Autophagy regulates adipose mass and differentiation in mice

Abstract

The relative balance between the quantity of white and brown adipose tissue can profoundly affect lipid storage and whole-body energy homeostasis. However, the mechanisms regulating the formation, expansion, and interconversion of these 2 distinct types of fat remain unknown. Recently, the lysosomal degradative pathway of macroautophagy has been identified as a regulator of cellular differentiation, suggesting that autophagy may modulate this process in adipocytes. The function of autophagy in adipose differentiation was therefore examined in the current study by genetic inhibition of the critical macroautophagy gene autophagy-related 7 (Atg7). Knockdown of Atg7 in 3T3-L1 preadipocytes inhibited lipid accumulation and decreased protein levels of adipocyte differentiation factors. Knockdown of Atg5 or pharmacological inhibition of autophagy or lysosome function also had similar effects. An adipocyte-specific mouse knockout of Atg7 generated lean mice with decreased white adipose mass and enhanced insulin sensitivity. White adipose tissue in knockout mice had increased features of brown adipocytes, which, along with an increase in normal brown adipose tissue, led to an elevated rate of fatty acid, beta-oxidation, and a lean body mass. Autophagy therefore functions to regulate body lipid accumulation by controlling adipocyte differentiation and determining the balance between white and brown fat.

Figure 1. An inhibition of autophagy blocks 3T3-L1 cell TG accumulation and differentiation.

(A) Total protein was isolated from VEC and siATG7 cells and immunoblotted with antibodies for Atg7, LC3, and β-actin. The LC3-I and LC3-II forms are indicated. (B) TG levels in VEC and siATG7 cells at the days indicated after initiation of adipocyte differentiation. Results are represented as mean + SEM (n = 4–8). *P < 0.02; **P < 0.006 compared with VEC cells. (C) Immunoblots of proteins isolated from VEC and siATG7 cells on the indicated days of differentiation and probed with the antibodies shown. (D) TG levels on day 6 of differentiation in control, untreated wild-type cells (Con) and cells treated with 3-methyladenine (3MA) or ammonium chloride/leupeptin (A/L). Results are shown as mean + SEM (n = 6–9). *P < 0.0006 compared with untreated cells. (E) Immunoblots of day 6 control and 3-methyladenine– and ammonium chloride/leupeptin–treated cells.

Figure 2. ATG7^F/F-aP2-Cre mice have decreased WAT and increased BAT mass.

(A) Immunoblots of proteins isolated from the indicated tissues from control (Con) ATG7^F/F and knockout ATG7^F/F-aP2-Cre mice. The LC3-I and LC3-II forms are indicated. (B) Survival curves for RD- and HFD-fed mice (n = 13–28). (C) Representative gonadal fat pads from the 2 types of mice. (D) Gonadal WAT weights in RD- and HFD-fed mice (n = 5–14). *P < 0.001. (E) WAT weight as a percentage of total body weight (n = 4–24). *P < 0.005. (F) Interscapular BAT weights (n = 3–17). *P < 0.05. (G) BAT weight as a percentage of total body weight (n = 3–17). *P < 0.00002. (H) Total fat mass as determined by magnetic resonance spectroscopy (n = 8–20). *P < 0.00001. (I) Lean body mass in the same animals (n = 8–20). *P < 0.002. Results are mean + SEM. P values are as compared with control animals.

Figure 3. HFD-fed ATG7^F/F-aP2-Cre mice have increased insulin sensitivity.

(A) Serum glucose values from control and knockout mice (n = 10–29). *P < 0.00002. (B) Serum insulin levels (n = 7–11). *P < 0.05. (C) HOMA values (n = 4–6). *P < 0.05. (D) Glucose tolerance test (n = 4–5). *P < 0.02. Results are shown as mean + SEM or mean ± SEM. P values are as compared with control mice. (E) Immunoblots of total protein from WAT of control and knockout mice 30 minutes after insulin injection for phospho-Akt (p-Akt), total Akt, phospho-GSK-3α/β (p-GSK-3α/β), and total GSK-3β.

Figure 4. Gonadal WAT in knockout mice has characteristics of brown fat.

(A) H&E sections of WAT from control and knockout mice. Scale bars: 50 μm; 20 μm (insets). (B) Number of adipocytes per area. *P < 0.001. (C) Number of LD per area. *P < 0.01. (D) Mean LD area. *P < 0.000001. (E) Percentage of adipocytes that have multiloculated LD. *P < 0.00002. Results are shown as mean + SEM (n = 5–6). P values are as compared with control mice. (F) F4/80 immunohistochemical staining of control and knockout mice fed RD or HFD. Arrows indicate areas of positive staining for F4/80. Scale bars: 50 μm.

Figure 5. Loss of Atg7 alters the molecular characteristics of WAT and BAT.

(A) Western blots of proteins from control and knockout mice fed RD or HFD. Cyt ox, cytochrome oxidase, cyt c, cytochrome c. (B) Western blots of protein samples from WAT and BAT of HFD-fed mice. (C) Immunoblots of protein isolates from WAT of young control and knockout mice. (D) Representative H&E sections of interscapular BAT. Scale bars: 50 μm; 20 μm (insets). (E) Western blots of BAT protein from RD- and HFD-fed mice.

Figure 6. Levels of fatty acid β-oxidation are increased in Atg7-knockout mice.

(A) Rates of gonadal WAT β-oxidation in control and knockout mice fed RD or HFD (n = 3–12). *P < 0.05; **P < 0.001. (B) Rates of β-oxidation in interscapular BAT (n = 3–10). *P < 0.02. (C) Total rate of WAT and BAT β-oxidation (n = 3–11). *P < 0.05. Results are shown as mean + SEM. P values are as compared with control mice fed the same diet.