Machine Learning and UHPLC–MS/MS-Based Discrimination of the Geographical Origin of Dendrobium officinale from Yunnan, China

A rapid targeted screening method for 22 compounds, including flavonoids, glycosides, and phenolics, in <i>Dendrobium officinale</i> was developed using UHPLC-MS/MS, demonstrating good linear correlation coefficients, precision, repeatability, and stability. <i>D. officinale</i> from the Guangnan and Maguan regions can be effectively classified into two distinct categories using PCA. In addition, OPLS-DA discriminant analysis enables clear separation between groups, with samples forming well-defined clusters. The 22 chemical components provide valuable origin-related information for <i>D. officinale</i>. The compounds with VIP values of >1 included eriodictyol, vanillic acid, protocatechuic acid, gentisic acid, and naringenin. The difference in naringenin content between <i>D. officinale</i> from the two production areas was minimal. By contrast, eriodictyol and vanillic acid were relatively abundant in <i>D. officinale</i> from Guangnan, while gentisic acid and protocatechuic acid were more prevalent in <i>D. officinale</i> from Maguan. The pathways with higher Kyoto Encyclopedia of Genes and Genomes enrichment were primarily associated with lipid metabolism and atherosclerosis, fluid shear stress and atherosclerosis, and nonalcoholic fatty liver disease. These findings suggest that <i>D. officinale</i> exhibits promising lipid-balancing properties and potential cardiovascular health benefits. Seven machine learning algorithms-Random Forest, XGBoost, Support Vector Machine, k-Nearest Neighbor, Backpropagation Neural Network, Random Tree, and CatBoost-demonstrated superior accuracy and precision in distinguishing <i>D. officinale</i> from the Guangnan and Maguan regions. The key compounds with higher weights-vanillic acid, chrysoeriol, trigonelline, isoquercitrin, gallic acid, 4-hydroxybenzaldehyde, eriodictyol, sweroside, apigenin, and homoeriodictyol-play a crucial role in model construction and the identification of <i>D. officinale</i> from the Guangnan and Maguan regions. The quantification of 22 compounds using UHPLC-MS/MS, combined with PCA, OPLS-DA, and machine learning, enables effective discrimination of <i>D. officinale</i> from these two Yunnan production areas.