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.

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

Full routes dataset? #4

Open
najwalb opened this issue Dec 18, 2024 · 2 comments
Open

Full routes dataset? #4

najwalb opened this issue Dec 18, 2024 · 2 comments

Comments

@najwalb
Copy link

najwalb commented Dec 18, 2024

Hello,

Great work! Do you happen to have the full routes for the test targets you're using (i.e. USPTO-190, and the 2 Pitachio)? The paper contains statistics about the test routes, but the data you shared here only gives the target and the goal starting material.

@najwalb
Copy link
Author

najwalb commented Dec 18, 2024

Ok, I found links to the full routes of USPTO-190 in this issue in RetroStar's github repo. Here are the links for ease of reference: train, val, test.

I also made a pull request to retrostar to add the links to their readme. Do I understand correctly that you're using the same routes as RetroStar for USPTO-190? And any chance you can share the pistachio routes?

@ykevu
Copy link
Collaborator

ykevu commented Jan 20, 2025

Hi Najwa, thank you for your interest in our work! We did use the same routes as Retro* for USPTO-190. However, our train/val/test split was different (and can be found at our figshare).

Unfortunately, we cannot share the full routes for the Pistachio sets as they are derived from proprietary reaction data (but we were allowed to release the targets and SMs by NextMove).

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants