A sterol-regulatory element binding protein is required for cell polarity, hypoxia adaptation, azole drug resistance, and virulence in Aspergillus fumigatus

Abstract

At the site of microbial infections, the significant influx of immune effector cells and the necrosis of tissue by the invading pathogen generate hypoxic microenvironments in which both the pathogen and host cells must survive. Currently, whether hypoxia adaptation is an important virulence attribute of opportunistic pathogenic molds is unknown. Here we report the characterization of a sterol-regulatory element binding protein, SrbA, in the opportunistic pathogenic mold, Aspergillus fumigatus. Loss of SrbA results in a mutant strain of the fungus that is incapable of growth in a hypoxic environment and consequently incapable of causing disease in two distinct murine models of invasive pulmonary aspergillosis (IPA). Transcriptional profiling revealed 87 genes that are affected by loss of SrbA function. Annotation of these genes implicated SrbA in maintaining sterol biosynthesis and hyphal morphology. Further examination of the SrbA null mutant consequently revealed that SrbA plays a critical role in ergosterol biosynthesis, resistance to the azole class of antifungal drugs, and in maintenance of cell polarity in A. fumigatus. Significantly, the SrbA null mutant was highly susceptible to fluconazole and voriconazole. Thus, these findings present a new function of SREBP proteins in filamentous fungi, and demonstrate for the first time that hypoxia adaptation is likely an important virulence attribute of pathogenic molds.

Figure 1. Generation and confirmation of a SrbA null mutant in Aspergillus fumigatus.

(A) Schematic of wild type (CEA10) and SDW1 (SrbA null mutant) genomic loci. (B) Southern blot analysis of wild type, SDW1, and SDW2 strains. Genomic DNA from the respective strains was isolated and digested overnight with NcoI. An approximate 1 kb genomic region of the SrbA locus was utilized as a probe. The expected hybridization patterns and sizes were observed for the wild type CEA10 (5721 bp) and SrbA mutant (SDW1) (3622 bp) strains. In addition, confirmation of ectopic reconstitution of the SrbA null mutant was confirmed by the presence of the wild type srbA locus hybridization signal and persistence of the SrbA null mutant locus (strain SDW2).

Figure 2. SrbA is required for hyphal growth under hypoxic conditions.

1×10⁶ conidia of CEA10, SDW1 = ΔsrbA, SDW2 = ΔsrbA+srbA were plated on GMM plates and incubated at 37°C under normoxic and hypoxic conditions. (A) The diameter of the colony was measured over 96 h every 24 h. Under normoxic conditions no significant difference in growth speed and colony size or morphology could be observed (P>0.01). (B) Under hypoxic conditions the wild type CEA10 and the reconstituted strain SDW2 showed comparable growth (P>0.01) but the mutant strain SDW1 did not demonstrate any detectable growth. Error bars represent standard error from the triplicate experiments.

Figure 3. SrbA mediates resistance to Fluconazole (FL) and Voriconazole (VO) in Aspergillus fumigatus.

A clear ellipse indicates the susceptibility to the respective drug. As expected, Fluconazole has no effect on CEA10 and SDW2, but in the absence of SrbA, SDW1 is highly susceptible to Fluconazole (MIC = 1.0 µg/ml). CEA10 and SDW2 are susceptible to Voriconazole (MIC for both = 0.125 µg/ml); however, SDW1 also displays increased susceptibility (MIC = 0.012 µg/ml) to this important antifungal agent. The numbers on the scale correspond to the Fluconazole and Voriconazole concentrations on the E-test strip (in micrograms per milliliter).

Figure 4. Hyphal morphology and growth of wild type strain CEA10 and SrbA null mutant SDW1.

Strains were grown overnight on slides coated with GMM. Brightfield microscopy pictures of wild type CEA10 and SDW1 at 200-fold and 400-fold magnification. SDW1 showed abnormal hyphal formation and apparent cell polarity defect with multiple branches and unusual thick structures at the apical tips of the hyphae. Bars = 100 µm.

Figure 5. Abnormal cell wall-plasma membrane interface and hyphal morphology is evident in the absence of SrbA.

(A–C) Transmission electron micrographs showing sections of conidia of wild type CEA10 (A) and SDW1 (B,C). Compared with the round wild type conidia having clear boundaries between plasma membrane and cell wall layers, most of the SDW1 conidia were distorted in shape and possessed faint, somewhat shriveled boundaries. Note that frequent “tearing” took place mainly at the cell wall – plasma membrane interface during microscopic examination of the SDW1 conidia (arrows). This phenotype was observed in over 80% of SDW1 conidia examined. Inset panels depict a 3× magnified view of the conidial cell wall region. Bars = 500 nm. (D–H). Transmission electron micrographs showing longitudinal and transverse hyphal sections of wild type CEA10 (D,F) and SDW1 (E,G,H). Close observation of the hyphal tips show phenotypic differences between wild type and SDW1. Abnormal cell wall – plasma membrane interfaces and apical swellings in SDW1 hyphae were frequently observed, while the wild type showed normal round-shaped apexes. With respect to cell wall morphology around the hyphal apex, SDW1 had an abnormally expanded cell wall (arrows) containing numerous electron dense objects (arrowheads), which likely resulted in hyphal tip bending (H). Inset panels depict a magnified view of the boxed region. Bars = 1 µm, except for the inset panels of E and H where they denote 500 nm.

Figure 6. Conidia germination is not affected by loss of SrbA.

Germination media was inoculated with approximately 10⁶ conidia/ml of the A. fumigatus strains CEA10, SDW1, and SDW2. After 7 hours the germination rate was determined by counting a total of 100 spores and noting the number of germinated spores. Three replicates were performed. No significant difference in germination was observed between CEA10, SDW1, and SDW2 (P>0.01).

