Glycogen metabolism links glucose homeostasis to thermogenesis in adipocytes

Abstract

Adipocytes increase energy expenditure in response to prolonged sympathetic activation via persistent expression of uncoupling protein 1 (UCP1)^1,2. Here we report that the regulation of glycogen metabolism by catecholamines is critical for UCP1 expression. Chronic β-adrenergic activation leads to increased glycogen accumulation in adipocytes expressing UCP1. Adipocyte-specific deletion of a scaffolding protein, protein targeting to glycogen (PTG), reduces glycogen levels in beige adipocytes, attenuating UCP1 expression and responsiveness to cold or β-adrenergic receptor-stimulated weight loss in obese mice. Unexpectedly, we observed that glycogen synthesis and degradation are increased in response to catecholamines, and that glycogen turnover is required to produce reactive oxygen species leading to the activation of p38 MAPK, which drives UCP1 expression. Thus, glycogen has a key regulatory role in adipocytes, linking glucose metabolism to thermogenesis.

Extended Data Fig. 1 |. Glycogen metabolism is enhanced in beige adipocytes.

a, b, Gene expression in iWAT from mice treated with either vehicle or CL-316,243 for. 7 days. n = 5 mice (vehicle) and 6 mice (CL-316,243). c, Protein expression in mice treated as in a, n = 5 mice (vehicle) and 6 mice (CL-316,243). d, Glycogen levels in iWAT of vehicle or CL-316,243 treated mice, n = 4 mice (vehicle) and 5 mice (CL-316,243). e, Electron micrographs of iWAT from vehicle or CL-316,243 treated mice. Arrows point to glycogen granules. Scale bar, Left two images − 1 μm, right two images – 260 nm. Shown are representative images of tissues from 6 different mice (3 vehicle and 3 Cl-316,243). f, Periodic acid-Schiff (PAS) staining for glycogen and UCP1 immunostaining in iWAT of vehicle or CL-316,243 treated miceUcp1. Right panels show a higher magnification of areas marked by a square. Scale bars, 4 left images – 2 mm, high magnification images – 100μm. Shown are representative images of tissues from 6 different mice (3 vehicle and 3 Cl-316,243). g, Gene expression in iWAT-derived stromal-vascular fraction and primary mature adipocytes from vehicle or CL-316,243 treated mice n = 4 biological replicates per treatment. Data are presented as mean ± s.e.m. *P < 0.05, **P < 0.01, ***P < 0.001. ^#P < 0.05, ^##P < 0.01. *Significance between vehicle and CL-316,243 treatment. ^#Significance between SVF and vehicle treated mature adipocytes. Statistical significance for a, b and d was determined by two-sided t-test, two-way ANOVA with adjustments for multiple comparisons was used for g.

Extended Data Fig. 2 |. CL-316,243 treatment does not affect the expression of glycogen metabolizing genes in BAT.

a, gene expression in human preadipocytes, differentiated adipocytes or differentiated adipocytes treated with forskolin for 3 days. n = 52 biological replicates per treatment. Statistical significance was determined using two-way ANOVA with adjustments for multiple comparisons, ***-p < 0.001. b, Mice were treated with either vehicle or CL-316,243 for 7 days. Gene expression in BAT was determined using qPCR, n = 5 mice per treatment. c, Quantification of protein expression data shown in Extended Data Fig. 1C (main text), expression was normalized to HSP90. n = 5 mice ( Vehicle), n = 6 mice (CL-316,243). Statistical significance was determined using two-sided t-test. d, Protein expression in BAT from mice treated as in b was determined by SDS-PAGE, n = 5 mice (vehicle), n = 6 mice (CL-316,243). No statistical significance detected. Data in a–c are presented as mean ± s.e.m.

Extended Data Fig. 3 |. PTG-KO does not affect the response to CL-316,243.

a-e, RNAseq data from iWAT-derived mature adipocytes of WT and PTG-KO mice treated with either vehicle or CL-316,243, n =3. a, Differential gene expression analyses of RNAseq data. b, Log₂ of fold change of gene expression of CL-316,243 treated WT mice versus vehicle-treated WT mice. Statistical significance was determined using two-sided t-test. c, Log₂ of fold change of gene expression of CL-316,243 treated PTG-KO mice versus vehicle treated PTG-KO mice. Statistical significance was determined using two-sided t-test. d, e, Pathway analyses of RNAseq were conducted using Gene Set Enrichment Analysis. f, Quantification of UCP1 protein expression data shown in Fig. 1f (main text), expression was normalized to RalA. n = 4 mice per treatment. Statistical significance was determined using two-sided t-test. g, Serum FFA levels in WT and PTG-KO mice treated with either vehicle or CL-316,243 for 20 min, n = 5 mice per genotype per treatment. Statistical significance was determined using two-way ANOVA with adjustments for multiple comparisons. Data are presented as mean ± s.e.m. *-p < 0.05. ***-p < 0.001. Accession number to cite these SRA data: PRJNA752350.

