Abstract
The P2Y(6) receptor, activated by uridine diphosphate (UDP), is a target for antagonists in inflammatory, neurodegenerative, and metabolic disorders, yet few potent and selective antagonists are known to date. This prompted us to use machine learning as a novel approach to aid ligand discovery, with pharmacological evaluation at three P2YR subtypes: initially P2Y(6) and subsequently P2Y(1) and P2Y(14). Relying on extensive published data for P2Y(6)R agonists, we generated and validated an array of classification machine learning model using the algorithms deep learning (DL), adaboost classifier (ada), Bernoulli NB (bnb), k-nearest neighbors (kNN) classifier, logistic regression (lreg), random forest classifier (rf), support vector classification (SVC), and XGBoost (XGB) classifier models, and the common consensus was applied to molecular selection of 21 diverse structures. Compounds were screened using human P2Y(6)R-induced functional calcium transients in transfected 1321N1 astrocytoma cells and fluorescent binding inhibition at closely related hP2Y(14)R expressed in CHO cells. The hit compound ABBV-744, an experimental anticancer drug with a 6-methyl-7-oxo-6,7-dihydro-1H-pyrrolo[2,3-c]pyridine scaffold, had multifaceted interactions with the P2YR family: hP2Y(6)R inhibition in a non-surmountable fashion, suggesting that noncompetitive antagonism, and hP2Y(1)R enhancement, but not hP2Y(14)R binding inhibition. Other machine learning-selected compounds were either weak (experimental anti-asthmatic drug AZD5423 with a phenyl-1H-indazole scaffold) or inactive in inhibiting the hP2Y(6)R. Experimental drugs TAK-593 and GSK1070916 (100 µM) inhibited P2Y(14)R fluorescent binding by 50% and 38%, respectively, and all other compounds by < 20%. Thus, machine learning has led the way toward revealing previously unknown modulators of several P2YR subtypes that have varied effects.