Metformin induces a dietary restriction-like state and the oxidative stress response to extend C. elegans Healthspan via AMPK, LKB1, and SKN-1

Abstract

Metformin, a biguanide drug commonly used to treat type-2 diabetes, has been noted to extend healthspan of nondiabetic mice, but this outcome, and the molecular mechanisms that underlie it, have received relatively little experimental attention. To develop a genetic model for study of biguanide effects on healthspan, we investigated metformin impact on aging Caenorhabditis elegans. We found that metformin increases nematode healthspan, slowing lipofuscin accumulation, extending median lifespan, and prolonging youthful locomotory ability in a dose-dependent manner. Genetic data suggest that metformin acts through a mechanism similar to that operative in eating-impaired dietary restriction (DR) mutants, but independent of the insulin signaling pathway. Energy sensor AMPK and AMPK-activating kinase LKB1, which are activated in mammals by metformin treatment, are essential for health benefits in C. elegans, suggesting that metformin engages a metabolic loop conserved across phyla. We also show that the conserved oxidative stress-responsive transcription factor SKN-1/Nrf2 is essential for metformin healthspan benefits in C. elegans, a mechanistic requirement not previously described in mammals. skn-1, which functions in nematode sensory neurons to promote DR longevity benefits and in intestines for oxidative stress resistance lifespan benefits, must be expressed in both neurons and intestines for metformin-promoted healthspan extension, supporting that metformin improves healthy middle-life aging by activating both DR and antioxidant defense longevity pathways. In addition to defining molecular players operative in metformin healthspan benefits, our data suggest that metformin may be a plausible pharmacological intervention to promote healthy human aging.

Figure 1. Metformin increases healthspan without a requirement for function of the insulin signaling pathway.

A. Survival curves of wild-type (N2) animals raised at 20°C on nematode growth media plates containing either no metformin or final concentrations of 1 mM, 10 mM, or 50 mM metformin. (Note that C. elegans has a highly protective cuticle and intestinal lining that generally limit drug uptake such that it is not unusual for polar drugs to be applied at a concentration 1000 fold higher than their predicted affinity for the target , ; physiological levels of drug in the animals are anticipated to be much lower). For the trial presented here, median survival for animals on 0 mM, 1 mM, 10 mM, and 50 mM metformin plates was 15, 15, 17, and 21 days, respectively. The survival curves of the nematodes raised on 0 mM, 1 mM, and 10 mM metformin plates are not significantly different, while the survival curve for animals raised on 50 mM metformin is significantly different than the 0 mM metformin control (P<0.0001 by the Log-rank (Mantel-Cox) test; benefits are lost at 100 mM metformin, data not shown). The pooled data for all trials show an approximately 27% increase in median lifespan with 50 mM metformin treatment and a significantly right-shifted survival curve (P<0.0001 by the Log-rank test), see Table S1A. All studies documented here involved life-long metformin exposure, but a preliminary trial in which metformin was introduced at the last larval stage suggests that treatment in adult life is sufficient to confer some lifespan benefit (data not shown). B. Swimming rates for wild-type animals raised from eggs on plates (time 0) containing either no metformin or 50 mM metformin at 20°C. We recorded the number of body bends/30 seconds for individual animals placed in liquid media at early adulthood (5 days), mid-life (10 days), and late life (15 days). We present the averages of three independent trials. Metformin-treated animals swim at similar rates in young adulthood, supporting that metformin does not induce hyperactive swimming or confer developmental defects, but the swimming rates of animals raised on 50 mM metformin are significantly higher than those of the control group on days 10 and 15 (P = 0.0058 and P = 0.0346, respectively, by unpaired t tests), indicating extended mid-life and late-life locomotory ability consequent to metformin treatment. C. Survival curves of null mutant daf-16(mgDf50) raised on 0 mM and 50 mM metformin plates at 20°C. The median survival is 11 and 15 days for animals raised on 0 mM and 50 mM metformin, respectively, and the survival curves of the two groups are significantly different (P = 0.0111 by the Log-rank test). 1 mM and 10 mM metformin do not significantly change the survival curves of daf-16(mgDf50) animals (data not shown). We performed this experiment a total of four times with similar results (pooled data show a 15% median lifespan increase and a significantly right-shifted survival curve (P<0.0001, Log-rank) for animals treated with 50 mM metformin, see Table S1B for additional data). D. Survival curves of age-1(hx546) mutants raised on 0 mM and 50 mM metformin plates at 20°C. Median survival for animals on 0 mM and 50 mM metformin is 24 and 31 days, respectively, and the survival curves are significantly different by the Log-rank test (P = 0.0014). We found similar median survival extension in a single repeat of this experiment (pooled data for the two trials show an approximate 36% median lifespan increase and significantly different survival curves (P<0.0001, Log-rank), see Table S1C).

