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.

arXiv comment25 pages, 11 figures

References in corpus (40)

• Anomalous transport in the crowded world of biological cells
• Lévy walks
• In vivo anomalous diffusion and weak ergodicity breaking of lipid granules
• First-passage times in complex scale-invariant media
• Single particle tracking in systems showing anomalous diffusion: the role of weak ergodicity breaking
• Elephants can always remember: Exact long-range memory effects in a non-Markovian random walk
• Economic Fluctuations and Diffusion
• Nonergodic Subdiffusion from Brownian Motion in an Inhomogeneous Medium
• 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
• Machine learning method for single trajectory characterization
• Classification of diffusion modes in single-particle tracking data: Feature-based versus deep-learning approach
• Spectral content of a single non-Brownian trajectory
• Measurement of Anomalous Diffusion Using Recurrent Neural Networks
• Noisy continuous time random walks
• Development of anomalous diffusion among crowding proteins
• Bayesian deep learning for error estimation in the analysis of anomalous diffusion
• Classification of particle trajectories in living cells: machine learning versus statistical testing hypothesis for fractional anomalous diffusion
• Nonergodic dynamics of force-free granular gases
• Nonergodic Diffusion of Single Atoms in a Periodic Potential
• Classification, inference and segmentation of anomalous diffusion with recurrent neural networks
• Brownian motion and beyond: first-passage, power spectrum, non-Gaussianity, and anomalous diffusion
• Optical Antenna-based Fluorescence Correlation Spectroscopy to Probe the Nanoscale Dynamics of Biological Membranes
• Characterization of anomalous diffusion classical statistics powered by deep learning (CONDOR)
• Learning physical properties of anomalous random walks using graph neural networks
• Anomalous Scaling of Stochastic Processes and the Moses Effect
• Boosting the performance of anomalous diffusion classifiers with the proper choice of features
• Inferring pointwise diffusion properties of single trajectories with deep learning
• Moses, Noah and Joseph Effects in Coupled Lévy Processes
• Bayesian inference of scaled versus fractional Brownian motion
• Characterization of anomalous diffusion through convolutional transformers
• Codifference can detect ergodicity breaking and non-Gaussianity
• Extreme Learning Machine for the Characterization of Anomalous Diffusion from Single Trajectories (AnDi-ELM)
• Unsupervised learning of anomalous diffusion data
• 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
• Variational inference of fractional Brownian motion with linear computational complexity
• Brownian non-Gaussian diffusion of self-avoiding walks
• Preface: Characterisation of Physical Processes from Anomalous Diffusion Data

Cited by in corpus (9)

• Quantitative evaluation of methods to analyze motion changes in single-particle experiments
• Modelling intermittent anomalous diffusion with switching fractional Brownian motion
• Semantic Segmentation of Anomalous Diffusion Using Deep Convolutional Networks
• Multifractional Brownian motion with telegraphic, stochastically varying exponent
• Machine Learning Analysis of Anomalous Diffusion
• Change-point detection in anomalous-diffusion trajectories utilising machine-learning-based uncertainty estimates
• Anomalous statistics in the Langevin equation with fluctuating diffusivity: from Brownian yet non-Gaussian diffusion to anomalous diffusion and ergodicity breaking
• Recurrent neural network analysis of single trajectories switching between anomalous diffusion states
• Improved mean squared displacement analysis for anomalous single particle trajectories