Acute intermittent hypoxia drives hepatic de novo lipogenesis in humans and rodents

Abstract

Background and aims: Non-alcoholic fatty liver disease (NAFLD) is the most common chronic liver condition. It is tightly associated with an adverse metabolic phenotype (including obesity and type 2 diabetes) as well as with obstructive sleep apnoea (OSA) of which intermittent hypoxia is a critical component. Hepatic de novo lipogenesis (DNL) is a significant contributor to hepatic lipid content and the pathogenesis of NAFLD and has been proposed as a key pathway to target in the development of pharmacotherapies to treat NAFLD. Our aim is to use experimental models to investigate the impact of hypoxia on hepatic lipid metabolism independent of obesity and metabolic disease.

Methods: Human and rodent studies incorporating stable isotopes and hyperinsulinaemic euglycaemic clamp studies were performed to assess the regulation of DNL and broader metabolic phenotype by intermittent hypoxia. Cell-based studies, including pharmacological and genetic manipulation of hypoxia-inducible factors (HIF), were used to examine the underlying mechanisms.

Results: Hepatic DNL increased in response to acute intermittent hypoxia in humans, without alteration in glucose production or disposal. These observations were endorsed in a prolonged model of intermittent hypoxia in rodents using stable isotopic assessment of lipid metabolism. Changes in DNL were paralleled by increases in hepatic gene expression of acetyl CoA carboxylase 1 and fatty acid synthase. In human hepatoma cell lines, hypoxia increased both DNL and fatty acid uptake through HIF-1α and -2α dependent mechanisms.

Conclusions: These studies provide robust evidence linking intermittent hypoxia and the regulation of DNL in both acute and sustained in vivo models of intermittent hypoxia, providing an important mechanistic link between hypoxia and NAFLD.

Keywords: HIF; Hypoxia; Lipid metabolism; NAFLD.

Fig. 1

The assessment of the effect of intermittent hypoxia in the fasting state and during a hyperinsulinemia euglycemic clamp on insulin sensitivity, glucose metabolism (C–E) and free fatty acid metabolism (F–H) in healthy male volunteers. A: The experimental protocol comparing the effect of acute intermittent hypoxia (blue bars) and room air (red bars) (DNL = de novo lipogenesis; SAT = subcutaneous adipose tissue). B: A representative trace of continuous SaO₂ and heart rate monitoring showing the effect of the intermittent hypoxia protocol to achieve desaturations (using ApneaLink^TM plus). C–F: The assessment of the effect of intermittent hypoxia (blue bars) vs control (air) (red bars) on indices of glucose and lipid metabolism measured using a combination of stable isotopes and subcutaneous abdominal adipose microdialysis. C: Glucose production was quantified using the appearance of isotopically labelled glucose ([²H]-glucose) measured in the fasting steady state. D: The rate of glucose infusion required to achieve euglycemia corrected for plasma insulin (M/I) measured in the hyperinsulinemia steady state. E: Glucose disposal was quantified isotopically in the hyperinsulinemia state. F: NEFA appearance. G: NEFA disposal. NEFA metabolism (F & G) was quantified by measuring the appearance and disposal of isotopically labelled palmitate ([U¹³C]-palmitate) within the NEFA total palmitate isolated from the plasma fraction measured using gas chromatography mass spectrometry. H: The rate of glycerol appearance within the subcutaneous abdominal adipose tissue interstitial fluid assed by adipose tissue microdialysis in the fasting and hyperinsulinemia steady state. Data are presented as mean ± standard error, *p < 0.05 (Student's t-test). (For interpretation of the references to colour in this figure legend, the reader is referred to the Web version of this article.)

Fig. 2

The effect of acute intermittent hypoxia on plasma TAG, VLDL TAG and DNL measured in the plasma TAG and VLDL TAG fractions in healthy male volunteers. Room air (red bars), intermittent hypoxia (blue bars). A and B: TAG was measured within the plasma (A) and isolated VLDL fractions (B). C and D: DNL measured in the plasma TAG (C) and VLDL TAG fractions (D). DNL was measured via quantification of deuterated water into the isolated palmitate TAG fraction either from whole plasma (C) or the liver specific VLDL fraction (D). (VLDL = very low-density lipoprotein; TAG = triacylglycerol; DNL = de novo lipogenesis); Data is presented as mean ± standard error, *p < 0.05 (Student's t-test). (For interpretation of the references to colour in this figure legend, the reader is referred to the Web version of this article.)

