We showed previously that mouse J774 macrophages resistant to 200 µM ciprofloxacin were characterized by a markedly reduced accumulation of this drug [27] that was attributed to the overexpression of the ABC transporter Abcc4 [21].

To further understand the mechanisms leading to this overexpression, we have now compared the accumulation of ciprofloxacin and the expression of Abcc4 (protein and mRNA levels) in wild-type cells vs. cells resistant to ciprofloxacin concentrations of 100, 150 and 200 µM. The data illustrated in Figure 1 show that the accumulation of ciprofloxacin was decreased in parallel with the increased level of resistance. However, the process was not linearly related to the drug concentration used for selection, most of the effect being obtained only in cells resistant to the highest concentration. This reduction of ciprofloxacin accumulation was associated with a commensurate increase in the expression of Abcc4, both at the mRNA and protein levels. The lowest panel of Figure 1 shows the correlation between ciprofloxacin accumulation and protein levels of Abcc4.

Conventional karyotype coupled to Multicolor FISH (mFISH) showed that the wild-type J774 cell line was characterized by a near-triploid karyotype (Figure S1) and exhibited particularly a derivative of Chr 14 characterized by the replacement of its telomeric end by a part of Chr 3 (Figure 2, Chr B) in addition to the two apparently normal Chromosomes 14. The Abcc4 locus localized at Chr 14qE4 was analyzed by FISH using BAC (Bacterial Artificial Chromosome) probes, on metaphases in comparison to a more centromeric control locus (see Figure S2 for typical images and Figure 3 for a schematic representation of chromosomes with Abcc4 loci observed in the different cell lines and a quantification of the different clones).

Wild-type macrophages remained disomic for Abcc4 locus, as we observed 2 different copies of Abcc4 on two apparently normal Chromosomes 14 (Figure 2, Chr A), in comparison to the control probe (normally located at Chr 14qA3), which exhibited a third signal on the derivative Chromosome 14 (Figure 2, Chr B). In the intermediate resistant cell line CR100, we predominantly observed the wild-type pattern (almost 67% of the metaphases). A third copy of the Abcc4 locus was identified in about 1/3 of the cells, either on an additional apparently normal Chromosome 14 with both Abcc4 and control probes (27% of the metaphases, Figure 3), or on a marker Chromosome (7% of the metaphases). At the next step of selection with ciprofloxacin (CR150 cells), only 21% of the analyzed metaphases displayed the wild-type pattern while all the others showed different clones characterized by a low level chromosomal amplification of Abcc4 (approximately 3 copies) located either on one or on two Chromosomes 14, or associated to a marker Chromosome which did not exhibit the Chromosome 14 centromeric control probe.

In the fully ciprofloxacin-resistant cell line CR200, we observed Abcc4 high-level amplification as a homogenous staining region (hsr) in all metaphases (Figure S2) on different marker Chromosomes that did not exhibit the Chromosome 14 centromeric control probe. Of note, all metaphases observed for the CR200 cell line displayed 2 apparently normal Chr 14 and no Abcc4 copy on the derivative Chr 14, as in wild-type cells. To identify the marker Chromosomes with Abcc4 hsr, we performed a mFISH analysis followed by Abcc4 hybridization (Figure 2 and Figure S2). Upon examination of 73 metaphases, the hsr was found with a localization that was either centromeric to a derivative Chr 5 (72.5% of the metaphases, clone I) (Figure 2, Chr C) or telomeric to a derivative Chr 16 (10%, clone III) (Figure 2, Chr D). Interestingly, in 13.5% and 4% of the observed metaphases, the Abcc4 amplification was found on either two (clone II) or one (clone IV) smaller marker Chromosome(s) (Figure 2, Chr M). These contained three heterochromatic regions aside of the centromere and were suspected to correspond to a derivative of Chr 13 by mFISH, although the chromosomal origin of the centromeric region remained uncertain (Figure 2, Chr M). Other additional genomic alterations were acquired in the resistant cells, namely −der(9)T(9;19),+13,−idic(13) in all clones, +9, in clones I and II, and +der(1)T(1;2)(H?;?) in clone III, as identified by mFISH.

