Scaffold‐Directed Face Selectivity Machine‐Learned from Vectors of Non‐covalent Interactions

Abstract This work describes a method to vectorize and Machine‐Learn, ML, non‐covalent interactions responsible for scaffold‐directed reactions important in synthetic chemistry. Models trained on this representation predict correct face of approach ca. 90 % Michael additions or Diels–Alder cycloadditions. These accuracies are significantly higher than those based traditional ML descriptors, energetic calculations, intuition experienced chemists. Our results also emphasize the importance models being provided with relevant mechanistic knowledge; without such knowledge, these cannot easily “transfer‐learn” extrapolate previously unseen reaction mechanisms.