Extract Latent Features of Single Particle Trajectories with Historical Experience Learning.

Researchers

Journal

Modalities

Models

Abstract

Single particle tracking (SPT) has enabled real-time, in situ quantitative studies of complex systems. However, inferring dynamic state changes from noisy and under-sampling trajectories encounter challenges. Here we introduce a data-driven method for extracting features of sub-trajectories with historical experience learning (Deep-SEES), where a SPT analysis pipeline based on a self-supervised architecture automatically searches for the latent space, allowing effective segmentation of the underlying states from noisy trajectories without prior knowledge on the particle dynamics. We validated our method on a variety of noisy simulated and experimental data. Our results showed that the method can faithfully capture both stable states and their dynamic switch. In highly random systems, our method outperformed commonly used unsupervised methods in inferring motion states, which is important for understanding nanoparticles interacting with living cell membranes, active enzymes, and liquid-liquid phase separation. Self-generating latent features of trajectories could potentially improve the understanding, estimation, and prediction of many complex systems.Copyright © 2023 Biophysical Society. Published by Elsevier Inc. All rights reserved.