Artificial intelligence predicts the immunogenic landscape of SARS-CoV-2: toward universal blueprints for vaccine designs

Brandon Malone; Boris Simovski; Clement Moline; Jun Cheng; Marius Gheorghe; Hugues Fontenelle; Ioannis Vardaxis; Simen Tennoe; Jenny-Ann Malmberg; Richard Stratford; Trevor Clancy

Any viable vaccine to tackle SARS-CoV-2 that incorporates T cell epitopes in its design would need to contain a constellation of overlapping epitopes that protect the vast majority of the human HLA population against the virus. In this study we attempt to demonstrate that the SARS-CoV-2 immunogenic landscape clusters into distinct groups across the spectrum of HLA alleles in the human population. Our predicted immunogenic landscape of the SARS-CoV-2 virus is therefore then processed through a robust comprehensive statistical Monte Carlo simulation, incorporating the integrative immune parameters, to identify epitope hotspots for a broad adaptive immune response across the most common HLA genetic makeup in the human population. The resulting epitope hotspots we identified may represent areas in the viral proteome that are most likely to be viable vaccine targets and represent blueprints for vaccine designs that may be universal in nature.