The high attrition rate of drug discovery is a pressing issue for neurodegenerative diseases where very few disease-modifying drugs have been approved. Numerous trials targeted at the suspected pathological species, misfolded protein aggregates, have failed due to the differential toxicity of aggregate species and the complex kinetics that govern their formation. To address this problem, I have developed a machine learning approach to identify small molecule inhibitors of the proliferation of misfolded ?-synuclein aggregates through secondary nucleation, a process that has been implicated in Parkinson?s disease and related synucleinopathies. Secondary nucleation results in soluble oligomer proliferation, the suspected cause of pathology. These oligomers are heterogeneous, transient and challenging to measure via bulk techniques. We integrate single molecule approaches into the pipeline to characterise oligomers formed during the aggregation and validate the identified inhibitors.
