Additional Resources
For more comprehensive information about this project, please refer to the following detailed documents:
📄 Full Technical Report
Explainable_AI_Driven_Adverse_Drug_Reactions_Prediction_Toward_Pediatric_Drug_Discovery___Development.pdf (available in the project repository)
This comprehensive report provides:
Complete methodology and theoretical background
Detailed experimental results and analysis
Comparative performance evaluation
Discussion of clinical implications and future work
Full literature review and citations
📝 Detailed Implementation Notes
My Notes.pdf (available in the project repository)
Contains in-depth technical insights including:
Step-by-step implementation details
Data preprocessing decisions and rationale
Model architecture design choices
Training optimization strategies
Troubleshooting notes and lessons learned
🔗 Project Repository
GitHub Repository: https://github.com/htootayzaaung/Explainable-AI-Driven-Adverse-Drug-Reactions-Prediction-Toward-Pediatric-Drug-Discovery-Development
Complete source code
Jupyter notebooks
Data processing scripts
Model checkpoints and logs
📊 Data Sources
The project integrates multiple public datasets:
GDSC2: Drug sensitivity measurements
CCLE 22Q2: Gene expression profiles
COSMIC Cancer Gene Census: Cancer-associated genes
This GitBook provides a high-level overview of the project workflow. For complete technical details, experimental validation, and comprehensive analysis, please consult the full report and implementation notes.
Last updated