add xgdp

[tereshchuk1]

Adds XGDP. The model combines a GNN branch for drug molecular graphs with a 1D-CNN branch for cell line gene expression, with optional cross-attention.

Adapted from the original repository with the following changes for drevalpy integration:

• Merged upstream/development and resolved conflicts
• Edge features aligned to 7-dim to match the existing create_drug_graphs.py featurizer
• CNN input size computed dynamically instead of hardcoded
• Fixed MSE loss shape mismatch
• Added ensure_drug_graphs fixture to tests/conftest.py
• Suppressed S614 for torch.load(..., weights_only=False) (required for torch_geometric.data.Data)

[codecov-commenter]

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

Codecov Report

❌ Patch coverage is 21.29472% with 924 lines in your changes missing coverage. Please review.
✅ Project coverage is 74.79%. Comparing base (7d24cd6) to head (6162099).
⚠️ Report is 39 commits behind head on development.

Files with missing lines	Patch %	Lines
drevalpy/models/XGDP/_models.py	11.45%	881 Missing ⚠️
drevalpy/models/XGDP/xgdp.py	84.93%	22 Missing ⚠️
tests/conftest.py	22.22%	21 Missing ⚠️
❗ Your organization needs to install the Codecov GitHub app to enable full functionality.

Additional details and impacted files

@@               Coverage Diff               @@
##           development     #446      +/-   ##
===============================================
- Coverage        80.34%   74.79%   -5.56%     
===============================================
  Files              101      118      +17     
  Lines             8171    10124    +1953     
===============================================
+ Hits              6565     7572    +1007     
- Misses            1606     2552     +946     

☔ 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.