The prevalence of diabetic nephropathy is increasing rapidly world-wide [1], but presently there is no treatment and approximately 45% of all cases of end-stage renal disease are due to diabetic nephropathy [2]. The recent focus of mechanisms underlying diabetic nephropathy has shifted from the glomerulus to the proximal tubule [3]. The kidney proximal tubule performs a majority of the active transport in the kidney, which requires a high ATP production and a high cellular content of mitochondria. The ensuing high rate of oxidative phosphorylation is a potential source of superoxide radicals since an estimated 0.1–0.2% of the mitochondrial O₂ usage results in superoxide formation. Increased passage of electrons down the respiratory chain increases the mitochondria membrane potential and therefore also formation of superoxide [4].

Mitochondria uncoupling may be a protective mechanism to counter increased mitochondria superoxide formation. Shunting of protons across the inner mitochondrial membrane lowers the membrane potential and limits superoxide formation. However, O₂ consumption required for proton transport uncoupled from ATP production will be added to that required for oxidative phosphorylation and therefore increases total O₂ consumption. The level of mitochondria uncoupling can be evaluated in isolated mitochondria during ATP-synthase inhibition [5]. Then, the addition of electron-donating substrates such as glutamate can increase O₂ consumption only if an uncoupling mechanism is present. This is denoted as glutamate-stimulated O₂ consumption of isolated mitochondria in the present study. There are five different isoforms of uncoupling proteins (UCP) known to mediate mitochondria uncoupling [6], but UCP-2 is the isoform expressed in both rat and human kidneys [5], [7] where it is reported to mediate mitochondria uncoupling in the diabetic kidney [5]. Whereas reduced superoxide formation, via mitochondria uncoupling, may protect the diabetic kidney from damaging oxidative stress, the concomitantly increased O₂ consumption may result in hypoxia and contribute to the development of diabetic nephropathy. Indeed, kidney tissue hypoxia in diabetes has been reported [8]. The present study investigates the role of UCP-2 in the regulation of mitochondria function and oxidative stress in the diabetic kidney by applying in vivo siRNA-mediated knockdown of UCP-2.

UCP-2 protein expression was increased in the kidneys of diabetic rats but siRNA resulted in −30% decreased expression compared to baseline in control animals and −55% compared to baseline in diabetic animals. Scrambled siRNA did not significantly alter UCP-2 protein expression in any of the groups compared to corresponding untreated animals (Fig. 1). Diabetic animals displayed increased blood glucose levels compared to control animals. siRNA did not affect either blood glucose levels or body weights (Table 1). Diabetic animals administered UCP-2 siRNA displayed increased state 4 respiration compared to untreated controls, whereas scramble siRNA had no effect. State 3 respiration and RCR of isolated mitochondria did not differ between any of the groups (Fig. 2).

Mitochondria glutamate-stimulated O₂ consumption was increased in mitochondria isolated from the kidneys of untreated diabetic rats compared to corresponding controls. UCP-2 siRNA, but not scrambled siRNA, increased glutamate-stimulated O₂ consumption in both controls and diabetics. GDP inhibited glutamate-stimulated O₂ consumption in untreated diabetics and diabetic animals receiving scrambled siRNA. No effect of GDP was observed in any of the control groups (Fig. 3). ADP inhibited glutamate-stimulated O₂ consumption in mitochondria isolated from diabetic animals treated with UCP-2 siRNA, but had no effect in any of the other groups (Fig. 4). CAT inhibited glutamate-stimulated O₂ consumption in both control and diabetic animals treated with UCP-2 siRNA, but did not affect glutamate-stimulated O₂ consumption in any of the untreated animals or animals treated with scrambled siRNA (Fig. 5).

Baseline TMRM-uptake in presence of oligomycin was similar in all control groups and untreated diabetics. Baseline TMRM-uptake was lower in diabetic animals treated with UCP-2 siRNA compared to all other groups. GDP increased TMRM-uptake in untreated diabetic animals, but had no effect in any of the other groups. Furthermore, CAT increased TMRM-uptake in UCP-2 siRNA-treated diabetic animals whereas CAT had no effect in any of the other groups (Fig. 6).

Mitochondria ATP production was similar in all groups, and substantially lower in the presence of either FCCP, oligomycin or the combination of oligomycin and CAT (Fig. 7).

