An AI platform to facilitate the rapid development of T cell based diagnostic tests: applied to SARS-CoV-2

During 2022, the NOI has continued to work on repurposing the NEC prediction platform, the NEC "Immune Profiler" (NIP), to profile the SARS-CoV-2 virus and other pathogens, and identify good immunogenic T-cell targets. In addition, NOI has worked on developing other platforms and statistical tools, which use predictions from NIP and work in tandem with the tool digital twin analysis, which was developed earlier in the project to model the HLA diversity in the human population. This enables the AI ​​platform to identify hotspot combinations (and constitutive epitopes) that are cross-reactive across virus types within the same viral family, and which at the same time have a high degree of coverage in the total human population. This enables the design of blueprints for new diagnostics and vaccines that not only work against specific viruses, but can provide broad protection against new variants or other related virus types. In parallel, OUS has developed a refined "flow-based-activation-induced" marker analysis, to further characterize the SARS-CoV-2 test peptides that were identified earlier in the project using the NIP prediction platform. OUS has identified and verified a subset of these peptides that stimulated robust CD4+ and CD8+ T cell "recall" responses in PBMCs from both SARS-CoV-2 convalescent individuals and immunized donors. Finally, these peptides were used to screen for vaccine-generated CD8+ T-cell immune responses in cohorts consisting of high-risk immunocompromised patients. The data has been shared with the Norwegian Institute of Public Health and Norwegian health politicians, and has contributed to changing guidelines for vaccination of high-risk immunocompromised patients. The data also clearly show the usefulness of NIP in identifying peptides that can be used in a diagnostic setting.