The IRE1alpha-XBP1 pathway of the unfolded protein response is required for adipogenesis

Abstract

Signaling cascades during adipogenesis culminate in the expression of two essential adipogenic factors, PPARgamma and C/EBPalpha. Here we demonstrate that the IRE1alpha-XBP1 pathway, the most conserved branch of the unfolded protein response (UPR), is indispensable for adipogenesis. Indeed, XBP1-deficient mouse embryonic fibroblasts and 3T3-L1 cells with XBP1 or IRE1alpha knockdown exhibit profound defects in adipogenesis. Intriguingly, C/EBPbeta, a key early adipogenic factor, induces Xbp1 expression by directly binding to its proximal promoter region. Subsequently, XBP1 binds to the promoter of Cebpa and activates its gene expression. The posttranscriptional splicing of Xbp1 mRNA by IRE1alpha is required as only the spliced form of XBP1 (XBP1s) rescues the adipogenic defect exhibited by XBP1-deficient cells. Taken together, our data show that the IRE1alpha-XBP1 pathway plays a key role in adipocyte differentiation by acting as a critical regulator of the morphological and functional transformations during adipogenesis.

Figure 1

XBP1 is essential for adipocyte differentiation. (A) Q-PCR analysis showing total Xbp1mRNA levels in 3T3-L1 CONi and XBP1i #4 during differentiation. Data normalized to d0 time-point of 3T3-L1 CONi cells. Data are means ± s.e.m. *, P<0.05 using unpaired two-tailed Student’s t-test comparing CONi to XBP1i at the same time-point. (B) Immunoblots showing the levels of XBP1s and key adipogenic markers (C/EBPβ , C/EBPα , and PPARγ ) during adipogenesis. 3T3-L1 preadipocytes treated with 300 nM Tg for 4 h was loaded as a control. XBP1u (30kD) protein was not detectable. HSP90 and CREB, loading controls. (C) Top, Immunoblots of XBP1s protein in wildtype MEFs stably expressing CONi, XBP1i #4, #5 or both treated with 300 nM Tg for 4 h. CREB, a loading control. Bottom, Macroscopic pictures of Oil Red-O staining of 3T3-L1 cells expressing CONi, XBP1i #4 and #5 differentiated for 8 days (d8). (D) Left, macroscopic pictures of Oil Red-O staining of wildtype (WT) and XBP1^−/− MEFs differentiated for 24 days (d24). Right, immunoblots of XBP1s protein in MEFs treated with 300 nM Tg for 4 h

Figure 2

C/EBPβ induces Xbp1 expression. (A) Q-PCR analysis of Xbp1 mRNA in 3T3-L1 cells (d0) treated with various stimuli as indicated for 8 h. Data normalized to the mock-treated sample (CON). (B) Q-PCR analysis showing the expression patterns of Xbp1 and Cebpb mRNA within the first 24 h postinduction in differentiating 3T3-L1 cells. (C) Immunoblot showing the expression patterns of XBP1s, CHOP10 and C/EBPβ proteins in differentiating 3T3-L1 cells. HSP90, a loading control. (D) ChIP analysis showing the recovery of Xbp1 promoter from immunoprecipitates of C/EBPβ or control IgG prepared from differentiated 3T3-L1 cells at d0, 8 h postinduction and d4. The amount of Xbp1 promoter (-580 to -425 bp) recovered was quantitated using Q-PCR. Data normalized to the IgG controls at each point. (E) Luciferase assay showing effects of C/EBPβ on wildtype (WT) or mutated Xbp1 reporter activity (−689 to +37 bp) in HEK293T cells transiently transfected with control GFP (CON) or C/EBPβ . ΔC/EBP, deletion of the C/EBP binding site (Fig. S2B). (F–G) Knockdown of C/EBPβ reduces Xbp1 level. Western blot (F) showing the protein level of C/EBPβ in 3T3-L1 stably expressing CONi or C/EBPβ i. Q-PCR analysis (G) of Cebpb and Xbp1 mRNA levels at 4 h or 8 h postinduction. Data are represented as mean ± s.e.m. *, P<0.05 using unpaired two-tailed Student’s t-test comparing either the samples included by the brackets or that particular sample to the rest samples.

