The human CIB1-EVER1-EVER2 complex governs keratinocyte-intrinsic immunity to β-papillomaviruses

Abstract

Patients with epidermodysplasia verruciformis (EV) and biallelic null mutations of TMC6 (encoding EVER1) or TMC8 (EVER2) are selectively prone to disseminated skin lesions due to keratinocyte-tropic human β-papillomaviruses (β-HPVs), which lack E5 and E8. We describe EV patients homozygous for null mutations of the CIB1 gene encoding calcium- and integrin-binding protein-1 (CIB1). CIB1 is strongly expressed in the skin and cultured keratinocytes of controls but not in those of patients. CIB1 forms a complex with EVER1 and EVER2, and CIB1 proteins are not expressed in EVER1- or EVER2-deficient cells. The known functions of EVER1 and EVER2 in human keratinocytes are not dependent on CIB1, and CIB1 deficiency does not impair keratinocyte adhesion or migration. In keratinocytes, the CIB1 protein interacts with the HPV E5 and E8 proteins encoded by α-HPV16 and γ-HPV4, respectively, suggesting that this protein acts as a restriction factor against HPVs. Collectively, these findings suggest that the disruption of CIB1-EVER1-EVER2-dependent keratinocyte-intrinsic immunity underlies the selective susceptibility to β-HPVs of EV patients.

Figure 1.

Identification of homozygous mutations affecting human CIB1 in a cohort of 24 EV patients. (A) Pedigrees of six kindreds affected by EV. Familial segregation of homozygous CIB1 mutations (m/m) in six consanguineous families indicating an AR pattern of inheritance with complete clinical penetrance. (B) Graphical representation of the CIB1 cDNA exon (c.CIB1) and protein (p.CIB1) structure with presentation of the EF-hand domains. The arrows at the top indicate the location of the cDNA positions affected by the CIB1 mutations found in the families, whereas those at the bottom indicate their consequences at protein level. *, stop codon; del, deletion; ins, insertion; fs, frameshift.

Figure 2.

CIB1 levels in patient-derived cells and healthy skin biopsy specimens. (A) CIB1 mRNA levels were assessed by RT-qPCR in patient-derived LCLs for kindred A and P12 and in whole blood from P13. Each symbol represents the mean of three independent measurements per cell line/donor. Statistical significance (***, P < 0.001) was assessed in a one-way ANOVA followed by Dunnett’s multiple comparison test for kindred A. Levels were 47% lower than the corresponding control mean in P12 and 80% lower in P13. (B) CIB1 protein was detected in LCLs and PBMCs with a polyclonal antibody directed against the N terminus of CIB1. GAPDH and Akt served as loading controls. Cellular material from kindreds A and B was analyzed three times. PBMCs from kindred E were analyzed once. (C) CIB1 protein level in skin biopsy specimens from healthy donors were measured by IHC with a monoclonal antibody directed against CIB1. An isotype Ig was included as a control. These results are representative of two experiments, each performed on two patients. *, epidermis; >, hair shaft. Bars: (top) 100 μm; (middle and bottom) 50 μm. (D) CIB1 protein was detected in primary keratinocytes from three healthy controls (ctrl 1–3), kindreds A, C, and D, or in whole-skin lysates from kindred F. L, lesion. These results are representative of three and one independent experiments, respectively. Asterisk indicates a nonspecific band.

Figure 3.

