Deep-learning based profiling of patient-derived cells as a tool for genomic and translational medicine

Project Narrative: The functional interpretation of genetic variation in diseases faces critical roadblocks, due to the lack of scalable methods to assess the significance of candidate variants experimentally, while accounting for genomic context. This proposal introduces a morphological profiling method, that is able to rapidly identify disease-associated phenotypes in patient cells and offers a cost-efficient and unbiased way to determine the significance of putative pathogenic variants at scale. If successful, this proposal will establish cellular profiling of patient cells as a powerful platform to advance genomic and translational medicine.