Identification of putative unique immunogenic ZIKV and DENV1-4 peptides for diagnostic cellular based tests

Abstract

Since the re-emergence of Zika virus in 2014 and subsequent association with microcephaly, much work has focused on the development of a vaccine to halt its spread throughout the world. The mosquito vector that transmits this virus is widespread and responsible for the spread of other arboviridae including Dengue. Current diagnostic methods rely on serologic testing that are complicated by cross reactivity and therefore unable to distinguish Zika from Dengue infection in the absence of virus isolation. We performed an in silico analysis to identify potential epitopes that may stimulate a unique T-lymphocyte response to distinguish prior infection with Zika or Dengue. From this analysis, we not only identified epitopes unique to Zika and Dengue, but also identified epitopes unique to each Dengue serotype. These peptides contribute to a pool of peptides identified for vaccine development that can be tested in vitro to confirm immunogenicity, absence of homology and global population coverage. The current lack of accurate diagnostic testing hampers our ability to understand the scope of the epidemic, implications for vaccine implementation and complications related to monoinfection and co-infection with these two closely related viruses.

Figure 1

Workflow for ZIKV peptide antigenicity predictions. Briefly, chain A of 5GS6 from the Protein Database was submitted to the IEDB MHC class I and II binding tools and MHC-NP tool. (a) Class I results were first filtered by ANN predicted IC₅₀ levels as recommended in Paul et al. followed by filtering for those results in the top 1 percentile rank. Subsequent results were then sorted by sequence and those predicted to bind ≥3 class I alleles were chosen for further analysis. (b) Class II results were first filtered for those results in the top 1 percentile rank and then sorted by sequence with those predicted to bind ≥2 class II alleles chosen for further analysis. (c) MHC-NP initial results were filtered for those hits with a probability score of ≥0.8. Cross-referencing of class II and MHC-NP data against class I data was performed to generate putative peptides (Table 1).

Figure 2

Workflow for DENV peptide antigenicity predictions. Briefly, each serotype NS2a consensus sequence as well as the DENV NS2a consensus sequence were submitted to the IEDB MHC class I and II binding tools and MHC-NP tool. (a) Class I results were first filtered by ANN predicted IC₅₀ levels as recommended in Paul et al. followed by filtering for those results in the top 1 percentile rank. Subsequent results were then sorted by sequence and those predicted to bind ≥3 class I alleles were chosen for further analysis. (b) Class II results were first filtered for those results in the top 1 percentile rank and then sorted by sequence with those predicted to bind ≥3 class II alleles chosen for further analysis. (c) MHC-NP initial results were filtered for those hits with a probability score of ≥0.8. Cross-referencing of class II and MHC-NP data against class I data was performed to generate putative peptides (Table 2).

Figure 3

Top PatchDock predictions of epitope binding to MHC class I alleles as rendered by PyMOL Molecular Graphics System. Epitopes are shown as sticks with rainbow coloring (blue to red, N-terminus to C-terminus). HLA allele binding grooves are shown as cartoon with β-sheets in yellow, α-helices in red, and loops in green. DENV4 peptide KMSPGYVLGV did not bind within the binding groove of HLA-A*02:01 in any of the top ten PatchDock predictions. (a) ZIKV peptide KSYFVRAAK bound to HLA-A*03:01. (b) ZIKV peptide FLVEDHGFGV bound to HLA-A*02:01. (c) ZIKV peptide GVFHTSVWLK bound to HLA-A*03:01. (d) DENV1 peptide MLMTGTLAVF bound to HLA-A*02:01. (e) DENV2 peptide ILLVAVSFV bound to HLA-A*02:01. (f) DENV3 peptide MIAGVFFTFV bound to HLA-A*02:01. (g) DENV peptide MAIFIEEVMR bound to HLA-B*35:01. (h) DENV peptide MMLKLVTNF bound to HLA-B*15:01.