Two chemists warn that AI-generated molecular structures are often incorrect, which could harm chemistry education and scientific accuracy, calling for a ban on AI use for chemical representations until the technology improves.
Researchers from the Skaggs School of Pharmacy and Pharmaceutical Sciences at the University of California San Diego have developed a technique called reverse metabolomics to identify chemical structures in the human body. By analyzing mass spectrometry data, the researchers were able to map the metabolic pathways of various compounds, including those produced by the human microbiome. This approach has the potential to advance our understanding of human health and disease, as well as aid in the discovery of new therapeutic targets.