Metformin retards aging in C. elegans by altering microbial folate and methionine metabolism

Abstract

The biguanide drug metformin is widely prescribed to treat type 2 diabetes and metabolic syndrome, but its mode of action remains uncertain. Metformin also increases lifespan in Caenorhabditis elegans cocultured with Escherichia coli. This bacterium exerts complex nutritional and pathogenic effects on its nematode predator/host that impact health and aging. We report that metformin increases lifespan by altering microbial folate and methionine metabolism. Alterations in metformin-induced longevity by mutation of worm methionine synthase (metr-1) and S-adenosylmethionine synthase (sams-1) imply metformin-induced methionine restriction in the host, consistent with action of this drug as a dietary restriction mimetic. Metformin increases or decreases worm lifespan, depending on E. coli strain metformin sensitivity and glucose concentration. In mammals, the intestinal microbiome influences host metabolism, including development of metabolic disease. Thus, metformin-induced alteration of microbial metabolism could contribute to therapeutic efficacy-and also to its side effects, which include folate deficiency and gastrointestinal upset.

Graphical abstract

Figure 1

The Biguanide Drugs Phenformin and Metformin Decelerate Aging in C. elegans (A and B) Metformin (A) and phenformin (B) extend lifespan in a dose-dependent manner. Phenformin alters fecundity and reduces body size (see Figures S1A–S1D). (C) Phenformin (4.5 mM) does not increase lifespan in the presence of 50 mM metformin, consistent with similar mechanism of drug action. (D) Metformin decreases the exponential increase in age-related mortality (for survival curve see Figure S1E). (E) Later-life administration (day 8) of metformin increases lifespan at lower concentrations (25, but not 50 or 100 mM). See also Figure S1. For statistics, see Table S1.

Figure S1

Effects of Biguanides on Fecundity, Growth, and Lifespan, Related to Figure 1 (A) Dose-dependent reduction in daily fecundity by phenformin. (B) Effect of phenformin on daily fecundity as a proportion of total fecundity. Note the apparent, slight reproductive delay. (C) Dose-dependent reduction in brood size by phenformin. (D) Phenformin causes a reduction in body length (L4 stage). (E) Metformin robustly increases lifespan when administered from early adulthood onward. Combined data for all survival assays performed, and corresponding to mortality data in Figure 1D (dots represent confidence intervals). We also compared effects of metformin administered for 2 generations prior to the start of the survival assay with administration from the L4 stage onward, and detected no difference (Table S1). (F and G) Effects of metformin on lifespan are not affected by FUdR. For statistics see Table S1. Error bars, SEM. ^∗p < 0.05; ^∗∗p < 0.01; ^∗∗∗p < 0.001.

Figure 2

Metformin Extending Effects on C. elegans Lifespan Require Live Bacteria (A) Metformin shortens lifespan of C. elegans cultured axenically (i.e., in the absence of E. coli). (B) Metformin shortens lifespan of C. elegans cultured on UV-irradiated E. coli (OP50). (C) Metformin pretreatment of bacteria is sufficient to extend lifespan. (D) Metformin extends lifespan in the absence of E. coli proliferation (blocked by carbenicillin). (E) Metformin extends lifespan in the presence of the less pathogenic bacterium Bacillus subtilis. (F) Retardation of bacterial growth by metformin, monitored over an 18 hr period. (G) Biguanide drugs cause altered bacterial lawn morphology. (H) Bacterial viability is reduced by carbenicillin and UV treatment, but not metformin. (I) Metformin extends lifespan in the presence of multi-antibiotic resistant E. coli OP50-R26. See also Figure S2. For statistics, see Table S2.

Figure S2

Biguanides Inhibit Bacterial Growth, Related to Figure 2 (A and B) Metformin shortens lifespan in the absence of bacteria (bacterial deprivation on NGM plates) (Kaeberlein et al., 2006; Lee et al., 2006). (C) Dose-dependent inhibition of E. coli OP50 growth by phenformin (LB liquid media, 18 hr period). (D–E) Dose dependent inhibition of growth of Bacillus subtilis by metformin (LB liquid media, 18 hr period). (F) Metformin causes altered bacterial lawn morphology in Bacillus subtilis. (G) Inhibition of bacterial growth by metformin is more marked at pH = 6.0 than at pH = 7.0. (H) Effects of metformin on C. elegans lifespan are pH-sensitive. See Table S2 for statistics. Error bars, SEM. ^∗p < 0.05; ^∗∗p < 0.01; ^∗∗∗p < 0.001.

Figure 3

Metformin Effects on C. elegans Lifespan Correlate with Effects of Metformin on Bacterial Growth (A) Metformin extends lifespan in the presence of respiratory-deficient E. coli strain GD1. (B) Growth in the presence of metformin does not impair respiration in E. coli OP50. (C–E) Effects on lifespan are independent of bacterial subgroup (B or K-12) and lipopolysaccharide (LPS) structure. K-12 strains possess longer LPS structures than B strains and CS2429. CS2429 is an LPS truncated mutant derived from isogenic parent strain CS180. HB101 is a B/K-12 hybrid. (F) Relationship between bacterial growth inhibition by metformin (50 mM) and effects on lifespan among different E. coli strains. (G) OP50-MR E. coli is resistant to growth inhibition by metformin. This strain also shows cross-resistance to phenformin (Figures S3C–S3E). (H) Metformin shortens lifespan in the presence of OP50-MR. Error bars represent SEM. ^∗p < 0.05; ^∗∗p < 0.01; ^∗∗∗p < 0.001. See also Figure S3. For statistics, see Table S3.

