A 1 mM octadecyl-mercaptan (C18-mercaptan, Aldrich, Steinheim, Germany) solution in ethanol was used for the incubation of the gold sensors. The lipid film forming solutions was diphytanoyl-phosphatidylcholin (Avanti Polar Lipids Inc. Pelham, AL) and octadecylamin (60∶1, wt/wt, 98%, Riedel-DeHaen AG, Seelze Hannover, Germany). Phloretin, Luteolin, Kaempferol, Tamoxifen, Genistein, Quercitin, Furosemide, 2-[3-(trifluoromethyl)anilino]nicotinic acid (NFA), 4,4′-diisothiocyanatostilbene-2,2′-disulfonic acid (DIDS), 5-nitro-2-(3-phenylpropylamino)benzoic acid (NPPB), p-chlorophenoxy-acetic acid (CPA), p-chlorophenoxy-propionic acid (CPP), indanyloxyacetic acid 94 (IAA-94) and 9-anthracene-carboxylic acid (9-AC) were obtained from Sigma-Aldrich. NS5818 and NS3736 were synthesized at Bioduro, (Beijing, China).

Rat ClC-7 was cloned with a C-terminal GFP-fusionprotein into pcDNA5/FRT/TO using HindIII and EcoRV. Point mutations were introduced using the QuikChange Site-Directed Mutagenesis Kit (Stratagene, La Jolla, USA) at position 64 of GFP (Phe to Leu, primer: 5′ - CCA ACA CTT GTC ACT ACT CTC ACT TAT GGT GTT CAA TGC - 3′; 5′ - GCA TTG AAC ACC ATA AGT GAG AGT AGT GAC AAG TGT TGG - 3′) resulting in EGFP and at position 213 of rClC-7 (Gly to Arg, primer: 5′ - CAG ATC AAG TGC TTC CTC AAT AGG GTG AAG ATC CCC CAG GTG GTG - 3′; 5′ - CAC CAC GTG GGG GAT CTT CAC CCT ATT GAG GAA GCA CTT GAT CTG - 3′) resulting in the mutant comparable to the human G215R. Mouse Ostm1 was obtained in pFROG and could be transfected directly.

The pcDNA5 constructs were co-transfected with pOG44 into a Flp-In™ CHO cell line (all Invitrogen™, Karlsruhe, Germany) using Effectene (Qiagen, Hilden, Germany). Stable transfectants were selected by maintaining the cells in HAM's F-12 medium (PAA Laboratories, Cölbe, Germany), containing 10% FCS, 1% Penicillin/Streptomycin and 600 µg/ml Hygromycin for 10–14 days. Medium was replaced every 2–3 days. These cell lines, constitutively and homogeneously expressing the ClC-7 fusion protein, were additionally transfected with pFROG-mOSTM1 and selected for stable transfectants with 500 µg/ml G418. For single clone isolation, cells were seeded at a theoretical concentration of one cell/well in 96well plates. After 7 days, when single colonies were visible, the clones were expanded and analyzed for their expression pattern using confocal microscopy. For membrane preparation, cells were grown in multiple 15 cm culture dishes. At a confluency of 90–95% cells were harvested and collected by centrifugation (800× g). Subsequently, pellets were flash frozen in liquid nitrogen and stored at −80°C until preparation.

Human ClC-Ka (NM_004070) was stably co-expressed with its β-subunit barttin (NM_057176) in CHO cells using the bipromoter vector pBudCE 4.1 (Invitrogen). ClC-Ka was inserted via Hind III and Xba I downstream of the CMV promoter, while Barttin was inserted after the EF-1a promoter using Kpn I and Xho I. Stable clones were selected by 150 µg/ml zeocin (Invitrogen). Cells were cultured and harvested as described before.

EcClC-1 was expressed in E. coli (BL21 DE3), purified as described before [26] and reconstituted into liposomes (E. coli polar lipids, LPR = 10) [27].

Cell pellets were resuspended in buffer (10 mM TRIS, pH 7.5, 250 mM sucrose, 2 mM dithiothreitol (DTT) and 1 tablet Roche Complete™) and disrupted in a Parr Bomb (Parr Instruments Deutschland GmbH, Frankfurt/Main, Germany). Total membranes were collected by ultracentrifugation (30 min, 100.000× g @ 4°C) and fractionated by density gradient centrifugation (3 h, 100.000× g @ 4°C) [20] using a discontinuous sucrose gradient of 9%, 31%, 45% and 51%. Membrane bands at the gradient interfaces were collected, diluted 10 fold in resting buffer and pelleted by ultracentrifugation (30 min, 100.000× g @ 4°C). Protein concentration was determined by Bradford assay (BioRad, München, Germany). For long term storage, membranes were flash frozen in resting buffer (with 10% glycerol, 2 mM DTT and protease inhibitors) and stored at −80°C.