Figure 7. C4-demethylation is altered in the absence of SrbA.

Representative GC-MS chromatograms of sterol extracts from wild type (A) and SDW1 (B). Key: A- ergosta-5,8,22-trien-3β-ol, B- ergosterol, C- ergosta-5,7,22,24(28)-tetraen-3β-ol, D- ergosta-5,7,24(28)-trien-3β-ol, E- 24-ethylcholesta-5,7,22-trien-3β-ol, F- 4-methylfecosterol, G- 4methylergosta-5,8,24(28)-trien-3β-ol, H- 4,4-demethylergosta-8,24(28)-dien-3β-ol. An accumulation of 4-methyl sterols is observed in the absence of SrbA, suggesting a blockage in enzymes involved in sterol C-4 demethylation. The ratio of C-4 methylated sterols to ergosterol in the absence of SrbA was 1.94 whereas no C-4 methylated sterols accumulated in the wild type.

Figure 8. Role of SrbA in Aspergillus fumigatus virulence.

(A) Outbred CD-1 mice (n = 12) were immunosuppressed by i.p. injection of cyclophosphamide (150 mg/kg) 2 days prior to infection and s.c. injection of Kenalog (40 mg/kg) 1 day prior to infection and injection of 150 mg/kg cyclophosphamide 3 days post-inoculation and 40 mg/kg Kenalog 6 days post-inoculation. Mice were inoculated intranasally with 10⁶ conidia in a volume of 40 µl of wild type CEA10, ΔsrbA mutant strain SDW1 and the srbA reconstituted strain SDW2. P value for comparison between SDW1 and wild type CEA10, P = 0.0002. (B) gp91^phox−/− mice (n = 6) were challenged intratracheally with 10⁶ conidia in a volume of 40 µl of wild type CEA10, ΔsrbA mutant strain SDW1 and the srbA reconstituted strain SDW2. A log rank test was used for pair wise comparisons of survival levels among the strain groups. P value for comparison between SDW1 and wild type CEA10, P = 0.0054. SDW1 is significantly less virulent than the wild type CEA10 and the reconstituted strain SDW2 in both murine models. All animal experiments were repeated in duplicate with similar results.

Figure 9. Representative histopathology of CD-1 mouse model SDW1 infected survivors.

Hematoxylin and eosin (H&E) or Gommori's methenamine silver (GMS) stains at 100-fold magnification. No sign of inflammation or fungal burden was observed in any surviving animal on day +14, +21 and +28 of the infection. This result indicates that in this murine model, the immune system is capable of clearing the fungal infection in the absence of SrbA. Bar = 100 µm.

Figure 10. Histopathology of X-CGD mouse model 24 hours after infection.

Mock = 0.01% Tween inoculated, WT = CEA10, SDW1 = ΔsrbA, SDW2 = ΔsrbA+srbA. Mice were inoculated with 1×10⁶ conidia intratracheally, euthanized on day +1 after inoculation, lungs removed, fixed in formaldehyde, and stained with hematoxylin and eosin (H&E) or Gommori's methenamine silver (GMS) stain. On day 1 no difference in size and state of lesions could be observed in the infected mice. GMS staining revealed that fungal colonization and germination is observed in all infected animals but not the mock control. This result indicates that SDW1 conidia are viable in vivo during the early stages of infection. Bar = 100 µm.

Figure 11. Histopathology of X-CGD mouse model day 4 after infection.

Mock = 0.01% Tween inoculated, WT = CEA10, SDW1 = ΔsrbA, SDW2 = ΔsrbA+srbA. Mice were inoculated with 1×10⁶ conidia intratracheally, euthanized on day +4 after inoculation, lungs removed, fixed in formaldehyde, and stained with hematoxylin and eosin (H&E) or Gommori's methenamine silver (GMS) stain. Significant inflammation, necrosis, and an influx of immune effector cells (primarily neutrophils) is observed on day +4 in all infected animals but not the mock control. However, lesions are more localized and not as extensive in mice infected with SDW1. Open alveoli and more localized inflammation are clearly observed in mice infected with SDW1. Interestingly, GMS staining revealed that fungal growth is less extensive in SDW1 as well. This result indicates that as the infection progresses, SDW1 is incapable of continued hyphal growth despite the absence of NADPH oxidase in this murine model. Bar = 500 µm for 40×; Bar = 100 µm for 200×.

Figure 12. Representative histopathology of X-CGD mouse model SDW1 infected survivors.

Hematoxylin and eosin (H&E) or Gommori's methenamine silver (GMS) stains. Resolution of inflammation and necrosis is observed in all surviving animals on day +14 of the infection. However, lesions are still apparent as is common in these mice, but necrosis and debris is significantly reduced. Fungal tissue remains evident on GMS stains indicating that despite surviving the infection, these mice have not entirely cleared the fungal infection. This result confirms the importance of a functional NADPH oxidase in resistance to Aspergillus infections, and suggests that increased hypoxia prevents proliferation of fungal tissue in the absence of SrbA. Bar = 500 µm for 40×; Bars = 100 µm for 100× and 200×.

Figure 13. Loss of SrbA does not affect susceptibility to conidia killing by RAW264.7 cells.

RAW264.7 cells (macrophages) were infected with a total of 1.25×10⁶ freshly harvested A. fumigatus conidia of strains CEA10, SDW1, and SDW2 to obtain a conidia∶macrophage ratio of 5∶1. Conidia and macrophages were incubated together for 6 hours. After 6 hours, conidia were collected from the macrophages and plated onto glucose minimal media. Shown is the percent of recovered conidia after 6 hours incubation of two biological replicates. No significant difference in conidia killing was observed between CEA10, SDW1, and SDW2 (P>0.01).