Extended Data Fig. 4 |. Adipose specific PTG-KO reduces energy expenditure.

a, Quantification of protein expression data shown in Fig. 2a (main text), expression was normalized to HSP90. n = 5 mice per treatment per genotype. b, c, Carbon dioxide production (VCO₂) in WT and PTG-AKO mice treated with CL-316,243. n = 4 mice per treatment per genotype. b, Average VCO₂ over the first three days of CL-316,243 treatment. c, Average VCO₂ during days 4–7 of CL-316,243 treatment. d, Quantification of UCP1 protein expression data shown in Fig. 2e (main text), expression was normalized to HSP90. n = 4 mice per treatment per genotype. e, Gene expression in iWAT of WT and PTG-AKO mice fed HFD for three months and then treated with either vehicle or CL-316,243 for 7 days. n = 6 mice per treatment per genotype. f, Body weight of WT and PTG-AKO mice fed HFD for three months before (day 0) and after 7 days (day 6) daily injections of Cl-316,243. n = 7 mice (WT), n = 6 mice (PTG-AKO). g, Weight of the inguinal white adipose tissue of WT and PTG-AKO mice fed HFD for three months and then treated for 7 days with either vehicle or Cl-316,243. n = 7 mice (WT), n = 6 mice (PTG-AKO). h, Linear regression analysis on anthropometric measurements in relation to gene expression from adipose tissue of 770 men. Data are presented as mean ± s.e.m. Statistical significance determined by two-way ANOVA with adjustments for multiple comparisons. *P < 0.05, **P < 0.01, ***P < 0.001. ^#P < 0.05. * - significance between vehicle and Cl-316–243 treatment within the same genotype. ^#- significance between WT and PTG-AKO mice treated with CL-316,243.

Extended Data Fig. 5 |. Overexpression of PTG increases UCP1 expression in vitro.

a, Glycogen levels in mouse primary hepatocytes treated with either vehicle or glucagon (10nM). n = 2 biological replicates per treatment. b, c, HEK-293t cells transfected with a Ucp1-promoter-driven turbo-GFP (Ucp1-GFP) alone or with FLAG tagged PTG (PTG-FLAG). b, Images of transfected cells were acquired using the Nikon eclipse Ts2R microscope. Shown are representative images from 3 independent experiments. Scale bar − 1μm. c, GFP expression levels were determined by western blot. d, Preadipocytes were treated with either Cl-316,243 alone or in combination with Tautomycin. Protein expression was determined by western blot. n = 3 biological replicates per treatment. e, Quantification of protein expression data shown in D. n = 3 biological replicates per treatment. f, Quantification of protein expression data shown in Fig. 3e (main text). n = 2 biological replicates per treatment per genotype. g, Quantification of protein expression data shown in Fig. 3g (main text). n =3 biological replicates per treatment. Data are presented as mean ± s.e.m. Statistical significance was determined using two-way ANOVA with adjustments for multiple comparisons. *P < 0.05, **P < 0.01. ^#P < 0.05. * - Significance between the zero time point and Glucagon/Cl-316,243 treatment within the same genotype. ^# - Significance between genotypes within the same time point.

Extended Data Fig. 6 |. Glycogen metabolism affects ROS production in response to Cl-316,243.

a, Quantification of protein expression data shown in Fig. 4c (main text). n = 2 biological replicates per treatment. Data are presented as mean ± s.e.m. Statistical significance was determined using two-way ANOVA with adjustments for multiple comparisons. *P < 0.05, **P < 0.01, ***P < 0.001. ^#P < 0.05. * - Significance between the zero time point and the assigned time point within the same treatment. ^# - Significance between different vehicle and NAC treatments within the same time point. b and c, Global cysteine oxidation in preadipocytes treated with either vehicle or Cl-316,243 (b) or Cl-316,243 alone or in combination with GPI (c), was determined as described in the methods section. b, Blue dots represent proteins with higher cysteine oxidation in vehicle-treated cells, red dots represent proteins with higher cysteine oxidation in Cl-316,243 treated cells. c, Blue dots represent proteins with higher cysteine oxidation in Cl-316,243 treated cells, red dots represent proteins with higher cysteine oxidation in cells treated with Cl-316,243 in combination with GPI. Statistical significance was determined using two-sided t test, cysteine sites shown had at least 5% change between treatments with a p < 0.05.

