The project will develop computational tools based on recent developments in advanced statistical algorithms, referred to as “deep learning,” to handle the “big data” generated by metabolomics. The first tool, DeepMet, will increase the number of molecules that can be identified in metabolomic experiments. The second, MetUnknown, will help assign chemical structures to molecules that are as of yet unknown. Together, these tools will help shine a light on the 98% of the metabolome that is overlooked by current methods.