Factor H interferes with the adhesion of sickle red cells to vascular endothelium: a novel disease-modulating molecule

Study design

We studied SCD subjects (n=29; 26 SS and 3 Sβ⁰) referred to the Department of Medicine, University of Verona and Azienda Ospedaliera Integrata of Verona (Italy) between January 2012 and January 2017. SCD patients were evaluated at steady state, and none of them had been on either hydroxyurea or a transfusion regimen during the 6 months immediately prior to our analysis. Healthy controls were matched by age, sex and ethnic background. The study was approved by the Ethical Committee of the Azienda Ospedaliera Integrata of Verona (Italy) and informed consent was obtained from patients and healthy controls (ethical approval FGRF13IT). Table 1 shows the demographic characteristics of both the healthy subjects and SCD patients studied. Biochemical and hematologic parameters as well as plasma levels of C3 and C4 were determined according to clinical and laboratory standards at the Laboratory of Medicine, University of Verona and Azienda Ospedaliera Integrata of Verona (Italy). Plasma C5a (EIA Quidel Corp., San Diego, CA, USA), plasma vascular cell adhesion molecule-1 (Invitrogen, Carlsbad, CA, USA) and serum FH (Hycult Biotech, Uden, the Netherlands) were determined by enzyme-linked immunosorbent assays, according to the manufacturers’ protocols.³¹

Evaluation of C5b-9 complement deposition on fixed skin biopsies

Skin punch biopsies were carried out on the volar surface of the left arm on apparently normal skin. The samples were paraffin-embedded and stained with hematoxylin and eosin before examination; they were also used to estimate the presence of C5b-9 complement deposition within the microvasculature.³² Details on the immunofluorescent and immunohistochemical staining assays are reported in the Online Supplementary Methods.^32–34

Measurements of phosphatidylserine-positive and C3d-positive red blood cells

Phosphatidylserine-positive cells were detected as previously reported.^35–37 Details are given in the Online Supplementary Methods.

Red blood cell adhesion assay

The real-time adhesion of RBC collected from healthy and SCD subjects on inactive or activated endothelium [in the absence or presence of tumor necrosis factor-alpha (TNF-α), respectively] was determined as previously reported^38–40 with or without FH or the FH19-20 or FH68 domains.⁴¹ Details are provided in the Online Supplementary Methods.

Development of an algorithm to determine red blood cell transit and flux trajectory

The algorithm to determine RBC transit and flux trajectory is described in the Online Supplementary Methods.

P-selectin and Mac-1 expression in vitro in vascular endothelial cells

Details on immunoblotting⁴² and the cytofluorimetric analysis to determine P-selectin and Mac-1 expression are given in the Online Supplementary Methods.

Statistical analysis

All calculations were performed using the IBM SPSS 20.0 statistical package (IBM Inc., Armonk, NY, USA). The level of aggregation was expressed as median values with the minimum-maximum range and shown by means of either dot or box plots. Data were analyzed with non-parametric tests, the Mann-Whitney U test for unpaired samples and the Wilcoxon signed-rank test for paired samples. A P value <0.05 was considered statistically significant.

Patients with sickle cell disease show activation of the alternative complement pathway and increased C3d-positive red blood cells

Untreated SCD subjects at steady state were studied. As shown in Table 1, reduced hemoglobin, increased reticulocyte counts and raised levels of plasma lactate dehydrogenase, all signs of chronic hemolytic anemia, were observed. In SCD patients, we also found significant increases of the levels of plasma C-reactive protein and surface vascular cell adhesion molecule-1, indicating the presence of a chronic inflammatory vasculopathy in agreement with previous reports.^2,3,9,43 Serum C3 and C4 levels were similar in healthy and SCD subjects (data not shown); whereas levels of the complement activation fragment C5a were significantly elevated in SCD patients when compared to the levels in healthy individuals (Figure 1A); statistical analyses were performed to exclude the possible contribution of confounding factors such as gender or smoking status. Our finding is consistent with previous reports, and confirms the substantial complement activation in SCD patients, likely via the AP.^15–22

