Diffusion-Model-Guided Identification of a Candidate α-Synuclein Aggregation Inhibitor under Secondary-Nucleation-Dominated Conditions

Abstract The process of α-synuclein aggregation results in the formation of amyloid deposits that accumulate in the brain of patients affected by Parkinson’s disease and related synucleinopathies. Among possible therapeutic strategies for these conditions, one approach is based on the development of compounds capable of inhibiting α-synuclein aggregation. An effective inhibition could be achieved by blocking the nucleation sites on the surface of the amyloid fibrils that are responsible for their autocatalytic proliferation. Here, we use an E(3)-equivariant conditional diffusion model to identify candidate inhibitors of this type. With this approach, we generated pocket-conditioned molecules, identified purchasable analogues, and experimentally tested selected compounds. We thus identified a compound that delays α-synuclein aggregation under conditions in which secondary nucleation is the dominant process. These results illustrate the use of conditional diffusion models to identify candidate aggregation inhibitors.