SMART‐Miner: A convolutional neural network‐based metabolite identification from 1H‐13C HSQC spectra

• Published in: Magnetic resonance in chemistry Vol. 60; no. 11; pp. 1070 - 1075
• Main Authors: Kim, Hyun Woo, Zhang, Chen, Cottrell, Garrison W., Gerwick, William H.
• Format: Journal Article
• Language: English
• Published: Bognor Regis Wiley Subscription Services, Inc 01.11.2022
• Subjects: Artificial neural networks; Convolutional Neural Network; Deep Learning; HSQC Spectra; Metabolites; Mixture Analysis; NMR Metabolomics; NMR spectroscopy; Spectra; Structure Identification
• ISSN: 0749-1581; 1097-458X
• DOI: 10.1002/mrc.5240

The identification of metabolites from complex biofluids and extracts of tissues is an essential process for understanding metabolic profiles. Nuclear magnetic resonance (NMR) spectroscopy is widely used in metabolomics studies for identification and quantification of metabolites. However, the accurate identification of individual metabolites is still a challenging process with higher peak intensity or similar chemical shifts from different metabolites. In this study, we applied a convolutional neural network (CNN) to 1H‐13C HSQC NMR spectra to achieve accurate peak identification in complex mixtures. The results reveal that the neural network was successfully trained on metabolite identification from these 2D NMR spectra and achieved very good performance compared with other NMR‐based metabolomic tools. The accurate identification of individual metabolites in a mixture is challenging. We applied a convolutional neural network (CNN) to 1H‐13C HSQC NMR spectra to achieve accurate peak identification in complex mixtures.