Since studies in atypical hemolytic uremic syndromes have shown that skin biopsy might be a feasible method for documenting AP activation by C5b-9 vascular deposition,³² we obtained skin biopsies from SCD patients at steady state. We considered skin to be an interesting window of observation in SCD, since (i) it might be involved in the clinical manifestations of SCD, such as leg ulcers; and (ii) it has been widely used in SCD mouse models to functionally characterize the microvasculature.^44–47 As shown in Figure 1B, we observed microvascular intense, focal granular deposition of C5b-9 in small vessels throughout the dermis of SCD patients. This pattern is similar to that reported in skin biopsies from patients with atypical hemolytic uremic syndrome, which is a thrombotic microangiopathy related to complement dysfunction.³² No deposition of C5b9 was observed in skin from healthy controls (Online Supplementary Figure S1A,B). Co-localization of C59b deposits and CD31⁺ skin vessels was confirmed by immunohistochemical staining only in the skin biopsies from SCD patients (Figure 1C, Online Supplementary Figure S2A,B).

Taken together, our data indicate an activation of the AP in SCD, with possible involvement of complement in SCD vasculopathy and in related cellular adhesion events.

To understand whether AP activation occurs directly on sickle RBC, we measured the amounts of circulating RBC carrying C3-derived opsonins by detecting the presence of the common C3d fragment.^11,12 As shown in Figure 1D, higher numbers of C3d⁺ RBC were found in SCD patients in the steady state than in healthy subjects (representative scatter-plots are shown in Online Supplementary Figure S3). This fraction further increased in a subgroup of SCD patients during acute pain crises (SS steady state 2.5±0.8% versus SS pain crisis: 6.1±0.7% P<0.02; n=10), in agreement with an observation by Mold et al.¹⁸ Since a previous report linked activation of the AP with deposition of C3 opsonins to the exposure of phosphatidylserine on SCD RBC surfaces, we evaluated the percentage of phosphatidylserine-positive RBC in our SCD patients¹⁷ and did indeed find higher percentages of phosphatidylserine-positive RBC in SCD patients than in healthy subjects in agreement with previous studies^35,36 (Figure 1E). In contrast to paroxysmal nocturnal hemoglobinuria, in which opsonization leads to rapid lysis of affected RBC.^11,12 the presence of functional membrane regulators on SCD erythrocytes allowed a low level of C3-fragment deposition, which might also be considered as a marker of complement activation on sickle RBC. We, therefore, reasoned that the presence of C3b, iC3b or C3dg may function as a site of adhesion of SCD RBC to activated vascular endothelial surfaces, which may carry ligands for C3 fragments, such as Mac-1 and P-selectin.^48,49 To study this possibility, we used the C3b and iC3b binding plasma protein FH as an inhibitor^25–27 and saw no significant differences in FH serum levels between healthy subjects and SCD patients [AA median: 841 (range 616–1528) μg/mL versus SCD median: 980 (741–1301) μg/mL; P=NS].

Factor H prevents the adhesion of sickle red blood cells to tumor necrosis factor-α-activated vascular endothelium

We performed an ex vivo adhesion assay using TNF-α-activated vascular endothelial cells and monitored, in real time, the adhesion of RBC collected from healthy and SCD subjects to inactive (no TNF-α) or activated endothelium (plus TNF-α) as previously described.^38–40 Consistent with the literature, we observed significantly increased adhesion of SCD RBC to TNF-α-activated endothelium when compared to normal RBC (Figure 2A, Online Supplementary Video S1). We next investigated the effect of FH on the adhesion of healthy or SCD RBC to activated vascular endothelium. The dose-response curve with FH showed a significant reduction in RBC adhesion at concentrations ≥9 nM (Figure 2B). This was more pronounced for SCD RBC than for healthy RBC (Figure 2B). We, therefore, expanded the tests to include a larger number of SCD patients using FH concentrations of 9 or 18 nM; as expected, reduced adhesion of SCD RBC to the vascular endothelium was observed in the presence of either 9 nM or 18 nM FH (Figure 3A). Previous studies have identified two major regions on FH (i.e., domains 6-8 and 19-20) as the putative sites of interaction with cell surface constituents such as glycosaminoglycans; furthermore, domains 19-20 are also responsible for binding to sialic acids or C3d-containing deposits.²⁹ We, therefore, evaluated whether any of these segments had activity similar to that of full-length FH.