Plasma MDA levels were elevated in untreated diabetic animals compared to controls but unaffected by UCP-2 siRNA (Fig. 8). TBARS in kidney cortex was increased in untreated diabetics, but decreased in the diabetic animals administered UCP-2 siRNA. Neither UCP-2 siRNA to controls nor scrambled siRNA to any of the groups altered kidney tissue TBARS (Fig. 9).

The main new finding from the present study was that mitochondria uncoupling directly can regulate mitochondria membrane potential and oxidative stress in the diabetic kidney.

Baseline mitochondria uncoupling in the diabetic kidney was evident as increased UCP-2 expression, glutamate-stimulated O₂ consumption and increased mitochondria membrane potential after UCP-2 blockade by GDP, which is consistent with our previous report [5]. However, UCP-2 knockdown in diabetic animals resulted in a paradoxical increase in uncoupling evidenced by increased glutamate-stimulated O₂ consumption. This was a distinct uncoupling pathway since it was unaffected by blockade of UCP-2 with GDP. Since this increased uncoupling after siRNA to UCP-2 was inhibited by blockade of the ANT with ADP or CAT, we concluded that it was mediated via the ANT. The failure of GDP to inhibit this uncoupling excludes a role for residual UCP-2. During normal function, ANT exchanges ADP for ATP across the mitochondria inner membrane [9] and alters between two conformations (c and m-conformation) as translocation occurs. However, ANT can mediate mitochondria uncoupling under certain conditions. The amount of mitochondrial ANT has been reported to determine the level of basal uncoupling [10] and uncoupling via the ANT can be induced by fatty acids [11].

It was surprising that the elevated mitochondria uncoupling in UCP-2 siRNA-treated diabetics was inhibited by addition of ADP after blocked ATP-synthesis since, in absence of ATP, the ANT pathway should be inactive. However, ATP also is produced by the citric cycle. Indeed, although mitochondria ATP production during ATP-synthase inhibition was substantially reduced, some ATP production remained. Presumably, this was sufficient to exchange for ADP and induce ANT-mediated mitochondrial uncoupling. However, the ANT may lock in c-conformation in the presence of oligomycin and excess ADP or CAT. This would inhibit proton leakage and reduce mitochondria uncoupling. Moreover, in potato tuber mitochondria the ANT can import double stranded DNA independently of ATP-synthesis i.e. unaffected by oligomycin alone. Importantly, locking the ANT in c-conformation with either oligomycin and ADP or CAT significantly reduced DNA import [12]. In mitochondria isolated from siRNA-treated diabetic rats the ANT provides a second ATP-independent uncoupling pathway, presumably to regulate oxidative stress. Locking the ANT in c-conformation had no effects in untreated diabetic animals, demonstrating that ANT is not causing the mitochondrial uncoupling in these animals.

Mitochondria uncoupling was unaffected by ADP in untreated diabetic rats even though ADP has been reported to inhibit UCP [13]. However, the lack of UCP-2 inhibition by ADP has previously been reported in kidney mitochondria from diabetic rats [5] and, to the best of our knowledge, inhibition of UCP-2-mediated uncoupling by ADP has only been studied during normal conditions. Therefore, future studies are needed in order to evaluate if ADP actually can inhibit UCP-2 function in diabetic kidney mitochondria.

UCP-2 knockdown in control animals resulted in increased mitochondria uncoupling, which paradoxically did not result in decreased mitochondrial membrane potential. It may be speculated that glutamate (i.e. electron-donating NADH) is present in sufficient amount to counteract relatively small changes in uncoupling activity and therefore maintain normal membrane potential. This speculation is supported by the results showing increased TMRM uptake after addition of CAT to these mitochondria.

Mitochondria membrane potential, as indicated by TMRM-uptake, was not increased in untreated diabetic animals, which is contrary to previous reports [14], [15]. These studies were performed on isolated mitochondria under conditions reflecting those of control animals and therefore do not reflect the in vivo situation of hyperglycemia and increased mitochondria substrate load. Incubation with GDP increased membrane potential in untreated diabetics, directly demonstrating a regulatory role of mitochondria uncoupling via UCP-2 in the regulation of mitochondria membrane potential. Interestingly, increased ANT-mediated uncoupling in the UCP-2 siRNA-treated diabetics resulted in significantly lower mitochondrial membrane potential. Importantly, CAT increased mitochondria membrane potential in diabetic animals administered UCP-2 siRNA, which further supports a crucial compensatory involvement of ANT after acutely reduced UCP-2 function.

