Machine-Learning Solutions for the Analysis of Single-Particle Diffusion Trajectories

Abstract

Single-particle traces of the diffusive motion of molecules, cells, or animals are by-now routinely measured, similar to stochastic records of stock prices or weather data. Deciphering the stochastic mechanism behind the recorded dynamics is vital in understanding the observed systems. Typically, the task is to decipher the exact type of diffusion and/or to determine system parameters. The tools used in this endeavor are currently revolutionized by modern machine-learning techniques. In this Perspective we provide an overview over recently introduced methods in machine-learning for diffusive time series, most notably, those successfully competing in the Anomalous-Diffusion-Challenge. As such methods are often criticized for their lack of interpretability, we focus on means to include uncertainty estimates and feature-based approaches, both improving interpretability and providing concrete insight into the learning process of the machine. We expand the discussion by examining predictions on different out-of-distribution data. We also comment on expected future developments.

25 pages, 11 figures

References in corpus (17)

• Anomalous transport in the crowded world of biological cells
• Lévy walks
• First-passage times in complex scale-invariant media
• Weak ergodicity breaking of receptor motion in living cells stemming from random diffusivity
• Scaled Brownian motion: a paradoxical process with a time dependent diffusivity for the description of anomalous diffusion
• Spectral content of a single non-Brownian trajectory
• Measurement of Anomalous Diffusion Using Recurrent Neural Networks
• Development of anomalous diffusion among crowding proteins
• Classification of particle trajectories in living cells: machine learning versus statistical testing hypothesis for fractional anomalous diffusion
• Optical Antenna-based Fluorescence Correlation Spectroscopy to Probe the Nanoscale Dynamics of Biological Membranes
• Bayesian inference of scaled versus fractional Brownian motion
• Codifference can detect ergodicity breaking and non-Gaussianity
• WaveNet-Based Deep Neural Networks for the Characterization of Anomalous Diffusion (WADNet)
• Gramian Angular Fields for leveraging pretrained computer vision models with anomalous diffusion trajectories
• Anomalous diffusion originated by two Markovian hopping-trap mechanisms
• Brownian non-Gaussian diffusion of self-avoiding walks
• Preface: Characterisation of Physical Processes from Anomalous Diffusion Data