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

Although T cells cannot prevent the initial entry of a virus into host cells, they can provide protection by recognizing viral peptides presented by human leukocyte antigens (HLAs) on the surface of host-infected cells, or antigen presenting cells (APCs). Several studies have demonstrated in SARS-CoV that virus specific CD8 T cells are required for mounting an effective immune response and viral clearance [9, [15] [16] [17] [18] [19] . A vaccine design that confers optimal protection may also need to involve the generation of memory T cell responses [20] . It has been shown that the activation of memory T cells specific for a conserved epitope shared by SARS-CoV and MERS-CoV is a potential strategy for developing coronavirus vaccines [21] . In addition, levels of memory T cell responses to SARS-CoV against peptides from its structural proteins were detected in a proportion of SARS-recovered patients, several years after infection [22, 23] . However, an adequate T cell response in isolation may not be sufficient.