Extended Data Fig. 7 |. PTG-KO reduces energy expenditure during long term cold adaptation.

a, Core body temperature of WT and PTG-KO mice measured every 90 min during an acute cold exposure (4 °C), n = 8 mice per genotype. b, Brown adipose tissue glycogen levels in WT and PTG-KO mice at room temperature (RT) or cold exposed for 6 h and allowed to recover for 4 h at RT (4 °C-RT), n = 3 mice per genotype per condition. c, Core body temperature during a second cold exposure in WT and PTG-KO mice that were first cold exposed for 6 h and allowed to recover at room temperature for 4 h, n = 8 mice per genotype. d, e and f, gene expression in iWAT of WT and PTG-BKO mice housed either at room temperature or subjected to prolonged cold adaptation (7 days at 18 °C followed by 14 days at 4 °C), n = 8 mice per genotype. g, Protein expression in iWAT of the mice described in d, n = 5 mice per genotype. h, Oxygen consumption (VO₂) in WT and PTG-BKO mice before and during prolonged cold adaptation n = 8 mice per genotype. i, Working model. Acute activation of the β3-adrenergic receptor in white adipocytes results in lipolysis and glycogenolysis through the activation of PKA and subsequent activation of HSL and GP respectively. Prolonged β3-adrenergic receptor activation results in enhanced glycogen accumulation turnover which is required for ROS-dependent p38 activation and the subsequent expression of Ucp1. Data are presented as mean ± s.e.m. Statistical significance was determined two-way ANOVA with adjustments for multiple comparisons. *P < 0.05, **P < 0.01. ^#P < 0.05. * - significance between room temperature and cold exposure within the same genotype. ^#- significance between WT and PTG-KO/PTG-BKO with the same treatment.

Extended Data Fig. 8 |. Increased expression of BAT-Ucp1 following long-term cold exposure does not require PTG.

a, Quantification of protein expression data shown in Extended Data Fig. 7 (main text). n = 5 mice per genotype. b, Protein expression levels in BAT of WT and PTG-BKO mice housed either at room temperature or subjected to prolonged cold adaptation was determined by SDS-PAGE, n (22 °C) = 4, n (4 °C) = 5. c carbon dioxide production (VCO₂) in WT and PTG-BKO mice before and during prolonged cold adaptation. n = 8 mice per genotype. Data are presented as mean ± s.e.m. Statistical significance was determined using two-sided t test (A) or two way ANOVA with adjustments for multiple comparisons (C). *P < 0.05. ^#P < 0.05. * - Significance between 4 °C and 22 °C within the same genotype. ^# - Significance between different genotypes within the same time point.

Fig. 1 |. PTG-KO reduces the expression of UCP1 in beige adipocytes.

a, Glycogen levels in iWAT from wild-type (WT) and PTG-KO mice treated with either vehicle or CL-316,243 for 7 days. n = 5 mice per treatment per genotype. b, c, Gene expression in iWAT of mice treated as in a. n = 6 mice per treatment per genotype. d, e, GSEA on RNA-seq data from mature adipocytes isolated from PTG-KO and WT mice with or without CL-316,243 treatment for 7 days. n = 3 mice per genotype per condition. NES, normalized enrichment score. f, Expression of the specified proteins in iWAT of wild-type and PTG-KO mice treated as in a. n = 4 mice per treatment per genotype. g, Glycogen accumulation and UCP1 expression analysed by periodic acid-Schiff (PAS) and immunohistochemistry, respectively. Scale bars, 2 mm. Shown are representative images of tissues from 8 different mice, 2 per genotype per treatment. Data are mean ± s.e.m. Two-way analysis of variance (ANOVA) with adjustments for multiple comparisons (a–c). *P < 0.05, **P < 0.01, ***P < 0.001, ^##P < 0.01, ^###P < 0.001. *P value for difference between vehicle and CL-316,243 treatment within the same genotype; ^#P value for difference between wild-type and PTG-KO mice treated with CL-316,243.

