Probing the rules of cell coordination in live tissues by interpretable machine learning based on graph neural networks

Takaki Yamamoto, Katie Cockburn, Valentina Greco, Kyogo Kawaguchi

Abstract: Author summary During development and homeostasis, cells coordinate with each other to grow, deform, and maintain the tissues. Even with the modern high-throughput cell profiling technologies and high-resolution microscopy, it is still challenging to infer how cell coordination affects the dynamics such as cell fate choice, due to the complexity of the problem and the limited methods to perform perturbation experiments. We here propose a versatile framework of analysis utilizing an interpretable machine learning method based on graph neural network (GNN) which infers the cell-to-cell interaction rules from live images of multicellular dynamics. From the spatiotemporal graphs generated from live images of skin stem cells, we identified previously unaddressed neighbor fate coupling as well as rules consistent with past findings. We further found distinct interaction rules in a different skin region of the body, indicating that our method is useful in probing the diverse mechanism behind the robustness and flexibility in multicellular systems. The GNN framework is applicable for interaction rule discovery for general multicellular dynamics as well as in a wide range of systems where modeling by stochastic interacting agents is effective.

External IDs:dblp:journals/ploscb/YamamotoCGK22