An ERK/Cdk5 axis controls the diabetogenic actions of PPARγ

Abstract

Obesity-linked insulin resistance is a major precursor to the development of type 2 diabetes. Previous work has shown that phosphorylation of PPARγ (peroxisome proliferator-activated receptor γ) at serine 273 by cyclin-dependent kinase 5 (Cdk5) stimulates diabetogenic gene expression in adipose tissues. Inhibition of this modification is a key therapeutic mechanism for anti-diabetic drugs that bind PPARγ, such as the thiazolidinediones and PPARγ partial agonists or non-agonists. For a better understanding of the importance of this obesity-linked PPARγ phosphorylation, we created mice that ablated Cdk5 specifically in adipose tissues. These mice have both a paradoxical increase in PPARγ phosphorylation at serine 273 and worsened insulin resistance. Unbiased proteomic studies show that extracellular signal-regulated kinase (ERK) kinases are activated in these knockout animals. Here we show that ERK directly phosphorylates serine 273 of PPARγ in a robust manner and that Cdk5 suppresses ERKs through direct action on a novel site in MAP kinase/ERK kinase (MEK). Importantly, pharmacological inhibition of MEK and ERK markedly improves insulin resistance in both obese wild-type and ob/ob mice, and also completely reverses the deleterious effects of the Cdk5 ablation. These data show that an ERK/Cdk5 axis controls PPARγ function and suggest that MEK/ERK inhibitors may hold promise for the treatment of type 2 diabetes.

Extended Data 1

Metabolic profiling of adipose-specific Cdk5 knockout mice on a standard chow diet. Fasting plasma levels of (a) glucose, (b) insulin, (c) total triglycerides, (d) free fatty acids (FFA), and (e) total cholesterol (n = 16 Ctl, 17 KO). (f) Body weights and (g) intraperitoneal glucose tolerance test. Mice were 12 wk of age (n = 14 Ctl, 11 KO). No significant differences were observed. Error bars ± SEM.

Extended Data 2

Energy homeostasis of adipose-specific Cdk5 knockout mice maintained on a high fat diet. Following a 48 hr acclimatization period, singly housed mice were monitored for (a) oxygen consumption (VO₂), (b) carbon dioxide production (VCO₂), (c) respiratory exchange ratio (RER), (d) ambulatory locomotor activity, (e) cumulative food intake, and (f) body weights (n = 8 per group). Shaded areas signify the dark phase of the light cycle. No significant differences were observed. Error bars ± SEM.

Extended Data 3

Activity of alternative kinases in adipose tissue from CDK5 FKO mice. Brown adipose tissue protein lysates from mice maintained on a HFD for 12 wk. Blotting for phospho-p38, phospho-JNK, and phospho-S473 and pT308 AKT was performed before loading for total protein amounts.

Extended Data 4

Conservation of the sites on MEK2 phosphorylated by Cdk5. Mouse MEK2 T395/T397 corresponds to human MEK2 T394/T396. These sites share identity to MEK1 T386/T388 in both humans and mouse. Cdk5 has previously been shown to phosphorylate MEK1 at T286, a site not shared with MEK2. ERK has been shown to phosphorylate MEK1 T386 and contribute to regulation of kinase activity. Homo, Homo sapiens; trog, Pan troglodytes; mus, Mus musculus; rat, Rattus norvegicus; bos, Bos taurus; canis, Canis lupus familiaris.

Extended Data 5

Body weight of control and of adipose-specific Cdk5 knockout mice maintained on a high fat diet following treatment with PD0325901 as in Fig. 4a–c. The body weights are not significantly different by ANOVA. Error bars ± SEM.

Extended Data 6

Effects of PD0325901 treatment on ob/ob mice. (a) Glucose tolerance test, (b) adiponectin levels, and (c) body weights of ob/ob mice treated with PD0325901 (n = 7 vehicle, 8 PD). * p = < 0.05 by Student’s t-test. Error bars ± SEM.

