Search

Summary

CryoGAN uses ideas from deep generative adversarial learning to perform image reconstruction in single-particle cryo-electron microscopy (cryo-EM). In this chapter, we begin by introducing single-particle cryo-EM. We then formulate the associated image-reconstruction problem and discuss the main solutions found in the literature. Next, we describe the CryoGAN algorithm and show some representative results. Finally, we discuss what our experiences with Cryo-GAN suggest about the advantages and disadvantages of such deep generative adversarial methods in single-particle cryo-EM and beyond.

Phase plate (PP) imaging has proven to be valuable in transmission cryo electron microscopy of unstained, native-state biological specimens. Many PP types have been described, however until the recent implementation of the “hole-free” phase plate (HFPP), imaging has been challenging. We found the HFPP to be simple to construct and to set up in the transmission electron microscopy, but care in implementing automated data collection is needed. Performance may be variable, both initially and over time, thus it is important to monitor and evaluate image quality by observing the power spectrum. We found that while some HFPPs gave transfer to high resolution without CTF oscillation, most reached high resolution when operated with modest defocus.

Search Results

Refine search

Refine search

Actions for selected content:

2 results

15 - CryoGAN: A Deep Generative Adversarial Approach to Single-Particle Cryo-EM

Summary

Practical Experience with Hole-Free Phase Plates for Cryo Electron Microscopy

Search Results

Refine search

Refine search

Actions for selected content:

Save Search

2 results

15 - CryoGAN: A Deep Generative Adversarial Approach to Single-Particle Cryo-EM

Summary

Practical Experience with Hole-Free Phase Plates for Cryo Electron Microscopy