A transfer learning approach for reaction discovery in small data situations using generative model

Sustainable practices in chemical sciences can be better realized by adopting interdisciplinary approaches that combine the advantages of machine learning (ML) on the initially acquired small data in reaction discovery. Developing new re-actions generally remains heuristic and even time and resource intensive. For instance, synthesis of fluorine-containing compounds, which constitute -20% of the marketed drugs, relies on deoxyfluorination of abundantly available alco-hols. Herein, we demonstrate the use of a recurrent neural network-based deep generative model built on a library of just 37 alcohols for effective learning and exploration of the chemical space. The proof-of-concept ML model is able to generate good quality, synthetically accessible, higher-yielding novel alcohol molecules. This protocol would have superior utility for deployment into a prac-tical reaction discovery pipeline.

Automated summary

Sustainable practices in chemical sciences can be better achieved by adopting interdisciplinary approaches that combine the advantages of machine learning in reaction discovery with small initial data. The use of a recurrent neural network-based deep generative model allows for effective learning and exploration of the chemical space, generating high-quality novel alcohol molecules.