This project applies machine learning to classify genetic variants from the ClinVar database into categories such as Benign, Pathogenic, and Uncertain significance (VUS).
The goal is to build a reproducible ML pipeline for mutation classification using variant-level features.
- Download and preprocess ClinVar variant data
- Engineer features suitable for ML classification
- Train and evaluate classification models (Random Forest, XGBoost, etc.)
- Compare performance across multiple algorithms
- Deploy results and share insights