Timothy J. O’Donnell

This paper explores the use of LLM-based coding agents in scientific computing, presenting case studies in the life sciences and discussing their potential and challenges.

The paper maps T cell epitopes in SARS-CoV-2, showing that immunodominant regions are conserved across variants and important for immune surveillance.

The paper trains a new version of AlphaFold2, OpenFold, and evaluates its generalization ability and learning mechanisms.

The paper develops an allele-specific MHC peptide binding predictor using imputed training data, achieving performance comparable to existing methods.