Explore a cutting-edge approach to computational oncology in this 49-minute talk by Cristian Axenie at the Alan Turing Institute. Discover how biophysics-informed machine learning is revolutionizing cancer research by fusing traditional mathematical models with abundant genomic data. Learn about a novel system that extracts disease dynamics from clinical data, revealing human-understandable properties and hidden features. Examine how this approach can describe nonlinear conservation laws in cancer kinetics, symmetries in tumor staging transitions, preoperative spatial tumor distribution, and pharmacokinetics of neoadjuvant therapies. Gain insights into how this innovative method enhances the mechanistic understanding of cancer dynamics by leveraging heterogeneous clinical data and advanced machine learning techniques.