Identification of Potential Tryptase Inhibitors from FDA-Approved Drugs Using Machine Learning, Molecular Docking, and Experimental Validation.

This study explores the innovative use of machine learning (ML) to identify novel tryptase inhibitors from a library of FDA-approved drugs, with subsequent confirmation via molecular docking and experimental validation. Tryptase, a significant mediator in inflammatory and allergic responses, presents a therapeutic target for various inflammatory diseases. However, the development of effective tryptase inhibitors has been challenging due to the enzyme's complex activation and regulation mechanisms. Utilizing a machine learning model, we screened an extensive FDA-approved drug library to identify potential tryptase inhibitors. The predicted compounds were then subjected to molecular docking to assess their binding affinity and conformation within the tryptase active site. Experimental validation was performed using RBL-2H3 cells, a rat basophilic leukemia cell line, where the efficacy of these compounds was evaluated based on their ability to inhibit tryptase activity and suppress β-hexosaminidase activity and histamine release. Our results demonstrated that several FDA-approved drugs, including landiolol, laninamivir, and cidofovir, significantly inhibited tryptase activity. Their efficacy was comparable to that of the FDA-approved mast cell stabilizer nedocromil and the investigational agent APC-366. These findings not only underscore the potential of ML in accelerating drug repurposing but also highlight the feasibility of this approach in identifying effective tryptase inhibitors. This research contributes to the field of drug discovery, offering a novel pathway to expedite the development of therapeutics for tryptase-related pathologies.