Obesity-associated variants within FTO form long-range functional connections with IRX3

Abstract

Genome-wide association studies (GWAS) have reproducibly associated variants within introns of FTO with increased risk for obesity and type 2 diabetes (T2D). Although the molecular mechanisms linking these noncoding variants with obesity are not immediately obvious, subsequent studies in mice demonstrated that FTO expression levels influence body mass and composition phenotypes. However, no direct connection between the obesity-associated variants and FTO expression or function has been made. Here we show that the obesity-associated noncoding sequences within FTO are functionally connected, at megabase distances, with the homeobox gene IRX3. The obesity-associated FTO region directly interacts with the promoters of IRX3 as well as FTO in the human, mouse and zebrafish genomes. Furthermore, long-range enhancers within this region recapitulate aspects of IRX3 expression, suggesting that the obesity-associated interval belongs to the regulatory landscape of IRX3. Consistent with this, obesity-associated single nucleotide polymorphisms are associated with expression of IRX3, but not FTO, in human brains. A direct link between IRX3 expression and regulation of body mass and composition is demonstrated by a reduction in body weight of 25 to 30% in Irx3-deficient mice, primarily through the loss of fat mass and increase in basal metabolic rate with browning of white adipose tissue. Finally, hypothalamic expression of a dominant-negative form of Irx3 reproduces the metabolic phenotypes of Irx3-deficient mice. Our data suggest that IRX3 is a functional long-range target of obesity-associated variants within FTO and represents a novel determinant of body mass and composition.

Extended Data Figure 1. Long range interactions in mouse and zebrafish

4C-seq data for the Irx3/Fto locus, visualized with the UCSC genome browser. a, Data (also shown in the circular plot in Fig. 1) generated using whole mouse embryos (E9.5), showing the frequency of interactions with the promoter of Irx3 (blue, top) or Fto (magenta, bottom). The background signal corrects for the strong correlation between (non-specific) ligation events and the linear distance along the chromosome. Poisson statistical significance (-log (p-value)) of the 4C-seq interactions over the background is plotted. Significant interactions (p<0.01), “targets,” are displayed in black. b, as above but for adult mouse brain (8 wks). c, as above for whole zebrafish embryos (24hrs post fertilization). In all, the region orthologous to the obesity association interval in the first intron of Fto is highlighted in pink.

Extended Data Figure 2. Long-range interactions at the FTO/IRX3 locus

a, ENCODE data for ChIA-PET using RNA polymerase 2 (POL2) in MCF7 (human breast adenocarcinoma) cells shows interactions between IRX3 and the obesity association interval in the first intron of FTO. No interactions are observed between the FTO promoter and the association interval. This public data is available from and was visualized with the WashU EpiGenome Browser (http://epigenomegateway.wustl.edu/browser/). b, Hi-C data previously generated{Jin, 2013 #49} in human IMR-90 (fetal lung) cells. In the association interval, the IRX3 signal is stronger than the background (random) signal. However, the signal for FTO is not. c, 3C data generated with adult (8 wks) mouse brain. Using bait (red circle) in the association interval (red rectangle), we observe more frequent interactions with the Irx3 promoter compared to control regions 1 and 2 that are 29 and 42 kb away, respectively, indicative of looping.

Extended Data Figure 3. Gene expression in mouse tissue

a, FTO expression in lung and brain, shown by RNA in situ hybridization for mouse Fto mRNA, in newborn (P1) mouse. Lungs and heart (left, whole organs) were processed simultaneously and in the same well as brain (right, sagittal section) so that the relatively higher expression in brain can be observed. b, LacZ staining for beta-galactosidase expression driven from the human FTO promoter. At top, the promoter-lacZ fusion is in the context of 162kbp of human genomic sequence carried in a bacterial artificial chromosome (BAC) containing the first three exons of FTO, the entire obesity-associated interval and any enhancers present. The broad expression is consistent with previous reports in human and mouse (see main text for references). At bottom, the promoter-lacZ construct is isolated: only the 1,237 bp proximal to the transcriptional start site are included. Broad expression is recapitulated, indicating the robust transcriptional competency of the human FTO promoter. c, In contrast, the 2,820 bp proximal human IRX3 promoter is not sufficient to drive lacZ expression, which is consistent with an enhancer-dependent transcriptional control mechanism.

