Add sparsego

[tereshchuk1]

PR Checklist for all PRs

• This comment contains a description of changes (with reason)

New features

Added SparseGO model for drug response prediction based

• drevalpy/models/SparseGO/ — model implementation (sparse VNN + drug ANN)
• drevalpy/datasets/featurizer/create_sparsego_features.py — featurizer to generate GO ontology input files
• registered in MODEL_FACTORY, hyperparameters from the original paper, optional dependencies mygene and obonet added

[codecov-commenter]

⚠️ Please install the to ensure uploads and comments are reliably processed by Codecov.

Codecov Report

❌ Patch coverage is 28.07692% with 374 lines in your changes missing coverage. Please review.
✅ Project coverage is 77.97%. Comparing base (7d24cd6) to head (f02b019).
⚠️ Report is 20 commits behind head on development.

Files with missing lines	Patch %	Lines
drevalpy/models/SparseGO/sparsego.py	13.26%	268 Missing ⚠️
drevalpy/models/SparseGO/utils.py	10.57%	93 Missing ⚠️
drevalpy/models/baselines/multi_view_lightgbm.py	87.00%	13 Missing ⚠️
❗ Your organization needs to install the Codecov GitHub app to enable full functionality.

Additional details and impacted files

@@               Coverage Diff               @@
##           development     #439      +/-   ##
===============================================
- Coverage        80.34%   77.97%   -2.37%     
===============================================
  Files              101      106       +5     
  Lines             8171     8860     +689     
===============================================
+ Hits              6565     6909     +344     
- Misses            1606     1951     +345     

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[PascalIversen]

This should not be in this PR :)

[PascalIversen]

With gene_list=None, load_and_select_gene_features returns all genes from gene_expression.csv in order of the CSV, not just the ontology genes, and not in gene2ind.txt order. The model is then trained on the wrong inputs I think. Could you check this?