Predictive Modeling of Disease Risk Using Genomic Data – A Hands-On ML Workshop

• Understand the basics of genomics and disease prediction.

• Learn to handle and explore genomic datasets (SNPs, gene expression).
• Apply feature engineering techniques for biological data.
• Build machine learning models using scikit-learn and XGBoost.
• Evaluate models using ROC, AUC, and confusion matrix.
• Interpret models with SHAP for feature importance analysis.
• Gain skills applicable in precision medicine and biomedical research.

• Introduction to genomics and predictive modeling
• Data Loading and Exploration (e.g., SNP or gene expression data)
• Feature Engineering – Encode SNPs or normalize gene expression
• Train-test split & Baseline Models (Logistic Regression, Decision Trees)

• Advanced Models – XGBoost & Random Forest
• Model Evaluation – ROC, AUC, Confusion Matrix
• SHAP-based Interpretability – Understanding top features

Participants will:

✅ Gain hands-on experience in loading, processing, and modeling genomic data using Python.
✅ Understand how to apply machine learning models (Logistic Regression, Random Forest, XGBoost) for predicting disease risk.
✅ Learn how to evaluate models using metrics like ROC, AUC, and confusion matrices.
✅ Be able to interpret models using SHAP to identify key genomic features influencing disease outcomes.
✅ Receive reusable notebooks and datasets for future projects and research.
✅ Build a foundation for entering interdisciplinary careers that integrate biology, data science, and AI.
✅ Earn a certificate of participation (if included), useful for resumes and academic portfolios.

• Students and Researchers in biotechnology, bioinformatics, computational biology, and data science who wish to gain practical experience in applying machine learning to real genomic datasets.
• Life Science Professionals seeking to upskill in data-driven techniques for disease prediction and personalized medicine.
• AI/ML Enthusiasts interested in exploring applications of machine learning in the biomedical and healthcare domain.
• Educators and Academicians looking to integrate applied genomics and ML into their teaching or curriculum development.
• Healthcare Innovators and Entrepreneurs aiming to understand the intersection of genomics and predictive analytics for research or product development.