Extended Data Figure 4. IRX3 expression in human brain

a, IRX3 expression in human tissues including brain. Expression data, measured on Affymetrix HG-U133 arrays, were obtained from the Body Atlas, Tissues, at http://www.nextbio.com. The median expression across all 128 human tissues from 1,068 arrays is shown by the red line. b, IRX3 expression in 11 different regions of human brain. Data were retrieved from Human Brain Transcriptome data at http://www.molecularbrain.org. Abbreviations: Amyg: amygdala; Caud nuc: caudate nucleus; Cere: cerebellum; Corp Call: corpus callosum; DRG: dorsal root ganglion; Frnt Cort: frontal cortex; Hippo: hippocampus; Hypo: hypothalamus; Pit: pituitary; Spine: spinal cord; Thal: thalamus.

Extended Data Figure 5. Linkage Disequilibrium in FTO

LD plot from HapMap phase II European dataset, visualized in the UCSC browser. LD blocks are outlined in black. Obesity-associated SNPs from the National Human Genome Research Institute (NHGRI) GWAS catalog are shown above, in green, demonstrating why this LD block is considered to define the “association interval.

Extended Data Figure 6. Irx3KO male mice are leaner with reduced adiposity

a, Representative photograph of WT and Irx3KO mice fed ND at 18 weeks of age. b, Representative anatomical views of WT and Irx3KO mice fed ND. Yellow dotted lines depict subcutaneous IWAT (left) and visceral PWAT (right). c, Tissue weights as a percentage of body weight showed smaller fat pad sizes in Irx3KO mice, compared to WT mice, in both ND and HFD conditions. (ND, WT/KO: n = 20/12; HFD, WT/KO: n = 8/5). Data are mean ± s.e.m. (*, P < 0.05 vs. WT, ND; #, P < 0.05 vs. WT, HFD). d, Representative H&E sections of PWAT, IWAT, and BAT from ND-fed mice demonstrated smaller adipocyte size in Irx3KO mice than control. e, qPCR of WT and Irx3KO PWAT for the indicated marker genes: Leptin (lep) and adiponectin (adipoq) are adipogenic markers, positively and negatively associated with adiposity, respectively; Monocyte chemoattractant protein-1 (Mcp1) correlate positively with adiposity. (*, P < 0.05 vs. the corresponding with WT value) (WT/KO: n = 10/7).

Extended Data Figure 7. Irx3KO female mice are leaner with reduced adiposity

a, Body weight (BW) changes of WT and Irx3KO female mice fed a normal diet (ND). (WT/KO: n = 15/14). b, BMI, calculated by BW/body length² (BL), is lower in Irx3KO female mice. (WT/KO: n = 7/7). c–d, body composition analysis showed reduced fat mass and to a less extent lean mass in Irx3KO female mice compared to WT mice, leading to decreased fat mass ratio. (WT/KO: n = 9/8). e, Representative H&E-stained sections of mammary gland (MG) WAT and periovarian (PO) WAT revealed smaller adipocyte size in Irx3KO female mice, compared to WT. f, MGWAT and BAT weights as a percentage of body weight. (WT/KO: n = 4/5). Data are mean ± s.e.m. (*, P < 0.05 vs. the corresponding with WT value)

Extended Data Figure 8. Higher energy expenditure of Irx3KO mice

a, Energy expenditure, corrected for lean mass (kcal/kg/hr), over 24 hour period of 18 week old WT and Irx3KO mice fed with ND and HFD. (ND WT/KO: n = 7/5; HFD WT/KO: n = 8/4). b, Locomotor activity of WT and Irx3KO mice. c, Average amount of food intake over 24 hour period with or without normalization to lean mass. d, Average locomotor activity measured over 24 hours. e–f, Elevated Ucp1 gene and protein expression in BAT. (WT/KO: n = 7/6). Data are mean ± s.e.m. *, P < 0.05 vs. the corresponding with WT value.

Extended Data Figure 9. Hypothalamic-specific Irx3 dominant negative mice are leaner with reduced adiposity

a, Schematic diagram of generation of transgenic mice overexpressing dominant-negative Irx3 in the hypothalamus. b, Immunoblotting showed EnR-Irx3 expression in the hypothalamus of mutant mice without affecting endogenous Irx3 expression, compared to control mice. c, Tissue weights as a percentage of body weight showed that fat pad sizes are smaller in mutant mice, compared to control mice. d, Reduced leptin expression and increased adiponectin gene expression in PWAT of mutant mice. (control/mutant: n = 5/7). Data are expressed as mean ± s.e.m. *, P < 0.05 compared to control group.

