A computational pipeline combining machine learning and molecular simulations identifies repurposed PI3Kα inhibitors from FDA-approved drugs

The computational repurposing of existing drugs has proven to be a fast-track strategy in the development of new cancer therapy. Nonetheless, integrated mechanistically grounded approaches are required for a more reliable in silico identification of new drug-target pairs. In this study, we introduce an integrated workflow combining machine learning with molecular docking, kinase selectivity profiling, molecular dynamics simulations, and ADMET assessment to systematically repurpose FDA-approved drugs as inhibitors of the oncogenic kinase PI3Kα. A robust quantitative structure-activity relationship (QSAR) model (test set R² = 0.825) prioritized candidates from a library of 2,458 approved drugs. Through this pipeline, three promising candidates (Vemurafenib, Fedratinib, and Zafirlukast) were identified, each exhibiting stable interactions with PI3Kα, favorable binding free energies, and targeted polypharmacology rather than promiscuous inhibition. Molecular dynamics simulations confirmed that ligand binding reduces protein flexibility and confines the conformational landscape. These results provide a multi-layered computational rationale for repurposing these FDA-approved drugs as PI3Kα inhibitors. Overall, this hybrid approach illustrates how combining data-driven and physics-based methods can enhance the precision of computational drug repurposing, effectively transforming the large library of approved drugs into a tractable source for novel targeted cancer therapies. • An integrated ML and molecular simulation pipeline for drug repurposing against PI3Kα is presented. • A robust ensemble QSAR model (R²test = 0.825) prioritized inhibitors from an FDA-approved drug library. • Molecular docking identified Vemurafenib, Fedratinib, and Zafirlukast as high-affinity PI3Kα binders. • 200-ns MD simulations confirmed the stability of the drug-PI3Kα complexes and reduced protein flexibility. • The candidates exhibit favorable kinase selectivity and ADMET profiles, supporting experimental testing.