Biophysical Modeling for Predicting Human T Cell Repertoire Specificity

Despite the role that T cell receptor (TCR) recognition plays in controlling cancer and viral nonself-signatures, we at present lack biophysically interpretable methods to reliably predict TCR specificity. Such modeling would enable the development of optimized vaccines and cancer immunotherapy. This talk will discuss recent efforts to create a biophysically interpretable model of T cell receptor-antigen binding for predicting receptor specificity across an array of antigens. In the setting of HLA-A*02:01-restricted TCRs, we demonstrate the utility of this model to simultaneously predict the antigenicity of disparate peptides, as well as closely related (point-mutated) variants of a preidentified antigen. Lastly, we will discuss current efforts to incorporate AI-predicted structures into our training for improved predictions.