Increased mitochondria uncoupling may be a protective mechanism to regulate mitochondria superoxide formation and prevent excessive oxidative damage in the diabetic kidney [16]. Indeed, the increased ANT-mediated uncoupling after UCP-2 knockdown reduced oxidative stress in the diabetic kidney. However, this may to be a kidney specific mechanism since although whole-body oxidative stress, indicated by circulating MDA-levels was increased in diabetes, it was not significantly reduced by siRNA to UCP-2. The explanation for the discrepancy between kidney and whole-body regulation of oxidative stress in diabetes may relate to specific role of UCP-2 in the kidney. However, UCP-2 is the only isoform in the kidney whereas in other tissues UCP-3 and other isoforms will presumably not be affected by UCP-2 siRNA. Therefore, compensatory uncoupling via ANT in other tissues body may not occur to the same extent as much in other tissues, resulting in less effect on circulating markers of oxidative stress. Also, reactive oxygen species are produced by several different sources and the kidney proximal tubule is especially influenced by mitochondria-derived superoxide formation due to its high metabolic demand. It is therefore possible that the beneficial effect of mitochondria uncoupling in reducing oxidative stress is more pronounced in the kidney compared to the whole body. It seems likely that even though oxidative stress levels are increased in diabetes mitochondria uncoupling may present a mechanism to limit an even more exaggerated oxidative stress level in the diabetic kidney.

The results from the present study confirm the importance of mitochondria uncoupling in regulating mitochondrial oxidative stress. Indeed, when uncoupling via UCP-2 was inhibited the uncoupling function was rapidly and quantitatively replaced by a nascent uncoupling via ANT. A similar compensatory mitochondria uncoupling via ANT has been reported from skeletal muscle mitochondria of UCP-3 knockout-mice. Two weeks caloric restriction resulted in increased CAT-sensitive uncoupling and it was proposed that increased ANT uncoupling compensates for the absence of UCP-3 [17]. Furthermore, ANT is expressed in the rat kidney [18] and is activated by fatty acids, alkenals such as 4-hydroxynonenal [19] and AMP [20]. Oxidative stress in diabetes increases lipid peroxidation and an enhanced free fatty acid production would be expected to increase ANT activity. Thus, increased ANT activation via lipid peroxidation products, may explain the increased kidney mitochondria uncoupling after UCP-2 siRNA. We speculate that ANT compensates for decreased UCP-2 function to protect the mitochondria from excessive diabetes-induced oxidative stress. Indeed, Duval et al. demonstrated that UCP-2 siRNA increased mitochondria superoxide production in murine endothelial cells [21]. It is possible that the initial event after UCP-2 siRNA administration in our study is increased mitochondrial superoxide production, leading to lipid peroxidation and activation of ANT-mediated mitochondria uncoupling. Remarkably, the compensatory ANT-mediated uncoupling is more potent compared to the UCP-2-mediated uncoupling in untreated diabetic animals, as evident from both the lower mitochondrial membrane potential and the reduced oxidative stress in the kidney of these animals. However, increased mitochondria uncoupling results in increased mitochondrial O₂ consumption. It should be noted that the normal kidney O₂ consumption is high already during baseline conditions due to the high metabolic demand for active tubular transport. This will be further elevated in diabetes due to enhanced proximal transport without a corresponding increase in blood flow [16], resulting in tissue hypoxia throughout the diabetic kidney [8]. Kidney hypoxia is strongly implicated as a common pathway for end-stage renal disease [22] and it may be speculated that although a further increased mitochondria uncoupling via the ANT results in lower oxidative stress, the concomitantly increased O₂ consumption will accelerate kidney tissue hypoxia and development of diabetic nephropathy.

In conclusion, the present study demonstrates that UCP-2 is directly involved in regulating mitochondrial membrane potential and therefore also is a potential mechanism to prevent excessive mitochondria superoxide formation in the diabetic kidney. Abolished UCP-2-mediated mitochondria uncoupling results in an even more potent ANT-mediated uncoupling which reduces membrane potential and oxidative stress damage in the diabetic kidney. However, mitochondria uncoupling increases total O₂ consumption and can potentially amplify the already existing kidney tissue hypoxia in diabetes and therefore accelerate development of diabetic nephropathy (Fig. 10).