Fig. 3

The effect of intermittent hypoxia on DNL in rodents. Adult male Wistar rats were exposed to either normoxia (ambient air) (n = 8) (red bars) or intermittent hypoxia (IH) (blue bars) (n = 7) (FiO₂ to 10 ± 1% 12 times/hr for 6 h/day during sleep for 14 days). A: Animal weights across the study protocol (circles (red) = controls; squares (blue) = intermittent hypoxia). B: Nadir, peak and baseline oxygenation of the cages (representative data from 1 h in 2 cages). C: Hepatic gene expression (ACC1: acetyl-coA carboxylase; FASN: fatty acid synthase; CTP1A: carnitine palmitoyltransferase 1A). D: Liver DNL measured as enrichment of the liver lipid palmitate fraction with deuterated water (271/270 = tracer:tracee ratio of enriched to non-enriched palmitate). E: Plasma DNL measured as enrichment of the plasma lipid palmitate fraction with deuterated water. F: Liver triaclygylercol (TAG). Control animals in air (red bars), intermittent hypoxia (IH) (blue bars). Data is presented as mean ± standard error, *p < 0.05 (Student's t-test). (For interpretation of the references to colour in this figure legend, the reader is referred to the Web version of this article.)

Fig. 4

The effect of hypoxia on in vitro hepatocyte lipid metabolism. A: mRNA levels measured by qRT-PCR in Huh-7 hepatoma cells incubated under 1% (blue bars) or 21% (red bars) oxygen for 24 h. Gene expression of (sterol regulatory element-binding protein 1 (SREBF1) and fatty acid synthase (FASN), relative to GAPDH. B: The effect of hypoxia (1% (blue bars) vs 21% (red bars)) for 24 h on de novo lipogenesis in Huh-7 and HepG2 cells (DNL). C: The effect of hypoxia ((1% (blue bars), 3% (white bars) and 21% (red bars)) on DNL (Huh7 cells). DNL was determined by measuring 1-[¹⁴C]-acetate incorporation into the lipid fraction of cells incubated with ¹⁴C-acetate cultured under stated oxygen tensions. D: The effect of hypoxia (1% (blue bars) vs 21% (red bars)) for 24 h on free fatty acid (FFA) uptake in Huh7 and HepG2 cells. E: The effect of hypoxia ((1% (blue bars), 3% (white bars) and 21% (red bars)) on FFA uptake (Huh7 cells). FFA uptake was defined by the amount of ³H palmitate taken up by cells after 12 h incubation with ³H-palmitate in serum-free media F: The effect of hypoxia on β-oxidation (1% (blue bars) vs 21% (red bars)) for 24 h in Huh-7 and HepG2 cells. β-oxidation was measured by the amount of ³H-water released by cells into the culture media. Data represents 3 independent experiments in quadruplicates. Error bars indicate mean ± standard error (n = 3) *p < 0.05; **p < 0.001 (Student's t-test). (For interpretation of the references to colour in this figure legend, the reader is referred to the Web version of this article.)

Fig. 5

The hypoxia induced effect on de novo lipogenesis is HIF dependent. A: HIF1-α and HIF2-α Western blot in response to different oxygen tensions. B: Inhibiting HIF signaling with NSC 134754 (NSC) abrogates the hypoxia (1% (blue bars), 21% (red bars)) induced increase in DNL in a dose-dependent manner (NSC doses are 0.02–0.1 μM). C: HIF stabilization with 10 μM of FG4592 results in increased DNL in 21% oxygen (red bars). D: HIF1-α and HIF2-α can be stably overexpressed in normoxia. E: Overexpression of HIF1-α and HIF2-α results in increased DNL and fatty acid uptake (F). Huh-7 cells were transfected with siRNA-mediated scrambled RNA (scRNA), HIF1 or HIF-2α for 24 h. Cells were incubated at 21% (red bars) or 1% (blue bars) oxygen for a further 24 h. Following this, HIF protein expression was determined by Western blotting from lysate. Following transfection, 1-[¹⁴C]-acetate incorporation into lipid and ³H-palmitate uptake was measured in these cells. Experiments were performed three times in quadruplicates. Data are presented as mean ± standard error, *p < 0.05; **p < 0.001 (Student's t-test). (For interpretation of the references to colour in this figure legend, the reader is referred to the Web version of this article.)