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 effect of salt treatment on Brassica carinata (BC) microgreens grown under different light wavelengths on glucosinolates (GLs) and phenolic compounds were evaluated. Quantifiable GLs were identified using ultra-high performance-quadrupole time of flight mass spectrometry. Extracts’ ability to activate antioxidant enzymes (superoxide dismutase (SOD) and catalase (CAT)) was evaluated on human colorectal carcinoma cells (HCT116). Furthermore, BC compounds’ ability to activate expression of nuclear transcription factor-erythroid 2 related factor (Nrf2) and heme-oxygenase-1 (HO-1) proteins was examined using specific antibodies on HCT116 cells. Sinigrin (SIN) was the abundant GLs of the six compounds identified and its content together with total aliphatic GLs increased in saline conditions. Fluorescent (FL) and blue plus red (B1R1) lights were identified as stable cultivation conditions for microgreens, promoting biomass and glucobrassicin contents, whereas other identified individual and total indole GLs behaved differently in saline and non-saline environments. Blue light-emitting diodes and FL light in saline treatments mostly enhanced SIN, phenolics and antioxidant activities. The increased SOD and CAT activities render the BC microgreens suitable for lowering oxidative stress. Additionally, activation of Nrf2, and HO-1 protein expression by the GLs rich extracts, demonstrate their potential to treat and prevent oxidative stress and inflammatory disorders. Therefore, effective salt treatments and light exposure to BC microgreens present an opportunity for targeted regulation of growth and accumulation of bioactive metabolites.

Lactuca indica L. has been traditionally used as a wild vegetable and as a medicinal plant for centuries. The various compounds present in it and their biological activities have been extensively reported. Hairy-root culture combined with agrobacterium-meditated metabolic engineering is a useful technique to achieve stable production of biologically active plant compounds. Here, we evaluated the enhancement of secondary metabolites in L. indica L. and their bioactivities by testing culture media composition and the use of an elicitor. Hairy roots were induced and cultured in MS or SH liquid media for 2 weeks prior to treatment with various concentrations of MeJa, for different periods. The resulting phenolic contents and physiological activities were analyzed. Higher total phenolic, flavonoid, and hydroxycinnamic acids contents were attained by elicitation with MeJa. Metabolite accumulation, especially in SH media and in the presence of MeJa, was time dependent. Particularly, accumulation of chicoric acid increased markedly with time. Similarly, we observed time dependent positive and negative responses of antioxidant activity in DPPH and ABTS assays, respectively. As in previous studies, the highest correlation was found between total phenolic content and total flavonoid content. Further, 3,5-DCQA showed the highest correlation with total phenolic content, total flavonoid content, and antioxidant activities in hydroxycinnamic acids. Our data effectively identified optimal culture conditions to increase the accumulation of secondary metabolites and antioxidant activity in hairy roots cultures of L. indica L.

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.