search

tbepler / topaz

Pipeline for particle picking in cryo-electron microscopy images using convolutional neural networks trained from positive and unlabeled examples. Also featuring micrograph and tomogram denoising with DNNs.
GNU General Public License v3.0
172 stars 64 forks source link

3D demonising and ctf correction #71

Closed samuelhaysom closed 3 years ago

samuelhaysom commented 3 years ago

I'm not sure if this is the best forum for this question but I was wondering if the included general models for 3D demonising of tomograms was trained on tomograms that are ctf corrected? If so, will it matter if I use it to Denoise non-CTF corrected micrographs or, if that is my intended use, should I train a new model for this purpose?

tbepler commented 3 years ago

The tomograms used for training were not CTF corrected, but I don't expect there will be a noticeable difference in performance if denoising CTF corrected ones.

tbepler commented 3 years ago

I'm going to close this issue since it seems like there aren't any other questions.