New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Random seed should be random in production #15

Open

keiran-rowell-unsw opened this issue Oct 11, 2024 · 2 comments

Assignees

Labels

bug

Member

keiran-rowell-unsw commented Oct 11, 2024

https://github.com/Australian-Structural-Biology-Computing/proteinfold/blob/8ce05982ff57ba3722c4e87093307b68f9923d43/modules/local/run_alphafold2.nf#L67C23-L67C28

Should be truly random as each 5 models on 5 trained networks need to explore different starting areas of the NN parameter space.

We can keep 53343 as a magic number for debugging purposes and new hardware (tell M. Grogan)?

keiran-rowell-unsw added the bug label

keiran-rowell-unsw assigned keiran-rowell-unsw and nbtm-sh

Collaborator

jscgh commented Oct 11, 2024

https://github.com/Australian-Structural-Biology-Computing/proteinfold/blob/8ce05982ff57ba3722c4e87093307b68f9923d43/modules/local/run_alphafold2_pred.nf#L49C1-L49C30

Occurs in _pred as well.

Collaborator

nbtm-sh commented Oct 14, 2024 •

edited

Loading

Fixed in df3b0cdd2b40984e9c0a79a57fecd8e91b90312d and 7e753ad05f39abea71923065c366ff81cf7695a6.

Will run tests and open pull request

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment