Neutrophil extracellular traps directly induce epithelial and endothelial cell death: a predominant role of histones

Abstract

Neutrophils play an important role in innate immunity by defending the host organism against invading microorganisms. Antimicrobial activity of neutrophils is mediated by release of antimicrobial peptides, phagocytosis as well as formation of neutrophil extracellular traps (NET). These structures are composed of DNA, histones and granular proteins such as neutrophil elastase and myeloperoxidase. This study focused on the influence of NET on the host cell functions, particularly on human alveolar epithelial cells as the major cells responsible for gas exchange in the lung. Upon direct interaction with epithelial and endothelial cells, NET induced cytotoxic effects in a dose-dependent manner, and digestion of DNA in NET did not change NET-mediated cytotoxicity. Pre-incubation of NET with antibodies against histones, with polysialic acid or with myeloperoxidase inhibitor but not with elastase inhibitor reduced NET-mediated cytotoxicity, suggesting that histones and myeloperoxidase are responsible for NET-mediated cytotoxicity. Although activated protein C (APC) did decrease the histone-induced cytotoxicity in a purified system, it did not change NET-induced cytotoxicity, indicating that histone-dependent cytotoxicity of NET is protected against APC degradation. Moreover, in LPS-induced acute lung injury mouse model, NET formation was documented in the lung tissue as well as in the bronchoalveolar lavage fluid. These data reveal the important role of protein components in NET, particularly histones, which may lead to host cell cytotoxicity and may be involved in lung tissue destruction.

Figure 1. NET cause lung epithelial cell death in a concentration-dependent manner.

(A) The morphology of A549 cells was evaluated after 4 or 16 h treatment with medium (control), NET or staurosporine. Shown are representative pictures of >8 independent experiments at 20× magnification. (B) Cell growth from (A) was quantified by measuring the difference between occupied cell area after 16 h and 4 h. (C) Multicaspase activity of A549 cells was measured after 16 h treatment with two concentrations of NET (3.4 and 10.1 µg/ml DNA-NET) or staurosporine. Shown are representative data of three independent experiments (mean SD), *p<0.05; **p<0.01; ***p<0.001. (D) Immunofluorescence staining of A549 cells after 16 h treatment with two concentrations of NET (3.4 and 10.1 µg/ml DNA-NET) or staurosporine was performed for ethidium homodimer III (ethidium-HD, red), annexin V (green), and Hoechst 33342 (black and white). Shown are representative pictures of three independent experiments. (E) Percentage of ethidium-HD and annexin-V positive cells from (D) was evaluated by morphometry analysis.

Figure 2. NET induce cytotoxicity in epithelial and endothelial cells independent of digestion.

(A) The extent of cytotoxicity was measured after treatment of A549 cells for 16 h with undigested NET (−), completely (DNase), partially digested (MNase) or boiled forms of NET. The same concentration of DNA alone as DNA-NET (3.4 µg/ml) as well as DNase or MNase alone were used as controls. Shown are representative data of five independent experiments (mean SD), ***p<0.001, and ns = non-significant. (B) The degree of cytotoxicity was measured after treatment of HUVEC, HPAEC, AT-II or MLE-12 cells for 16 h with undigested NET (−) or completely (DNase) forms of NET as well as DNA alone. Shown are representative data of three (except for AT-II, n = 2) independent experiments (mean SD), ns = non-significant.

Figure 3. Histones induce epithelial and endothelial cell death.

(A) A549 cells were treated for 16 h with different concentrations of histone type II-A, and the cell morphology was evaluated. (B) A549 cell numbers were counted after treatment with various concentrations of histones for 16 h. (C) HUVEC or A549 cells were treated with 200 µg/ml histones for 16 h or left untreated (control). (D) HUVEC were treated for 16 h with different concentrations of histones, and the extent of cytotoxity was measured. B and D are representative data of three independent experiments, and in A and C pictures are representative pictures from three independent experiments at 20× magnification.

Figure 4. APC decreases epithelial cytotoxicity induced by histones but not by NET.

(A) Histones (200 or 100 µg/ml), pre-incubated for 1 h at 37°C in the absence or presence of 100 nM human APC, were incubated with A549 cells for 16 h, followed by analysis of cytotoxicity. (B) NET were incubated with APC (mass ratio APC: NET proteins, 1∶5, 1∶2 and 1∶1) or without APC for 1 h at 37°C, followed by incubation with A549 cells for 16 h and measurement of cytotoxicty. APC alone or active-site blocked APC (APC+PPACK) were incubated with A549 cells for control. (C) DNase-digested and (D) undigested forms of NET were pre-incubated with 100 nM APC for 20 to 80 min before incubation with A549 cells for 16 h, followed by determination of cytotoxicty. Shown are representative data of four independent experiments (mean SD), ***p<0.001 and ns = non-significant.

Figure 5. Histone antibodies and polysialic acid decrease NET-mediated cytotoxicity.

(A) NET were pre-incubated with different antibodies against histones (DNA/H1, H2A, H2B, H3, citrullinated H3 [cit H3], H4) or with isotype-matched control antibodies. Antibody-treated NET or NET alone (−) were incubated with A549 cells for 16 h to analyze the cytotoxicity. Shown are representative data of three independent experiments (mean SD), ***p<0.001 and ns = non-significant. (B) Histones or (C) NET were pre-incubated with antibody against histone H4 or polysialic acid (PSA), followed by incubation with A459 cells for 16 h to analyze the cytotoxicity. Note that polysialic acid considerably decreased both histone- and NET-mediated cytotoxicity.

Figure 6. Inhibition of neutrophil elastase does not inhibit NET-induced cytotoxicity.

(A) The supernatants of unstimulated (Unstim) or stimulated (Stim) neutrophils (50 nM PMA for 4 h) were collected and analyzed for elastase activity in the absence (filled bars) or presence (open bars) of neutrophil elastase inhibitor (NEI). Likewise, NET were isolated from stimulated cells and digested with DNase or MNase or kept undigested (−), followed by analysis of elastase activity in the same way. (B) Cytotoxicity of A549 cells was measured after 16 h treatment with NET (DNase-digested) in the absence or presence of NEI. Similar results were seen for MNase- or non-digested NET as well as with different NEI concentrations from 0.125 to 1 mM. Shown are representative data of three independent experiments (mean SD), ***p<0.001 and ns = non-significant.

Figure 7. Myeloperoxidase inhibition moderately decreases NET-induced cytotoxicity of epithelial cells.

Nondigested or DNase-digested NET were pre-incubated without or with myeloperoxidase inhibitor (MPOI), followed by incubation of NET with epithelial cells, A549 or AT-II cells, for 16 h and quantification of cytotoxicty. MPOI alone (37 ng/ml) was not toxic for the epithelial cells. Shown are representative data of three (for AT-II cells, n = 2) independent experiments (mean SD), *p<0.05 and ns = non-significant.

Figure 8. NET formation in LPS-induced lung injury mouse model.

(A) Immunofluorescence staining of lung sections from mice after 24 h intratracheal LPS administration was performed, as compared to the control section, for DNA/histone (red), neutrophil elastase (green) and DAPI (blue). The higher magnification views of the insets (1, 2 and 3), which were randomly chosen, showed co-localization of neutrophil elastase (green) and DNA/histone (red) in NET structures. (B) Immunofluorescence staining of sections from PBS- or LPS-treated mice was performed for DNA/histone (red), CD46 (green) as a cell membrane marker and DAPI (blue). The randomly chosen insets (4, 5 and 6) showed NET formation in LPS-treated lungs in higher magnification views as appeared by extracellular chromatin, disintegration of the cell membranes as well as weak signal for DAPI (indication of chromatin decondensation). DAPI alone and DNA/histone alone were also shown for the insets 4, 5 and 6. In A and B, yellow arrows indicate some of the tissue destruction areas adjacent to NET. Shown are representative pictures of >10 fields of tissue staining. (C) Immunofluorescence staining of lung sections from mice after 24 h intratracheal LPS administration was performed for myeloperoxidase (MPO, red), citrullinated histone H3 (Cit His3, green) and DAPI (blue). The higher magnification views (right column) of the selected areas showed co-localization of myeloperoxidase with citrullinated histone H3 which indicate NET formation.

Figure 9. Neutrophils (PMN) in the BALF of mice produce NET after LPS treatment.

(A) PMN, recruited to the BALF of mice following intratracheal LPS administration, were counted at different time intervals. (B) At the same time intervals, neutrophil elastase activity was measured in the supernatant of BALF (free elastase, open bars) as well as in the MNase-digested pellet of BALF (NET-related elastase, filled bars). (C) PMN were isolated from BALF of mice stimulated intratracheally with LPS for 24 h, and immunofluorescence staining of isolated cells was performed for DNA/histone (red), CD46 (green) and DAPI (blue) (upper row). Isolated PMN were further stimulated with PMA for 1.5 h (lower row); arrows indicate NET formation which is demonstrated by appearance of the extracellular chromatin, disintegration of the cell membranes as well as chromatin decondensation. Shown are representative data of three independent experiments (mean SD), ***p<0.001.