In the revertant cell line Rev200 for which 31 metaphases were examined, we observed the wild-type phenotype (2 apparently normal Chr 14, and one without the Abcc4 locus) in around half of them (16), but 9 metaphases displayed a remaining high-level amplification of Abcc4 on the small marker Chr M (Figure 3), as already observed in the CR200 cell line. Moreover, in the remaining 6 metaphases, we observed an additional copy of Abcc4, located on a very small unidentified marker Chromosome (Chr N; Figures 2 and S2). All these observations were in agreement with the analysis of interphasic cells, made on a larger cell population (200 nuclei), for each cell line (data not shown).

As DnajC3 is located close to Abcc4 at Chromosome 14qE4, and because we already detected DnajC3 protein overexpression in the fully ciprofloxacin-resistant cells in an ongoing proteomic study [Caceres et al., in preparation], we looked for a possible co-amplification of DnajC3 with Abcc4. FISH analysis with the DnajC3 specific probe combined with the control probe on Chromosome 14 indeed revealed similar patterns of gene amplification in all the resistant cell lines, like those observed with Abcc4 probe (data not shown). Moreover, when we hybridized together Abcc4 and DnajC3 probes, we observed the co-localization of both probes in amplified regions, either at Chromosome 14 in intermediate resistant cells (CR150 cell line, Figure 4, left panel), or in the hsr in the fully ciprofloxacin-resistant CR200 cell line (Figure 4, right panel).

As all the work presented so far had been performed with a murine cell line, we examined whether ciprofloxacin is also a substrate of the human homologue transporter. To this effect, we compared the accumulation of ciprofloxacin (a) in wild-type J774 macrophages (basal expression of Abcc4) and in J774 macrophages resistant to 200 µM of ciprofloxacin and (b) in HEK293 human cells and HEK293/4.63 transduced with the cDNA coding for human ABCC4 and expressing it to high levels [28]. The accumulation of ciprofloxacin was drastically reduced in HEK293/4.63 cells compared to HEK293 cells, and was increased by gemfibrozil, a broad-spectrum inhibitor of MRP transporters (see Figure S3), demonstrating that ciprofloxacin is also a substrate of the human homologue of Abcc4.

All cell culture reagents were purchased from Invitrogen (Carlsbad, CA). Ciprofloxacin HCl (potency 85%) was received from Bayer HealthCare (Wuppertal, Germany) as microbiological standard. Other chemical products were purchased from Sigma-Aldrich (St. Louis, MO).

J774 mouse macrophage-like cells [48] (referred to as wild-type cells) were cultured and maintained as already described [49]. Ciprofloxacin-resistant macrophages and their revertant were fully described in a previous publication of our group [27]. Resistant cells were obtained by chronic exposure to progressively increasing concentrations of ciprofloxacin (100 µM, 150 µM, and 200), yielding to cell lines referred to here as CR100 (used at the 5th passage), CR150 (used at the 3rd passage) and CR200 (used at the 76th passage) respectively. Revertant cells (referred to here as Rev200) were obtained by returning CR200 cells to ciprofloxacin-free and used here at their 84th passage in the absence of selective pressure. Human Embryonic Kidney HEK293 cells and HEK293/4.63 cells transduced with human ABCC4 cDNA were obtained from P. Borst (Het Netherlands Kanker Instituut, Amsterdam, The Netherlands). They were cultivated in Dulbecco's modified Eagle's medium supplemented with 10% fetal calf serum [28].

These experiments were performed exactly as previously described [21], [27], [50]. Cell-associated ciprofloxacin was assayed by fluorimetry (λ_exc = 275 nm and λ_em = 450 nm) and its cellular concentration expressed by reference to the total cell protein content as measured by the Lowry's method [51].

Abcc4 expression was assessed at mRNA and proteins levels, as described previously [21]. Real-time PCR experiments were performed starting from 1 µg of total purified RNA transcribed into cDNA, and using SYBR Green detection. Two housekeeping genes, Ywhaz and Rpl13a (mouse geNorm normalization kit, PrimerDesign Ltd., Southampton, UK) were used for normalization. The relative quantification of Abcc4 gene in cell lines of interest was done using levels measured for wild-type J774 macrophages as baseline, based on Pfaffl's equation [52]. Western-blots were performed on cell crude extracts. After electrophoresis on acrylamide gel and transfer to nitrocellulose membrane, proteins of interest were detected using anti-ABCC4 monoclonal antibody (M₄I-10; Alexis Biochemicals, Lausen, Switzerland) or anti-actin polyclonal antibodies (Sigma-Aldrich) (dilution 1/1000), followed by appropriate horseradish peroxidase-coupled secondary antibodies (dilutions 1/600). Blots were then revealed by chemiluminescence assay (SuperSignal West Pico, Pierce, Thermo Fisher Scientific Inc., Rockford, IL).

