AI in Cancer Research: Multi-Omics, Biomarker Discovery & Precision Medicine

Aim

Workshop Objectives

Workshop Structure

Day 1: AI & Multi-Omics Foundations in Cancer Research

• Introduction to AI applications in modern cancer research
• Understanding cancer biology through molecular and clinical data
• Overview of multi-omics technologies: Genomics, Transcriptomics, Proteomics, Epigenomics, Clinical data integration
• Understanding cancer datasets and public resources: TCGA, GEO, cBioPortal
• Fundamentals of AI and machine learning workflows for cancer data analysis
• Challenges in integrating heterogeneous biological and clinical datasets

Hands-on Session:

Explore cancer omics datasets, perform data preprocessing, and visualize molecular profiles from publicly available cancer datasets.

Tools:
Python | Google Colab | Pandas | NumPy | Matplotlib | TCGA/GEO

Day 2: AI-Based Biomarker Discovery & Cancer Molecular Profiling

• Understanding cancer biomarkers and molecular signatures
• Machine learning approaches for biomarker identification
• Feature selection and dimensionality reduction techniques
• Integrating multi-omics features for cancer classification
• Combining molecular profiles with clinical characteristics: Patient demographics, Disease stage, Survival information, Treatment response data
• Pathway and network-based interpretation of AI-generated biomarkers

Hands-on Session:

Develop a machine learning workflow to identify potential cancer biomarkers using molecular and clinical datasets.

Tools:
Python | Scikit-learn | Random Forest | XGBoost | PCA | SHAP

Day 3: AI-Driven Precision Medicine & Personalized Cancer Insights

• Multi-omics and clinical data integration for precision oncology
• AI-based patient stratification and cancer subtype classification
• Predicting treatment response and patient outcomes using machine learning
• Explainable AI (XAI) for understanding cancer predictions
• Applications of AI in: Biomarker-guided therapy selection, Drug response prediction, Target identification, Personalized therapeutic strategies

Hands-on Session:

Build and interpret an AI-based cancer prediction model by integrating molecular features with clinical parameters and explain predictions using XAI approaches.

Tools:
Python | Machine Learning Models | SHAP | Bioinformatics Databases

Who Should Enrol?

Important Dates

Workshop Outcomes