Controversy surrounds corrected chemical structures

By Victoria Atkinson2022-11-08T09:30:00

A printout of a carbon NMR spectrum. There are several different hand-drawn structures on one side, most of them crossed out. A hand holding a red pen is circling one of the structures

Source: © Royal Society of Chemistry and © Shutterstock; data 10.1021/ja502167h

Researchers used machine learning-powered NMR prediction to correct improbable structures – but some of their revisions have been challenged

Structural and mechanistic revisions using machine learning-augmented computational NMR have caused controversy between researchers. The team analysed and corrected various unusual structures and mechanisms from the chemical literature but has since been challenged on the accuracy of their proposals. These disputes show that chemists need to strike a balance between relying on computation, experiment and intuition.