Supported Applications

CryoLithe

Description

CryoLithe is a supervised machine learning method to directly reconstruct the tomogram from aligned cryo-ET tilt series. The methods is trained on real measurements using FBP+cryo-CARE+IsoNet reconstructions as the reference. The network exploits the imaging geometry to extract small patches from the tilt series to recover the volume. Thus it is practically robust to various data distirbutions. The method provides FBP+cryo-CARE+IsoNet type of reconstructions in a fraction of the time.
Usage
To list all executables provided by CryoLithe, run: $ sbgrid-list cryolithe
Installation
Use the following command to install this title with the CLI client: $ sbgrid-cli install cryolithe Available operating systems: Linux 64
Primary Citation*

V. Kishore, V. Debarnot, A. Khorashadizadeh, R. D. Righetto, B. D. Engel, and I. Dokmanić. 2025. Efficient reconstruction and denoising of cryo-ET data with end-to-end localized deep learning. arXiv. Cornell University.
- *Full citation information available through