Beyond Prediction: AI as a Creative Partner in Organic Synthesis

Abstract

.

Artificial intelligence (AI) has rapidly progressed from being a niche curiosity to becoming a real force in the chemical sciences. In organic synthesis, however, AI’s role is still mostly viewed in two ways: helping automate retrosynthetic planning and speeding up reaction optimization. These advances—like the retrosynthesis engine developed by Segler et al. (2018)[1] and the optimization workflows from Doyle’s group (Shields et al., 2021)[2]—have been game-changing in specific cases. But if we see AI only in these roles, we risk overlooking its bigger potential.

.

Keywords

Machine learning - Artificial intelligence - Organic synthesis - Reactivity and mechanisms - Cross-domain strategies - Chemical space expansion

Publication History

Received: 13 August 2025

Accepted after revision: 30 September 2025

Article published online:
05 November 2025

• References

• 1 Segler MHS, Preuss M, Waller MP. Nature 2018; 555: 604-610
• 2 Shields BJ, Stevens J, Li J. et al. Nature 2021; 590: 89-96
• 3 Corey EJ, Wipke WT. Science 1969; 166: 178-192
• 4 Granda JM, Donina L, Dragone V, Long D-L, Cronin L. Nature 2018; 559: 377-381
• 5 Herges R, Hoock C. Science 1992; 255 (5045) 711-713
• 6 Sanchez-Lengeling B, Aspuru-Guzik A. Science 2018; 361: 360-365
• 7 Jones N. Nature. 2025 10.1038/d41586-025-00377-9
• 8 Beker W, Roszak R, Wołos A. et al. J Am Chem Soc 2022; 144: 4819-4827
• 9 Reid JP, Proctor RSJ, Sigman MS, Phipps RJ. J Am Chem Soc 2019; 141: 19178-19185
• 10 Burger B, Maffettone PM, Gusev VV. et al. Nature 2020; 583: 237-241