Understanding the effects of higher order sequence features on peptide MHC binding

Abstract

Understanding the factors that contribute to peptide-MHC (pMHC) affinity is critical for the study of immune responses and the development of novel therapeutics. In this thesis we propose the use of sequence feature representations as a means of capturing and categorizing these factors, and we develop the theoretical framework and justification for their use. We then apply sequence feature representations to analyze data derived from yeast display platforms, which enable the collection of pMHC binding data for vast libraries of peptides. Methods for interpreting data from these platforms are still at an early stage, so in this thesis we also develop an approach for extracting useful information from such data. We demonstrate that the resulting sequence feature representations accurately capture the kinetics underlying pMHC binding, can be used to predict pMHC binding well enough to rival the current state of the art, and can be interpreted to show that they correlate with our current structural understanding of pMHC complexes.