Learning Collective Cell Migratory Dynamics from a Static Snapshot with Graph Neural Networks

Abstract

Multicellular self-assembly into functional structures is a dynamic process that is critical in the development of biological structures and diseases, including embryo development, organ formation, tumor invasion, and other processes. Being able to infer collective cell migratory dynamics from their static configuration is valuable for both understanding and predicting these complex behaviors. However, the identification of structural features that can indicate multicellular motion has been difficult, and existing metrics largely rely on physical instincts. Here we show that, through the use of a graph neural network, the motion of multicellular collectives can be inferred from a static snapshot of cell positions, in both experimental and synthetic datasets. Published by the American Physical Society 2024