SMART-Miner: A convolutional neural network-based metabolite identification from 1 H- 13 C HSQC spectra.
Hyun Woo KimChen ZhangGarrison W CottrellWilliam H GerwickPublished in: Magnetic resonance in chemistry : MRC (2021)
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 1 H- 13 C 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.
Keyphrases
- convolutional neural network
- magnetic resonance
- high resolution
- ms ms
- bioinformatics analysis
- deep learning
- neural network
- gene expression
- mass spectrometry
- computed tomography
- machine learning
- density functional theory
- magnetic resonance imaging
- dna methylation
- solid state
- body composition
- contrast enhanced
- resistance training