Figure 3

Adipogenesis is associated with a low level of physiological UPR. (A) Western blot showing mobility shift of IRE1α using Phos-tag or regular SDS-PAGE gels in (left) HEK293T and (right) 3T3-L1 cells treated with 300 nM Tg for indicated period of time. “p” and “0”, hyper-and non-phosphorylated IRE1α , respectively. Solid and dotted lines on the left hand side, Phos-tag and regular gels, respectively. (B) Immunoblot showing separation of p-IREα from IRE1α using regular and Phos-tag gels with or without CIP treatment (1 h) in differentiating 3T3-L1 adipocytes. Two positive controls: Tg1, HEK293T cells treated 300nM Tg for 1.5 h; Tg 2, 3T3-L1 cells treated 300nM Tg for 4 h. HSP90, a loading control. (C) Western blot showing mobility shift of IRE1α in white adipose tissues (WAT) collected from wildtype lean and ob/ob animals using Phos-tag with or without CIP treatment. The age of the mice (in weeks) shown. (D-F) RT-PCR analysis of Xbp1 splicing (Xbp1u and s) in (D) differentiating 3T3-L1 adipocytes, (E) WAT of wildtype lean (wt) and obese animals, and (F) differentiating 3T3-L1 and MEFs with XBP1 deficiency at d8 and d9, respectively. Samples treated with Tg for 2 or 5 h were used as controls. L32, a loading control. (G) Electron microscopic images of differentiated 3T3-L1 CONi or XBP1i adipocytes at d5. Each image taken from a different cell. Arrows, ER; m, mitochondrion; N, nucleus; L, lipid droplets. Scale bar shown at the right corner of each panel. (H) Macroscopic images of differentiation of 3T3-L1 expressing CONi or XBP1i plus pBabe-vector, XBP1s or XBP1u. Oil Red-O staining was carried out on d6. (I-K) Knockdown of IRE1α reduces Xbp1 splicing and attenuates differentiation. Western blot analysis (I) showing the IRE1α and XBP1s protein levels in XBP1i and IRE1α i #4 3T3-L1 cells. Nuclear-extracts were used for blots showing the levels of XBP1s in cells treated with 300nM Tg for 3 h. HSP90 and CREB, loading controls. (J) RT-PCR analysis of Xbp1 splicing (Xbp1u and s) in 3T3-L1 cells treated with Tg for 3 h and quantitated as above. (K) Macroscopic images of differentiation of 3T3-L1 expressing CONi, XBP1i, C/EBPβ i or IRE1α i#4. Oil Red-O staining was carried out on d10. For RT-PCR analysis of Xbp1 splicing, quantification was done using the NIH ImageJ software where band densities was calculated and subtracted from the background. Data are represented as mean ± s.e.m. of data from at least three experiments *, P<0.05 using unpaired two-tailed Student’s t-test comparing the samples included by the brackets.

Figure 4

XBP1 controls Cebpa expression. (A) Western blot analysis of C/EBPα and C/EBPβ protein levels in XBP1^−/− and wildtype MEFs. GRP78 and GAPDH, loading controls. (B) Q-PCR analysis in differentiating 3T3-L1 expressing CONi and XBP1i #4. Data normalized to d0 time-point of 3T3-L1 CONi adipocytes. (C) Conservation of XBP1 binding sites on the Cebpa promoter. The core binding element ACGT is underlined. (D) ChIP analysis showing the recovery of Cebpa promoter from immunoprecipitates of C/EBPβ , XBP1 or control IgG prepared from 3T3-L1 cells at d0, 8 h postinduction and d4 as indicated. The amount of Cebpa promoter (−335 to −82 bp) recovered was quantitated using Q-PCR. Data normalized to the IgG controls at each point. (E) Luciferase assay showing effects of XBP1s on Cebpa reporter activity (−320 to +45 bp) in HEK293T cells transiently transfected with control GFP (CON) and XBP1s. The Cebpa reporter constructs with either mutation (XBPmt) or deletion (ΔXBP) of the XBP1 binding sites were included. Data represented as mean ± s.e.m.. *, P<0.05 using unpaired two-tailed Student’s t-test comparing the samples included by the brackets. (F) Model showing the role of IRE1α-XBP1 in adipogenesis. The new findings described in this paper are highlighted in bold. See text for details.