The Cell and Tissue Network Lab is an interdisciplinary research group decoding pancreatic sensory function through machine learning and biophysical modeling of cell collectives
We use machine learning (ML) and biophysics modeling to address functional and medically-relevant questions in pancreas sensory function. We analyze functional and morphological datasets of pancreas cell collectives and their relationship to the perfusion of the organ. Pancreas is fascinating since its cell collectives must act jointly, in coordination, to sense the metabolic state of the body and respond by appropriate secretion of enzymes and hormones; breakdowns can result in diabetes or pancreatitis. Methodologically, we apply out-of-the-box ML technology for image processing and disease prediction, and also develop novel ML approaches in the unsupervised and reinforcement-learning domain to extract interpretative and normative models of the cell collective function, thereby iteratively driving new experiments. Specifically, we use ML to identify cell subpopulations, to model the distribution of their joint activity in defined physiological and diet states, under pharmacological perturbations, and in disease (via unsupervised learning), and to predict optimal cell collective function under time-varying naturalistic metabolic conditions (via reinforcement learning). This interdisciplinary theory-experiment collaboration has the potential to significantly advance our understanding of the biology and pathology of the pancreas in particular, as well as of chemical signaling in cell collectives in general.