Skip to content

Feature rdkit_scaled and mordred_filtered_scaled feature sets #397

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

Closed
wants to merge 29 commits into from

Conversation

stewarthe6
Copy link
Collaborator

This is built off of PR396.

This contains new versions of rdkit and mordred features where certain features are scaled by the number of heavy atoms if they have a pearson correlation with the heavy atom count > 0.5. Power relationships between a feature and heavy atom count was considered, but no clear relationships were found.

Features based on VSA (van der Waals surface area) features are scaled, though they may not correlate due to binning. In rdkit, there are VSA features where the VSA is binned based on a property or vice versa. The contents of the bins may not correlate with the heavy atom count, but the sum of all bins highly correlates with heavy atom count.

Benefits of these new features are still being evaluated.

stewarthe6 and others added 22 commits January 21, 2025 10:10
Ipc should not be changed to AvgIpc like this because it would break all rdkit_raw models.
…th RobustScaler and PowerTransformer. Updated documentation in related sections. Added functions to ModelFileReader to read out transformer specific parameters. Changed models that test RobustScaler and PowerTransformer to use RF to speed up the training
Copy link

codecov bot commented Apr 2, 2025

Codecov Report

Attention: Patch coverage is 51.75439% with 55 lines in your changes missing coverage. Please review.

Files with missing lines Patch % Lines
atomsci/ddm/pipeline/featurization.py 18.96% 47 Missing ⚠️
atomsci/ddm/utils/model_file_reader.py 50.00% 8 Missing ⚠️
@@            Coverage Diff             @@
##            1.7.0     #397      +/-   ##
==========================================
- Coverage   34.54%   29.95%   -4.60%     
==========================================
  Files          50       50              
  Lines       13497    13564      +67     
==========================================
- Hits         4663     4063     -600     
- Misses       8834     9501     +667     
Files with missing lines Coverage Δ
atomsci/ddm/pipeline/compare_models.py 5.52% <ø> (-27.55%) ⬇️
atomsci/ddm/pipeline/model_tracker.py 17.45% <ø> (ø)
atomsci/ddm/pipeline/model_wrapper.py 49.58% <100.00%> (-14.74%) ⬇️
atomsci/ddm/pipeline/parameter_parser.py 86.68% <100.00%> (-2.94%) ⬇️
atomsci/ddm/pipeline/transformations.py 64.39% <100.00%> (+7.54%) ⬆️
atomsci/ddm/utils/hyperparam_search_wrapper.py 0.00% <ø> (ø)
atomsci/ddm/utils/model_file_reader.py 61.64% <50.00%> (-3.75%) ⬇️
atomsci/ddm/pipeline/featurization.py 48.66% <18.96%> (-13.46%) ⬇️

... and 7 files with indirect coverage changes

🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
  • 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

@mauvais2 mauvais2 deleted the branch 1.7.0 May 20, 2025 18:24
@mauvais2 mauvais2 closed this May 20, 2025
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.

2 participants