Extracting medicinal chemistry intuition via preference machine learning

• DOI: 10.1038/s41467-023-42242-1
• Publication Date: 2023-10-31T17:02:00Z
• Authors: Oh-Hyeon Choung; Riccardo Vianello; Marwin Segler; Nikolaus Stiefl; José Jiménez-Luna
• Keywords: Intuition; Prioritization

The lead optimization process in drug discovery campaigns is an arduous endeavour where the input of many medicinal chemists weighed order to reach a desired molecular property profile. Building expertise successfully drive such projects collaboratively very time-consuming that typically spans years within chemist's career. In this work we aim replicate by applying artificial intelligence learning-to-rank techniques on feedback was obtained from 35 at Novartis over course several months. We exemplify usefulness learned proxies routine tasks as compound prioritization, motif rationalization, and biased de novo design. Annotated response data provided, developed models code made available through permissive open-source license.