A Machine Learning Approach to Identify Small Molecule Inhibitors of Secondary Nucleation in α-Synuclein Aggregation

Abstract Drug development is an increasingly active area of application of machine learning, prompted by the need to overcome the high attrition rates of conventional drug discovery pipelines. This issue is especially pressing for neurodegenerative diseases, where disease-modifying drugs are not widely available yet. To address this problem, we describe an approach based on a combination of machine learning with chemical kinetics to target diseases caused by protein misfolding and aggregation. We use this approach to identify specific inhibitors of the proliferation of α-synuclein aggregates through secondary nucleation, a process implicated in Parkinson’s disease. Our results demonstrate that this approach leads to the identification of novel chemical matter with an improved hit rate and potency over more traditional approaches.