DNA-PAINT Imaging Accelerated by Machine Learning

Min Zhu; Luhao Zhang; Luhong Jin; Jincheng Chen; Yongdeng Zhang; Yingke Xu

doi:10.3389/fchem.2022.864701

DNA-PAINT Imaging Accelerated by Machine Learning

Front Chem. 2022 May 10:10:864701. doi: 10.3389/fchem.2022.864701. eCollection 2022.

Authors

Min Zhu¹, Luhao Zhang¹, Luhong Jin^{1

2}, Jincheng Chen¹, Yongdeng Zhang³, Yingke Xu^{1

2

4

5}

Affiliations

¹ Key Laboratory of Biomedical Engineering of Ministry of Education, State Key Laboratory of Modern Optical Instrumentation, Zhejiang Provincial Key Laboratory of Cardio-Cerebral Vascular Detection Technology and Medicinal Effectiveness Appraisal, Department of Biomedical Engineering, Zhejiang University, Hangzhou, China.
² Alibaba-Zhejiang University Joint Research Center of Future Digital Healthcare, Hangzhou, China.
³ School of Life Sciences, Westlake University, Hangzhou, China.
⁴ Binjiang Institute of Zhejiang University, Hangzhou, China.
⁵ Department of Endocrinology, The Affiliated Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, China.

Abstract

DNA point accumulation in nanoscale topography (DNA-PAINT) is an easy-to-implement approach for localization-based super-resolution imaging. Conventional DNA-PAINT imaging typically requires tens of thousands of frames of raw data to reconstruct one super-resolution image, which prevents its potential application for live imaging. Here, we introduce a new DNA-PAINT labeling method that allows for imaging of microtubules with both DNA-PAINT and widefield illumination. We develop a U-Net-based neural network, namely, U-PAINT to accelerate DNA-PAINT imaging from a widefield fluorescent image and a sparse single-molecule localization image. Compared with the conventional method, U-PAINT only requires one-tenth of the original raw data, which permits fast imaging and reconstruction of super-resolution microtubules and can be adopted to analyze other SMLM datasets. We anticipate that this machine learning method enables faster and even live-cell DNA-PAINT imaging in the future.

Keywords: DNA-PAINT; U-Net; machine learning; single-molecule localization microscopy; super-resolution imaging.