Machine learning-based optimization of a small-molecule suppressor of the cellular prion protein
A reduction in the levels of the cellular prion protein (PrPC) is expected to ameliorate cellular toxicity in both Alzheimer’s disease (AD) and prion diseases. The latter are invariably fatal diseases that include Creutzfeldt-Jakob disease in humans and bovine spongiform encephalopathy (BSE), also known as ‘Mad Cow Disease’, in cattle. To identify a rational method for reducing PrPC levels, the Schmitt-Ulms group has been studying the evolution, function and molecular environment of PrPC for more than ten years.
These efforts culminated recently in a rational small molecule-based strategy that accomplishes a profound (>50%) reduction of PrPC levels. The current proposal describes an academic-industry partnership between the Schmitt-Ulms group and Cyclica. It pairs the machine learning-based discovery platform of Cyclica for the prediction of optimized drug-like molecules with cell-based screening, pharmacological and toxicological analyses. Its overarching goal is to identify an optimized small molecule lead compound that exhibits most favorable characteristics for the intended indication. Its success will represent an indispensable milestone for moving this treatment approach to the clinic.