BBK32 attenuates antibody-dependent complement-mediated killing of infectious Borreliella burgdorferi isolates

Abstract

Borreliella burgdorferi, the causative agent of Lyme disease, has evolved unique complement evasion proteins that promote its ability to establish and maintain infection in mammalian hosts. Among these is B. burgdorferi BBK32, a multifunctional surface lipoprotein that binds extracellular matrix (ECM) components, including fibronectin (Fn). In addition to its ECM-binding functions, BBK32 binds to C1r, the initiator protease of the classical pathway of complement, and protects B. burgdorferi from complement-mediated killing following exposure to normal human serum. The disparate functions of BBK32 in adhesion and complement evasion have previously been studied in isolation. Herein we demonstrate that full-length BBK32 binds both Fn and C1 concurrently, indicating that binding of these macromolecules do not sterically hinder their simultaneous interaction. Given the link of antibody dependence to the classical pathway, we tested how the presence of BBK32 would protect infectious B. burgdorferi from borrelial-specific antibodies in a complement-dependent manner. BBK32 provided protection against complement activation in the presence of borrelial-specific antibodies in vitro. We also demonstrated, using both flow cytometry and fluorescence microscopy, that BBK32 results in the reduction of C4 deposition on the surface of borrelial cells. This work demonstrates that BBK32 can simultaneously bind to both C1r and Fn and contributes to the broader understanding of the ability of B. burgdorferi to evade antibody-dependent complement-mediated killing. These observations are significant as they suggest that BBK32 plays a dual role in adhesion and dissemination in infectious B. burgdorferi, as well as immune evasion activities, which ostensibly promotes its pathogenic potential.

Fig 1. AlphaFold3 model of the C1r-BBK32-Fn ternary complex.

AlphaFold3 was used to simultaneously fold BBK32 (orange, residues 131–354; UNIPROT: O50835), the C1r serine protease (SP) domain (grey, residues 464–702; UNIPROT: P00736), and the Fibronectin N-terminal domains (FN NTD; ²FnI-⁵FnI) (cyan, residues 95–273, UNIPROT: P02751). Structural alignments to the published crystal structures of BBK32-C (PDB: 6N1L), the complex of BBK32-C and C1r (PDB: 7MZT), and the complex of BBK32-N with ²FnI-³FnI (PDB: 4PZ5) are shown inset. C1r and Fn from the crystal structures are drawn in red in each alignment, while BBK32 residues are shown in blue. Root mean square deviation (rmsd) (αC) is shown for each alignment.

Fig 2. BBK32 binds C1 and Fn concurrently.

A. SPR assays were performed using immobilized BBK32 injected with 20 nM human Fn, 50 nM human C1, and B. a co-injection of 20 nM human Fn and 50 nM human C1. C. The ability of BBK32 to concurrently interact with human Fn and C1 was calculated by subtracting the human Fn curve from the co-injection curve and comparing that curve to the human C1-alone injection curve. Three technical replicates were performed. Error bars represent SD. Statistical significance of the residual binding signals were assessed using a one-way ANOVA with a Tukey’s multiple comparisons test, * P < 0.002, ns = not significant.

Fig 3. Differential binding of human Fn and C1r to B. burgdorferi strain B31-A3, bbk32 mutant, and functional and non-functional bbk32 derivatives.

A. Overlay experiments performed using B31-A3 GFP parent, and isogenic bbk32 mutant strain (GP100), native bbk32 complement (GP100 pCD100), and a bbk32-R248A/K327A double alanine (DA) mutant complement (GP100 pAP7). B. Identical overlays for strain ML23 pBBE22luc (parent), the bbk32 mutant derivative (JS315 pBBE22luc), native bbk32 complement (JS315 pCD100), and a bbk32-R248A/K327A double alanine (DA) mutant complement (JS315 pAP7). For both sets of strains, protein lysates were incubated with human Fn or human C1r and then probed separately with antibody reagents specific for either human Fn or C1r (see Methods). These same samples were also probed with monoclonal antibodies to BBK32 and B. burgdorferi FlaB (third row and bottom row, both panels, respectively).

Fig 4. Loss of BBK32 complement binding and inhibition results in increased C4 deposition.

The serum-sensitive derivative B314 was transformed with either native bbk32 or the bbk32-R248A/K327A allele that lacks C1r binding or inhibition activity. Both cells were incubated with antibodies against B. burgdorferi, followed by C5-depleted human serum. The level of C4c deposition was then scored for 10,000 events using flow cytometry tracking the deposition of C4c on the surface of the spirochetes. The isolate encoding wildtype bbk32 is shown in Panel A, the strain with bbk32-R248A/K327A (double alanine mutant [DA]) is depicted in Panel B, and a control with no antibody to C4c is indicated in Panel C (see Methods for detail). Panel D shows the data comparing wildtype bbk32 (green) relative to expressing bbk32-R248A/K327A (purple) in B. burgdorferi strain B314 as a histogram plot with the background binding shown in Panel C subtracted. The presence of wildtype BBK32 reduces the amount of C4c deposition relative to the BBK32-R248/K327A DA mutant consistent with the mutant’s inability to bind and inhibit C1r and reduce classical complement activation. The mean for three individual replicates is shown with standard deviation. * P = 0.02.

Fig 5. Qualitative assessment of increased deposition of complement components in bbk32 mutant strains.

Green fluorescent protein (GFP) producing B. burgdorferi strains B31-A3 GFP, GP100 (B31-A3 GFP bbk32::Str^R), GP100 pCD100 (bbk32::Str^R with native bbk32 complement), and GP100 pAP7 (bbk32::Str^R with bbk32-R248A/K327A [DA] complement) were incubated with rabbit anti-B. burgdorferi antibody coupled with C5-depleted serum. Cells were then probed with murine anti-C4c, followed by anti-mouse Cy5. Cells were fluorescently imaged via confocal microscopy and B. burgdorferi antibody binding and C4c deposition were assessed. Cells that have increased colocalization of GFP together with C4c are depicted in light blue in the lower row of each strain tested.

Fig 6. Antibody-dependent complement-mediated killing of B. burgdorferi strain B31-A3 derivatives.

A. The B31-A3-GFP parent strain, the isogenic bbk32 mutant GP100 (B31-A3-GFP bbk32::Str^R), the GP100 strain complemented with either native bbk32 (GP100 pCD100) or bbk32-R248A/K327A double alanine (DA) mutant (GP100 pAP7) were each separately incubated with anti-B. burgdorferi antibody coupled with NHS, rabbit isotype control antibody coupled with NHS, or anti-B. burgdorferi antibody coupled with heat-inactivated NHS. B. Identical assays were performed for the ML23 derivatives (see Table 1 and Fig 3). Viability of each data set was then assessed via dark-field microscopy based on cell motility and overt membrane disruption in triplicate. Error bars represent standard deviation values. * P < 0.05; ** P < 0.01; *** P < 0.001.