Figure S3

Effects of Metformin and Phenformin on Bacterial Growth and Lifespan of Various Bacterial Strains, Related to Figure 3 (A) Metformin shortens worm lifespan in the presence of the wild-type E. coli K-12 strain MG1655. (B) E. coli sensitivity to growth inhibition by metformin shows no correlation with E. coli effects on wild-type worm lifespan. (C) E. coli OP50-MR is resistant to growth inhibition by metformin compared to OP50 parent strain (c.f. Figure 2F). (D) E. coli OP50-MR is resistant to growth inhibition by phenformin compared to OP50 parent strain. (E) Relative resistance to growth inhibition by phenformin of E. coli OP50 (black) and OP50-MR (gray). (F) OP50-MR increases lifespan in the absence of metformin. For statistics see Table S3. Error bars, SEM. ^∗p < 0.05; ^∗∗p < 0.01; ^∗∗∗p < 0.001.

Figure 4

Metformin Inhibits Bacterial Folate Metabolism (A) The folate and methionine cycles. Metabolites analyzed, red; enzymes, blue; supplements, purple. DHF, dihydrofolate; DHFR, dihydrofolate reductase; Glu, glutamate; Hcy, homocysteine; Met, methionine; MS, methionine synthetase; MTHFR, methylenetetrahydrofolate reductase; pABA, p-aminobenzoic acid; SAH, S-adenosylhomocysteine; SAMe, S-adenosylmethionine; SAMS, S-adenosylmethionine synthase; THF, tetrahydrofolate; TRI, trimethoprim. Dotted lines represent feedback loops. (B) Metformin alters folate homeostasis in E. coli OP50 but not OP50-MR. The values for each metabolite are the sum of the values for the different glutamate side chains (1–7) divided by sum of all folate metabolites measured. (C) Metformin alters 5-methyl-THF polyglutamylation in OP50 but not OP50-MR. (D) The DHFR inhibitor TRI increases C. elegans lifespan in a dose-dependent manner. See Figure S4D for E. coli growth retardation by TRI. (E) Effects of metformin and TRI on lifespan are nonadditive, consistent with similar modes of action. (F) Principal component analysis (Metaboanalyst) of OP50 metabolites with TRI and metformin. Note that TRI abolishes effects of metformin. Error bars represent SEM. ^∗p < 0.05; ^∗∗p < 0.01; ^∗∗∗p < 0.001. See also Figure S4. For statistics, see Table S4.

Figure S4

Metformin and Trimethoprim Alter Bacterial Metabolism and Extend C. elegans Lifespan by Common Mechanisms, Related to Figure 4 (A) Diagram showing folate synthesis, one-carbon substitution, polyglutamylation and catabolism in E. coli (adapted from Kwon et al., 2008). Blue, enzymes involved in these reactions: FPGS, folylpolyglutamate synthetase; DHFR, dihydrofolate reductase. Red: DHF, dihydrofolate; THF, tetrahydrofolate. Black: pABA, p-aminobenzoic acid; Glu, glutamate; GTP, guanosine triphosphate; PteGlu, pteroylmonoglutamic acid; pABGlu, p-aminobenzoyl-l-glutamate. (B) Folate polyglutamylation profiles of detectable folate metabolites of E. coli OP50 grown in the presence or absence of metformin. Metformin strongly affects polyglutamylation levels of all folates detected. (C) Folate polyglutamylation profiles of detectable folate metabolites of E. coli OP50-MR bacteria grown in the presence or absence of metformin (note the absence of effects in most cases). (D) Trimethoprim (TRI) acts as a bacteriostatic antibiotic to delay bacterial growth in a dose-dependent manner. (E) Hierarchical cluster analysis of metabolites of TRI and metformin-treated OP50 and OP50-MR using the Ward method. Metabolite clusters from the TRI+metformin condition or TRI alone are indistinguishable from each other. Metformin treatment of OP50-MR creates a cluster of metabolites similar to OP50-MR and OP50 in the absence of treatment and distinct from OP50 treated with metformin. (F) TRI does not extend worm lifespan in the presence of a TRI-resistant strain of E. coli OP50 (OP50-triR) expressing the type IIa DHF reductase (Kim, 2009). (G) TRI-resistance in E. coli has no effect on induction of life extension by metformin. For statistics see Table S4. Error bars, SEM. ^∗p < 0.05; ^∗∗p < 0.01; ^∗∗∗p < 0.001.

