Phylogeny-aware linear B-cell epitope predictor detects candidate targets for specific immune responses to Monkeypox virus

Abstract

Monkeypox is a disease caused by the Monkeypox virus (MPXV), a double-stranded DNA virus from genus Orthopoxvirus under family Poxviridae, that has recently emerged as a global health threat after decades of local outbreaks in Central and Western Africa. Effective epidemiological control against this disease requires the development of cheaper, faster diagnostic tools to monitor its spread, including antigen and serological testing. There is, however, little available information about MPXV epitopes, particularly those that would be effective in discriminating between MPXV infections and those by other virus from the same family. We used the available data from the Immune Epitope Database (IEDB) to generate and validate a predictive model optimised for detecting linear B-cell epitopes (LBCEs) from Orthopoxvirus, based on a phylogeny-aware data selection strategy. By coupling this predictive approach with conservation and similarity analyses, we identified nine specific peptides from MPXV that are likely to represent distinctive LBCEs for the diagnostic of Monkeypox infections, including the independent detection of a known epitope experimentally characterised as a potential specific diagnostic target for MPXV. The results obtained indicate ability of the proposed pipeline to uncover promising targets for the development of cheaper, more specific diagnostic tests for this emerging viral disease.

The rise of taxon-specific epitope predictors

“…Although this approach can be useful, it is limited by the fact that both data volume and the expected homogeneity of traits within these taxonomic levels are often highly variable. A more promising approach, which we outline in a previous report [ 3 ], is to have pipelines capable of automatically selecting the optimal taxonomic level to use when building models for a specific pathogen. This approach obviates the need for a pre-defined taxonomic level and enables automatic adaptation to pathogens from data-rich as well as data-scarce groups.…”

“…having peptides from either the same or homologous proteins placed in distinct splits, may also lead information being accidentally leaked across splits if feature calculation uses protein-level information. Splitting the data based on protein clusters [ 2 , 3 ] is a simple way to prevent the issue, as this strategy guarantees that peptides from the same protein or from highly-similar proteins are always kept together during, e.g. cross-validation.…”

Estimating the Limits of Organism-Specific Training for Epitope Prediction

“…Unfortunately, large volumes of validated epitope data are not available for most organisms, which is particularly exacerbated in the case of emerging pathogens that may represent pandemic risk. As an example, at the start of the 2022 global monkeypox outbreak only five LBCEs were listed on the IEDB for the MPX virus, with no negative examples [47], a common scenario for emerging zoonotic pathogens which could preclude the training of models using exclusively organism-specific data. The aim of this study is therefore to investigate the limits of organism-specific training, by focusing on two main questions: (i) How does the number of available organism-specific training peptides affect prediction performance?…”