To investigate the vesicular localization of the wild type (wt) and mutant ClC-7-EGFP fusion proteins, cells were grown on coverslips for 24 to 48 hours. After reaching a confluence of 50–80% cells were incubated with 50 nM LysoTracker®-Red for 15 min or 1 µM ER-Tracker™-Red for 30 min, respectively (Invitrogen). Samples were analyzed instantaneously with a confocal laser-scanning microscope (LSM 510, Zeiss) using the argon laser line at 488 nm for EGFP and a 543 nm HeNe laser for Lyso- and ER-Tracker excitation. Fluorescence was detected through a 500–550 nm band pass filter and a 560 nm long pass filter, respectively. Images were recorded with an Achroplan 63×/0.95 W water immersion objective in multi track mode with sequential excitation of EGFP and Tracker dye, respectively. LysoTracker®-Red was prevented from exposure to broadband illumination before confocal imaging to prevent photoconversion [28].

For a quantitative analysis of the membrane fractions the EGFP fluorescence of the ClC-7 fusion proteins was analyzed using a microplate fluorescence reader (Lambda Fluoro, BIO-TEK Instruments, Winooski, USA). Membrane fractions were diluted to an equal concentration of 1 mg/ml in 50 µl buffer (60 mM HEPES, pH 7.2, 3 mM CaCl₂, 300 mM NaAsp). EGFP was excited using a 480/20 nm band pass filter, fluorescence emission was detected through a 530/25 nm band pass filter. The samples were analyzed in Greiner 96well flat bottom plates, the optical position was the well bottom.

Expression of the ClC-7-EGFP fusion protein and vesicular distribution of the membrane fractions was tested by Western blot. 15 µg total protein were loaded on a 4–12% bis-tris gel. After electrophoretic separation, proteins were blotted on a nitrocellulose or PVDF membrane (Invitrogen) and blocked for 1 hour in 5% nonfat dry milk (PBS-T). The blot was incubated with a rabbit-anti-GFP antibody (Clontech, Mountain View, CA, USA) (1∶100) overnight at 4°C. Lysosome or ER-enriched membrane fractions were identified, using a monoclonal mouse anti-LAMP-1 (Abcam) and a polyclonal rabbit anti-calnexin antibody (Stressgen, Ann Arbor, MI, USA). For detection of mOstm1 and ClC-3 rabbit anti-mOstm1 [10] and anti-ClC-3 [29] antibodies were used. For detection, appropriate AP (alkaline phospatase) or HRP (horse radish peroxidase) coupled secondary antibodys (BioRad, München, Germany) were used. Finally, AP blots were developed using AP developer kit (BioRad, München, Germany). HRP blots were detected with SuperSignal® West Pico or Femto (Pierce, Epsom, UK) and developed on film (BioMax, Kodak, Stuttgart) using a CURIX 60 developer (AGFA, Köln). Densitometry analysis of Western blot bands was performed using ImageJ (NIH, Bethesda, Maryland, USA) [30].

Electrophysiological measurements were performed on a commercial SURFE²R One instrument (IonGate Biosciences, Frankfurt, Germany). The experiments were carried out at room temperature (22°C). After the formation of the SSM [20], liposomes, membrane vesicles or membrane fragments (set to equal protein concentrations: ∼2 mg/ml) were adsorbed to the SURFE²R sensors (SSM-area ∼7 mm²) using a centrifugation procedure of 800× g for 45 min. For the ClC-7 measurements the 31/45% membrane fractions were used. Before mounting the sensors into the SURFE²R One instrument they were kept in Cl⁻ free buffer (60 mM HEPES, pH 7.2, 3 mM Ca-gluconate, 300 mM Na-aspartate). The solution exchange protocol consisted of 3 phases with a duration of 2 s each and a flow rate of 250 µl/s: a flow of nonactivating solution (NA) followed by activating solution (A) followed by nonactivating solution (NA). Solution A contained one or both transported substrates of ClC-7 (Cl⁻, H⁺). In the case of Cl⁻ concentration jumps, NA contained aspartate⁻ at the same concentration as Cl⁻ to minimize solution exchange artifacts. In addition all solutions contained a basic buffer which was 60 mM HEPES, pH 7.2, 3 mM CaCl₂, 300 mM Na-aspartate at neutral pH. Detailed buffer compositions are given in the figure legends.

Different buffers or inhibitor concentrations could be applied automatically using the autosampler of the SURFE²R One instrument. After changing buffer conditions (eg. pH) the sensors were incubated for 10–15 minutes before measurement to allow equilibration of the internal vesicle volume to the buffer conditions.

