From Data to Dynamics - Mechanistic Learning in Cancer Modeling

Explore mechanistic learning approaches in cancer modeling through this 59-minute plenary conference talk that bridges data science and dynamic systems in oncology research. Discover how mathematical frameworks can transform cancer data into predictive models that capture underlying biological mechanisms. Learn about innovative methodologies for integrating experimental observations with computational models to better understand tumor dynamics, treatment responses, and disease progression. Examine case studies demonstrating how mechanistic learning can reveal insights into cancer biology that traditional statistical approaches might miss. Gain insights into the mathematical foundations that enable researchers to move beyond correlation-based analyses toward causal understanding of cancer processes. Understand the challenges and opportunities in developing robust mechanistic models that can inform clinical decision-making and therapeutic strategies.