Prion Disease Therapeutics

National Institute Of Allergy And Infectious Diseases

Investigators

Linked publications, trials & patents

Abstract

Therapeutics for tauopathies such as Alzheimer's disease and chronic traumatic encephalopathy are sorely needed. Machine learning methods hold the promise to reduce the costs and the failure rates of conventional drug discovery pipelines. This issue is especially pressing for neurodegenerative diseases, where the development of disease-modifying drugs has been particularly challenging. To address this problem, we helped the Vendroscolo lab at Cambridge University develop and validate a machine learning approach to identify small molecule inhibitors of tau aggregation, a process implicated in multiple tauopathies. Because the proliferation of tau aggregates takes place through autocatalytic secondary nucleation, they aimed to identify compounds that bind the catalytic sites on the surface of the aggregates. To achieve this goal, they used structure-based machine learning in an iterative manner to first identify and then progressively optimize secondary nucleation inhibitors. We assisted this process by testing lead compounds obtained in their iterative search in our tau RT-QuIC seed amplification assay. Our testing provided direct evidence for inhibition, or lack thereof, of tau aggregation that is driven by the pathological tau aggregates of Alzheimer’s disease. The results of this study demonstrated that the overall approach facilitated the identification of more potent compounds that block tau aggregation.