Figure 2. Metformin does not further increase the median lifespan of DR-constitutive mutant eat-2, and metformin treatment triggers several DR phenotypes in wild-type C. elegans without impairing feeding.

A. Survival curves of eat-2(ad1116) mutants raised on 0 mM, 1 mM, 10 mM, and 50 mM metformin plates at 20°C. The median survival is 23, 25, 19, and 19 days for 0 mM, 1 mM, 10 mM, and 50 mM metformin, respectively. The survival curves of the animals raised on 0 mM and 1 mM metformin are not significantly different, but survival of the 10 mM and 50 mM groups are significantly reduced compared to controls (P = 0.0050 and 0.0033, respectively, by the Log-rank test). We performed this experiment a total of four times, with two of the trials showing significantly different survival curves for the 10 mM and 50 mM groups. Pooled data show approximately 9% declines in median lifespan for 10 mM and 50 mM metformin treatment and significant shifts in survival curves (P = 0.0037 and 0.0114 for 10 mM and 50 mM metformin treatment, respectively, by the Log-rank test), see Table S1D. B. Age pigment fluorescence measurements in wild-type animals raised on 0 mM, 1 mM, 10 mM, and 50 mM metformin plates. We found that age pigment fluorescence decreases with increasing metformin concentration with the levels in the 50 mM group significantly lower than the controls (P = 0.0270 by an unpaired t test). Scores are the average age pigment fluorescence intensity levels of three independent trials. We also observed shifts in the excitation wavelength corresponding to peak age pigment fluorescence intensity in animals treated with 100 mM metformin (see Fig. S1). C. Progeny profiles of wild-type animals raised on 0 mM, 1 mM, 10 mM, and 50 mM metformin. We recorded the number of progeny produced by 60 individuals for each group for each day of egg-laying. We found no significant differences between the progeny profiles of the 0 mM, 1 mM, and 10 mM metformin groups. The 50 mM metformin-treated animals, however, exhibit delays in egg-laying, with significantly higher percentages of total progeny produced on days 3 and 4 compared to the controls (P = 0.0431 and 0.0084 for days 3 and 4, respectively, by an unpaired t test). The 50 mM group also shows lower levels of progeny production on days 1 and 2 compared to controls, with the levels on day 2 being significantly different (P = 0.0361 by an unpaired t test). Data shown represent the average of three independent trials. D. Quantitation of Nile Red staining of lipid deposits in wild-type animals raised on 0 mM, 1 mM, 10 mM, and 50 mM metformin. Fluorescence levels decrease with increasing metformin concentration, with significantly lower levels in the 10 mM and 50 mM metformin groups (P = 0.0400 and 0.0205 for 10 mM and 50 mM metformin, respectively, by an unpaired t test). Data represent the average of three independent experiments. Animals not stained with the Nile Red dye produced no detectable levels of fluorescence in this wavelength range (data not shown). E. Pharyngeal pumping rates of wild-type animals raised on 0 mM, 1 mM, 10 mM, and 50 mM metformin. We recorded pumping rates of 30 individuals for 30 seconds on day 4 of life, and the averages of three separate experiments are shown. Pharyngeal pumping did not differ significantly for any of the groups (P = 0.9231, 0.1689, and 0.9142 for 1 mM, 10 mM, and 50 mM metformin, respectively, by unpaired t tests).

