The integration of hyperspectral imaging with machine learning algorithms has presented a promising strategy for the non-invasive and rapid detection of plant metabolites. For this study, we developed prediction models using partial least squares regression (PLSR) and boosting algo-rithms (such as AdaBoost, XGBoost, and LightGBM) for five metabolites in Brassica juncea leaves: total chlorophyll, phenolics, flavonoids, glucosinolates, and anthocyanins. To enhance the model performance, we employed several spectral data preprocessing methods and feature-selection al-gorithms. Our results showed that the boosting algorithms generally outperformed the PLSR models in terms of prediction accuracy. In particular, the LightGBM model for chlorophyll and the AdaBoost model for flavonoids improved the prediction performance, with R2p = 0.71–0.74, com-pared to the PLSR models (R2p = 0.53–0.58). The final models for the glucosinolates and anthocya-nins performed sufficiently for practical uses such as screening, with R2p = 0.82–0.85 and RPD = 2.4–2.6. Our findings indicate that the application of a single preprocessing method is more effective than utilizing multiple techniques. Additionally, the boosting algorithms with feature selection ex-hibited superior performance compared to the PLSR models in the majority of cases. These results highlight the potential of hyperspectral imaging and machine learning algorithms for the non-destructive and rapid detection of plant metabolites, which could have significant implications for the field of smart agriculture.
The marine carotenoid fucoxanthin (FX) has various health benefits but suffers from poor bioavailability. We hypothesize that the bioavailability of FX in microalga Phaeodactylum tricornutum extract (PE) could be improved through nanoencapsulation. Here, we developed two types of nanoparticles: one consisting of alginate and casein (A-C-PE, 246 nm diameter, 79.6% encapsulation efficiency) and the other A-C-PE coated with chitosan (CS-A-C-PE, 258 nm, 78.1%). Both types of nanoparticles incorporating PE showed controlled FX release during simulated gastrointestinal digestion, as well as 1.8-fold improvement of membrane permeability in Caco-2/TC7 cells compared to non-encapsulated PE. Pharmacokinetic behavior of two FX metabolites (fucoxanthinol and amarouciaxanthin A) in mouse plasma was monitored after oral administration. The results showed that 31.8-332.1% more FX metabolites from the nanoparticles were absorbed into plasma than those from PE. In conclusion, encapsulation of PE in both types of nanoparticles significantly promoted the bioavailability of FX.
Kale is a prominent leafy vegetable because of its high content of bioactive compounds and various health benefits. Microalgae have been suggested as a biostimulator that can replace chemical fertilizers by enhancing crop yield and supporting soil carbon sequestration. In this study, the effect of Chlorella vulgaris as a plant biostimulant on the growth and secondary metabolite contents of “Red Russian” kale (Brassica napus var. Pabularia) with green leaves and purple veins has been demonstrated. Three Chlorella treatments were used: CS, C. vulgaris suspension; CB, C. vulgaris biomass; and CFS, filtered C. vulgaris-free supernatant. The plant growth rates, phytochemical contents, and individual glucosinolate and anthocyanin contents were determined. There was no significant difference under the CS and CB treatments, while CFS negatively influenced on kale growth with 37% reduction of dried weight. In contrast, metabolite production differed according to Chlorella treatments. Total contents of chlorophyll and carotenoid were increased by 1.57 and 1.41 folds by CS treatment, whereas total contents of phenol and flavonoids were enhanced by 1.30 and 1.22 folds by CFS treatment. Totally, seven glucosinolates and four anthocyanins were characterized and quantified individually. Notably, CFS treatment increased gluconasturtiin and all anthocyanins the most, 10.28-fold and 5.90-fold, respectively.
Partial least squares regression (PLSR) prediction models were developed using hyperspectral imaging for noninvasive detection of the five most representative functional components in Brassica juncea leaves: chlorophyll, carotenoid, phenolic, glucosinolate, and anthocyanin contents. The region of interest for functional component analysis was chosen by polygon selection and the extracted average spectra were used for model development. For pre-processing, 10 combinations of Savitzky–Golay filter (S. G. filter), standard normal variate (SNV), multiplicative scatter correction (MSC), 1st-order derivative (1st-Der), 2nd-order derivative (2nd-Der), and normalization were applied. Root mean square errors of calibration (RMSEP) was used to assess the performance accuracy of the constructed prediction models. The prediction model for total anthocyanins exhibited the highest prediction level (RV2 = 0.8273; RMSEP = 2.4277). Pre-processing combination of SNV and 1st-Der with spectral data resulted in high-performance prediction models for total chlorophyll, carotenoid, and glucosinolate contents. Pre-processing combination of S. G. filter and SNV gave the highest prediction rate for total phenolics. SNV inclusion in the pre-processing conditions was essential for developing high-performance accurate prediction models for functional components. By enabling visualization of the distribution of functional components on the hyperspectral images, PLSR prediction models will prove valuable in determining the harvest time.