Personal, social, and environmental health
Adverse health outcomes can be driven by social and environmental determinants of health as well as individual behavior. Improving health outcomes requires addressing each of these factors. At the Hampton Roads Biomedical Research Consortium, we aim to improve health outcomes by leveraging domain expertise, incorporating community knowledge, and using machine learning to link and understand diverse multi-modal datasets.
Hydrodynamic models of social behavior
Community behavior arises from the decisions of each individual in the population. While physics provides tools to model large-scale behavior, incorporating individual preferences and decision-making remains an open problem. We use data-driven analysis to adapt hydrodynamic approaches to capture social behavior and examine a case study of residential dynamics in US Census data. Our model predicts an emergent societal memory at the transition between integration and segregation which slows community change. Collaboration with Daniel Seara, Michel Fruchart, Yael Avni, David Martin, and Vincenzo Vitelli (UChicago).
Predicting post-treatment lymphopenia in lung cancer patients
Circulating lymphocytes absorb significant radiation during treatment which can induce post-treatment complications such as a condition called lymphopenia. We developed an algorithm which estimates blood circulation through targeted organs, calculates the absorbed dose, and predicts lymphocyte death. Using this algorithm, we investigated treatment planning considerations for reducing lymphopenia in patients treated using stereotactic body radiation therapy. Collaboration with Wijesooriya group (UVA)Data-driven biophysics
Continuum mechanics is a physical modeling framework that can describe many materials' behavior but struggles to handle biology. The motion of a cell, for example, comes from actions and feedback loops involving many interacting proteins at the sub-cellular scale. To describe cell behavior using classical mechanics, one must figure out how to account for this microscopic complexity at the continuum scale. With the Vitelli group at UChicago, we combine machine learning, active matter theory, and close collaboration with experimental groups to build interpretable physical models of diverse biological systems.
Drosophila embryogenesis
Morphogenesis is how an organism gets its shape. In flies, this is regulated by genes which are tightly coupled to force-generating proteins throughout the embryo. We use machine learning to analyze movies of developing Drosophila embryos and discover equations governing the dynamics of morphogenesis. Using this model, we identify a genetic signaling pathway which sets the stage for embryo development. Collaboration with Michel Fruchart (ESPCI Gulliver), Vincenzo Vitelli (UChicago), and Streichan Lab (UCSB)
Adherent cell mechanics
Cell behavior is driven by biochemical processes involving many different proteins. Using machine learning, we investigate links between specific proteins and mechanics and find that one protein, zyxin, is all you need to predict cellular forces. From this, we build interpretable continuum models which capture cell behavior by incorporating biochemical complexity. Collaboration with Matthew Schmitt (UChicago), Vincenzo Vitelli (UChicago), and Gardel (UChicago) and Oakes (Loyola Chicago) labs.Wakes and shocks
How does a material respond to a local disturbance, impurity, or excitation? The answer depends on the nature of the disturbance and the material properties. Alongside collaborators from ENS Lyon and UVA, we have investigated properties of wakes in shocks in a range of contexts using tools from physics and machine learing.
Nonlinear waves in non-reciprocal solids
Out-of-equilibrium systems break many assumptions of classical continuum mechanics, such as detailed balance, requiring new approaches to model-building. Using a microfluidics experiment as a case study, we learn nonlinear dynamics directly from data using neural operators and sparse regression. We trace the origin of a novel term in the extracted equations to non-reciprocal hydrodynamic interactions between droplets. Collaboration with Alexis Poncet (ENS Lyon), Denis Bartolo (ENS Lyon), and Vincenzo Vitelli (Chicago).