Identification of tissue-specific transcriptional markers of caloric restriction in the mouse and their use to evaluate caloric restriction mimetics

Abstract

Caloric restriction (CR) without malnutrition has been shown to retard several aspects of the aging process and to extend lifespan in different species. There is strong interest in the identification of CR mimetics (CRMs), compounds that mimic the beneficial effects of CR on lifespan and healthspan without restriction of energy intake. Identification of CRMs in mammals is currently inefficient due to the lack of screening tools. We have performed whole-genome transcriptional profiling of CR in seven mouse strains (C3H/HeJ, CBA/J, DBA/2J, B6C3F1/J, 129S1/SvImJ, C57BL/6J, and BALB/cJ) in white adipose tissue (WAT), gastrocnemius muscle, heart, and brain neocortex. This analysis has identified tissue-specific panels of genes that change in expression in multiple mouse strains with CR. We validated a subset of genes with qPCR and used these to evaluate the potential CRMs bezafibrate, pioglitazone, metformin, resveratrol, quercetin, 2,4-dinitrophenol, and L-carnitine when fed to C57BL/6J 2-month-old mice for 3 months. Compounds were also evaluated for their ability to modulate previously characterized biomarkers of CR, including mitochondrial enzymes citrate synthase and SIRT3, plasma inflammatory cytokines TNF-α and IFN-γ, glycated hemoglobin (HbA1c) levels and adipocyte size. Pioglitazone, a PPAR-γ agonist, and L-carnitine, an amino acid involved in lipid metabolism, displayed the strongest effects on both the novel transcriptional markers of CR and the additional CR biomarkers tested. Our findings provide panels of tissue-specific transcriptional markers of CR that can be used to identify novel CRMs, and also represent the first comparative molecular analysis of several potential CRMs in multiple tissues in mammals.

Keywords: aging; biomarkers; caloric restriction; gene expression; mouse.

Figure 1

Graphical summary of gene‐set enrichment analysis of genes altered in expression in WAT in response to CR. The ‘waterfall plot’ was constructed by finding the significant (Bonferroni‐corrected P‐value < 0.05, Z score larger than 4.34) GO term having the largest overlap with the list of genes significantly changed with CR in multiple strains (mitochondrial part GO:0044429, 71 genes) and placing it in the top row of the figure. We next removed these genes from the list and found the significant GO term having the highest overlap with the remainder of the list (organophosphate metabolic process GO:0019637, 58 genes). The process was repeated as long as new significant GO gene sets described as‐yet‐undescribed genes in the list. Genes identified by this sequential process are counted along the x‐axis, and the overlap between the GO terms can be visually assessed. Shading under the ‘waterfall’ component of the graph indicates genes that were also annotated to previously named categories. The sequential coverage calculation identifies a dominant set of significant GO terms. For a full list of significant gene sets and associated z scores in adipose tissue, see Data S1: Table SS4 (Supporting information).

Figure 2

Change in body weight (22 vs. 8 weeks of age) in response to interventions. Relative to control mice, CR was the only intervention to significantly reduce body weight. Data represent means with standard error of the mean. *P < 0.05.

Figure 3

Change in adipocyte size in response to interventions. CR, PIOG, and LCARN reduced adipocyte size (A), and representative micrographs for these interventions are shown in (B). Data represent means with standard error of the mean. *P < 0.05. n = 5–6 per group.

Figure 4

Effect of interventions on mitochondrial parameters. CR increased WAT citrate synthase activity (A) and increased the abundance of SIRT3 protein in liver (B). Only PIOG significantly mimicked the effect of CR, increasing citrate synthase activity. BEZA, PIOG, and LCARN all reduced levels of SIRT3 compared to control diet‐fed animals. Representative staining for SIRT3 (n = 2 samples per group) is shown in (C), along with molecular weight standards as well as a negative control from SIRT3 knockout mice (KO). Data represent means with standard error of the mean. *P < 0.05.

Figure 5

Effect of interventions on circulating biomarkers of CR. Glycated hemoglobin in whole blood (A), plasma interferon gamma (B), and plasma tumor necrosis factor α (C) were all significantly reduced by CR. Interferon gamma was also decreased by 24DNP, METF, PIOG, QUER, and RESV; however, PIOG significantly increased plasma tumor necrosis factor α. Data represent means with standard error of the mean, n = 10 mice per group; *P < 0.05.