development and rational design of vaccines. Author SummaryEfficient determination of neutralizing epitopes of viral fusion proteins is paramount in the development of antibody-based therapeutics against rapidly evolving or undercharacterized viral pathogens. Advances in the determination of viral fusion proteins in multiple conformations with cryptic epitopes during attachment and fusion has highlighted the importance of epitope accessibility due to viral fusion protein flexibility, a physical trait not accounted for in previous B-cell epitope prediction methods. Given the relatively limited number of viral fusion proteins that have been determined in multiple conformations that also have been extensively subjected to epitope mapping techniques,, which are predominantly class I fusion proteins, we chose a limited feature set in combination with a low-complexity Bayesian classifier model to avoid overfitting. We show that this model demonstrates higher accuracy in out-of-sample performance than publicly available epitope prediction methods. Additionally, due to limited structural annotation of neutralizing epitope residues, we provide examples of how our model better discerns conformation-specific epitopes, which is critical for subunit vaccine design, and how this may provide a novel approach to assess the structural changes of antigenicity of viral fusion protein homologues.