In-silico screening of potential target transporters for glycyrrhetinic acid (GA) via deep learning prediction of drug-target interactions

Abstract

Glycyrrhetinic acid (GA) is one of the major bioactive components of the leguminous plant Glycyrrhiza spp. (Chinese licorice). The mechanism by which GA is transported within or out of cells remains completely unknown. Given the fact that living organisms harbor thousands of membrane transporters, experimental verification of membrane transporters for specific GA transporters is both laborious and time consuming. In this study, we carried out virtual screening of membrane transporters to predict their probability of binding with GA. Our mining strategy relied on deep learning prediction of drug-target interactions (DTI) combined with molecular docking. We used combinations of drug and protein descriptors to create 12 deep learning models to compare the performance of each descriptor followed by the evaluation of predictions via molecular docking scores. The ABC transporter BPT1p was predicted as a target that achieved the highest docking score among all tested proteins (−10.9 kcal/mol). Additionally, the models predictions of ABC transporters such as NPC1, MRP1, MRP3, NPC1L1, ABCA3 and PDR11, which have similar substrates reflect the ability of the models to learn the sequence features associated with similar compound molecules. We conclude that, our mining method was an effective approach for predicting membrane transporter substrates.