Fig. 2 |. Adipose-specific PTG knockout reduces UCP1 expression and energy expenditure.

a, Protein expression in iWAT of wild-type and PTG-AKO mice treated with either vehicle or CL-316,243. n = 5 mice per genotype per treatment. b, c, Oxygen consumption (VO₂) in wild-type and PTG-AKO mice. n = 4 mice per genotype per treatment. b, Average VO₂ over the first three days of CL-316,243 treatment. c, VO₂ on days 4–7 of CL-316,243 treatment. d, Body weight of obese (3-month high-fat-diet-fed) wild-type and PTG-AKO mice. n = 14 (wild type), n = 12 (PTG-AKO). e, Protein expression in iWAT of obese wild-type and PTG-AKO mice treated with vehicle or CL-316,243 for 7 days; DE, dark exposure; LE, light exposure. n = 4. f, Body weight loss in wild-type and PTG-AKO mice treated as described in e. n = 7 mice per genotype per treatment. g, Blood glucose levels in obese wild-type and PTG-AKO mice treated with either vehicle or CL-316,243 for 7 days. n = 7 mice per genotype per treatment. h, Linear regression of microarray data from subcutaneous adipose biopsies of lean (n = 26) and obese (n = 30) women. Data are mean ± s.e.m. Two-way ANOVA with adjustments for multiple comparisons (b–d, f, g). *P < 0.05, **P < 0.01. ^#P < 0.05. *P value for difference between vehicle and CL-316,243 treatment within the same genotype; ^#P value for difference between wild-type and PTG-AKO mice treated with CL-316,243.

Fig. 3 |. Attenuation of glycogen metabolism reduces the activation of p38.

a, Glycogen levels in CL-316,243-treated wild-type and PTG-KO preadipocytes. n = 3 biological replicates per genotype per treatment. b, G1P levels in wild-type and PTG-KO preadipocytes. n = 3 biological replicates per genotype per treatment. c, Gene expression in wild-type and PTG-KO preadipocytes treated as in a. n = 3 biological replicates per genotype per treatment. d, Ucp1 expression in response to CL-243,316 after pre-treatment with either p38 inhibitor (10 μM SB203580), PKA inhibitor (10 μM H89) or vehicle in wild-type preadipocytes. n = 3 biological replicates per treatment. e, Activation of p38 and HSL phosphorylation by CL-316,243 in wild-type and PTG-KO preadipocytes. n = 2 biological replicates per genotype per treatment. f–h, Wild-type preadipocytes treated with either CL-316,243 alone or in combination with 10 μM GPI. n = 3 biological replicates per treatment. f, Glycogen levels. g, Activation of p38. h, Thermogenic gene expression. Data are mean ± s.e.m. Two-way ANOVA with adjustments for multiple comparisons. *P < 0.05, **P < 0.01, ***P < 0.001, ^#P < 0.05, ^##P < 0.01, ^###P < 0.001, ^†††P < 0.001. In a–c: *P value for difference between vehicle and CL-316,243 treatment within the same genotype; ^#P value for difference between wild-type and PTG-KO mice treated with CL-316,243 at the same time point. In d, f, h: *P value for difference between vehicle and CL-316,243 treatment; ^#P value for difference between CL-316,243 treatment and CL-316,243 treatment in combination with H89 or SB203580 (daggers) at the same time point.

Fig. 4 |. Glycogen metabolism contributes to ROS production in adipocytes.

a, ROS production in response to CL-243,316 in wild-type preadipocytes. n = 5 biological replicates per treatment. b, Induction of ROS-detoxification genes by CL-316,243 in wild-type preadipocytes. n = 3 biological replicates per treatment. c, ROS-dependent activation of p38 in wild-type preadipocytes treated with CL-316,243 (CL) alone or in combination with the ROS scavenger N-acetyl-l cysteine (NAC). n = 2 biological replicates per treatment. d, Thermogenic gene expression in preadipocytes treated as in c. n = 3 biological replicates per treatment. e, ROS-related pathway analysis using GSEA on RNA-seq data from mature adipocytes isolated from iWAT of PTG-KO and wild-type mice treated with vehicle or CL-316,243 for 7 days. n = 3 biological replicates per genotype per treatment. f, ROS production in wild-type preadipocytes, wild-type preadipocytes treated with GPI, and PTG-KO preadipocytes. n = 3 biological replicates per genotype per treatment. g, Mitochondrial ROS production in preadipocytes treated with vehicle or Cl-316,243 with and without GPI treatment. n = 12 biological replicates per treatment. Data are mean ± s.e.m. Two-sided t-test and two-way ANOVA (a). *P < 0.05, **P < 0.01, ***P < 0.001, ^#P < 0.05, ^###P < 0.001. In a, b, d, g: *P value for difference between vehicle and CL-316,243 treatment; ^#P value for difference between CL-316,243 treatment and CL-316,243 treatment in combination with the specified inhibitor at the same time point. In f, h: *P value for difference between vehicle and CL-316,243 treatment; ^#P value for difference between CL-316,243 treatment of wild-type preadipocytes and CL-316,243 treatment of PTG-KO preadipocytes.