Geometric deep learning reveals the spatiotemporal fingerprint of microscopic motion

Abstract

The characterization of dynamical processes in living systems provides important clues for their mechanistic interpretation and link to biological functions. Thanks to recent advances in microscopy techniques, it is now possible to routinely record the motion of cells, organelles, and individual molecules at multiple spatiotemporal scales in physiological conditions. However, the automated analysis of dynamics occurring in crowded and complex environments still lags behind the acquisition of microscopic image sequences. Here, we present a framework based on geometric deep learning that achieves the accurate estimation of dynamical properties in various biologically-relevant scenarios. This deep-learning approach relies on a graph neural network enhanced by attention-based components. By processing object features with geometric priors, the network is capable of performing multiple tasks, from linking coordinates into trajectories to inferring local and global dynamic properties. We demonstrate the flexibility and reliability of this approach by applying it to real and simulated data corresponding to a broad range of biological experiments.

17 pages, 5 figure, 2 supplementary figures

Cited by in corpus (13)

• Light, Matter, Action: Shining light on active matter
• Inferring pointwise diffusion properties of single trajectories with deep learning
• Quantitative evaluation of methods to analyze motion changes in single-particle experiments
• Semantic Segmentation of Anomalous Diffusion Using Deep Convolutional Networks
• Deep Learning for Optical Tweezers
• Discovering dynamic laws from observations: the case of self-propelled, interacting colloids
• Roadmap for Animate Matter
• Machine Learning Analysis of Anomalous Diffusion
• Learning Dynamics from Multicellular Graphs with Deep Neural Networks
• Enhanced Spatial Clustering of Single-Molecule Localizations with Graph Neural Networks
• Integrating Physics and Topology in Neural Networks for Learning Rigid Body Dynamics
• Recurrent neural network analysis of single trajectories switching between anomalous diffusion states
• Improved mean squared displacement analysis for anomalous single particle trajectories