Metaphase chromosomes were obtained according to standard methods for mouse cell lines [53]. Cells were grown for 48 h into 6-well plates (initial density of 5×10⁴ cells per cm²) and fed with fresh medium 4 h before addition of a mitotic spindle inhibitor (KaryoMAX® Colcemid™ Solution, Invitrogen) at a final concentration of 0.02 µg/ml. After 45 min of incubation at 37°C, cells were washed with PBS, detached by trypsinization and collected by centrifugation (900 rpm, 10 min). They were then submitted to hypotonic choc by resuspension in KCl 75 mM and incubation for 10 min at room temperature. After centrifugation (900 rpm, 5 min), cell pellets were resuspended in Carnoy's fixative (methanol/glacial acetic acid, 3/1) and incubated 15 min at room temperature. This fixation step was repeated three times. Metaphase chromosomes were obtained after spreading and air-drying of fixed cells onto microscope glass slides. Metaphase cells were banded with trypsin denaturation followed by a Wright staining. Metaphases were analysed with Ikaros Imaging System (MetaSystems, Altlussheim, Germany). Karyotypes were described according to The Rules for Nomenclature of Chromosome Aberrations (Revised: January 2005) from the International Committee on Standardized Genetic Nomenclature for Mice (http://www.informatics.jax.org/mgihome/nomen/anomalies.shtml). A total of 8 and 21 metaphasic cells were analyzed, for wild-type and resistant macrophage (CR200) cell lines, respectively.

Fluorescence in situ hybridization (FISH) analysis was performed using Bacterial Artificial Chromosome (BAC) probes (from the Roswell Park Cancer Institute, Buffalo, NY) specific for Abcc4 (clone RP23-390O15) and DnajC3 loci (clone RP23-378H12) (both located at Chr 14qE4), and for a more centromeric locus of Chromosome 14 which served as control (clone RP23-364J13, located at Chr 14qA3). BAC localizations have been checked by end sequencing analysis on a Beckman CEQ2000 sequencer (Beckman Coulter, Fullerton, CA). After extraction, BAC probes were labeled by random priming with fluorescent dUTP (Cy3-dUTP [red] or fluorescein-12-dUTP [green]), using the BioPrime® DNA Labeling System (Invitrogen). Hybridization and fluorescence detection were carried out according to standard procedures [54]. Briefly, fluorescent probes (Abcc4 or DnajC3 probes: 20 ng/µl; control probe: 24 ng/µl), denatured at 70°C for 5 min and preannealed with a 50-fold excess of mouse Cot-1 DNA (Invitrogen), were hybridized overnight at 37°C to cytogenetic slides pretreated with pepsin 0.01%/HCl 0.01 M at 37°C for 13 min, and then denatured at 75°C for 2 min 20 sec in 70% formamide/2xSSCP (saline sodium citrate phosphate buffer). After washing (2 min in 0.4xSSC [saline sodium citrate buffer] at 30°C), cells were counterstained with 4,6-diamidino-2-phenylindole (DAPI) and observed with a Zeiss Axioplan2 microscope equipped with a HBO103W lamp (Zeiss, Oberkochen, Germany). Images were captured with the Isis Imaging System (MetaSystems). For each hybridization, a minimum of 30 metaphases and of 200 interphasic cells were analyzed.

Fresh metaphase spreads were pretreated with RNase A (100 µg/ml)/2xSSC for 45 min at 37°C, then denatured as previously described. The multicolour probe kit (21XMouse, MetaSystems) was denatured according to manufacturer's instructions, and then hybridized to metaphases at 37°C for 3 to 4 days. Post-hybridization washes and counterstaining were performed according to manufacturer's instructions, using DAPI/antifade (MetaSystems). Ten metaphases were analyzed for wild-type macrophage cells, and more than 20 for resistant cells CR200. When mFISH was combined with Abcc4 probe hybridization, we compared metaphases hybridized first with mFISH probes, then washed and hybridized again with the Abcc4 probe.