Osteonecrosis (ON) is a disabling disorder mainly affecting the hips of young adults in the third and fourth decade of their life. ON has been associated with a variety of risk factors and can be characterized as idiopathic (of no apparent etiology) or secondary from several etiology-associated factors, such as hyperlipidaemia, hypercortisonism, dysbaric phenomena, autoimmune diseases, endotoxic reactions, alcoholism and smoking [1], [2]. Thrombophilia and hypofibrinolysis have also been associated with the pathogenesis of ON which consequently results to bone ischemia, apoptosis of the osteocytes and the bone marrow and final establishment of a bone infarct. [3].

Low oxygen tension, also known as hypoxia, is one of the main pathophysiological characteristics of osteonecrosis [4]. Hypoxia can also occur in many other known diseases like ischemic conditions [5] (myocardial infarct, strokes), cancer [6] or even osteoarthritis [7]. HIF-1 (Hypoxia inducible factor-1) is the major transcriptional regulator triggered in hypoxia in order to promote adaptation to the new environment [8]. HIF-1 binds to regulatory DNA sequences called Hypoxia-Response Elements (HRE) thus controlling the expression of genes involved in cell metabolism, erythropoiesis, angiogenesis, invasion and metastasis. It is a heterodimer that consists of HIF-1α, which is the oxygen regulated subunit, and the constitutively expressed HIF-1β [9]. Under normal oxygen conditions, HIF-1α is continuously produced and destroyed in a process involving hydroxylation of two prolines within the oxygen-dependent degradation domain (ODD). Hydroxylation is mediated by conserved prolyl hydroxylases (PHDs), which act as oxygen sensors. Under hypoxic conditions, hydroxylation is impaired and HIF-1α is stabilized, it translocates to the nucleus where it dimerizes with HIF-1β, thus promoting the transcription of its target genes [10].

The role of HIF-1α in osteonecrosis still remains elusive. It was shown that HIF-1α is significantly increased in the ischemic side of the epiphysial cartilage in the femoral head [11]. HIF-1α was also detected at the reparative zone of collapsed femoral heads of ON patients [12]. Moreover, VEGF (Vascular Endothelial Growth Factor), which is a target of HIF-1α, was also increased in ischemia of femoral head, leading to revascularization of the cartilage thus promoting remodeling after the collapse [11], [12]. The importance of HIF-1α to the cartilage was known before, since it has been reported that HIF-1α is essential not only for cell growth and survival of growth plate chondrocytes in vivo [4], [13] but also for extracellular matrix formation [14]. Latest studies suggest that hypoxia promotes via HIF-1α a metabolic reprogramming in bone marrow–derived angiogenic cells which leads to increased survival in ischemic tissue [15]. For these reasons HIF-1α could be a protein of great significance in the pathogenesis or reparative progress of ON. Furthermore many genetic risk factors (mostly associated with coagulation and fibrinolysis) were already been linked to the pathogenesis of ON [16]. For these reasons we investigated the genetic implication of three well-known and characterized polymorphisms (C111A in exon 2 and C1772T and G1790A in exon 12) of HIF-1α in the appearance of ON.

In order to examine the association of HIF-1α gene polymorphisms with the susceptibility to osteonecrosis (ON) we analyzed the genotype and allele frequencies of three known SNPs located in HIF-1α translated regions (C111A in exon 2, and C1772T and G1790A in exon 12 [23]) between ON patients of different etiologies and control subjects. Analysis of the genotypes was performed on PCR fragments amplified from DNA extracted from peripheral blood using specific restriction endonucleases (Fig 1, A, C, D). To confirm the polymorphisms found, sequencing of the PCR fragments of all subjects carrying the rare allele was performed (Fig 1B for C1772T SNP).

