pass drug_descriptors (contains mordred descriptors) to consecutive build runs for datasets #323

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

Open

ymahlich opened this issue Feb 5, 2025 · 1 comment

Assignees

Labels

bug 'build' update data update

Collaborator

ymahlich commented Feb 5, 2025

This feature / fix serves two purposes:

fixes potential floating point operation inconsistencies that lead to the behavior observed in discrepancies in mordred values for the same improve_drug_id across different datasets #321 (discrepancies in modred values for the same chemical compound (calculated form identical SMILES strings) in different drug response datasets
speeds up the build process

ymahlich assigned jjacobson95

ymahlich added bug enhancement 'build' update labels

ymahlich added this to CoderData

ymahlich mentioned this issue

discrepancies in mordred values for the same improve_drug_id across different datasets #321

Open

sgosline added data update and removed enhancement labels

Member

sgosline commented Apr 24, 2025 •

edited

Loading

This is a much simpler fix than trying to figure out the cause. Update build_drugs.sh to pass drug descriptor files in addition to drug file.

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