Effect of Genotype and Environment on Salvia miltiorrhiza Roots Using LC/MS-Based Metabolomics

Abstract

Salvia miltiorrhiza (S. miltiorrhiza) Bunge is broadly used as herbal medicine for the clinical treatments of cardiovascular and cerebrovascular diseases. Despite its commercial and medicinal values, few systematic studies on the metabolome of S. miltiorrhiza roots have been carried out so far. We systematically described the metabolic profiles of S. miltiorrhiza using high pressure liquid chromatography mass spectrometry (LC/MS) in conjunction with multivariate statistical analyses, aimed at monitoring their biological variations of secondary metabolites related to three locations and four S. miltiorrhiza genotypes. A total of 40 bioactive constituents were putatively annotated in S. miltiorrhiza root samples. This study found that both the same S. miltiorrhiza genotype growing at three different locations and four S. miltiorrhiza genotypes growing at the same location had significant metabonomic differences identified by the principal component analysis (PCA) approach. By using orthogonal projection to latent structure with discriminant analysis (OPLS-DA), 16 and 14 secondary metabolites can be used as potential location-specific and genotype-specific markers in S. miltiorrhiza, respectively. The specificity of LC/MS profiles offered a powerful tool to discriminate S. miltiorrhiza samples according to genotypes or locations.

Keywords: LC-MS; Salvia miltiorrhiza Bunge; metabolite profiling; multivariate analysis; secondary metabolites.

Figure 1

PCA scores plots and loading plot derived from LC-MS data for S. miltiorrhiza extracts from three different locations (A, Zhuyang; B, Changqing; C, Taian) for each genotype ((a) Genotype 1; (b) Genotype 2; (c) Genotype 3; and (d) Genotype 4). Sixteen red colored metabolites in loading plot were the location-specific metabolites that we obtained from OPLS-DA: 7, Salvianolic acid F; 13, Salvianolic acid I; 14, Salvianolic acid E; 15, Rosmarinic acid; 17, Lithospermic acid; 18, Prolithospermic acid derivative; 20, Salvianolic acid B; 32, Tanshinone IIB; 36, Trijuganone C; 44, 15,16′-dihydrotanshinone I; 47, Methyltanshinonate; 48, Trijuganone B; 52, Cryptotanshinone; 53, Tanshinone I; 55, 1,2′-dihydrotanshinone I; and 60, Tanshinone IIA.

Figure 2

OPLS-DA scores plots (left) and coefficient-coded loadings plots (right) deriver from LC-MS data for S. miltiorrhiza extracts obtained from three different locations (ZY, Zhuyang; CQ, Changqing; TA, Taian) for each genotype ((a) Genotype 1; (b) Genotype 2; (c) Genotype 3; and (d) Genotype 4): 7, Salvianolic acid F; 13, Salvianolic acid I; 14, Salvianolic acid E; 15, Rosmarinic acid; 17, Lithospermic acid; 18, Prolithospermic acid derivative; 20, Salvianolic acid B; 32, Tanshinone IIB; 36, Trijuganone C; 44, 15,16′-dihydrotanshinone I; 47, Methyltanshinonate; 48, Trijuganone B; 52, Cryptotanshinone; 53, Tanshinone I; 55, 1,2′-dihydrotanshinone I; and 60, Tanshinone IIA.

Figure 2

OPLS-DA scores plots (left) and coefficient-coded loadings plots (right) deriver from LC-MS data for S. miltiorrhiza extracts obtained from three different locations (ZY, Zhuyang; CQ, Changqing; TA, Taian) for each genotype ((a) Genotype 1; (b) Genotype 2; (c) Genotype 3; and (d) Genotype 4): 7, Salvianolic acid F; 13, Salvianolic acid I; 14, Salvianolic acid E; 15, Rosmarinic acid; 17, Lithospermic acid; 18, Prolithospermic acid derivative; 20, Salvianolic acid B; 32, Tanshinone IIB; 36, Trijuganone C; 44, 15,16′-dihydrotanshinone I; 47, Methyltanshinonate; 48, Trijuganone B; 52, Cryptotanshinone; 53, Tanshinone I; 55, 1,2′-dihydrotanshinone I; and 60, Tanshinone IIA.

Figure 3

Absolute quantification of eight selected metabolites. Concentrations are given in g/kg DW. Data are shown as mean of concentration ± SD. Values between three locations having different lowercase letters (a, b, and c) are significantly different at p < 0.001/3 (Bonferroni correction).

Figure 4

PCA scores plots and loading plots derived from LC-MS data for S. miltiorrhiza extracts from four different genotypes (1, Genotype 1; 2, Genotype 2; 3, Genotype 3; and 4, Genotype 4) for each location ((a) Zhuyang; (b) Changqing; and (c) Taian). 14 red colored metabolites in loading plots were the genotype-specific metabolites which we obtained from OPLS-DA: 2, Procatechuic acid; 7, Salvianolic acid F; 13, Salvianolic acid I; 14, Salvianolic acid E; 15, Rosmarinic acid; 17, Lithospermic acid; 18, Prolithospermic acid derivative; 20, Salvianolic acid B; 30, 7α-hydroxyallyl-royleanone; 32, Tanshinone IIB; 44, 15,16′-dihydrotanshinone I; 47, Methyltanshinonate; 55, 1,2′-dihydrotanshinone I; and 60, Tanshinone IIA.