Non-destructive determination of ginsenosides in ginseng by combined hyperspectral and X-ray techniques based on ensemble learning

Exploring molecular mechanisms underlying changes in lipid fingerprinting of salmon (Salmo salar) during air frying integrating machine learning-guided REIMS and lipidomics analysis

Lipid oxidation in air-fried seafood poses a risk to human health. However, the effect of a prooxidant environment on lipid oxidation in seafood at different air frying (AF) temperatures remains unknown. An integrated machine learning (ML) - guided REIMS and lipidomics method was applied to explore lipid profiles, lipid oxidation, and lipid metabolic pathways of salmons under different AF temperatures (140, 160, 180, and 200 °C). A significant difference in the lipidomic fingerprinting of air-dried salmon at different temperatures was shown by the main ML methods (neural networks, support vector machines, ensemble learning, and naïve bayes). In total, 773 differential expression metabolites (DEMs) were identified, including glycerophospholipids (GPs), glycerides (GLs), and sphingolipids. A total of 34 DEMs with p values <0.05 and variable importance of projection values >1.0 were analyzed, belonging to linoleic acid metabolism, GL metabolism, and GP metabolism pathways. Correlation network analysis revealed that some characteristic DEMs (phosphatidylcholine, lyso-phosphatidylcholine, triglycerides, fatty acids, and phosphatidylethanolamine) were highly correlated with lipid oxidation. In addition, variations of volatile compounds, color values, texture characteristics, and thiobarbituric acid-reactive substance values were analyzed to corroborate the oxidation characteristics.

Rapid and non-destructive identification of Panax ginseng origins using hyperspectral imaging, visible light imaging, and X-ray imaging combined with multi-source data fusion strategies

The geographical origin of Panax ginseng significantly influences its nutritional value and chemical composition, which in turn affects its market price. Traditional methods for analyzing these differences are often time-consuming and require substantial quantities of reagents, rendering them inefficient. Therefore, hyperspectral imaging (HSI) in conjunction with X-ray technology were used for the swift and non-destructive traceability of Panax ginseng origin. Initially, outlier samples were effectively rejected by employing a combined isolated forest algorithm and density peak clustering (DPC) algorithm. Subsequently, random forest (RF) and support vector machine (SVM) classification models were constructed using hyperspectral spectral data. These models were further optimized through the application of 72 preprocessing methods and their combinations. Additionally, to enhance the model's performance, four variable screening algorithms were employed: SelectKBest, genetic algorithm (GA), least absolute shrinkage and selection operator (LASSO), and permutation feature importance (PFI). The optimized model, utilizing second derivative, auto scaling, permutation feature importance, and support vector machine (2nd Der-AS-PFI-SVM), achieved a prediction accuracy of 93.4 %, a Kappa value of 0.876, a Brier score of 0.030, an F1 score of 0.932, and an AUC of 0.994 on an independent prediction set. Moreover, the image data (including color information and texture information) extracted from color and X-ray images were used to construct classification models and evaluate their performance. Among them, the SVM model constructed using texture information from X -ray images performed the best, and it achieved a prediction accuracy of 63.0 % on the validation set, with a Brier score of 0.181, an F1 score of 0.518, and an AUC of 0.553. By implementing mid-level fusion and high-level data fusion based on the Stacking strategy, it was found that the model employing a high-level fusion of hyperspectral spectral information and X-ray images texture information significantly outperformed the model using only hyperspectral spectral information. This advanced model attained a prediction accuracy of 95.2 %, a Kappa value of 0.912, a Brier score of 0.027, an F1 score of 0.952, and an AUC of 0.997 on the independent prediction set. In summary, this study not only provides a novel technical path for fast and non-destructive traceability of Panax ginseng origin, but also demonstrates the great potential of the combined application of HSI and X-ray technology in the field of traceability of both medicinal and food products.

Specific fractionation of ginsenosides based on activated carbon fibers and online fast screening of ginseng extract by mass spectrometry

Ginseng is beneficial in the prevention of many diseases and provides benefits for proper growth and development owing to the presence of various useful bioactive substances of diverse chemical heterogeneity (e.g., triterpenoid saponins, polysaccharides, volatile oils, and amino acids). As a result, understanding the therapeutic advantages of ginseng requires an in-depth compositional evaluation employing a simple and rapid analytical technique. In this work, three types of surface-activated carbon fibers (ACFs) were prepared by gas-phase oxidation, strong acid treatment, and Plasma treatment to obtain CO2-ACFs, acidified-ACFs, and plasma-ACFs, respectively. Three prepared ACFs were compared in terms of their physicochemical characterization (i.e., surface roughness and functional groups). A separation system was built using a column with modified ACFs, followed by mass spectrometry detection to investigate and determine substances of different polarities. Among the three columns, CO2-ACFs showed the optimum separation effect. 13 strong polar compounds (12 amino acids and1 oligosaccharide) and 15 lesser polar compounds (ginsenosides) were separated and identified successfully within 4 min in the ginseng sample. The data obtained by CO2-ACFs-TOF-MS/MS and UHPLC-TOF-MS/MS were compared. Our approach was found to be faster (4 min vs. 36 min) and greener, requiring much less solvent (1 mL vs. 10.8 mL), and power (0.06 vs. 0.6 kWh). The developed methodology can provide a faster, eco-friendly, and more reliable tool for the high-throughput screening of complex natural matrices and the simultaneous evaluation of several compounds in diverse samples.