Learning Dynamics from Multicellular Graphs with Deep Neural Networks
arXiv:2401.12196 · doi:10.1103/PRXLife.2.043010
Abstract
Multicellular self-assembly into functional structures is a dynamic process that is critical in the development and diseases, including embryo development, organ formation, tumor invasion, and others. Being able to infer collective cell migratory dynamics from their static configuration is valuable for both understanding and predicting these complex processes. 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 using a graph neural network (GNN), the motion of multicellular collectives can be inferred from a static snapshot of cell positions, in both experimental and synthetic datasets.
arXiv commentAccepted for publication at PRX Life
References in corpus (17)
- Novel type of phase transition in a system of self-driven particles
- Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
- A density-independent glass transition in biological tissues
- Motility-driven glass and jamming transitions in biological tissues
- Collective and single cell behavior in epithelial contact inhibition
- Computational models for active matter
- Universal geometric constraints during epithelial jamming
- Anisotropy links cell shapes to tissue flow during convergent extension
- Inferring the dynamics of underdamped stochastic systems
- Learning the dynamics of cell-cell interactions in confined cell migration
- Geometric deep learning reveals the spatiotemporal fingerprint of microscopic motion
- Learning hydrodynamic equations for active matter from particle simulations and experiments
- Learning force fields from stochastic trajectories
- Shear-driven solidification and nonlinear elasticity in epithelial tissues
- Topological metric detects hidden order in disordered media
- Learning developmental mode dynamics from single-cell trajectories
- Topological packing statistics distinguish living and non-living matter