This project will develop multimodal machine learning models that jointly learn from brain imaging and omics data to capture both the phenotypic and genetic dynamics of Parkinson’s disease. Building on established repositories such as the Parkinson’s Progression Markers Initiative (PPMI), we will blend modern deep learning with proven bioinformatics to discover predictors for patient subtyping. Models will be tested retrospectively by checking whether they rediscover known PD subtypes and will then be evaluated on independent cohorts.

This work is carried out as a joint postdoctoral project between Astex Pharmaceuticals and Prof. Pietro Lio’s group at the Department of Computer Science and Technology, University of Cambridge.