Skip to content

Nci fix#232

Merged
sgosline merged 9 commits intomainfrom
nci-fix
Oct 21, 2024
Merged

Nci fix#232
sgosline merged 9 commits intomainfrom
nci-fix

Conversation

@sgosline
Copy link
Copy Markdown
Member

@sgosline sgosline commented Oct 18, 2024

This PR does a few things:

  1. addresses the disagreement in AUC values introduced by my move from the pharmacoGX data to the NCI60 (and adds documentation so i remember the pharmacoGx details)
  2. closes NCI60 has more than 60 cell lines in our current data #231 to filter for only 83 cell lines
  3. updated the .gitignore file to include local build data
  4. updates NCI60 dataset to the October 2024 release
  5. added some extra logic to drug code to filter by existing smile string.

@sgosline
Copy link
Copy Markdown
Member Author

Coderdata is still out of date due to #125 , as it only has about 35k drugs in the broad_sanger file.

@@ -39,7 +52,7 @@ def main():
if not os.path.exists('DOSERESP.csv'):
Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I assume this file was already unzipped and in the filepath, but if not, the name of the zipped file should be DOSERESP.zip.

@sgosline
Copy link
Copy Markdown
Member Author

I just pushed the updates for the MPNST data so it's also on the same scale of dose/resp. i think beatAML is already in uM.

@sgosline sgosline merged commit 4025953 into main Oct 21, 2024
@sgosline sgosline deleted the nci-fix branch April 24, 2025 18:56
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

Successfully merging this pull request may close these issues.

NCI60 has more than 60 cell lines in our current data

2 participants