The amount of structural data on protein drug targets continues to grow. However, successfully mining this data to form testable hypotheses that drive drug discovery can prove challenging. Selectivity for the target protein is a crucial property in the development of new therapeutics. In a recent paper in the Journal of Chemical Information and Modeling, authors from the CCDC, Exscientia, and Oxford University show how an automated process leveraging "ensemble hotspot maps" can identify key structural differences that contribute to the selectivity of a compound for one protein over another.