CryoLithe: Rapid Cryo-ET Reconstruction via Transform-Localized Deep Learning

Vinith Kishore¹ , Valentin Debarnot² , Amir Khorashadizadeh¹ , Ricardo D. Righetto³ , Benjamin D. Engel³ , Ivan Dokmanić¹ .

¹ Department of Mathematics and Computer Science, University of Basel,
² INSA‐Lyon, Universite Claude Bernard Lyon 1, CNRS, Inserm, CREATIS UMR 5220, U1294,
³ Biozentrum, University of Basel.

CryoLithe a supervised learning method. The strength of CryoLithe is that reconstructing such a volume takes 4 minutes, against 12 hours for Icecream and 24 hours for DeepDeWedge. A strong or not so strong feature is that CryoLithe doesn’t require any parameters, only the aligned tilt-series. This webpage aims at providing reconstruction example and documentation on how to use the code.

What to expect with CryoLithe?

We illustrate CryoLithe on a tomogram from the test dataset (EMPIAR-11830).

In the following figures, we reported CryoLithe along with:

Icecream, a self-supervised framework for cryo-ET reconstruction that integrates equivariance principles from modern imaging theory into a deep-learning architecture. This is probably state-of-the-art reconstruction in term of quality for most tomograms.
Topaz-Denoise, a deep learning method for rapid denoising of cryoEM images and cryoET tomogram.
Filtered back-projection, or weighted back projection. This was performed using Imod and the tilt function.

About technical details. The pixel size is 7.84Å and the tomogram contains 1024 x 1024 x 512 pixels.

❄️ CryoLithe