This is the first electrophysiological characterization of ClC-7 in its native environment, i.e. in the lysosomal membrane. Transient currents observed with membrane preparations of CHO cells expressing rat ClC-7 show characteristics of ClC-7 transport [4], [5]: (1) strong pH dependence with an increased activity at acidic pH, (2) ion selectivity Cl⁻>Br⁻>I⁻ and (3) pH-gradient driven anion transport. In addition, unspecific Cl⁻ transport inhibitors like DIDS and NS5818 inhibited the currents with relatively high affinity (Table 1).

An essential feature of ClC-7 is its function as a Cl⁻/H⁺-exchanger [4], [5]. Coupling of ClC-7 Cl⁻ transport activity to a proton motive force is demonstrated by two independent experiments: (1) Anion specific currents driven by a proton gradient only (Fig. 4B). (2) Modulation of anion specific currents by a co- and countergradient of protons (Fig. 4C). The latter is a distinct property of a proton coupled exchanger and is also found in the related EcClC-1 transporter and not in the Cl⁻ channel ClC-Ka (Fig. 4C).

Note that pH regulatory effects cannot be excluded in this experimental approach. It is known that ClC-Ka currents in two-electrode voltage clamp measurements [36] are strongly dependent on extracellular pH. However, a pH dependence of the ClC-Ka currents was not detected in our experiments. This may be related to the design of our measurements where the external pH of the membrane vesicles was kept constant at pH 7.2, while the internal pH was altered (implying right side out oriented membrane vesicles).

SSM based electrophysiology was essential in this study, because ClC-7 is expressed in intracellular membranes i.e. late endosomes and lysosomes, which are not accessible for conventional electrophysiology. Unlike other intracellular transporters of the CLC family such as ClC-4 and ClC-5, which could be investigated in oocytes or mammalian cell lines because of a “spill-over” to the plasma membrane at high overexpression [24], [37], ClC-7 related currents could not be detected using whole cell patch clamp or two-electrode voltage clamp measurements by different authors in a variety of cell systems [6], [7], [8], [10], [31]. This agrees with our localization studies which show no expression in the plasma membrane within the limits of detectability. There are, however, reports of trans-plasma membrane currents in oocytes, osteoclasts and HEK cells that have been assigned to ClC-7 [32], [38]. The reasons for this discrepancy are still unclear.

Fluorescence of the ClC-7-EGFP fusion protein was used to check the localization of ClC-7 expressed in CHO cells. In vivo ClC-7 resides in late endosomes, lysosomes and the ruffled membrane of osteoclasts [7], [8]. It is therefore not surprising to find wt ClC-7 in CHO cells predominantly in lysosomal membranes (Fig. 1A). In contrast, G213R ClC-7 shows a different intracellular distribution suggesting localization in the ER. This is quantitatively confirmed by densitometric analysis of ClC-7 western blots and by fluorimetric investigation of the different membrane fractions from sugar gradient fractionation. Wt ClC-7 is preferentially found in the 31/45% fraction which is enriched in lysosomal membranes while G213R ClC-7 is equally distributed between the lysosomal 31/45% fraction and the ER fraction 45/51% (Fig. 2B). Note, that densiometric and fluorimetric results are in good agreement. Therefore we propose that in CHO cells the G213R mutation is recognized by the ER-quality control, which prevents ClC-7 from leaving the ER where it is primarily formed and being transported to the lysosomal membrane.

Interestingly, Ostm1 significantly changes the expression pattern of G213R ClC-7, restoring the lysosomal localization to some extent. In addition, G213R ClC-7 co-expressing Ostm1 is characterized by a small preference for the lysosomal membrane fraction 31/45% used for the electrophysiological experiments (Fig. 2 B), resulting in an increase of the measurable currents. On the level of individual cell clones, an inhomogeneous pattern is found. Some cells show predominantly lysosomal, some cells predominantly ER localization. But Ostm1 significantly increases the lysosomal fraction (Fig. 1C). Because ClC-7 is not dependent on Ostm1 to reach the lysosomes in general [10], the function of Ostm1 in our experiments might be to compensate a putative folding defect caused by the G213R mutation. Thereby the protein it is no longer recognized by the ER quality control, resulting in a lysosomal “relocalization”. Previous studies indicated that Ostm1 is cleaved in or on its way to lysosomes [10]. While a significant amount of full length protein is still found in the ER fraction of the G213R membrane preparation, the 35 kDa fragment is observed in both lysosomal fractions, wt and mutant. Therefore, Ostm1 expression itself does not seem to be the limiting factor for the ER retained ClC-7 localization.