CIB1 forms a complex with EVER1 and EVER2. (A) CIB1 protein levels in LCLs derived from patients with loss-of-function mutations of EVER1 (D576*) and EVER2 (D362* or T150Mfs*3), and comparison with those in heterozygous carriers, positive controls (ctrl 1 and 2), P4 and P11, and patients with RHOH and MST1 deficiencies. (B) CIB1, EVER1, and EVER2 mRNA levels were assessed by RT-qPCR in controls (n = 4), CIB1 m/m (P1–P6 and P12), EVER1 m/m, and EVER2 m/m (n = 3 each) LCLs. Each symbol represents the mean of one cell line measured in three independent experiments. Statistical significance was assessed by one-way ANOVA followed by Dunnett’s multiple comparison tests relative to healthy controls. (C) CIB1 protein levels in LCLs derived from patients with loss-of-function mutations of EVER1 (D576*), EVER2 (T150Mfs*3), and a healthy control after reconstitution with WT EVER1 or EVER2 by retroviral transduction and stable selection. Asterisk indicates a nonspecific band. (D) CIB1, EVER1, and EVER2 mRNA levels were measured by RT-qPCR in LCLs derived from patients with loss-of-function mutations of EVER1 (D576*), EVER2 (T150Mfs*3), or CIB1 and a healthy control after reconstitution with WT EVER1 or EVER2 by retroviral transduction and stable selection. The data were first normalized against RNaseP as a housekeeping gene and then against an appropriate untransduced parental cell line by the ΔΔCt method. Statistical significance was assessed by one-way ANOVA followed by Dunnett’s multiple comparison test relative to the corresponding untransduced control. (B and D) ns, P > 0.05; *, P < 0.05; **, P < 0.01; ***, P < 0.001. (E) HEK293T cells were transfected with plasmids encoding CIB1-HA, FLAG-EVER1, and FLAG-EVER2 either separately or together; 24 h after transfection, samples were subjected to immunoprecipitation with FLAG (Fl)- or HA-specific antibodies (+). Samples incubated with nonspecific IgG served as specificity controls. Western blots were performed to detect coimmunoprecipitated CIB1-HA and FLAG-EVER1 or FLAG-EVER2. The immunoprecipitation of EVER1/2 and CIB1 was confirmed by reincubation with antibodies specific for FLAG and HA, respectively. The presence of all proteins was checked by Western blotting of an input sample taken before immunoprecipitation. GAPDH served as a loading control. vec, vector. (F) Healthy control keratinocytes were transfected with plasmids encoding CIB1-HA, FLAG-EVER1, and FLAG-EVER2 either alone or in combination; 24 h after transfection, cells were subjected to immunofluorescence imaging with Alexa Fluor 568–HA and Alexa Fluor 488–FLAG antibody combinations. DAPI was used for counterstaining. Colocalization was assessed by calculating Pearson’s correlation coefficient with Imaris software. Bar, 13 µm. The results shown are representative of three independent experiments.

Figure 4.

Analysis of zinc signaling/levels and NF-kB activation in the presence and absence of CIB1. (A) HEK293T cells were transfected with plasmids encoding CIB1, EVER1, and EVER2 either alone or in combination and with a 4×MRE-dependent EGFP reporter construct. After 24 h, cells were stimulated overnight with PMA/ionomycin (10 ng/ml and 50 ng/ml, respectively) or zinc sulfate (ZnSO₄; 100 µM). The next day, cells were stained with 1 µg/ml DAPI to exclude dead cells, and GFP fluorescence was determined with an LSRII flow cytometer. The RRR with the value for vector-transfected cells was set at 100%. Statistical significance was assessed by one-way ANOVA followed by Dunnett’s multiple comparison test relative to the appropriate vector-transfected control (ns, P > 0.05; *, P < 0.05; ***, P < 0.001; n = 3). (B) Flow cytometric quantification of absolute amounts of labile zinc in LCLs derived from healthy controls, EVER1-, EVER2-, or CIB1-deficient patients, or in keratinocytes from P14 with 1 µM FluoZin-3 as described by Haase et al. (2006). Statistical significance was assessed by one-way ANOVA followed by Dunnett’s multiple comparison test relative to the healthy controls (n = 3). (C) Kinetics of zinc flux in LCLs derived from healthy controls and EVER1-, EVER2-, or CIB1-deficient patients. Cells were loaded with 1 µM FluoZin-3 for 30 min. Fluorimetric measurement were performed on a Victor microplate reader. Baseline fluorescence was recorded every minute for 10 min. Cells were then loaded with 100 µM ZnSO₄ and recorded for 15 min. The specificity of the zinc signal was confirmed by adding the calcium-specific chelator BAPTA before the quenching of the signal with the zinc-specific chelator TPEN and recording for 20 min. No significant effect of genotype was detected in two-way repeat-measures ANOVA (n = 3). (D) HEK293T cells were transfected with plasmids encoding CIB1-FLAG, FLAG-EVER1, and EVER2 either alone or in combination. Cells were stimulated with 50 ng/ml TNFα 6 h after transfection, incubated overnight, and then harvested and processed for Western blotting. Membranes were probed for the canonical NF-κB component (p)IκBa and the noncanonical NF-κB component p100/p52. Expression of the constructs used for transfection was verified by incubation with a FLAG-specific antibody. GAPDH served as a loading control (n = 3). (E) Primary keratinocytes from unrelated donors (controls 1 and 2), a healthy family member from kindred A1 carrying the mutation in a heterozygous state (A1.viii.2), and one patient each from kindreds A1 and C were stimulated with 10 ng/ml TNFα for 5, 10, or 20 min and then harvested and processed for Western blotting. Membranes were probed for the canonical NF-κB component (p)IκBa. CIB1 levels were assessed with a polyclonal antibody. GAPDH served as a loading control. vec, empty vector (n = 3).