Extended Data 7

Inflammatory markers in epididymal WAT from ob/ob mice treated with MEK inhibitors. Gene expression analysis was performed on M1 macrophage markers Nos2 and TNFα; M2 macrophage markers Arg1, Chil3, Il10, Itgax, Clec10a/Mgl1 and Mgl2; chemotactic ligand Ccl2 and receptor Ccr2; and macrophage surface markers Emr1, Cd68, and Csf1r (n = 7–8 mice per group as in Fig. 4p–r). Gene expression was analyzed by ANOVA. Error bars ± SEM. * p < 0.05, ** p < 0.01, *** p < 0.001.

Extended Data 8

Schematic model of PPARγ regulation at S273. (a) In the lean state PPARγ is not phosphorylated. (b) In the obese state S273 phosphorylation is driven by both Cdk5 and ERK with CDK5 repressing MEK and ERK activity. (c) CDK5 knockout results in derepression of MEK and ERK kinases and increased phosphorylation of S273 PPARγ. (d) MEK inhibition dramatically reduces S273 PPARγ phosphorylation. (e) PPARγ ligands including the TZDs, block the accessibility of S273 PPARγ by either ERK or CDK5 kinases.

Figure 1

Insulin resistance following Cdk5 deletion in adipocytes. (a) Deletion of Cdk5 in epididymal white adipose tissue from Control (Cdk5^Flox/Flox) or adipocyte-specific knockout, KO (Cdk5^Flox/Flox::adiponectin-Cre) was confirmed by western blotting or (b) q-RTPCR. n = 5. (c) Fractionated adipose tissue confirmed deletion was confined to the adipocyte fraction of adipose tissue. (d) Body weight of control or KO mice when maintained on a high fat diet (HFD). n = 20 Ctl, 25 KO. (e) Fasting glucose (f) and fasting insulin in mice maintained on a HFD. n = 10 Ctl, 12 KO. (g) Glucose tolerance test and (h) insulin tolerance tests are consistent with impaired insulin sensitivity. n = 15 Ctl, 17 KO. (i) Western blots of white adipose tissue for pS273 PPARγ in control and KO mice quantified in (j). Error bars ± SEM. * p < 0.05, ** p < 0.01, *** p < 0.001.

Figure 2

Identification and characterization of ERK as a S273 PPARγ kinase. (a) ATP probe enriched phosphoproteomic analysis of kinases in control or Cdk5-FKO adipose tissue from mice on a HFD. Heat map indicating the most highly regulated phosphopeptide between control and Cdk5 KO (n = 3 per group, p=0.08) corresponds to the activation loop of ERK2 Mapk1/ERK2. (b) Normalized quantification of the abundance of the phosphopeptide and total abundance corresponding to the activation loop of ERK2 by mass spectrometry. (c) Western blot of ERK1 and 2 phosphorylation in brown adipose tissue from mice on a HFD. (d) Western blot of phospho-ERK1/2 in primary adipocytes differentiated in vitro for 8 days and serum starved for 18 hrs. (e) Inhibition of Cdk5 by 6 hr treatment of roscovitine in cultured F442A adipocytes at the indicated dose. (f) HEK 293 cells expressing wild type or an analogue sensitive (AS) mutant of Cdk5 were treated with the AS-specific inhibitor 1NMPP1 at 0, 0.1, 1.0 or 10 μM for 2 hr. (g) Cultured adipocytes stably expressing Cdk5-AS treated with the indicated dose of 1NMPP1. (h) PPARγ co-transfected with increasing doses of constitutively active ERK2 kinase (ERK-CA) or active Cdk5 (Cdk5 with p35). Western blotting was performed for both pS273 PPARγ and total PPARγ. (i) Phosphorylated residues identified by LC-MS/MS following in vitro kinase assay of recombinant Cdk5, ERK2, or MEK2 incubated with full length recombinant PPARγ. (j) In vitro ERK kinase assay with incubated with full length recombinant PPARγ and increasing doses of pioglitazone before western blotting for pS273 and total PPARγ. Error bars ± SEM.

