Machine Learning for Discovery of New ADORA Modulators

Adenosine (ADO) is an extracellular signaling molecule generated locally under conditions that produce ischemia, hypoxia, or inflammation. It is involved in modulating a range of physiological functions throughout the brain and periphery through the membrane-bound G protein-coupled receptors, called adenosine receptors (ARs) A(1)AR, A(2A)AR, A(2B)AR, and A(3)AR. These are therefore important targets for neurological, cardiovascular, inflammatory, and autoimmune diseases and are the subject of drug development directed toward the cyclic adenosine monophosphate and other signaling pathways. Initially using public data for A(1)AR agonists we generated and validated a Bayesian machine learning model (Receiver Operator Characteristic of 0.87) that we used to identify molecules for testing. Three selected molecules, crisaborole, febuxostat and paroxetine, showed initial activity in vitro using the HEK293 A(1)AR Nomad cell line. However, radioligand binding, β-arrestin assay and calcium influx assay did not confirm this A(1)AR activity. Nevertheless, several other AR activities were identified. Febuxostat and paroxetine both inhibited orthosteric radioligand binding in the µM range for A(2A)AR and A(3)AR. In HEK293 cells expressing the human A(2A)AR, stimulation of cAMP was observed for crisaborole (EC(50) 2.8 µM) and paroxetine (EC(50) 14 µM), but not for febuxostat. Crisaborole also increased cAMP accumulation in A(2B)AR-expressing HEK293 cells, but it was weaker than at the A(2A)AR. At the human A(3)AR, paroxetine did not show any agonist activity at 100 µM, although it displayed binding with a K(i) value of 14.5 µM, suggesting antagonist activity. We have now identified novel modulators of A(2A)AR, A(2B)AR and A(3)AR subtypes that are clinically used for other therapeutic indications, and which are structurally distinct from previously reported tool compounds or drugs.