Circadian alignment of early onset caloric restriction promotes longevity in male C57BL/6J mice

Abstract

Caloric restriction (CR) prolongs life span, yet the mechanisms by which it does so remain poorly understood. Under CR, mice self-impose chronic cycles of 2-hour feeding and 22-hour fasting, raising the question of if it is calories, fasting, or time of day that is the cause of this increased life span. We show here that 30% CR was sufficient to extend the life span by 10%; however, a daily fasting interval and circadian alignment of feeding acted together to extend life span by 35% in male C57BL/6J mice. These effects were independent of body weight. Aging induced widespread increases in gene expression associated with inflammation and decreases in the expression of genes encoding components of metabolic pathways in liver from ad libitum-fed mice. CR at night ameliorated these aging-related changes. Our results show that circadian interventions promote longevity and provide a perspective to further explore mechanisms of aging.

Fig. 1.. Effects of CR on body weight, circadian behavior and feeding in C57BL/6J male mice.

(A) Experimental design showing feeding conditions for each of the six groups. (B) Average body weights (± SE) of mice in all 6 groups (n = 43 for AL and n = 36 for each of the CR) taken every 3 weeks throughout the experiment. (C) Examples of double-plotted actograms from each experimental group overlaying wheel-running (black histograms) and feeding (red dots) behaviors. All mice were on ad lib feeding for the first six weeks (period above the line on the right of the actograms) before the CR began. (D-E) 24h profile of the wheel-running activity (D) and food intake (E) at different ages (averaged over 21 days, n=36–43 mice) for each group. (F) Energy intake per day (left axis) and number of food pellets per day (right axis) for each group throughout the experiment. For AL group, dark line is average, gray shading is SE. All CR groups were limited to 70% of ad lib consumption for the first 200 days of age and was not adjusted after 200 days so no variation is observed. (G) Daily wheel-running activity (average counts/min over 24 hours ± SE) throughout the experiment.

Fig. 2.. Extent of CR-mediated increases in longevity depend on feeding time.

(A) Survival curves for each group (n = 43 for AL and n = 36 for each of the CR) are shown in left panel with median lifespan (days) inset. Right panel summarizes the results, showing the increase in lifespan from timed feeding with the largest increase when food is restricted to night. (B) Correlation plots comparing lifespan (days) for each mouse with its daily averaged total activity (counts/min) at different ages. Increased activity significantly correlates with longer lifespan in older (but not young) mice in all groups (see asterisks, Spearman correlation). (C) Necropsy followed by histopathology results showing pathologies and diseases (left) and tissues mostly affected (right) at time of death for each feeding condition.

Fig. 3.. Gene expression signatures in liver change during aging in AL mice.

(A) Principal component analysis of gene expression from liver mRNA-seq. mRNA-seq data is from 48 mice for each feeding condition (24 from 6 months of age, 24 from 19 months of age), with livers collected every 4 hours over 48 hours while mice were in constant dark. Circles indicate young AL mice (solid line) cluster together while triangle aged AL mice (dashed line) are in a distinct cluster. Liver gene expression data among CR groups cluster together independently of age. (B) Volcano plot showing differential gene expression in young vs. aged AL mice. Red denotes genes whose expression is significantly increased in aged AL mice; blue denotes genes that are significantly decreased in old AL mice. The number of mRNAs in each category are shown in the right panel. (C) Gene ontology terms of genes that are increased in aged AL mice (top) and examples of gene expression (below; gray = young AL, red = aged AL). (D) Gene ontology terms of genes that are decreased in aged AL mice (top) and examples of gene expression (below; gray = young AL, blue = aged AL).

Fig. 4.. CR ameliorates age-related changes in liver gene expression observed under AL.

(A) Schematic comparison of differential gene expression between young and old mice in the six feeding conditions. Circles show the percentage of genes that are unchanged between young and aged mice (gray), increased in aged mice (red) and decreased in aged mice (blue). Pie chart on the right shows the percentage of genes susceptible for age-related changes in any feeding condition. (B) Spearman correlation plots comparing changes in gene expression between the Aging DE genes between AL and CR groups. (Aging DE genes are defined here as the 4077 genes that change with age in any of the 6 feeding conditions tested). (C) Schematic representation of genes that are protected from age-related changes in every CR group (left) with gene ontology terms of those significantly upregulated (middle) or downregulated (right) in aged AL mice. Represented are 10 nonredundant of the top 25 most significant enriched terms. Examples of age-related fold changes (log2FC ± SE) in gene expression are shown below for all feeding conditions. Grey-shaded areas indicate FC < 1.5 considered as not significant change. Schematic representation, gene ontology and representative genes that maintain similar levels between young and old ages due to (D) fasting (day or night) and (E) circadian alignment of feeding and fasting cycles.

Fig. 5.. Circadian rhythms in liver gene expression are blunted during aging in AL mice.

(A) Gene expression patterns from mRNA-seq were analyzed for circadian rhythms using ARSER, JTK_CYCLE (from Metacycle R Package) and RAIN circadian algorithms. Heatmaps (top) sorted by phase of gene expression. Each row is one gene with expression level in z-score at 12 time points (columns). Venn Diagram (bottom) shows the number of rhythmic genes in young (gray) and aged (red) AL livers using stringent criteria (significantly cycling according to three algorithms BH, p and q < 0.05 and Log₂FC > 0.3) to define rhythmicity. (B) Examples of circadian profiles of genes that are rhythmic in both young and aged AL livers (black = young, red = aged). (C) Comparison of phase (left, hours) and amplitude (right, daily fold-change) of the 694 genes that were rhythmic in both age groups. The red correlation line (Spearman) and linear regression (slope is statistically different from 1, p < 2e-16) in the fold change comparison indicates that aged animals showed overall reduced amplitude of rhythmic genes. (D-E) Gene ontology terms of genes that are cycling in either (D) young or (E) aged AL mice. Represented are 10 nonredundant of the top 25 most significant enriched terms.

Fig. 6.. Effects of caloric restriction and phase of feeding on circadian gene expression.

(A) Gene expression patterns from mRNA-seq were analyzed for circadian rhythms using ARSER, JTK_CYCLE (from Metacycle R Package) and RAIN circadian algorithms. Heatmaps sorted by phase of gene expression. Each row is one gene with expression level in z-score at 12 time points (columns). (B) Examples of the circadian profiles of the same genes shown in Fig. 5B, but comparing profiles from CR-night-2h (blue) to CR-day-2h (yellow) aged mice. (C) Comparison of circadian amplitude (daily fold-change) of 1491 rhythmic genes from young (left) and aged (right) CR groups. Top panels show amplitude density plots (median amplitude values are inset). Bottom panels are correlation plots comparing amplitude of genes from CR-night-2h to CR-day-2h in young (left) and aged (right) mice. The linear regression lines have slopes that are significantly less than 1 (p < 2e-16). (D) Phase correlation plots of rhythmic genes from young (left) and old (right) CR-night-2h-fed (blue) and CR-day-2h-fed (yellow) mice vs. AL fed mice from same ages. Phase is represented in hours. Numbers of shared cycling genes between each CR condition and AL are labeled on top of the correlation plot.