Figure 3

Regulation of MEK2 by Cdk5. (a) ATP probe phosphoproteomic analysis of activated kinases in Cdk5-FKO adipose tissue lysates following addition of recombinant active Cdk5 and p35 protein at the indicated dose. (b) The most highly regulated peptide includes MEK2 residues T395 and T397. (c) HEK 293 cells expressing AS mutant of Cdk5 were treated with the AS-specific inhibitor 1NMPP1 at 0, 0.1 1.0 or 10 μM for 2 hr before western blotting for MEK2 phospho-T395. (d) IP in vitro Kinase assay of MEK2-WT or T395A T397 (MEK2-AA) mutant. Flag-tagged WT-MEK2 or constitutively active CA-MEK2 (S222D S226D) were immunoprecipitated from HEK293 cells and incubated with ATP and recombinant ERK protein.

Figure 4

Metabolic consequences of MEK inhibition in vivo, HFD mice. (a) Glucose tolerance tests of HFD fed adipose-specific Cdk5-FKO mice or controls following treatment with vehicle or (b) MEK inhibitor PD0325901 (c) area under the curve. n = 10 for WT vehicle, KO vehicle, and KO PD groups. n = 9 for the WT PD group. (d) Insulin tolerance tests (n = 12 Ctl, 11 KO) or (e–j) hyperinsulinemic euglycemic clamps in HFD fed wild-type C57Bl/6 mice following treatment with PD0325901. (e) Glucose infusion rate (GIR) (f) whole-body glucose uptake/disposal (g) ³H-2-deoxy-glucose (2DG) tracer uptake into epididymal white adipose tissue (h) or gastrocnemius. (i) Percent suppression of endogenous glucose production (EGP). (j) Percent suppression of free fatty acids (FFA). n = 9 vehicle, 11 PD. (k) ERK phosphorylation in white adipose tissue from WT C57Bl6/J or ob/ob mice. (l) Glucose tolerance test in ob/ob mice following treatment with MEK inhibitor GSK1120212 or vehicle. (m) Fasting insulin values. (n) Plasma adiponectin levels and (o) body weight. (n = 8). (p–r) Gene expression in ob/ob white epididymal WAT following treatment with vehicle or either of two MEK inhibitors, PD0325901 or GSK1120212 (n = 7, 7, 8 respectively). (p) Genes responsive to PPARγ S273 phosphorylation, (q) genes responsive to PPARγ agonism, and (r) genes controlling “browning” of white adipose tissue and thermogenesis. (s) Phosphorylation of PPARγ in epididymal WAT in ob/ob mice after treatment with MEK inhibitors. Error bars ± SEM. * p < 0.05, ** p < 0.01, *** p < 0.001.

Figure 5

Metabolic consequences of MEK inhibition in ob/ob mice. (a) ERK phosphorylation in WAT from WT C57Bl6/J or ob/ob mice. (b) Glucose tolerance test in ob/ob mice following treatment with MEK inhibitor GSK1120212 or vehicle. (c) Fasting insulin values, (d) plasma adiponectin levels, and (e) body weights (n = 8). (f–h) Gene expression in ob/ob epididymal WAT following treatment with vehicle or either of two MEK inhibitors, PD0325901 or GSK1120212 (n = 7, 7, 8 respectively). (f) Genes responsive to PPARγ S273 phosphorylation, (g) genes responsive to PPARγ agonism, and (h) genes controlling “browning” of WAT and thermogenesis. (i) Phosphorylation of PPARγ in epididymal WAT in ob/ob mice after treatment with MEK inhibitors. AUC and gene expression were analyzed by ANOVA. Error bars ± SEM. * p < 0.05, ** p < 0.01, *** p < 0.001.