CONTRIBUTING.md

Contributing to Toxicity-Detection

Thank you for your interest in contributing! This is a B.Tech final year research project, and we welcome suggestions, bug reports, and improvements.

🐛 Bug Reports

If you find a bug, please open an issue with:

1. Description of the problem
2. Steps to reproduce (include code snippet if applicable)
3. Expected vs actual behavior
4. Environment info:

   Python version:
   PyTorch version:
   CUDA version (if applicable):
   OS:
   

💡 Feature Requests / Suggestions

Open an issue with the enhancement label. Good areas for contribution:

• Additional KAN basis functions (B-spline, Chebyshev, wavelet)
• Multi-task learning across all 12 Tox21 assays
• Integration with GNN (Graph Neural Networks) for structure-aware prediction
• Better visualization of learned activation functions
• Support for additional molecular fingerprint libraries (RDKit, Morgan)

🔧 Pull Requests

1. Fork the repository
2. Create a branch: git checkout -b feature/your-feature-name
3. Commit your changes: git commit -m 'Add: concise description'
4. Push: git push origin feature/your-feature-name
5. Open a Pull Request with a clear description

Code Style

• Follow PEP 8 for Python
• Add docstrings to all functions and classes
• Keep notebook cells clean and well-commented
• Use seed=42 for reproducibility

Testing

Before submitting, verify:

• The main notebook (toxicity_kan_sparse_cv.ipynb) runs end-to-end
• Per-fold preprocessing is maintained (no data leakage)
• Results are comparable to the reported benchmarks (AUC ≈ 0.85+)

📜 Code of Conduct

Be respectful, constructive, and academic in all interactions. This is an open science project.

---

This project is primarily a B.Tech research project. Major architectural changes should be discussed in Issues first.