/DB

Primary LanguagePython

Single particle diffusion characterization by deep learning

This repository contains the code accompanying the paper: Single particle diffusion characterization by deep learning.

The network models and functions provided here are used to classify single particle anomalous diffusion trajectories to one of three models:

  • Fractional Brownian motion
  • Continuous time random walk
  • Pure Brownian motion

In addition, the FBM regression networks can be used to extract the Hurst exponent from Fractional Brownian Motion trajectories.

Instructions on how to run the code can be found in the Instructions file.

If you find this code useful, please cite our work: Granik, N., Weiss, L.E., Nehme, E., Levin, M., Chein, M., Perlson, E., Roichman, Y. and Shechtman, Y., 2019. Single particle diffusion characterization by deep learning. Biophysical Journal.

For any questions and comments, please contact us: naorgranik@gmail.com yoavsh@bm.technion.ac.il