Chem. Sci., 2026, Accepted Manuscript DOI: 10.1039/D6SC00479B, Edge Article Alok Shaurya, Amir Hassan Begherzadeh Mostaghimi, David Turnbull, Fraser Hof, Jeffrey Francis Van Humbeck The availability of large datasets such as the Protein DataBank and ChEMBL have allowed for rapid progress in developing machine learning tools for predicting the biological activity of organic small...