parrot
November 1, 2023, 4:46am
1
Dear community,
I found two recently released paper talking about using self-supervised algorithms to solve the preferred orientation problem:
cryoPROS: Addressing preferred orientation in single-particle cryo-EM through AI-generated auxiliary particles https://doi.org/10.1101/2023.09.26.559492
spIsoNet: Resolving the Preferred Orientation Problem in CryoEM Reconstruction with Self-Supervised Deep Learninghttps://academic.oup.com/mam/article/29/Supplement_1/1918/7228117
Has anyone tried these ways? or any comments on these algorithms? I have a protein showing a little bit of preferred orientation, and I feel these self-supervised algorithms could be the right solution for us.
4 Likes
Bassem
April 16, 2024, 1:42am
2
Are these available out there now?
1 Like
Not to my knowledge for the first, but an update to spIsoNet has just hit bioRxiv…
And code is here:
Not tested yet.
3 Likes
Bassem
April 16, 2024, 8:43pm
4
I am giving that a go and it seems I am stuck at
.conda/envs/spisonet/lib/python3.10/site-packages/torch/cuda/__init__.py:628: UserWarning: Can't initialize NVML
I have it running on my system… Error looks like a cuda version or nvidia driver mismatch of some sort, but you might have more luck asking on the spIsoNet github page
Bassem
April 16, 2024, 9:28pm
6
Agree. thanks @olibclarke
1 Like
NVML errors usually mean the system needs a reboot for me.
1 Like
What kind of results have you seen using the software?
1 Like
parrot
April 17, 2024, 3:38pm
9
Really exciting to see this!
Does anyone know how to solve this?
Bassem
April 17, 2024, 3:53pm
10
That did the trick for NVML and then for torch errors i upgraded gcc https://github.com/IsoNet-cryoET/spIsoNet/issues/6
1 Like
Ah, I haven’t run gcc 4 in years… good to know to keep an eye out for, cheers!
