SPTnet: a deep learning framework for end-to-end single-particle tracking and motion dynamics analysis

Abstract

Single-particle tracking (SPT) provides high-resolution spatial-temporal information on biomolecule dynamics. However, localization inaccuracies, limited track lengths, heterogeneous fluorescence backgrounds, and potential molecular motion blur pose significant challenges that hinder the accurate extraction of movement trajectories and their underlying motion behavior. The conventional SPT pipeline struggles to comprehensively address detection, localization, linkage, and motion parameter inference simultaneously, resulting in information loss during sequential processing. To overcome these challenges, we propose SPTnet, an end-to-end deep learning framework that leverages a Transformer-based architecture to optimize trajectory and motion parameter estimations in parallel through a global loss. SPTnet bypasses traditional SPT processes, directly inferring molecular trajectories and motion parameters from fluorescence microscopy videos with a precision approaching the statistical information limit. Our results demonstrate that SPTnet outperforms conventional methods under commonly encountered but challenging conditions such as short trajectories, low signal-to-noise ratio (SNR), heterogeneous backgrounds, motion blur, and especially when molecules exhibit non-Brownian behaviors.