Title | Deep learning-assisted analysis of single molecule dynamics from liquid-phase electron microscopy |
Authors | Cheng, Bin Ye, Enze Sun, He Wang, Huan |
Affiliation | Peking Univ, Coll Chem & Mol Engn, Ctr Spect, Ctr Soft Matter Sci & Engn,Beijing Natl Lab Mol Sc, Beijing, Peoples R China Peking Univ, Coll Future Technol, Natl Biomed Imaging Ctr, Beijing 100871, Peoples R China Tsinghua Univ, Dept Elect Engn, Beijing 100084, Peoples R China |
Issue Date | Jan-2023 |
Publisher | CHEMICAL COMMUNICATIONS |
Abstract | We apply U-Net and UNet++ to analyze single-molecule movies obtained from liquid-phase electron microscopy. Neural networks allow full automation, and high throughput analysis of these low signal-to-noise ratio images, while achieving higher segmentation accuracy, and avoiding subjective errors as compared to the conventional threshold methods. The analysis enables the quantification of transient dynamics in chemical systems and the capture of rare intermediate states by resolving local conformational changes within a single molecule. |
URI | http://hdl.handle.net/20.500.11897/669509 |
ISSN | 1359-7345 |
DOI | 10.1039/d2cc05354c |
Indexed | SCI(E) |
Appears in Collections: | å å¦ä¸ å å å·¥ç¨ å¦é ¢ |