Extended Data Figure 10. Higher energy expenditure of Hypothalamic dominant negative Irx3 mice

a, Energy expenditure, corrected for lean mass (kcal/kg/hr), over 24 hour period of 18 week old mice. b, Locomotor activity. c–d, Average amount of food intake over 24 hour period with or without normalization to lean mass. e, Average locomotor activity measured over 24 hours. f–g, Elevated gene and protein expression of Ucp1 in BAT of mutant mice. (control/mutant: n = 5/7). Data are expressed as mean ± s.e.m. *, P < 0.05 compared to control group.

Figure 1. Long-range interactions in the IRX3/FTO locus

a, Mouse embryo 4C-seq interactions emanating from each promoter are displayed as links across the circle (darker link implies greater significance). Outer plots show significance of interactions above background (-log(p-value)). The obesity-associated interval is highlighted red. b, Magnified view of the association interval. Contained within are the orthologous locations of obesity-associated SNPs (black pips), and epigenetic marks associated with regulatory elements. Endogenous Irx3 expression is shown (1. lung, 2. brain) in Irx3^lacZ knockin mouse. Three enhancers (rectangles 3–5) drive reporter expression in lungs (3, 5) and brain (4). Other enhancers are shown in black.

Figure 2. BMI-associated SNPs are eSNPs for IRX3, not FTO, expression in human brain

a, SNPs associated with BMI in the FTO locus. 43 SNPs associated with IRX3 expression (eSNPs) are shown in red, including 11 also associated with BMI. No SNPs are associated with FTO expression (p-value>0.05). Arrowheads: IRX3 eSNPs outside the obesity-associated region (pink); arrow: rs9930506. b, In cerebellum, the allele of rs9930506 associated with increased BMI (risk allele) is correlated with increased IRX3 expression and not with FTO expression. c, Histogram plotting the number of SNPs associated with IRX3 expression in adipose (black) and brain (red) (y-axis) by the significance of their association with BMI (x-axis). Full statistical details in Methods.

Figure 3. Irx3 deficient mice are leaner and are protective against diet-induced obesity

a, Body weight in wild-type (WT) and Irx3KO mice fed normal (ND) or high-fat diet (HFD). b, Weight gain in ND or HFD. c, Fat and lean mass in WT and Irx3 KO mice. d, Fat and lean mass ratio as a percentage of body weight. e, Sections of inguinal white adipose tissue (IWAT; subcutaneous), perigonadal WAT (PWAT; visceral), brown adipose tissue (BAT), and liver from HFD-fed mice. f, Fto mRNA expression in hypothalamus and PWAT of Irx3 KO and WT mice.g-i, Glucose tolerance tests (GTT) in WT and Irx3 KO mice. Inset graphs show area under curve (AUC). j, Insulin tolerance test (ITT) in HFD-fed mice. k, Energy expenditure on ND- and HFD-fed mice. l, Gene expression in PWAT. m, Irx3 expression in the arcuate nucleus and median eminence. Left panel shows a ventral view of whole-mount stained brain. A dashed red line indicates the position of cross-section, displayed in the right panel. β-gal stained area in arcuate nucleus is marked by black line. HP, hypothalamus; OC, optic chiasm; MEm, median eminence; 3V, third ventricle. Data are expressed as mean ± s.e.m. *, P < 0.05 compared to control group. See additional statistical detail in Methods.

Figure 4. hypothalamus-specific dominant negative Irx3 mice recapitulate the metabolic phenotype of Irx3 deficient mice

a, Body weight of control (EnR-Irx3) and mutant mice (EnR-Irx3;Ins2-Cre) fed normal diet. b, Fat and lean mass ratio as a percentage of body weight.. c, H&E-stained sections of IWAT, PWAT and BAT. d, Glucose tolerance test. e, Energy expenditure corrected for lean mass (kcal/kg/hr). f, qPCR in PWAT in control and mutant mice. Data are expressed as mean ± s.e.m. *, P < 0.05 compared to control group. Additional detail in Methods.