Synthesis Predictions Enabled by Machine Learning

Reliable prediction of chemical reactivity remains in the realm of knowledgeable synthetic chemists. Automating this process by using artificial intelligence could accelerate synthesis design in future digital laboratories. While several machine learning approaches have demonstrated promising results, most current models use language models which is difficult to interpret and deviate from how human chemists analyze and predict reactions based on electronic changes. In this talk, I will talk about our recent efforts to learn organic reactivity based on chemical rules and algorithms. The issues related to the current reaction datasets and hence the importance of data curation to further improve the models will be discussed. I will then propose a new organic synthesis prediction AI methodology that can predict the reaction mechanisms with various chemical conditions.

1. J. Jang, G. Gu, J. Noh, J. Kim & Y. Jung, J Am Chem Soc 2020, 142, 18836.
2. S. Chen & Y. Jung, JACS Au 2021,  1, 1612–1620.
3. S. Chen & Y. Jung, Nat. Mach. Intell. 2022, 4, 772-780.
4. S. Kim, J. Noh, G. Gu, S. Shen & Y. Jung, Chem. Sci. 2023, 15, 1039-1045.
5. S. Chen, S. An, R. Rabazade, Y. Jung, Nat. Commun. 2024, (accepted).