Loading...
Bridging Cell and Organism Scales to Model Viral, Cell, and Microenvironmental Determinants of Infection Outcome
We address the hard problem of linking what happens inside infected tissues to how an infection plays out in immune organs.
The team pairs experiments with scientific machine learning to track how the EBV and HIV viruses change cell behavior in real tissue settings and to build models that capture the spatial and temporal complexity of those changes. Using equation learning and biologically inspired neural networks, RP2 learns interpretable models directly from data, highlighting the microenvironmental factors that shape infection progression and immune response. The goal is a practical bridge from cells to lymph nodes that improves prediction of infection outcomes and guides better strategies to control disease.