Concerning the C1772T SNP there was no significant deviation from the Hardy-Weinberg equilibrium in control (P = 0.777) and patient group (P = 0.367, Table 2). Out of the 63 controls, 50 cases were type CC, 12 cases were type CT and 1 case was type TT. Concerning patients diagnosed with ON, out of the 134 cases, 101 cases were type CC, 32 cases were type CT and 1 case was type TT. Statistics showed no significant differences in genotype (P = 0.592, OR (95% CI) = 1.257 (0.608 to 2.597)) and allele (P = 0.742, OR (95% CI) = 1.162 (0.600 to 2.254)) frequencies for the C1772T polymorphism, between ON patients and controls (Table 3). In accordance with a previous corresponding study in a Korean population, that similarly did not find association between the C1772T SNP and ON in the whole patient sample, but detected however an association within a subgroup [24], we discriminated subjects in males and females and in subgroups of ON, depending on the etiology of appearance. When we compared control cases versus different ON subgroups (1: idiopathic, 2: steroid induced and 3: other etiologies), we still could not find a significant difference in genotype (P vs idiop.  = 1, OR (95% CI) = 0.887 (0.302 to 2.607), P vs steroid.  = 0.433, OR (95% CI) = 1.417 (0.644 to 3.120), P vs other etiol.  = 0.773, OR (95% CI) = 1.282 (0.436 to 3.881), Table 4) nor in allele frequencies (P vs idiop.  = 0.807, OR (95% CI) = 0.827 (0.302 to 2.267), P vs steroid.  = 0.590, OR (95% CI) = 1.244 (0.605 to 2.560), P vs other etiol.  = 0.604, OR (95% CI) = 1.366 (0.515 to 3.623), Table 4). When we used the male population in our subgroups for the analysis, the difference still remained non significant (data not shown).

Regarding the G1790A SNP there was no deviation from the Hardy-Weinberg equilibrium for the control group (P = 0.846) but there was a significant deviation for the patient group, probably due to the low sample number and the rarity of our mutant allele (P<0.0001, Table 2). Out of the 63 controls, 60 cases were type GG, 3 cases were type GA and we found no case of type AA. Concerning total ON patients, out of the 134 cases, 132 cases were type GG, 1 case was type GA and 1 case was type AA. Statistics showed again no significant differences in genotype (P = 0.3297, OR (95% CI) = 0.303 (0.049 to 1.862)) and allele (P = 0.3894, OR (95% CI) = 2.154 (0.428 to 10.830)) frequencies for this polymorphism between ON patients and controls (Table 3). Due to the small number of cases carrying the rare allele, we didn’t further compare controls with subgroups of ON patients.

As for C111A SNP, we did not find the rare A allele in controls nor in any of the subgroups of ON patients. Therefore, no association was attempted between controls and ON patients for this particular SNP (see Table 3).

Since the SNPs (C1772T and G1790A) that we tested were suggested not to be statistically significant concerning the appearance of ON, we further tried to validate our negative result by using a biological approach. For this we investigated the functional significance of the specific allelic variations in the HIF-1α locus, at the protein level. At first we investigated the activity of the variants using a transcription activity assay with a pGL3–5HRE-VEGF luciferase reporter construct. We co-transfected osteosarcoma Saos-2 and HEK293 cells with the reporter plasmid together with FLAG-HIF-1α wt or with the C1772T mutant (corresponds to FLAG-HIF-1α/P582S) and the G1790A mutant (corresponds to FLAG-HIF-1α/A588T, respectively [20]). Transfection with HIF-1α wt led to a 2.5 to 3fold increase in transcriptional activity both in Saos-2 and in HEK293 cells (Fig. 2, A and B). In Saos-2 cells the expression of both P582S and A588T variants originally led to a small decrease in activity compared to that observed in wt but this was proven not to be statistically significant (Fig. 2A, P_{vs P582S} = 0.7338, P_{vs A588T} = 0.3724). That was also the case for HEK293 cells, where the small differences observed between the activity of the variants were also proven not significant (Fig. 2B, P_{vs P582S} = 0.4652, P_{vs A588T} = 0.9537). Importantly enough, the variations observed between each mutant and the wt molecule showed different traits between the two cell lines tested. This fact implies their lack of significance as was already demonstrated by the statistic analysis. Since we excluded differences in transcriptional activity between HIF-1α variants we next tested if localization or protein expression of HIF-1α is affected by these two mutations. We showed that both HIF-1α P582S and HIF-1α A588T remain nuclear when transfected in Saos-2 and HEK293 cells, exactly like wt (Fig. 2C and D, respectively). Protein levels tested in both Saos-2 and HEK293 cells also remain unchanged between wt and mutants (Fig.2E and F).

In conclusion, in the present study we showed that C1772T and G1790A SNPs found in translated loci of HIF-1α are not associated with the occurrence of osteonecrosis. This could be because these specific polymorphisms seem to have no consequence in the overall activity or protein expression of HIF-1α.