Figure 3. Metformin extends median lifespan via an AMPK and LKB1-dependent mechanism.

A. Survival curves of AMPK catalytic subunit mutants aak-2(ok524) and aak-2(rr48) raised on metformin plates at 20°C for their entire lives. Median survival for aak-2(ok524) animals on 0 mM, 1 mM, 10 mM, and 50 mM metformin is 17, 17, 15, and 15 days, respectively, and there are no significant differences between any of the survival curves (Log-rank test). Median survival for aak-2(rr48) animals on 0 mM, 1 mM, 10 mM, and 50 mM is 13, 15, 15, and 15 days, respectively, and there are no significant differences between the survival curves. Pooled data from three independent trials for each aak-2 strain show approximately 11% declines with 10 mM and 50 mM metformin treatment in aak-2(ok524) animals, and approximately 6% and 19% declines with 10 mM and 50 mM metformin treatment, respectively, in aak-2(rr48) animals. Survival curves are significantly shifted to the left in aak-2(ok524) animals treated with 10 mM and 50 mM metformin (P = 0.0209 and <0.0001, respectively), and in aak-2(rr48) animals raised on 10 mM and 50 mM metformin (P = 0.0442 and 0.0004, respectively). See Table S1E for additional data. We conclude that AMPK activity is needed for median lifespan extension induced by metformin, and that metformin has detrimental lifespan effects in the absence of AMPK. B. Survival curves of temperature-sensitive lkb-1/par-4 mutants grown on 0 mM and 50 mM metformin plates, maintained at 15°C and shifted to 25°C at the L4 stage. C. elegans par-4 encodes an ortholog of mammalian LKB1, which has been shown to activate AMPK in both mammals and nematodes. Median survival is 9 days for the par-4(it47) mutants grown on both 0 mM and 50 mM metformin, and there is no significant difference between the survival curves by the Log-rank test. Similarly, par-4(it57) animals grown on both 0 mM and 50 mM metformin have a median survival of 11 days, and their survival curves are not significantly different by the Log-rank test. Pooled data from three independent trials using the par-4(it47) strain show no differences in median lifespan for 0 mM vs. 50 mM metformin-treated animals (9 days for both conditions), although the 50 mM metformin survival curve is significantly shifted to the left (P = 0.0500, Log-rank; Table S1F). Pooled data for four independent trials with the par-4(it57) mutants show a decrease in median lifespan (9 days for 50 mM metformin plates vs. 10 days for 0 mM metformin; Table S1F) and a significantly left-shifted survival curve for 50 mM metformin-treated animals (P = 0.0063, Log-rank; Table S1F). Thus, LKB1 is required for metformin to increase median lifespan, and, as is seen in the absence of AMPK, metformin has harmful effects when LKB1 is disrupted.

Figure 4. Metformin requires transcription factor SKN-1 to increase median lifespan, via a mechanism that acts in both ASI neurons and the intestine.

