Massachusetts General Hospital, Harvard Medical School
Broad Institute of MIT and Harvard
Genomics is expensive and destructive, making it challenging to monitor live cells in tissues and humans over time. Although imaging is non-destructive, low-cost, and scalable, it can be difficult to interpret. We aim to develop novel experimental and computational frameworks (Image2Omics) that use ML to bridge the gap between imaging and genomics and generate Omics data from various novel imaging modalities. This will enable fast and scalable query and prediction of genomics information from imaging, providing a foundation for the development of more generalizable ML methods for translating the language of biology (e.g., DALL-E and AlphaFold for Omics).