Neural network-assisted single-molecule localization microscopy with a weak-affinity protein tag

Soohyen Jang; Kaarjel K Narayanasamy; Johanna V Rahm; Alon Saguy; Julian Kompa; Marina S Dietz; Kai Johnsson; Yoav Shechtman; Mike Heilemann

doi:10.1016/j.bpr.2023.100123

Neural network-assisted single-molecule localization microscopy with a weak-affinity protein tag

Biophys Rep (N Y). 2023 Aug 18;3(3):100123. doi: 10.1016/j.bpr.2023.100123. eCollection 2023 Sep 13.

Authors

Soohyen Jang^{1

2}, Kaarjel K Narayanasamy^{1

3}, Johanna V Rahm¹, Alon Saguy⁴, Julian Kompa⁵, Marina S Dietz¹, Kai Johnsson⁵, Yoav Shechtman⁴, Mike Heilemann^{1

2}

Affiliations

¹ Institute of Physical and Theoretical Chemistry, Johann Wolfgang Goethe-University, Frankfurt am Main, Germany.
² Institute of Physical and Theoretical Chemistry, IMPRS on Cellular Biophysics, Johann Wolfgang Goethe-University, Frankfurt am Main, Germany.
³ Department of Functional Neuroanatomy, Institute for Anatomy and Cell Biology, Heidelberg University, Heidelberg, Germany.
⁴ Department of Biomedical Engineering, Technion - Israel Institute of Technology, Haifa, Israel.
⁵ Department of Chemical Biology, Max Planck Institute for Medical Research, Heidelberg, Germany.

Abstract

Single-molecule localization microscopy achieves nanometer spatial resolution by localizing single fluorophores separated in space and time. A major challenge of single-molecule localization microscopy is the long acquisition time, leading to low throughput, as well as to a poor temporal resolution that limits its use to visualize the dynamics of cellular structures in live cells. Another challenge is photobleaching, which reduces information density over time and limits throughput and the available observation time in live-cell applications. To address both challenges, we combine two concepts: first, we integrate the neural network DeepSTORM to predict super-resolution images from high-density imaging data, which increases acquisition speed. Second, we employ a direct protein label, HaloTag7, in combination with exchangeable ligands (xHTLs), for fluorescence labeling. This labeling method bypasses photobleaching by providing a constant signal over time and is compatible with live-cell imaging. The combination of both a neural network and a weak-affinity protein label reduced the acquisition time up to ∼25-fold. Furthermore, we demonstrate live-cell imaging with increased temporal resolution, and capture the dynamics of the endoplasmic reticulum over extended time without signal loss.