Prediction of hypericin content in Hypericum perforatum L. in different ecological habitat using artificial neural networks

BACKGROUND

Hypericum is an important genus in the family Hypericaceae, which includes 484 species. This genus has been grown in temperate regions and used for treating wounds, eczema and burns. The aim of this study was to predict the content of hypericin in Hypericum perforatum in varied ecological and phenological conditions of habitat using artificial neural network techniques [MLP (Multi-Layer Perceptron), RBF (Radial Basis Function) and SVM (Support Vector Machine)].

RESULTS

According to the results, the MLP model (R² = 0.87) had an advantage over RBF (R² = 0.8) and SVM (R² = 0.54) models and it was relatively accurate in predicting hypericin content in H. perforatum based on the ecological conditions of site including soil types, its characteristics and plant phenological stages of habitat. The results of sensitivity analysis revealed that phenological stages, hill aspects, total nitrogen, altitude and organic carbon are the most influential factors that have an integral effect on the content of hypericin.

CONCLUSIONS

The designed graphical user interface will help pharmacognosist, manufacturers and producers of medicinal plants and so on to run the MLP model on new data to easily discover the content of hypericin in H. perforatum by entering ecological conditions of site, soil characteristics and plant phenological stages.

Targeted metabolomic profiling reveals interspecific variation in the genus Hypericum in response to biotic elicitors

Shoot cultures of eight Hypericum species belonging to the sections Hypericum, Oligostema, Ascyreia and Webbia were evaluated for their phytochemical profiles by high-performance liquid chromatography. In total, 17 secondary metabolites assigned to the groups of anthraquinones, phloroglucinols, hydroxycinnamic acids and flavonoids were detected. Furthermore, the elicitation potential of 18 biotic factors derived from saccharides, endophytic fungi and Agrobacterium rhizogenes was examined and statistically analysed with the paired two-sample t-test and principal component analysis. The production of naphthodianthrones and emodin was predominantly stimulated by elicitors derived from Fusarium oxysporum and Trichoderma crassum, while Piriformospora indica promoted the phloroglucinols production. Among flavonoids, the aglycone amentoflavone was readily increased by several elicitors up to 15.7-fold in H. humifusum treated by potato-dextrose broth. However, the chlorogenic acid proved to be the most susceptible metabolite to elicitation, when 31.7-times increase was detected in H. maculatum shoots upon D-glucose treatment. In spite of several biotic factors have been tested, no metabolite was commonly induced in all Hypericum spp. as a response to elicitor treatments.