A. Survival curves of skn-1(zu135) mutants raised on 0 mM and 50 mM metformin plates at 20°C. The median survival of animals raised on both 0 mM and 50 mM metformin plates is 9 days, and the survival curves are not significantly different. Pooled data from a total of two experiments show no change in median lifespan or survival curves (see Table S1G). We conclude that skn-1 is required for metformin's effect on median lifespan. B. SKN-1 localization in L4-stage wild-type animals expressing SKN-1::GFP grown on 0 mM and 50 mM metformin plates at 20°C. SKN-1 is present constitutively in the nuclei of ASI neurons where it mediates the increased longevity response under dietary restriction. Under oxidative stress and with reduced insulin signaling, SKN-1 accumulates in intestinal nuclei leading to SKN-1 target gene expression , , . Whereas SKN-1::GFP is not apparent in intestinal nuclei of animals raised on 0 mM metformin plates (top panel), SKN-1::GFP accumulates in intestinal nuclei (arrowheads, bottom panel) of animals exposed to 50 mM metformin. C. Survival curves of skn-1(zu135) animals expressing skn-1 isoforms from either the native skn-1 promoter (Is007[skn-1::gfp]), an ASI neuron-specific promoter (geIs9[gpa4p::skn-1b::gfp]), or an intestine-specific promoter (geIs10[ges-1p::skn-1c::gfp]), and raised on 0 mM or 50 mM metformin plates at 20°C. While expressing skn-1::gfp from the native skn-1 promoter rescues the inability of metformin to increase the lifespan of skn-1(zu135) mutants (see A) (median lifespan of skn-1(zu135); Is007[skn-1::gfp] animals raised on 0 mM or 50 mM metformin is 13 and 20 days, respectively, and metformin treatment shifts the survival curve or these animals significantly to the right, P = 0.0008 by the Log-rank test), expressing skn-1 only in the ASI neurons or only in the intestine does not. In fact, metformin has significantly detrimental effects in skn-1(zu135) mutants that express skn-1::gfp only in the ASI neurons (mean lifespan for these animals raised on 0 mM or 50 mM metformin is 18 and 13 days, respectively, and the surivival curve with metformin treatment is shifted significantly to the left, P<0.0001 by the Log-rank test). We performed each of these lifespan assays a total of three times with similar results, see Table S1G. Pooled data for skn-1(zu135) animals expressing skn-1::gfp from the native skn-1 promoter show a median lifespan increase from 16 days for animals on 0 mM metformin to 20 days for animals on 50 mM metformin (a 25% increase), with a significantly right-shifted survival curve (P<0.0001 by the Log-rank test, Table S1G). Pooled data for skn-1(zu135) mutants expressing skn-1::gfp only in the ASI neurons show a median lifespan decrease from 16 days for animals on 0 mM metformin to 13 days for animals on 50 mM metformin, with a significantly left-shifted survival curve (P<0.0001 by the Log-rank test, Table S1G). Note that in these experiments we cannot rule out that the tissue-specific expression of skn-1 driven by heterologous promoters provides the normally appropriate level of expression, and thus the negative effects in ASI and intestine must be evaluated with cautious attention to this caveat. D. Quantification of SKN-1::GFP nuclear localization. Wild-type animals expressing SKN-1::GFP display significantly higher incidences of SKN-1::GFP accumulation in intestinal nuclei vs. controls when exposed to 50 mM metformin (P<0.0001 by the Chi-square test). Strikingly, AMPK is required for this effect: 50 mM metformin does not induce nuclear SKN-1::GFP accumulation in the aak-2(ok524) mutant background. “Low” indicates very little or no SKN-1::GFP localization to intestinal nuclei; “Medium” indicates strong SKN-1::GFP localization to nuclei in the anterior and/or posterior of the intestine; “High” indicates strong SKN-1::GFP accumulation in nuclei throughout the intestine. Although 10 mM NaN₃ did not trigger SKN-1::GFP nuclear localization on its own, we note that NaN₃ is an oxidative stressor that has been shown to induce nuclear SKN-1::GFP accumulation at high concentrations . To confirm that 50 mM metformin can induce SKN-1::GFP nuclear accumulation in the absence of NaN₃, we performed these experiments with N2 Is007[skn-1::gfp;rol-6dm] animals raised from eggs on 0 mM and 50 mM metformin and observed in liquid M9 media. We again found that 50 mM metformin significantly increases SKN-1::GFP nuclear accumulation under these conditions (Fig. S3A).

Figure 5. Summary model of metformin action on C. elegans healthspan.

Metformin activates SKN-1 to trigger DR-like metabolism and intestinal anti-oxidant gene expression. SKN-1 is needed in both the two ASI neurons and in the intestine for metformin to be beneficial. Since SKN-1 in the ASI neurons has been shown previously to be needed for DR lifespan extension , it seems probable that the ASIs play a role in the DR-like metabolism induced by metformin. LKB1 and AMPK are needed for metformin health benefits and AMPK acts upstream of intestinal SKN-1 for metformin benefits. *The relative order of action of SKN- and AMPK has not yet been experimentally addressed for ASI neurons. Dotted line—it is possible that signaling in the neurons could activate SKN-1 in intestine.