Perfusion experiments performed on TNF-α-activated endothelium demonstrated that, like intact FH, FH19-20 (18 nM) strongly prevented the adhesion of sickle RBC to the surface of TNF-α-activated vascular endothelium. Conversely, FH6-8 showed a trend, which did not reach statistical significance, toward a reduction in RBC adhesion (Figure 3B). Our data indicate that FH prevents sickle cell adhesion to the activated endothelium through its interaction with cell-surface sialic acids and C3b/iC3b found on the surface of pathological RBC (Figure 3B).

Factor H and its 19-20 domain normalize the sickle red blood cell trajectory and transverse velocity on tumor necrosis factor-α-activated vascular endothelium

We then developed a new algorithm for RBC to analyze their trajectory and transverse velocity, the velocity component perpendicular to the direction of flow of the RBC during their transit in the flow-chamber. The trajectory of each sickle RBC appeared irregular in space and was not uniform in time, especially when compared to that of healthy RBC (Figure 4A,B). This observation was based on the high transverse displacement and the presence of frequent stop-and-go motion that characterized the sickle RBC transit on the activated vascular endothelium. The transverse velocity is a parameter that is correlated with the disturbed movement of a particle. The path of healthy RBC appeared to be more regular, uniform, and parallel to the flow (Figure 4A, Online Supplementary Video S2). Thus, healthy RBC crossed the field of view more rapidly than did sickle RBC (0.8–1.2 s versus 1.7–2 s, respectively; P<0.05). In the presence of FH, the trajectory of sickle RBC was regularized (Figure 4C), reducing their transverse velocity to 7.71 ± 6.7 μm/s (average decrease of 81.13% versus vehicle-treated sickle RBC). The same behavior appeared in sickle RBC treated only with the FH 19-20 domain (Figure 4D), with the transverse speed being 6.56 ± 5.6 μm/s (an average decrease of 83.94% versus vehicle-treated sickle RBC). When the particle kinematics were quantified (Figure 3E), we found that the absolute value of the instantaneous transverse speed of sickle RBC was 40.86 ± 27.6 μm/s, whereas that of healthy cells was only 5.64 ± 4.9 μm/s (a difference of 86.20%). When healthy cells were compared to either FH- or FH19-20-treated sickle RBC, the absolute values for instantaneous transverse speed decreased significantly, reaching values similar to those observed for healthy RBC.

Anti-P-selectin and anti-Mac-1 antibodies prevent adhesion of sickle red blood cells to tumor necrosis factor-α-activated vascular endothelial surface

To better understand the binding proteins that may be important for adhesion of C3b/iC3b⁺ SCD red cells, we then evaluated the effects of anti-P-selectin or anti-Mac-1 antibodies on the adhesion of SCD to TNF-α-activated vascular endothelium. We chose these two molecules for the following reasons: (i) they are both modulated in endothelial cells:^2,50–55 (ii) P-selectin has been reported to bind C3b present on the membranes of circulating cells such as platelets;⁵⁶ and (iii) Mac-1 is a well-known receptor for iC3b, and potentially C3dg associated with the cell membrane.²⁵ In addition, P-selectin has been reported to bind RBC, targeting red cell plasma-membrane sialic acid, whereas the presence of a Mac-1 binding site on RBC membranes is still under investigation.^29,48,51,57 In our model, the expression of P-selectin and Mac-1 was significantly increased on TNF-α-activated vascular endothelium when compared to the expression on vehicle-treated cells (Online Supplementary Figure S4A). Both anti-P-selectin and anti-Mac1 antibodies prevented the adhesion of sickle RBC to the activated vascular endothelium (Figure 5A). Whereas the effect of the anti-P-selectin antibody on RBC adhesion may be mediated through interference with two different targets (i.e., iC3b and/or sialic acid), the interplay between Mac-1 and iC3b deposited on sickle RBC is considered to be more selective.^25,58 The anti-adhesive effect of the anti-Mac-1 antibody was more pronounced than that of the anti-P-selectin antibody, but the difference was not statistically significant. No effect on the adhesion of sickle RBC was documented in the presence of a control antibody (Online Supplementary Figure S4B). Collectively, these findings indicate that C3b/iC3b is deposited on sickle RBC membranes as a new ligand, bridging sickle RBC to the activated vascular endothelial surface through binding to the pro-adhesive molecules P-selectin and/or Mac-1.