Hypoxia is a main characteristic of several diseases like cancer, ischemic disorders and bone disorders like osteonecrosis and osteoarthritis, where it may also play a pivotal role in their pathogenesis [4], [5], [7], [8]. Osteonecrosis (ON) is a pathological condition that has been attributed to the reduction or loss of vascular supply. This results in the lack of oxygen and consequently to progressive collapse of the bone [3], [25]. HIF-1α is the key transcription factor activated upon lack of oxygen in order to promote the transcription of a great number of genes needed for adaptation to hypoxic conditions [9]. HIF-1α polymorphisms have been extensively studied in order to determine the association they may have in the appearance or progression of hypoxia related diseases. Among many (more than 30) polymorphisms, three are present in exons of HIF-1α (C1772T, G1790A, C111A). Moreover, two of them (C1772T, G1790A) are in the ODD domain of the HIF-1α gene, where they lead to ORF changes from Pro to Ser at codon 582 (C1772T) and from Ala to Thr at codon 588 (G1790A) [23], respectively. It has been shown before that C1772T and G1790A SNPs could be of importance in various types of cancer or specific disorders (like type II diabetes [26], [27] and heart ischemic incidents [28], [29]). However the genetic association or the level of importance they have in the etiology, progression or prognosis of these diseases is controversial among groups and remains subject of ongoing debate. Quite controversial are also the existing reports about the significance of these SNPs in the protein expression or function of HIF-1α. There are reports [20], [30], [31] suggesting that P582S and A588T HIF-1α transcriptional activities are higher than wild type. Yamada et al [26] found that transcriptional activities of these mutants differ significantly from wt HIF-1α only under hypoxia. It was also shown that P582S HIF-1α protein is expressed more compared to the wt [31], [32], maybe due to increased stability under normoxic conditions [31]. Furthermore, there is one study suggesting that the P582S mutation (or in combination with another mutation) may present decreased transcriptional activity compared to wt [29]. None of these studies has however addressed the mechanism underlying the alleles' influence on trigger/progression of the disease studied.

Concerning osteonecrosis, little is really known about HIF-1α SNPs. On the contrary, VEGF SNPs' role has been extensively studied, since VEGF is implicated in neovascularization of the necrotic bone, bone repair and formation [13], [33]. It was shown that SNPs in the promoter region of VEGF are associated with ON of femoral head [34], [35], [36].

In the present study we have investigated the correlation of C1772T, G1790A and C111A HIF-1α polymorphisms, with the appearance of osteonecrosis in a Greek population. We found that the C111A allele was so rare that statistical analysis was not possible. For the other two SNPs (C1772T, G1790A) we could not detect a statistically significant association with the appearance of ON. This is in agreement with the only previous association study about HIF-1α SNPs and ON (but of femoral head) in a Korean population, where the authors have shown no significant association between four SNP genotype and allele frequencies of HIF-1α (including C1772T in exon 12) and ON. Nevertheless in a sub-analysis of the same study, the authors propose that C1772T SNP could be of importance only in the idiopathic ON male group [24]. To check this hypothesis in our own cohort we divided our ON patients into 3 etiological subgroups (idiopathic; steroid induced; of other etiologies) and discriminated between men and women. Our sample number was rather poor in some of our subcategories (especially the idiopathic cases) mostly due to the rarity of such cases in our population. Additionally, our control group was also rather small (but comparable to the different patient subcategories) due to the strict limitations we followed in order to exclude any ON indications and appropriately match with the patients' clinical profile in respect to age, sex, BMI etc (see ‘Study Subjects’ under ‘Materials and Methods’). Despite the low number of patient samples in our subcategories we still did not observe a significant difference or at least a trend showing that these specific polymorphisms of HIF-1α could be genetically implicated with the appearance of any kind of ON.

Our biological approach in two different cell lines showed that HIF-1α mutants C1772T and G1790A do not differ from the wt at the protein level since they had no consequence on the localization, expression and activity of HIF-1α protein. To our knowledge this is the first study where the sub-cellular localization of the P582S and A588T mutants has been monitored and one of the very few where their protein levels are compared to wt. These findings concur with/and supplement our genetic results implying that the P582S and A588T mutations might not be genetically important for the appearance of ON because they do not have a profound impact on the overall function of the protein.

To summarize, we found no association of the two known SNPs of HIF-1α with the risk of developing ON of any etiology. We thus believe that these specific SNPs of HIF1α do not have a significant genetic effect on ON diagnosis. Nevertheless a possible implication of other known SNPs of HIF-1a with ON cannot be excluded. Since hypoxia is a key feature of ON, we might expect that downstream effectors of HIF-1α, like VEGF or other angiogenic or metabolic agents could be of value in the diagnosis, progression and therapy of bone diseases like osteonecrosis. However, further biological and functional analysis would be needed to confirm that.

We acknowledge Dr. I. Mylonis for experimental help and support.