The Combination of Untargeted Metabolomics and Machine Learning Predicts the Biosynthesis of Phenolic Compounds in Medicinal Plants (Genus ).

Phenolic compounds constitute an important family of natural bioactive compounds responsible for the medicinal properties attributed to plants (genus , Crassulaceae), but their production by these medicinal plants has not been characterized to date. In this work, a combinatorial approach including plant tissue culture, untargeted metabolomics, and machine learning is proposed to unravel the critical factors behind the biosynthesis of phenolic compounds in these species. The untargeted metabolomics revealed 485 annotated compounds that were produced by three species cultured in vitro in a genotype and organ-dependent manner. Neurofuzzy logic (NFL) predictive models assessed the significant influence of genotypes and organs and identified the key nutrients from culture media formulations involved in phenolic compound biosynthesis. Sulfate played a critical role in tyrosol and lignan biosynthesis, copper in phenolic acid biosynthesis, calcium in stilbene biosynthesis, and magnesium in flavanol biosynthesis. Flavonol and anthocyanin biosynthesis was not significantly affected by mineral components. As a result, a predictive biosynthetic model for all the genotypes was proposed. The combination of untargeted metabolomics with machine learning provided a robust approach to achieve the phytochemical characterization of the previously unexplored species belonging to the subgenus, facilitating their biotechnological exploitation as a promising source of bioactive compounds.