Figure 5

Effect of Metformin on the Methionine Cycle but Not the Folate Cycle in C elegans (A) Effect of metformin on C. elegans/E. coli system: little effect on nematode folate homeostasis. (B) Metformin induces a shift toward shorter-chain (n = 1–3) glutamate folate forms in C. elegans. (C) Metformin increases S-adenosylmethionine (SAMe) levels in E. coli (OP50). (D) Mutation of metr-1(ok521) (methionine synthetase, MS) increases lifespan only in the presence of metformin. (E) In C. elegans, metformin greatly reduces SAMe levels and increases S-adenosylhomocysteine (SAH) levels. (F) Metformin shortens lifespan in S-adenosylmethionine synthase-deficient sams-1(ok3033) mutants. Error bars represent SEM. ^∗p < 0.05; ^∗∗p < 0.01; ^∗∗∗p < 0.001. See also Figure S5. For statistics, see Table S5.

Figure S5

Folate Polyglutamylation Profiles of Detectable Folate Metabolites of Wild-Type Worms Grown in the Presence or Absence of Metformin, Related to Figure 5 Error bars, SEM of at least 3 independent biological replicates. ^∗p < 0.05; ^∗∗p < 0.01; ^∗∗∗p < 0.001.

Figure 6

AMP kinase and SKN-1 Protect Against Biguanide Toxicity (A) Phenformin increases pAAK-2 levels, suggesting AMPK activation (2-day-old adults). (B) Phenformin shortens lifespan in aak-2(ok524) AMPK loss-of-function mutants. (C) Phenformin does not extend lifespan in skn-1(zu135) mutants. (D) AMPK-dependent induction of expression by phenformin of SKN-1-activated reporter gst-4::gfp in L4 animals. (E) aak-2(ok524) but not daf-16(mgDf50) mutants are hypersensitive to growth inhibition by metformin, as measured by the food clearance assay. (F) skn-1(zu135) increases sensitivity to growth inhibition by metformin. (G) Metformin increases expression of gst-4::gfp under conditions that do not increase lifespan (maintenance on E. coli HT115). (H) Life extension by metformin pretreatment of E. coli is partially AMPK-dependent. (I) Life extension by metformin pretreatment of E. coli is not SKN-1-dependent. Error bars represent SEM of at least three independent biological replicates. ^∗p < 0.05; ^∗∗p < 0.01; ^∗∗∗p < 0.001. See also Figure S6. For statistics, see Table S6.

Figure S6

Role of AMP Kinase and SKN-1 in Metformin-Induced Longevity, Related to Figure 6 (A) Metformin does not detectably alter pAAK-2 levels in 1-day adults when developing in the presence of different drug concentrations or in day-8 and day-16 adults. (B) Metformin does not significantly increase lifespan in AMPK-deficient aak-2(ok524) mutant worms. (C) Metformin decreases the exponential increase in age-related mortality in AMPK-deficient aak-2(ok524) mutant worms, but increases initial mortality. (D) AMPK-deficient aak-2(ok524) mutant worms are hypersensitive to growth inhibition by phenformin as measured using the food clearance assay (Voisine et al., 2007). (E) TMP does extend lifespan in aak-2(ok524) mutant worms, though the magnitude of the extension is slightly reduced. (F) The folate-deficient (aroD) mutant E. coli (Virk et al., 2012) does extend lifespan in aak-2(ok524) mutants, though the magnitude of the extension is slightly reduced. (G) sams-1 RNAi does not extend lifespan in aak-2(ok524) (AMPK-deficient) mutant worms. (H) Metformin shortens lifespan in skn-1(zu135) mutant worms. (I) Diagram showing AMPK-dependent expression of SKN-1 gene targets such as gst-4 by biguanides; after Onken and Driscoll (2010). (J and K) Metformin induces gst-4::gfp expression in an AMPK dependent fashion, consistent with a previous report (Onken and Driscoll, 2010). (J) Representative epifluorescence microscopic images of gst-4::gfp expression in L4 larvae. (K) Quantification of reporter gene expression. See Table S6 for statistics. Error bars, SEM of at least 3 independent biological replicates. ^∗p < 0.05; ^∗∗p < 0.01; ^∗∗∗p < 0.001.

Figure 7

High Glucose Diet Suppresses Metformin-Induced Life Extension (A) Metformin decreases lifespan on 0.25% d-glucose. See Figure S7A for 1% d-glucose. (B) Metformin does not inhibit bacterial growth in the presence of 0.25% d-glucose. (C) Scheme summarizing direct and indirect effects of metformin on the C. elegans/E. coli system. Dotted lines indicate hypothetical feedback loops. Error bars represent SEM of at least three independent biological replicates. ^∗p < 0.05; ^∗∗p < 0.01; ^∗∗∗p < 0.001. See also Figure S7. For statistics, see Table S7.

Figure S7

Glucose Supplementation Blocks Metformin-Induced Lifespan Extension, Related to Figure 7 (A) Metformin does not extend C. elegans lifespan in the presence of 1% d-glucose. (B) Glucose supplementation alone slightly enhances bacterial growth. (C and D) 1% d-glucose reverses inhibition of bacterial growth by 50 mM metformin. See Table S7 for statistics. Error bars, SEM. ^∗p < 0.05; ^∗∗p < 0.01; ^∗∗∗p < 0.001.