Skip to content
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

Worse PDBbind performance with new splits #128

Closed
jyaacoub opened this issue Jul 30, 2024 · 2 comments · Fixed by #130
Closed

Worse PDBbind performance with new splits #128

jyaacoub opened this issue Jul 30, 2024 · 2 comments · Fixed by #130

Comments

@jyaacoub
Copy link
Owner

When retraining with new splits #113 we get way worse performance for alphaflow and the rest of the models in general.
jyaacoub added a commit that referenced this issue Jul 31, 2024
@jyaacoub
results(pdbbind): retrained DG and aflow on random split #128
0072b09
@jyaacoub jyaacoub mentioned this issue Jul 31, 2024
Merged
@jyaacoub
Copy link
Owner Author

Original results

image

retrained on splits

image

random splits to check

image

@jyaacoub
Copy link
Owner Author

jyaacoub commented Aug 2, 2024

Solution:

Use random test split! Then we can worry about only using protein-ligand pairs for OncoKB eval.

@jyaacoub jyaacoub closed this as completed Aug 2, 2024
jyaacoub added a commit that referenced this issue Aug 2, 2024
@jyaacoub
fix(splits): new random splits #113 #128 #131
b3e52a9 
To limit distribution drift issues mentioned in #131.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Retraining pdbbind on random split jyaacoub/MutDTA
1 participant
@jyaacoub