v1.4.1

[JudithBernett]

PR Checklist for all PRs

• This comment contains a description of changes (with reason)
• Referenced issue is linked
• If you've fixed a bug or added code that should be tested, add tests!
• Documentation in docs is updated. If you've created a new file, add it to the API documentation pages.

Welcome to @nictru, who authored his first PR to drevalpy!

Changes

• CLI commands for the nextflow pipeline #327
  • Added ignoring pickle-related flake8 errors: S403, S301 (Security concerns; not relevant here)
  • Updated to 1.4.1
  • Test data has been migrated to https://github.com/nf-core/test-datasets/tree/drugresponseeval/test_data: No longer pulling from Zenodo during automated tests
  • Raw CTRPv2 data is also in the nf-core test-datasets repository
  • conftest for all tests, not only for the model tests because one of the drp_model tests also needs the toy dataset

Bug fixes

• Fixed the pEC50 shift Curvecurator fix #337 The pEC50_curvecurator vaues are now shifted #310 :
  • All raw measures have to by supplied in µM.
  • EC50_curvecurator, IC50_curvecurator are therefore also reported in µM (-> computed by drevalpy)
  • pEC5_curvecurator is computed from M, though, otherwise the -log10 does not make sense. This is done internally by CurveCurator.
  • LN_IC50_curvecurator is computed from µM (-> computed by drevalpy)
• CLI commands for the nextflow pipeline #327 If the data has fewer than hyperparameters[pca_components] features, the PCA is run on all features.
• Fixed HTTP error 429 for test datasets #328 by migrating the test data to nf-core/test-datasets

New features

• Leaderboard: Added a leaderboard to gamify drug response prediction #344
• NaiveTissueDrugMeanPredictor predicts the mean drug effect + the mean tissue effect: Add naive tissue drug mean predictor #334. Is now the best-performing baseline for LCO
• CLI commands for the nextflow pipeline #327: CLI for all pipeline commands, separated by subworkflow -> cli_preprocess_custom, cli_run_cv, cli_model_testing; visualization in create_report.py

Maintenance

• Version updates

Version release checklist

• Update the version in pyproject.toml
• Update version/release in docs/conf.py
• Run ‚poetry update‘ to get the latest package versions. This will update the poetry.lock file
• Run ‚poetry export --without-hashes --without development -f requirements.txt -o requirements.txt‘ to update the requirements.txt file
• (If one of the sphinx packages has been updated, you also need to update docs/requirements.txt)

Then,

1. Open a PR from development to main with these changes.
2. Wait for a review and merge.
3. Create a new release on GitHub with the version number. Update the release notes with the changes made in this version.
4. If the Docker github action fails (e.g., no space left on device), you can do it manually:
   • Enable Docker buildx locally. If you don't have a builder that supports multi-arch, create one:

   docker buildx ls
   docker buildx create --use --name multiarch-builder
   docker buildx inspect --bootstrap
   

   • Login to ghcr docker login --username <GitHub-Username> --password <personal-access-token> ghcr.io
   • Build the multi-platform image, insert the correct version docker buildx build --platform linux/amd64,linux/arm64 -t ghcr.io/daisybio/drevalpy:v<INSERT-VERSION> -t ghcr.io/daisybio/drevalpy:latest --push .