Drug Repurposing of Fluvastatin as a DP2 Antagonist: An Ensemble Learning Strategy with In Vitro Cellular Functional Validation

Abstract

We present a framework to repurpose FDA-approved drugs as DP2 antagonists for asthma, using a two-stage strategy. First, we train and evaluate eight models—five machine learning algorithms and three graph neural networks—for their complementarity and performance. Then, we create a dynamically weighted ensemble predictor from the best models, trained on DP2 inhibitor activity data (pIC50). This ensemble showed strong predictive ability, with R² values of 0.752, 0.722, and 0.684 for different data splits. SHAP analysis identified key factors for DP2 activity, including a molecular weight of 420–550 Da and a specific fingerprint bit. After screening 2,019 approved drugs, three candidates were found and tested through assays like cytotoxicity, cAMP inhibition, and cell migration. Pitavastatin demonstrated inadequate activity at non-toxic concentrations, and levocabastine's inhibition was not concentration-dependent, making its IC₅₀ hard to determine. Fluvastatin, however, was a strong and specific DP2 antagonist with an IC₅₀ of 12.72 nM and achieved 94.9% inhibition of DK-PGD₂-induced cell migration at 243 nM. The study's code and data are publicly accessible. Contribution: This study presents a reproducible, open-source workflow that combines split-adaptive model selection with targeted functional assays for drug repurposing. In contrast to traditional static ensembles that amalgamate all available models without discrimination, our approach selectively integrates complementary models using dynamic weighting tailored to each data splitting strategy. Additionally, SHAP interpretability offers actionable insights into structure-activity relationships for lead optimization. In this study, the developed workflow demonstrates effective performance in the discovery of DP2 antagonists, offering a significant reference point for AI-driven drug repositioning targeting this receptor. Keywords: Asthma; DP2 receptor; DP2 antagonist; CRTH2 antagonist; Drug repurposing; Machine learning; Graph neural networks; Virtual screening