Figure 5.

Focal adhesion formation and scratch wounding in CIB1-deficient keratinocytes. (A) Primary keratinocytes from two donors, a healthy member of kindred A (A1.viii.2; CIB1 wt/m), and P5 were allowed to adhere to fibronectin-coated plates (10 µg/ml) for the times indicated and were then harvested and processed for Western blotting. The membranes were probed for the focal adhesion (FA) components vinculin and (p)FAK. GAPDH served as a loading control. (B and C) Primary keratinocytes from two donors, a healthy member of kindred A (A1.viii.2), and P5 were allowed to adhere to fibronectin-coated coverslips (10 µg/ml) for 24 h. Cells were fixed and stained with vinculin- and pFAK-specific antibodies. Z stacks were acquired with a confocal microscope. (B) Representative image for automated surface detection for control 1. Bar, 40 µm. (C) The volume (size), fluorescence intensity, and morphology of the vinculin- and pFAK-positive structures were automatically determined with Imaris. Values were normalized against the total number of surfaces detected. Statistical significance was assessed in one-way ANOVA followed by Dunnett’s multiple comparison test relative to control 1. No significant differences were detected for any of the parameters tested (P > 0.05). (D–F) Primary keratinocytes from two donors, a healthy member of kindred A (A1.viii.2; CIB1 wt/m), and P5 were allowed to adhere to fibronectin-coated plates (1 µg/ml) overnight. Scratch wounds were created with a pipette tip, and wound closure was monitored by live-cell microscopy every 20 min for 16 h. Bar, 283 µm. Wound closure was then quantified automatically with the MiToBo plugin in ImageJ with measurement of the cell-free area normalized against the starting point (set to 100%; D and E). Statistical significance was assessed by two-way repeated-measures ANOVA. Differences between controls 1 and 2, CIB1 wt/m, and P5 were statistically significant. Differences between control 2, CIB1 wt/m, and P5 were not significant. (F) For confirmation of the accuracy of the results obtained with the plugin, the total cell-free area at the start and end points was determined manually. The data shown are the means of two (controls 1 and 2) or three (CIB1 wt/m and P5) independent experiments with at least six data points acquired per set. Statistical significance was assessed by one-way ANOVA followed by Dunnett’s multiple comparison test relative to controls 1 or 2. (ns, P > 0.05; ***, P < 0.001).

Figure 6.

PLA and coimmunoprecipitation in HaCaT. (A) HaCaT cells were transfected with plasmids encoding FLAG-HPV5 E1, E2, E6, and E7, FLAG-HPV16 E1, E2, E5, E6, and E7, FLAG-HPV4 E8, FLAG–CRPV E8, and CIB1-HA alone or in combination. The day after transfection, samples were plated on microscopy slides, allowed to adhere, fixed in acetone, permeabilized, and subjected to Duolink PLAs with rabbit-HA– and mouse-FLAG–specific antibodies. Z stacks were acquired with a widefield microscope, and PLA-positive sites (defined as structures >0.35 µM²) were scored with Imaris software for 15–50 cells per condition. These pooled results were obtained in two independent experiments. The orange bars indicate the mean. (B) HaCaT cells were transfected with plasmids encoding CIB1-HA and the FLAG-tagged HPV E ORFs scoring positive in the PLA in A. 1 d after transfection, samples were subjected to immunoprecipitation (IP) with FLAG-specific antibodies. Western blots were performed to detect coimmunoprecipitated HPV5 E1, HPV16 E2, E5, HPV4 E8, and CRPV E8. The immunoprecipitation of CIB1 was confirmed by reincubation with a FLAG-specific antibody. The presence of all proteins was checked by Western blotting analysis on an input sample taken before immunoprecipitation. GAPDH served as a loading control (n = 3). vec, vector.

Figure 7.

Mechanism underlying EV. (A) In the general population, the CIB1–EVER1–EVER2 complex restricts the transcription of minichromosome of β-HPV, leading to the absence of clinical manifestation. The proteins E5 and E8 expressed by the other cutaneous HPVs (α2-, α4-, γ-, and μ-HPVs) are able to antagonize the CIB1–EVER1–EVER2 complex. However, additional restriction factors are probably contributing to the absence of HPV lesions in the vast majority of people. (B) In EV patients, the lack of CIB1–EVER1–EVER2 permits the transcription of β-HPV minichromosome, which leads to the development of EV lesions on the skin. However, the probable presence of additional restriction factors against cutaneous HPVs other than β-HPVs accounts for their normal control, which does not differ from the general population.