Strategy for Screening of Antioxidant Compounds from Two Ulmaceae Species Based on Liquid Chromatography-Mass Spectrometry

Abstract

Liquid chromatography-mass spectrometry (LC-MS)-based untargeted metabolomics implies that annotated metabolites can serve as potential markers of the associated bioactivities of plant extracts. Firstly, we selected Aphananthe aspera and Zelkova serrata (Family: Ulmaceae) from 16 Korean plant species based on their distinct principal component analysis (PCA) patterns in LC-MS datasets and antioxidant activity assays. Further, we chose 40% solid-phase extraction (SPE) extracts of the two species displaying the highest antioxidant activities coupled with distinct PCA patterns. Examining the metabolite compositions of the 40% SPE extracts, we observed relatively higher abundances of quercetin, kaempferol, and isorhamnetin O-glucosides for A. aspera, whereas quercetin, isorhamnetin O-glucuronides, and procyanidin dimer were relatively higher in Z. serrata. These metabolites were clearly distinguished in pathway map and displayed strong positive correlations with antioxidant activity. Further, we performed preparative high-performance liquid chromatography (prep-HPLC) analysis coupled with the 2,2'-azino-bis (3-ethylbenzothiazoline-6-sulfonic acid) assay to validate their functional correlations. As a result, quercetin O-sophoroside was determined as the main antioxidant in A. aspera, while isorhamnetin O-glucuronide and procyanidin dimer were the primary antioxidants in Z. serrata. The current study suggests that the LC-MS-based untargeted metabolomics strategy can be used to illuminate subtle metabolic disparities as well as compounds associated with bioactivities.

Keywords: Aphananthe aspera; LC-MS; Zelkova serrata; antioxidant activity; metabolite profiling; preparative HPLC combination.

Figure 1

Principal component analysis (PCA) score plot (A) and (C) from UHPLC-LTQ-IT-MS/MS; antioxidant activity assays using ABTS, DPPH radical scavenging, FRAP, TFC, and TPC assays (B) and (D) derived from stepwise SPE extracts of A. aspera (unfilled column) and Z. serrata (filled column): red column 20% SPE extract, black column 40% SPE extract, orange column 60% SPE extract, blue column 80% SPE extract, and violet column 100% SPE extract.

Figure 2

Multivariate statistical analysis of LC-MS datasets for 40% methanol SPE extracts of A. aspera (unfilled triangles) and Z. serrata (filled triangles): (A) OPLS-DA score plot, with VIP >1.0 and p-value <0.05 marked; (B) loading S-plot based on OPLS-DA. Numbers labeling each sample′s discriminant metabolites on the plot correspond to entries in Table 1.

Figure 3

Discriminant metabolic pathway. The unfilled and filled columns represent the relative abundance of discriminant metabolites between A. aspera and Z. serrata. The scheme of the pathway is derived from the KEGG database (KEGG, http://www.genome.jp/kegg). The Y-axis of the graph indicates peak areas at logarithmic scale. The data are presented as the mean ± standard deviation. Differences were considered significant at p-value < 0.05. The metabolite numbers in parentheses are those presented in Table 1. * The discriminant metabolites in A. aspera are indicated with red font ** and those in Z. serrata are indicated with blue font.

Figure 4

Visualization of the correlation networks between the identified secondary metabolites and ABTS radical scavenging activity assay of A. aspera (A) and Z. serrata (B) according to Pearson′s correlation coefficient. Correlation coefficients higher than 0.80 or lower than −0.80 with p-value < 0.05 are extracted and shown in these association networks. Each node indicates an identified metabolite and corresponding ABTS assay. Yellow node = antioxidant activity assay, Pink node = positively correlated metabolite, Blue node = negatively correlated metabolite. The sizes of the nodes represent the degrees of association. The numbers on the metabolites are those indicated in Table 1.

Figure 5

Preparative HPLC profiles, ABTS radical scavenging assay of A. aspera (unfilled columns) and Z. serrata (filled columns) extracts: (A) A. aspera preparative HPLC fractions at 300 nm; (B) Z. serrata preparative HPLC fractions at 300 nm, Data are shown as mean ± standard deviation; The number of the fractions indicate to Table 1 suggested metabolite number. * Selected fraction, which is contributed to relative potent antioxidant activity.

Figure 6

The structures of compounds selected in prep-HPLC fractions from A. aspera and Z. serrata extracts with potent antioxidant activities. * Main antioxidant compound in A. aspera; ** Main antioxidant compounds in Z. serrata. The number of the fractions, indicated in Table 1, suggest the metabolite number.