Metabolomics reveals amino acids contribute to variation in response to simvastatin treatment

Abstract

Statins are widely prescribed for reducing LDL-cholesterol (C) and risk for cardiovascular disease (CVD), but there is considerable variation in therapeutic response. We used a gas chromatography-time-of-flight mass-spectrometry-based metabolomics platform to evaluate global effects of simvastatin on intermediary metabolism. Analyses were conducted in 148 participants in the Cholesterol and Pharmacogenetics study who were profiled pre and six weeks post treatment with 40 mg/day simvastatin: 100 randomly selected from the full range of the LDL-C response distribution and 24 each from the top and bottom 10% of this distribution ("good" and "poor" responders, respectively). The metabolic signature of drug exposure in the full range of responders included essential amino acids, lauric acid (p<0.0055, q<0.055), and alpha-tocopherol (p<0.0003, q<0.017). Using the HumanCyc database and pathway enrichment analysis, we observed that the metabolites of drug exposure were enriched for the pathway class amino acid degradation (p<0.0032). Metabolites whose change correlated with LDL-C lowering response to simvastatin in the full range responders included cystine, urea cycle intermediates, and the dibasic amino acids ornithine, citrulline and lysine. These dibasic amino acids share plasma membrane transporters with arginine, the rate-limiting substrate for nitric oxide synthase (NOS), a critical mediator of cardiovascular health. Baseline metabolic profiles of the good and poor responders were analyzed by orthogonal partial least square discriminant analysis so as to determine the metabolites that best separated the two response groups and could be predictive of LDL-C response. Among these were xanthine, 2-hydroxyvaleric acid, succinic acid, stearic acid, and fructose. Together, the findings from this study indicate that clusters of metabolites involved in multiple pathways not directly connected with cholesterol metabolism may play a role in modulating the response to simvastatin treatment.

Trial registration: ClinicalTrials.gov NCT00451828.

Figure 1. Correlation matrix of metabolites altered by simvastatin in full range participants.

Correlations among metabolites in Table 1 were obtained by deriving a Spearman’s correlation coefficient between each pair of metabolites. The color scheme corresponds to correlation strength as shown by the color bar. Red: Better response, more reduction of the metabolite. Blue: Better response, less reduction or increase of the metabolite. The metabolites have been rescaled (divided by the largest absolute value of them) to be clearer on the map. Abbreviations: NIST, National Institute of Standards and Technology.

Figure 2. Correlation matrix illustrating two clusters of compounds correlated with simvastatin response in full range participants.

The two clusters were identified in a clustering analysis for the change of all metabolites (results not shown) according to their pairwise correlations using the MMC algorithm [14]). Correlations of metabolites to drug response in LDLC were given in the first row and column, and are rescaled (divided by the largest absolute value of them) to be clearer in the map. The color scheme corresponds to correlation strength as shown by the color bar. Red: Better response, more reduction of the metabolite. Blue: Better response, less reduction or increase of the metabolite. Abbreviations: LDLC, Low-Density Lipoprotein Cholesterol; NIST, National Institute of Standards and Technology.

Figure 3. OPLSDA of baseline metabolites classifies good and poor responders.

(A) Orthogonal partial least square discriminant analysis was used to classify good and poor responders based on log-transformed baseline concentration of metabolites (R² = 0.87, Q² = 0.31). Good responders are shown in black and poor responders in red. Baseline metabolites were log-transformed and normalized (described in methods). Performance evaluation by 7-fold cross validation yielded the following statistics: prediction accuracy: 74%; sensitivity: 70%; specificity: 79% (not shown). (B) ROC curve of true positive rate (x-axis) versus false positive rate (y-axis) yields an area under the curve (AUC) of 0.84. (C) Baseline metabolites ranked by importance in classifying good and poor responders in the OPLS model. *indicates a partially identified compound: pentonic acid is an aldonic acid with five carbons and hexaric acid is an aldonic acid with six carbons. Abbreviations: VIP, variable importance score; cvSE, standard error derived from cross validation.