This work focuses on improving MHC-I binding prediction, a crucial component in computational immunology and vaccine development. We developed enhanced methodologies that achieve better generalization properties compared to previous state-of-the-art approaches.

The research contributes to the broader field of computational biology by providing more accurate predictions for antigenic peptide discovery, which has important implications for understanding immune responses and developing targeted therapies.

Presented at: ICLR 2023 Machine Learning for Drug Discovery (MLDD) Workshop