Deep Reinforcement Learning of Cell Movement in the Early Stage of C. elegans Embryogenesis
Cell movement in the early phase of C. elegans development is regulated by a highly complex process in which a set of rules and connections are formulated at distinct scales. Previous efforts have demonstrated that agent-based, multi-scale modeling systems can integrate physical and biological rules and provide new avenues to study developmental systems. However, the application of these systems to model cell movement is still challenging and requires a comprehensive understanding of regulation networks at the right scales. Recent developments in deep learning and reinforcement learning provide an unprecedented opportunity to explore cell movement using 3D time-lapse microscopy images. We presented a deep reinforcement learning approach within an agent-based modeling system to characterize cell movement in the embryonic development of C. elegans. We tested our model through two scenarios within real developmental processes: the anterior movement of the Cpaaa cell via intercalation and the restoration of the superficial left-right symmetry. Our modeling system overcame the local optimization problems encountered by traditional rule-based, agent-based modeling by using greedy algorithms. It also overcame the computational challenges in the action selection which has been plagued by the traditional tabular-based reinforcement learning approach. Our system can automatically explore the cell movement path by using live microscopy images and it can provide a unique capability to model cell movement scenarios where regulatory mechanisms are not well studied. In addition, our system can be used to explore potential paths of a cell under different regulatory mechanisms or to facilitate new hypotheses for explaining certain cell movement behaviors.
READ FULL TEXT