Mapping T cell phenotype with machine learning to optimize cancer immunotherapy 2307563

Introduction T cells play a central role in adaptive immune responses, enabling vertebrates to fight infections and eliminate cancer cells. Cancer immunotherapies, and in particular adoptive T-cell therapies, thus aim to harness their tumor-destroying capabilities to treat, or even cure, cancer patients. Despite recent advances in the development of these therapies, a major limitation remains our inability to predict, a priori, which tumor-infiltrating T cells will be best equipped to carry out anti-tumor immunity. Indeed, this multifactorial problem requires a model that integrates information on T cell receptor (TCR) specificity, tumor antigen abundance, and T cell activation history within the complex tumor microenvironment, yet such considerations are largely absent from current T cell selection strategies. Methods To address this gap, we are using a combination approach of high-throughput robotic multiplexing with computational and machine learning techniques to identify signatures of T cell phenotype that best predict response to tumor antigens. Specifically, we aim to study the roles of antigen presentation, TCR/antigen affinity, and inflammatory milieu on shaping T cell phenotype at the single-cell level, and training machine learning models to re-derive the activation history of T cells both in vivo and ex vivo. Results Preliminary results from in vitro co-culture data of T cells with cognate antigen-bearing splenocytes suggests that T cell antigen strength can indeed be back-calculated from single cell phenotype as measured by spectral flow cytometry. Conclusion With a validated model of tumor antigenicity in T cells, this research project aims to better inform T cell selection and optimal preparation strategies for adoptive T-cell therapies.