Artificial Intelligence for Retrosynthetic Planning Needs Both Data and Expert Knowledge.

Strieth-Kalthoff F; Szymkuć S; Molga K; Aspuru-Guzik A; Glorius F; Grzybowski BA

Review article (journal) | Peer reviewed

Abstract

Rapid advancements in artificial intelligence (AI) have enabled breakthroughs across many scientific disciplines. In organic chemistry, the challenge of planning complex multistep chemical syntheses should conceptually be well-suited for AI. Yet, the development of AI synthesis planners trained solely on reaction-example-data has stagnated and is not on par with the performance of "hybrid" algorithms combining AI with expert knowledge. This Perspective examines possible causes of these shortcomings, extending beyond the established reasoning of insufficient quantities of reaction data. Drawing attention to the intricacies and data biases that are specific to the domain of synthetic chemistry, we advocate augmenting the unique capabilities of AI with the knowledge base and the reasoning strategies of domain experts. By actively involving synthetic chemists, who are the end users of any synthesis planning software, into the development process, we envision to bridge the gap between computer algorithms and the intricate nature of chemical synthesis.

Details about the publication

Journal: Journal of the American Chemical Society (J. Am. Chem. Soc.)
Volume: 146
Issue: 16
Page range: 11005-11017
Status: Published
Release year: 2024 (10/04/2024)
Language in which the publication is written: English
Keywords: Artificial Intelligence; Algorithms; Addition Reactions; Molecules, Organic Synthesis

Authors from the University of Münster

Glorius, Frank
Strieth-Kalthoff, Felix