Algorithms for Understanding and Fighting Infectious Disease

Abstract

Infectious disease is a persistent and substantial threat to human health, with consequences that include widespread mortality, suffering, and economic disruption. This thesis presents several algorithmic advances that, when coupled with biotechnologies for data collection and perturbation, are aimed at understanding infectious disease and using this knowledge to fight it. First, this thesis develops geometric algorithms that enable a panoramic understanding of the systems biology of the human immune system and of infectious pathogens at single-cell resolution. Next, this thesis will show how state-of-the-art Bayesian machine learning can explore complex biological spaces to search for new therapies that fight infectious disease. Finally, this thesis develops neural language models that can predict how pathogens mutate to evade human immunity, potentially enabling more broadly effective vaccines and therapies. Taken together, this thesis outlines a highly interdisciplinary, algorithmic approach to infectious disease research, with broader implications for computation and biology more generally.