Objectives: This study presents a versatile, AI-guided workflow for the targeted isolation and characterization of prenylated flavonoids from Paulownia tomentosa (Thunb.) Steud. (Paulowniaceae). Methods: The approach integrates established extraction and chromatography-based fractionation protocols with LC-UV-HRMS/MS analysis and supervised machine-learning (ML) custom-trained classification models, which predict prenylated flavonoids from LC-HRMS/MS spectra based on the recently developed Python package AnnoMe (v1.0). Results: The workflow effectively reduced the chemical complexity of plant extracts and enabled efficient prioritization of fractions and compounds for targeted isolation. From the pre-fractionated plant extracts, 2687 features were detected, 42 were identified using reference standards, and 214 were annotated via spectra library matching (public and in-house). Furthermore, ML-trained classifiers predicted 1805 MS/MS spectra as derived from prenylated flavonoids. LC-UV-HRMS/MS data of the most abundant presumed prenyl-flavonoid candidates were manually inspected for coelution and annotated to provide dereplication. Based on this, one putative prenylated (C5) dihydroflavonol (1) and four geranylated (C10) flavanones (2–5) were selected and successfully isolated. Structural elucidation employed UV spectroscopy, HRMS, and 1D as well as 2D NMR spectroscopy. Compounds 1 and 5 were isolated from a natural source for the first time and were named 6-prenyl-4′-O-methyltaxifolin and 3′,4′-O-dimethylpaulodiplacone A, respectively. Conclusions: This study highlights the combination of machine learning with analytical techniques to streamline natural product discovery via MS/MS and AI-guided pre-selection, efficient prioritization, and characterization of prenylated flavonoids, paving the way for a broader application in metabolomics and further exploration of prenylated constituents across diverse plant species.

Brown algae such as Ascophyllum nodosum (AN) and Fucus vesiculosus (FV) are gaining considerable attention as functional feed additives due to their health-beneficial properties. This study evaluated the antioxidant potential of AN and FV extracts in intestinal epithelial cells and the in vivo model Caenorhabditis elegans (C. elegans). Aqueous AN and FV extracts were characterized for total phenolic content (TPC), antioxidant capacity (TEAC, FRAP), and phlorotannin composition using LC-HRMS/MS. Antioxidant effects were assessed in vitro, measuring AAPH-induced ROS production in Caco-2 and IPEC-J2 cells via H₂DCF-DA, and in vivo, evaluating the effects of paraquat-induced oxidative stress and AN or FV treatment on worm motility, GST-4::GFP reporter expression, and gene expression in C. elegans. FV exhibited higher total phenolic content, antioxidant capacity (TEAC, FRAP), and a broader phlorotannin profile (degree of polymerization [DP] 2–9) than AN (DP 2–7), as determined by LC-HRMS/MS. Both extracts attenuated AAPH-induced oxidative stress in epithelial cells, with FV showing greater efficacy. In C. elegans, pre-treatment with AN and FV significantly mitigated a paraquat-induced motility decline by 22% and 11%, respectively, compared to PQ-stressed controls. Under unstressed conditions, both extracts enhanced nematode healthspan, with significant effects observed at 400 µg/g for AN and starting at 100 µg/g for FV. Gene expression analysis indicated that both extracts modulated antioxidant pathways in unstressed worms. Under oxidative stress, pre-treatment with AN and FV significantly reduced GST-4::GFP expression. In the nematode, AN was more protective under acute stress, whereas FV better supported physiological function in the absence of stressors. These findings demonstrate that AN and FV counteract oxidative stress in intestinal epithelial cells and in C. elegans, highlighting their potential as stress-reducing agents in animal feed.