Tumors consist of heterogeneous cells that evolve genetically, metabolically, and structurally to survive and evade therapies. MIT's Matthew G. Jones applies artificial intelligence and machine learning to decode common patterns in tumor progression, aiming to predict how cancers change over time. His lab focuses on understanding DNA amplifications as one mode of tumor evolution and integrates computational and experimental techniques to reveal molecular mechanisms driving these transformations.
This line of research seeks to inform treatment strategies by anticipating tumors' evolutionary responses. While the work is ongoing, such predictive modeling represents a shift towards viewing tumors not as static but as dynamic systems with internal rules. This approach has potential to enhance precision oncology but requires further validation across diverse cancer types.
Source & further reading
3 Questions: Building predictive models to characterize tumor progression ↗Source published 2026-03-10. This report was prepared with AI assistance from the linked primary-source material. Claims and limitations should be checked against the original announcement or research.