Insights into Thai and Foreign Hemp Seed Oil and Extracts' GC/MS Data Re-Analysis Through Learning Algorithms and Anti-Aging Properties.

This study successfully established a novel discriminative model that distinguishes between Thai and foreign hemp seed extracts based on gas chromatography/mass spectrometry (GC/MS) metabolic profiling combined with machine learning algorithms such as hierarchy clustering analysis (HCA), principal component analysis (PCA), and partial least square-discriminant analysis (PLS-DA). The findings highlighted significant metabolic features, such as vitamin E, clionasterol, and linoleic acid, related with anti-aging properties via elastase inhibition. Our biological validation experiment revealed that the individual compound at 2 mg/mL exhibited a moderate elastase inhibitory activity, 40.97 ± 1.80% inhibition (n = 3). However, a binary combination among these metabolites at 1 mg/mL of each compound demonstrated a synergistic effect against elastase activities up to 89.76 ± 1.20% inhibition (n = 3), showing 119% improvement. Molecular docking experiments aligned with biological results, showing strong binding affinities and enhanced inhibitory effects in all combinations. This integrated approach provided insights into the bioactive compounds responsible for anti-aging effects and established a dependable framework for quality control and standardization of hemp seed-based skincare products. Additionally, the developed models enable effective discrimination between Thai and foreign strains, which is valuable for sourcing and product consistency. Overall, this research advances our understanding of hemp seed phytochemicals and their functional potential, paving the way for optimized natural anti-aging formulations and targeted functional foods.