Commonly found in aging tissue, dystrophic calcification is defined as the abnormal deposition of calcium salts in altered or diseased tissues. It also occurs in pathologies such as diabetes, hypercholesterolemia, chronic renal failure and certain genetic conditions. Under pathological conditions, this abnormal mineralization can occur in response to metabolic, mechanical, infectious, or inflammatory injuries and its etiology is heterogeneous with overlapping yet distinct molecular mechanisms of initiation and progression. Pseudoxanthoma elasticum (PXE, OMIM 26480) in human and dystrophic cardiac calcification (DCC) in mice are similar pathologies both defined by dystrophic mineralization of cardiovascular, ocular and dermal tissues. Both conditions derive from loss-of-function mutations in the human ABCC6 and mouse Abcc6 genes [1], [2], [3], [4], [5]. PXE is characterized by dystrophic calcification primarily affecting elastic fibers in skin, arteries and the Bruch's membrane of the eye [6], [7], [8]. The causality of mutations of the ABCC6 gene in PXE was demonstrated in 2000 [2], [3], [5] and since then the clinico-genetic characteristics of the disease have been established [7], [8]. Interestingly, heterozygous carriers of ABCC6 mutant alleles present an increased susceptibility to cardiovascular diseases [9], [10], [11]. The transcriptional regulation of the gene [6], [12], [13] and the biochemical characteristics of the ABCC6 protein have been well defined [14]. ABCC6 functions as an organic anion efflux pump [14], [15] transporting an as yet unidentified substrate(s) from the liver to the circulation. Because ABCC6 is predominantly found in liver and kidney and with little or no expression in tissues affected by PXE [8], [16], [17] this pathology appears to be systemic in nature. This implies the presence of an abnormal circulating molecule(s) that results from the failure of ABCC6 to export its substrate(s), ultimately promoting calcification in peripheral tissues. We've detected the presence of such circulating molecules in the serum of adult PXE patients through their effects on elastic fibers deposited in cultures [18] and others have reached similar conclusions using a mouse model [19], [20].

Since the first PXE-causing mutations were characterized [2], [3], [5], [21], the number of identified disease-causing variants has exceeded 300 [22]. Despite the large number of PXE-specific mutations that have been identified in ABCC6, no clear genotype-phenotype correlation has emerged [7], [21], [22]. However, a significant clustering of missense mutations was identified in domain-domain interfaces predicted from a homology model of the human ABCC6 protein [23]. Amino acid substitutions in large plasma membrane proteins such as ABCC6 generally result in decreased activity, major conformation changes, low level of plasma membrane targeting or a combination thereof. Therefore, studying the consequences of naturally occurring disease-causing missense mutations can provide important insights into the relationship between protein structure and function, which may later assist in the development of therapeutic applications. In recent years, several studies have shown that sodium 4-phenylbutyrate (4-PBA) can partially restore the cellular trafficking of a mutated ABCC7/CFTR (ΔF508) and parts of its cellular function were restored in both cultured cells and human cystic fibrosis patients [24], [25], [26], though how much phenotype improvement was achieved is less clear. Other proteins with disease-causing mutations were also subjected to 4-PBA treatment to improve their folding/trafficking like ABCA3 [27], LDL-receptor [28], the bile salt export pump/ABCB11 [29], [30], [31], ATP7B [32] and ATP 8B1 [33] and ATP-Sensitive Potassium Channel/ABCC8 [34]. 4-PBA is a butyrate analogue approved for clinical use in human with urea cycle disorders and thalassemia [35], [36], [37]. It is thought to interfere with the Hsc70 protein in endoplasmic reticulum (ER), allowing a proportion of misfolded proteins to escape association with the chaperon thus improving cellular trafficking [26], [38]. To capitalize on these precedent studies, we characterized the structural and functional consequences of selected PXE-causing missense mutations on ABCC6 transport activity, protein stability and conformation using in vitro assays. We also investigated for the first time, the in vivo stability and cellular location of WT and mutated ABCC6 in fully differentiated hepatocytes by transiently expressing the human mutant proteins in the liver of C57BL/6J mice. We focused on identifying those mutants with preserved transport activity and intracellular mistargeting. Such mutants are candidates for pharmacological rescue of their intracellular maturation. Indeed, we determined the potential for recovery of plasma membrane targeting of a transport-competent ABCC6-mutant in liver of C57BL/6J mouse after 4-PBA treatments.

The ABCC6 model, previously generated by Fülöp et al [23] was analysed with the PyMOL Molecular Graphics System, Version 1.3, Schrödinger, LLC.

Expression of ABCC6 variants in Sf9 insect cells, ATP binding, nucleotide trapping and vesicular transport were performed as described in our previous papers [14], [39], [40], [41].

Expression of ABCC6 variants in MDCKII cells were achived by retroviral gene delivery as described [42].

The aim of our study was to characterize the structural and functional consequences of PXE-causing mutations in ABCC6 with a focus on the in vivo intracellular targeting of the human mutant proteins in mouse liver. Our main motivation was to identify disease-causing missense mutants with normal transport activity but with aberrant intracellular targeting. Such mutants were candidates for rescue of their intracellular maturation using chemical chaperons. We previously found an unequal distribution of ABCC6 missense mutations with high frequency on the ABC-ABC contact or in the transmission interface [23]. Therefore, we chose five missense mutations in these regions, V1298F and G1321S in the C-proxymal ABC domain and R1138Q, R1314W and R1339C in the transmission interface. The location of the mutated residues is illustrated on Figure 1, which depicts a model of the membrane topology of ABCC6 as well as a homology model of the protein. A N-terminal truncated mutant, del_1–277ABCC6 (ΔABCC6) missing the TMD₀ and L₀ domains has also been constructed as a control (Figure 1).

