Related Experiment Video
Updated: Jul 2, 2025
00:10
Single-Molecule Tracking Microscopy - A Tool for Determining the Diffusive States of Cytosolic Molecules
Published on: September 5, 2019
8.2K
Deep Learning-Assisted Automated Multidimensional Single Particle Tracking in Living Cells.
Dongliang Song1, Xin Zhang1, Baoyun Li1
1State Key Laboratory of Physical Chemistry of Solid Surfaces, Innovation Laboratory for Sciences and Technologies of Energy Materials of Fujian Province (IKKEM), College of Chemistry and Chemical Engineering, Xiamen University, Xiamen, China, 361005.
Nano Letters
|February 28, 2024
Summary
We developed a new deep learning system for high-speed 3D tracking of nanoparticle orientation in cells. This advanced single particle tracking (SPT) method provides precise molecular insights into cellular dynamics.
Area of Science:
- Biophysics
- Cell Biology
- Nanotechnology
Background:
- Single particle tracking (SPT) reveals molecular dynamics in cells.
- Tracking nanoparticle orientation provides detailed cellular activity information.
- Existing methods struggle with low signal-to-noise ratios (S/N) for rotational tracking.
Purpose of the Study:
- To develop an automated high-speed multidimensional SPT system.
- To track the 3D orientation of anisotropic gold nanoparticle probes in living cells.
- To overcome limitations of rotational tracking under low S/N conditions.
Main Methods:
- Integration of a deep learning algorithm with a multidimensional SPT system.
- Tracking anisotropic gold nanoparticle probes with high precision (<10 nm) and temporal resolution (0.9 ms).
- Utilizing deep learning for robust orientation tracking even at low S/N.
Main Results:
- Achieved high localization precision (<10 nm) and temporal resolution (0.9 ms).
- Resolved azimuth and polar angles with errors <2° under S/N of ~4.
- Demonstrated superior robustness and noise resistance compared to conventional methods at low S/N.
Conclusions:
- The developed system enables precise 3D orientation tracking of nanoparticles in living cells.
- This technology offers molecular-level insights into cellular activities, such as cargo transport.
- The deep learning approach enhances the reliability of SPT under challenging S/N conditions.
