AI-Driven Structural Biology for Next-Generation Therapeutics Targeting Cancer-Associated Thrombosis and Metastasis

Cancer-associated thrombosis (CAT) is a major complication in oncology, contributing to poor outcomes and increased mortality. Elevated levels of von Willebrand factor (VWF) and activation of the contact system drive both thrombus formation and metastatic progression in aggressive cancers such as pancreatic and ovarian. Current anticoagulants reduce clot risk but fail to target these underlying mechanisms and often increase bleeding risk in vulnerable patients.

This PhD project will combine artificial intelligence-driven protein engineering with advanced structural biology to develop next-generation therapeutics for CAT and metastasis. Building on our novel Inhibitor of Platelets and Coagulation (IPAC), the student will use deep learning models (e.g., AlphaFold, generative AI) to design, predict, and optimise variants of IPAC with enhanced selectivity for VWF and contact pathway components. These computationally engineered proteins will be validated through X-ray crystallography, biophysical assays (SPR), and ex vivo functional studies using cancer patient plasma.

This interdisciplinary project integrates computational drug design, structural biology, and translational haemostasis research to pioneer safer anti-thrombotic agents that also impede metastasis. The successful candidate will gain expertise in AI methods for protein design, high-resolution structure determination, and translational thrombosis biology—providing a unique platform to shape the future of precision therapeutics at the intersection of cancer and cardiovascular research.