We and others have accumulated a body of data that implicated ABCC6 as a new modulator of ectopic calcification in both human and mice [1], [2], [3], [4], [5]. This transmembrane protein is primarily expressed in liver, kidneys and intestine and transports unknown metabolite(s), which directly or indirectly control mineralization of dermal, ocular and cardiovascular tissues [46]. Mutations in the human ABCC6 gene cause pseudoxanthoma elasticum, a recessive disorder [2], [3], [5], [22], [47]. The vast majority of ABCC6 mutations are missense [7], [21], [22], [23] and several categories of missense substitutions can be distinguished based on the functional consequence of the amino acid replacement. Based on published data [26], [38], we have also anticipated that mutants with certain transport- and intracellular characteristics can be subjected to rescue by treatment with pharmacological compounds (called “chemical chaperons”). Therefore, the main objective of this study was to characterize the structural and functional consequences of ABCC6 missense mutations in vitro as well as in an accurate in vivo model and to identify mutants suitable for rescue. ABC transporters are traditionally studied in cultures of MDCKII cells, but these are not ideal for studying hepatic proteins. Indeed, MDCKII cells are transformed cells derived from canine kidney tissues and do not reproduce the biology of the liver where ABCC6 is primarily expressed. A transgenic animal approach would be more accurate, yet it is time-consuming and poorly suited to the analysis of multiple protein variants. We have overcome these obstacles by demonstrating the feasibility of using HTVI to study normal and mutant forms of the human ABCC6 protein in the fully differentiated liver of a living mouse. This method delivers DNA to the liver very effectively [43], [44], [48] and ensures the selective hepatic expression of the WT human protein in mouse liver with an adequate basolateral targeting. We also analyzed an artificially truncated mutant, ΔABCC6 as similar truncated ABCC1 and ABCC2 proteins were found to be inactive and not integrated into the plasma membrane [41], [49]. The WT human protein co-localized with the mouse Abcc6 (Figure 3A, B) and thus validated our in vivo experimental model. Conversely, ΔABCC6 was completely absent from the plasma membrane arguing for the similar role of the TMD₀ and L₀ domains of ABCC6 with those of ABCC1 and ABCC2 in intracellular trafficking. Interestingly, two of the PXE-causing mutants we characterized, R1138Q and R1314W showed a near normal transport activity in in vitro assays, whereas mutants V1298F and G1321S were transport-deficient. We also observed that mutant R1339C could not be expressed in insect cells as an intact protein, but was successfully produced as full-length polypeptide in mouse liver following tail vein injection. The five mutants we examined demonstrated various degrees of intracellular accumulation in vivo ranging from WT behavior with normal plasma membrane position (V1298) to intracellular localization similar to ΔABCC6 (R1321S, R1339C or R1314W). R1138Q, however, showed an intermediate behavior with partial plasma membrane localization and a relatively abundant intracellular presence (Figure 3, see also Table 1). Because we have established that mutants G1321S, R1314W, R1339C and R1138Q were likely retained in intracellular compartments as non-degraded, full-size polypeptides (Figure 4), we used immunofluorescent imaging to identify the potential intracellular compartments involved. We have found that mutants R1138Q and R1339C showed some association with the ER suggesting partial ER retention. R1314W was mostly retained in the ER (Figure 5) indicating that the main consequence of pathologic amino acid substitutions in the human ABCC6 protein is the alteration of folding and/or trafficking. Though we have not specifically investigated it in this study, we found no evidence of protein accumulation in aggresomes or microtubule-organizing centers in images of hepatocytes expressing the ABCC6 mutants [50], [51], [52]. However, this would certainly be worth investigating, perhaps using MDCKII cells.

In summary, we have identified three possible consequences of PXE-causing mutations: 1) Transport deficiency due to the inability to use ATP (V1298F); 2) Altered folding and/or protein stability leading to intracellular retention (R1314W, R1339C, G1321S) in the ER or other cellular organelles, which could be pharmacologically corrected; and 3) Reduced trafficking efficiency with normal in vitro transport activity (R1138Q). We have summarized these results in Table 1. Despite the variability in the fate of these mutated proteins, all five mutations resulted in loss of physiological function, which to some extent, provide an explanation for the observed lack of phenotype–genotype correlation in PXE [21], [22]. In these experiments, we identified two mutant candidates to test whether a chemical chaperon could facilitate intracellular trafficking in mouse liver. Several studies have shown the possibility of rescue of membrane targeting of misfolded cystic fibrosis ABCC7/CFTR mutant (ΔF508) by treating either cultured cells or human patients with 4-PBA [24], [25], [26]. Similar results were obtained with disease-causing mutants ABCB11 in MDCKII cells [29]. Therefore, we explored the effect of 4-PBA in mice transiently expressing transport-competent ABCC6 mutants, R1138Q and R1314W as well as the R1339C variant and the WT protein for control purposes (Figure 6). The treatment had a remarkable effect on R1314W reverting the apparent ER retention of this mutant protein back to a near normal membrane localization in hepatocytes. A detailed analysis of liver sections from 4-PBA treated mice expressing R1314W is shown on Supplementary Figure S1. Treatment of MDCKII cells expressing the R1314W mutant with PBA resulted in a similar improvement (Figure 6C) thereby confirming the in vivo data.

In the present work we demonstrated the efficient association of in vitro studies with in vivo experiments to evaluate the consequences of missense ABCC6 mutations providing a unique insight into the intracellular processing of this human ABC transporter in physiological conditions similar to that of human primary hepatocytes. We also found that our integrated approaches constituted an appropriate base not only for testing pharmacological compounds with the ultimate aim of finding allele-specific therapeutic solutions for PXE but could also be a model for the systematic investigation of hepatic ABC transporters and other liver-specific membrane proteins.