Mycotoxins are toxic secondary metabolites produced by various fungal species, posing significant food safety concerns due to their health impacts and economic burden. Accurate structural elucidation and quantitative analysis are essential for effective risk assessment and regulatory control. This review highlights recent advances in the application of nuclear magnetic resonance (NMR) spectroscopy for the structural and quantitative analysis of major mycotoxins, including aflatoxins, ochratoxins, fumonisins, trichothecenes, and zearalenone. One- and two-dimensional NMR techniques enable precise molecular characterization, positional isomer identification, including modified forms such as masked or conjugated mycotoxins, and toxicity-related molecular interaction investigation. NMR spectroscopy offers superior structural resolution, high reproducibility, and nondestructive analysis, making it invaluable in mycotoxin research. Quantitative NMR spectroscopy has emerged as a robust and accurate method for determining the absolute concentration and purity of mycotoxins, without requiring analyte-specific reference standards, an advantage particularly important for modified toxins lacking commercially available standards. The integration of NMR-based approaches strengthens analytical reliability, supports reference material development, and contributes to enhanced food safety assessment. This review also discusses ongoing analytical challenges and future directions, including the application of artificial intelligence to improve the automation and interpretation of NMR data in mycotoxin research.
31 July 2025 in Bulletin of the Korean Chemical Society
This study presents an approach for discriminating omega‐3 fatty acid forms using proton nuclear magnetic resonance (1H‐NMR) spectroscopy combined with machine learning and deep learning techniques. A total of 90 samples, comprising triglyceride, re‐esterified triglyceride, and ethyl ester forms, were analyzed. Principal component analysis–linear discriminant analysis, support vector machine (SVM), artificial neural network (ANN), and one‐dimensional convolutional neural network (1D CNN) models were applied using binned spectral data. In contrast, a two‐dimensional convolutional neural network (2D CNN) was constructed using spectral images. To prevent overfitting and optimize model hyperparameters, early stopping, cross‐validation, and Bayesian optimization were used across the different machine learning and deep learning models. The 1D and 2D CNN models both achieved 100% accuracy on the training and test sets, while the SVM and ANN models yielded slightly lower but still excellent performance, with a test accuracy of 94.4%. Model interpretability was enhanced through SHapley Additive exPlanations and Gradient‐weighted Class Activation Mapping, which identified critical spectral regions associated with classification decisions. These results demonstrate that the integration of artificial intelligence techniques with 1H‐NMR spectroscopy enables accurate, interpretable discrimination of omega‐3 fatty acid forms, offering a promising strategy for supplement authentication and quality control.