Rapid and accurate deorphanization of ligand-receptor pairs using AlphaFold

Secreted proteins are extracellular ligands that play key roles in paracrine and endocrine signaling, classically by binding cell surface receptors. Experimental assays to identify new extracellular ligand-receptor interactions are challenging, which has hampered the rate of novel ligand discovery. Here, using AlphaFold-multimer, we developed and applied an approach for extracellular ligand-binding prediction to a structural library of 1,108 single-pass transmembrane receptors. We demonstrate high discriminatory power and a success rate of close to 90 % for known ligand-receptor pairs where no a priori structural information is required. Importantly, the prediction was performed on de novo ligand-receptor pairs not used for AlphaFold training and validated against experimental structures. These results demonstrate proof-of-concept of a rapid and accurate computational resource to predict high-confidence cell-surface receptors for a diverse set of ligands by structural binding prediction, with potentially wide applicability for the understanding of cell-cell communication.