Deciphering anomalous heterogeneous intracellular transport with neural networks
| Autor: | Thomas A. Waigh, Mark Johnston, Viki Allan, Runze Chen, Nickolay Korabel, Daniel Han, Sergei Fedotov, Anna Gavrilova |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
0301 basic medicine
Computer science 01 natural sciences Biology (General) Artificial neural network General Neuroscience General Medicine Data point endosomes Trajectory Medicine Feedforward neural network Biological system Research Article Computational and Systems Biology Human QH301-705.5 Biochemical Phenomena Science Movement Neuroscience(all) Models Biological General Biochemistry Genetics and Molecular Biology MRC5 cell 03 medical and health sciences Motion lysosomes Immunology and Microbiology(all) 0103 physical sciences Humans Time series 010306 general physics Transport Vesicles Hurst exponent Fractional Brownian motion General Immunology and Microbiology business.industry Biochemistry Genetics and Molecular Biology(all) Deep learning Biological Transport Cell Biology 030104 developmental biology Artificial intelligence Neural Networks Computer business |
| Zdroj: | Han, D, Korabel, M, Chen, R, Johnston, M, Gavrilova, A, Allan, V, Fedotov, S & Waigh, T 2020, ' Deciphering anomalous heterogeneous intracellular transport with neural networks ', eLife, vol. 9, e52224 . https://doi.org/10.7554/eLife.52224 eLife eLife, Vol 9 (2020) |
| Popis: | Intracellular transport is predominantly heterogeneous in both time and space, exhibiting varying non-Brownian behavior. Characterization of this movement through averaging methods over an ensemble of trajectories or over the course of a single trajectory often fails to capture this heterogeneity. Here, we developed a deep learning feedforward neural network trained on fractional Brownian motion, providing a novel, accurate and efficient method for resolving heterogeneous behavior of intracellular transport in space and time. The neural network requires significantly fewer data points compared to established methods. This enables robust estimation of Hurst exponents for very short time series data, making possible direct, dynamic segmentation and analysis of experimental tracks of rapidly moving cellular structures such as endosomes and lysosomes. By using this analysis, fractional Brownian motion with a stochastic Hurst exponent was used to interpret, for the first time, anomalous intracellular dynamics, revealing unexpected differences in behavior between closely related endocytic organelles. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|