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 an early report in a preprint article demonstrated in a few sequences that the SARS-COV-2 genome has a lower mutation rate and genetic diversity compared to that of SARS-COV [34] , another preprint study has demonstrated that there are evolving genetic patterns emerging in different strains of SARS-COV-2 in diverse geographic locations [35] . A universal vaccine blueprint should ideally also be able to protect populations against different emerging clades of the SARS-COV-2 virus and we therefore compared the AP potential of approximately 3400 virus sequences in the GISAID database against the AP potential of the Wuhan Genbank reference sequence. The outcome of that comparison is illustrated in Figure 4 , and hints at a trend whereby SARS-COV-2 mutations seem to reduce their potential to be presented and consequently detected by the host immune system. Similar trends have been observed in chronic infections such as HPV and HIV.