Principal Scientist Frontage Labs Exton, Pennsylvania
The bioanalysis of personalized cancer neoantigen vaccine-based N-of-1 trials (PCVNT) invokes sophisticated multiple omics analysis and canonical complexities of cell-based assays, such as ELISPOT and high-dimension flow cytometry. Large consortium-based management has been deployed for PCVNT, e.g., Glioma Actively Personalized Vaccine Consortium (GAPVAC), among others, involving intensive precious resources and personnel with exceptional expertise. Agent AI could be a better solution for PCVNT. Here we report foundation model- based agentic AI bioanalysis of PCVNT. Our agentic AI for PCVNT set each patient’s bioanalysis as multi-layer network (metagraph) representations, including whole exome sequencing (WES) data, transcriptome, immunopeptidome, epitope predictions, vaccine peptides, ELISPOT assay, high dimensional functional flow cytometry analysis, as well as cytokine code assays. Our agentic AI alongside the infrastructure holds a great promise to enable deployment of regulated bioanalysis of PCVNT, fostering fitting of unmet needs in the precision and individual medicine era with an affordable benefit/cost ratio.
Learning Objectives:
Participants will be having a better understanding of the key features of bioanalysis Agentic AI built on foundation models, characterized by proactiveness, SMART (specific, measurable, achievable, relevant, time-bound), and decisiveness.
Participants will be exposed to cutting-edge multi-omic integration technology.
Participants will be learning individualized cancer vaccine AI-assisted biologics.