The currents shown in Fig. 3 demonstrate that the wt as well as the G213R mutant in the absence and presence of Ostm1 are functional transporters. Since the currents in Fig. 3C are normalized to equal protein expression level, these data suggest that mutation as well as co-expression with Ostm1 modulate the activity of the individual transporter: the G213R mutation reduces the activity by ∼30% while co-expression with Ostm1 enhances the activity by a factor of ∼2. This is a relatively crude estimate, because the normalization procedure to the expression level using the EGFP fluorescence of the different preparations introduces a significant systematic error in the analysis. The error is due to cross contamination of the lysosomal and ER fractions (compare Fig. 2A - Calnexin) and the relatively imprecise determination of the protein concentration using the Bradford assay. However, the fact that the G213R mutant retains a similar relative activity of ∼70% of the wt in both cases, with and without Ostm1, supports the conclusion that G213R ClC-7 retains most of the transport activity of the wt.

Interesting is also the enhancement of the normalized transporter currents by Ostm1 (Fig. 3C). This is observed for both, the wt and the mutant. Because of the normalization to equal protein expression, it represents again a property of the individual transporter and is unrelated to expression density in the measured membranes. However, in view of the considerable errors involved in the normalization procedure it remains questionable whether this represents a true functional enhancement of the transporter function.

Mutations in ClC-7 or its β-subunit Ostm1 lead to severe pathological phenotypes [39]. In neurons, a disrupted lysosomal function leads to accumulation of lysosomal storage material and neurodegeneration [7]. Another example is the decreased acidification of the resorption lacuna in osteoclasts. This causes reduced resorption of mineralized bone as is the case in ADO II [18], [19].

Mutations can cause a lack of function by direct impairment of protein activity, by a lack of protein expression or by its incorrect trafficking. It has been suggested previously [19], that expression and localization of ClC-7 is normal in ADO II patients implying that this pathology is caused by a reduced functionality of G213R ClC-7. Our data seem to challenge this hypothesis although they are strictly valid only for rat ClC-7 and for the CHO expression system. On the other hand, rat ClC-7 is 96% identical to the human protein [8] and eukaryotic protein trafficking is believed to follow similar laws in different mammalian cell types.

As shown above, the transporter function of G213R ClC-7 is not abolished. At the same time localization studies demonstrate that G213R ClC-7 is retained in the ER while the wt is correctly targeted to the lysosomal membranes (Fig. 1A). Applied to ADO II this suggests that G213R related ADO II is predominantly caused by defective trafficking, while the impaired transporter activity of the mutant ClC-7 plays only a marginal role. Interestingly, osteoclasts from ADO II patients show a reduced total resorption pit area but the area of the individual pits was the same [18] implying that some of the ADO II osteoclasts are still fully competent of bone resorption while others are inactive. This agrees with the inhomogeneous cell population found in G213 ClC-7 CHO cells (Fig. 1C) where in some cells predominantly the correct lysosomal localization is found while in others the transporter is retained in the ER.

Because of its involvement in bone pathology, ClC-7 is an interesting target for drug discovery. For example, inhibitors of ClC-7 are under discussion for the treatment of osteoporosis [22], [23], [25]. CHO cells were chosen because they produced only small background currents due to their low level of endogenous Cl⁻ conductance. Cl⁻ transporters like ClC-5 are not at all expressed in CHO [40] and also the tissue specific members of the ClC family like ClC-6 are not expected in CHO. ClC-3, which could be detected in western blot analysis (Fig. 2D) (possibly because of endosomal contamination of the membrane fractions) could together with endogenous ClC-7 be responsible for the small endogenous background currents in the CHO control preparations (Fig. 3A).

Assay quality is commonly estimated by the Z'- factor, with a Z'>0.5 being considered an “excellent” assay [41]. Our SSM-based electrophysiological assay for ClC-7 yielded a Z' = 0.78. To validate the assay a few plausible inhibitor candidates for ClC-7 were tested but no highly selective and high affinity compound was found that would be suitable as a drug candidate. Comparison of the determined inhibitor profile to that of ClC-3 and other chloride channels and transporters supports the assignment of the transient currents to ClC-7. ClC-3 is blocked by phloretin and tamoxifen, which was not the case in our experiments [42], [43]. Furthermore, our findings are in good agreement with osteoclast acidification and resorptions studies [44], where NPPB and the compound NS5818 [19], [45] could be identified as relatively potent inhibitors, while 9-AC, CPA and CPP had no effect on the osteoclast activity.

In conclusion, the inhibition study proves the suitability of SSM-based electrophysiology for screening of ClC-7 inhibitors. Among the small number of tested compounds no promising drug candidate for the inhibition of ClC-7 could be identified. For a realistic chance of detecting drug candidates larger compound libraries have to be screened using dedicated equipment which is now commercially available [20].