Discovery of potent and selective LRRK2 inhibitors with preserved activity against the G2019S mutant via multi-stage virtual screening

Targeting leucine-rich repeat kinase 2 (LRRK2) has emerged as a promising strategy for the treatment of Parkinson's disease (PD). Here, we report the identification of newly identified LRRK2 inhibitors using a multi-stage virtual screening strategy that integrates molecular docking, AI-driven predictive modeling, molecular dynamics (MD) simulations, and binding free energy change (ΔΔG) calculations. A library of 8,617 drug-like small molecules was screened, and ΔΔG analysis was subsequently used as a post-screening prioritization step to identify candidates predicted to maintain or enhance binding affinity against the pathogenic G2019S mutant. Notably, compound 3 exhibited an IC₅₀ value of 14.21 nM against the wild-type (WT) and 14.75 nM against the G2019S mutant, along with a preliminary kinase selectivity in profiling assays. MD simulations further revealed key interaction profiles that stabilize compound binding within the active sites of both WT and G2019S LRRK2. These findings underscore the utility of integrating AI-enhanced virtual screening with ΔΔG-based post-screening prioritizationto identify mutation-resilient inhibitors, offering a robust foundation for further optimization and therapeutic development in PD.