A graph-based machine learning approach combined with optical measurements to understand beating dynamics of cardiac organoids

The development of computational models for the pre- diction of cardiac cellular dynamics remains a challenge for the lack of first-principled mathematical models. We develop a novel ma- chine learning approach hybridizing physics simulation and graph networks to deliver robust predictions of cardiomyocyte dynamics. Embedded with inductive physical priors, the proposed constraint- based interaction neural projection (CINP) algorithm can uncover hidden physical constraints from sparse image data on a small set of beating cardiac cells and provide robust predictions for heterogenous large-scale cell sets. We also implement an in-vitro culture and imaging platform for cellular motion and calcium transient analysis to validate the model. We showcase our model’s efficacy by predict- ing complex organoid cellular behaviors in both in-silico and in-vitro settings.