Pro-inflammatory CD11c+CD206+ adipose tissue macrophages are associated with insulin resistance in human obesity

Abstract

Objective: Insulin resistance and other features of the metabolic syndrome have been causally linked to adipose tissue macrophages (ATMs) in mice with diet-induced obesity. We aimed to characterize macrophage phenotype and function in human subcutaneous and omental adipose tissue in relation to insulin resistance in obesity.

Research design and methods: Adipose tissue was obtained from lean and obese women undergoing bariatric surgery. Metabolic markers were measured in fasting serum and ATMs characterized by immunohistology, flow cytometry, and tissue culture studies. RESULTS ATMs comprised CD11c(+)CD206(+) cells in "crown" aggregates and solitary CD11c(-)CD206(+) cells at adipocyte junctions. In obese women, CD11c(+) ATM density was greater in subcutaneous than omental adipose tissue and correlated with markers of insulin resistance. CD11c(+) ATMs were distinguished by high expression of integrins and antigen presentation molecules; interleukin (IL)-1beta, -6, -8, and -10; tumor necrosis factor-alpha; and CC chemokine ligand-3, indicative of an activated, proinflammatory state. In addition, CD11c(+) ATMs were enriched for mitochondria and for RNA transcripts encoding mitochondrial, proteasomal, and lysosomal proteins, fatty acid metabolism enzymes, and T-cell chemoattractants, whereas CD11c(-) ATMs were enriched for transcripts involved in tissue maintenance and repair. Tissue culture medium conditioned by CD11c(+) ATMs, but not CD11c(-) ATMs or other stromovascular cells, impaired insulin-stimulated glucose uptake by human adipocytes.

Conclusions: These findings identify proinflammatory CD11c(+) ATMs as markers of insulin resistance in human obesity. In addition, the machinery of CD11c(+) ATMs indicates they metabolize lipid and may initiate adaptive immune responses.

FIG. 1.

Immunohistochemistry of subcutaneous adipose tissue in obesity. A: Formalin-fixed adipose tissue section stained for CD68 showing a crown (*) and several resident ATMs (arrowheads). B: Serial section stained for CD11c showing crown ATMs preferentially expressing CD11c. C: Formalin-fixed adipose section stained for CD11c and CD68 or with nonspecific isotype control antibodies confirming that crown ATMs (upper panel) but not resident ATMs (middle panel) express CD11c. D: Frozen adipose tissue section stained for CD206 showing a crown (*) and several resident ATMs. E: Frozen section stained for CD206 and CD11c (upper panel) or with isotype control antibodies (lower panel) showing crown ATMs expressing both CD11c and CD206 but resident ATMs expressing only CD206. Scale bar in all images = 50 μm. (A high-quality digital representation of this figure is available in the online issue.)

FIG. 2.

Flow cytometry of subcutaneous adipose tissue stromovascular cells. A: After excluding doublets and dead cells, a CD14 versus CD45 contour plot identified three stromovascular cell populations (PAs, LYMs, and ATMs). B: Cytospins of each population stained for CD68 confirmed that the CD14⁺CD45⁺ population represents ATMs. Scale bar = 20 μm. C: Flow cytometry phenotype of gated PA, LYM and ATM populations stained for CD11c and CD206 reveals that PA cells do not express either marker, while a minority of LYM cells express low levels of CD11c. ATM cells could be separated into three distinct subpopulations when stained for CD11c and CD206; one of these, CD11c⁺CD206⁻ ATMs, had a similar phenotype to blood monocytes (MONO). Background staining by isotype control antibodies is indicated by gray lines. D: CD11c⁺CD206⁻ and CD11c⁻ ATMs were isolated by flow cytometry cell sorting and stained with Oil red O. Representative images show CD11c⁺CD206⁺ ATMs contain more lipid than CD11c⁻ ATMs. Scale bar = 10 μm. (A high-quality digital representation of this figure is available in the online issue.)

FIG. 3.

A and B: ATM quantitation in subcutaneous and omental adipose obtained from FOb, Ob, and ObMS women. Crown density and mean adipocyte size determined by histology. C: Significant correlation between histological and flow cytometry measures of crown ATM density. D and E: CD11c⁺CD206⁺ (crown) and CD11c⁻ (resident) ATM densities determined by flow cytometry. F: The CD11c⁺CD206⁺/CD11c⁻ ratio is increased in ObMS women, confirming enrichment of crown ATMs in the metabolic syndrome. G and H: Relationship between insulin resistance and CD11c⁺CD206⁺/CD11c⁻ ratio in subcutaneous and omental adipose in the initial cohort of 24 obese women and in a subsequent cohort of 89 obese women. *, **, ***P < 0.05, 0.005, 0.0005, respectively (Mann Whitney t test).

FIG. 4.

A: Cell surface phenotype of subcutaneous ATMs and blood monocytes. Innate immune molecules. B: Integrins. C: CD34. D: Scavenger receptors. E: Adaptive immune molecules. Monocytes and ATM subsets were identified using anti-CD206FITC, -CD11c-allophycocyanin, and -CD14PC7 antibodies. PE-conjugated antibodies were used to determine the expression of cell surface markers. Results are means ± SE of three independent experiments. *Significantly different (P < 0.05) in ANOVA by posttest comparison.

FIG. 5.

Cytokine secretion by cultured ATMs subcutaneous CD11c⁻ and CD11c⁺CD206⁺ ATMs (20,000 cells/well) were isolated by flow cytometry cell sorting and cultured in duplicate for 24 h in 100 μl RPMI/10% FCS ± 20 ng/ml LPS. Cytokine concentrations in the supernatant are shown. Results are means ± SE of three independent experiments. Differences between CD11c⁻ and CD11c⁺CD206⁺ ATMs for all cytokines except CCL2 were significant (P < 0.05 by paired t test) following normalization.

FIG. 6.

A: Crown ATMs and PAs are enriched for mitochondria. Formalin-fixed adipose section stained with antibodies against VDAC1 and CD68 or nonspecific antibodies. VDAC1 staining intensity was greatest for crown ATMs and less intense for resident ATMs and CD68-negative cells. Scale bar = 50 μm. B: Mitochondria per cell was calculated as the relative amount of mitochondrial versus genomic DNA, determined by qPCR of DNA isolated from sorted stromovascular cells using CYTB and LEP primers. Results are means ± SE of three independent experiments. *Significantly different (P < 0.05) in ANOVA by posttest comparison. C: Stromovascular cells were incubated in RPMI/10% FCS with or without 50 nmol/l Mitotracker red for 15 min in a 37° water bath and then incubated on ice with CD206FITC, CD11cPE, and CD45PC7 antibodies before analysis using flow cytometry. Results are means ± SE of three independent experiments. *Significantly different (P < 0.05) in ANOVA by posttest comparison. (A high-quality digital representation of this figure is available in the online issue.)

FIG. 7.

Crown ATMs release factors that inhibit insulin action serum-free F3 medium was conditioned for 48 h with 50,000 total stromovascular cells, CD11c⁺CD206⁺ ATMs, CD11c⁻ ATM, LYM, or PA cells. Differentiated human SGBS adipocytes were then incubated in conditioned medium (20% vol/vol) in fresh F3 medium for 48 h, before measurement of insulin-stimulated ³H-deoxyglucose uptake. Data (means ± SE) are from four independent experiments using cells isolated from subcutaneous (n = 3) and omental (n = 1) adipose tissue from three obese women with metabolic syndrome. Glucose uptake was normalized to the cpm values from total stromovascular cell-conditioned medium and 10 nmol/l insulin (100%). *Significantly different (P < 0.05) in ANOVA by posttest comparison.