Human CEACAM1 is targeted by a Streptococcus pyogenes adhesin implicated in puerperal sepsis pathogenesis

Abstract

Life-threatening bacterial infections in women after childbirth, known as puerperal sepsis, resulted in classical epidemics and remain a global health problem. While outbreaks of puerperal sepsis have been ascribed to Streptococcus pyogenes, little is known about disease mechanisms. Here, we show that the bacterial R28 protein, which is epidemiologically associated with outbreaks of puerperal sepsis, specifically targets the human receptor CEACAM1. This interaction triggers events that would favor the development of puerperal sepsis, including adhesion to cervical cells, suppression of epithelial wound repair and subversion of innate immune responses. High-resolution structural analysis showed that an R28 domain with IgI3-like fold binds to the N-terminal domain of CEACAM1. Together, these findings demonstrate that a single adhesin-receptor interaction can drive the pathogenesis of bacterial sepsis and provide molecular insights into the pathogenesis of one of the most important infectious diseases in medical history.

Fig. 1. The R28 adhesin of puerperal sepsis S. pyogenes isolates interacts with CEACAM1.

a Schematic of CEACAM1 (CC1), containing the extracellular region (composed of four Ig-like domains termed N, A1, B1, and A2) and cytoplasmic tail containing two immunoreceptor tyrosine-based inhibitory motifs (ITIM) for signaling. b Schematic of the S. pyogenes R28 and S. agalactiae Rib proteins. Each protein has a signal peptide (S) and cell wall anchor (#) domains. R28 contains the N2 domain that can be divided into N2_A and N2_B (renamed IgI3) subdomains. The percentage residue identity between domains is indicated. c Binding of recombinant (r)CC1-Fc to immobilized R28 and Rib, quantified by ELISA (mean ± s.d. of n = 3 independent experiments). Statistical significance tested by two-tailed paired Student’s t test (**p = 0.0079). d Binding of rCC1-HIS variants to R28-IgI3, quantified by flow cytometry (mean ± s.d. of n = 6 independent experiments) e Core genome phylogeny of 287 representative S. pyogenes genomes. spr28 positivity (inner circle) and emm-type (outer circle) given. Scale: substitutions per site. f Expression of surface-localized R28 by S. pyogenes strains, quantified by flow cytometry (Data are represented as mean ± s.d.). g Binding of rCC1-HIS to S. pyogenes strains as in f, quantified using flow cytometry (Data are represented as mean ± s.d.). In f and g, each data point represents the mean from n = 2 independent experiments per strain (n = 30 emm28 strains, n = 11 emm2 strains, n = 10 emm77 strains). Closed circles show spr28 + strains and open circles show isogenic Δspr28 strains. Open squares show spr28- strains, typed by PCR. Dashed lines indicate signal from an R28-negative strain (S. pyogenes M1 5448) or a CC1-binding strain (S. agalactiae A909). h Adherence of isogenic S. pyogenes AL368 strains to CHO cell lines (mean ± s.d. from n = 8 independent experiments). Statistical significance tested by one-way ANOVA with Tukey’s post-hoc test (+R28 control vs. +R28 CC1 ***p = 0.0006, +R28 CC1 vs. -R28 CC1 ****p = 0.0001).

Fig. 2. CEACAM1 is a highly specific receptor for the R28 adhesin.

a Schematic of screening procedure for a library of 3359 HEK293 (Supplementary Data 1) cell line clones expressing human membrane proteins for ability to bind the streptococcal proteins R28 and Rib. Positive signals were obtained with 45 cell lines. b Binding of purified R28 protein to the 45 positively-hit HEK293 cell lines. Cells stained with rabbit anti-Rib sera (red) or normal rabbit sera (black) are shown. The relative fluorescence means ± s.d. of n = 4 from two independent experiments is shown. A representative image of fluorescence for the 45 cell lines (tested in duplicates) is shown in the inset, with FCGR1 identified as a non-specific hit. c Binding of recombinant CEACAM1-HIS (CC1), CEACAM3-HIS (CC3), CEACAM5-HIS (CC5), CEACAM6-HIS (CC6), and CEACAM8-HIS (CC8) to immobilized R28 and Rib quantified by ELISA (Mean ± s.d. of n = 3 independent experiments). Statistical significance tested for binding of each rCC to R28 or Rib by paired two-sided Student’s t test (Rib + CC1 vs. R28 + CC1 *p = 0.0266). d Binding of rCC1-HIS, rCC3-HIS, rCC5-HIS, rCC6-HIS, and rCC8-HIS to a panel (n = 15, including two isogenic Δspr28 strains) of S. pyogenes strains from lineage emm28, quantified by flow cytometry (Each data point represents mean of n = 3 independent experiments). Mean ± s.d. of each lineage is shown. e Adherence of wildtype S. pyogenes AL368 to HeLa or HeLa^CC1, HeLa^CC3, HeLa^CC5, HeLa^CC6, and HeLa^CC8 cells (Mean ± s.d. of n = 4 independent experiments). Statistical significance compared to control cell line by one-way ANOVA with Dunnetts’s post-hoc test (HeLa control vs. HeLa.CC1 ***p = 0.002).

Fig. 3. Structural basis and human specificity of R28-IgI3 interaction with CEACAM1.

a Crystal structure of N-terminal domain of CEACAM1 (CC1) domain in complex with R28-IgI3, shown as an electron density map. b Mutation of residues K45, I52, I53 and Y61 in R28-IgI3 abolishes binding to CC1-N (Mean ± s.d. of n = 6 independent experiments). Statistical significance tested between R28-IgI3 wildtype and variants by one-way ANOVA with Dunnetts’s post-hoc test (WT vs. K45A *p = 0.0219, WT vs. I52A *p = 0.0210, WT vs. I53A *p = 0.0214, WT vs. Y61A *p = 0.0257). c Mutation of residues F29, I91 and L95 in CC1-N abolishes binding to R28-IgI3 (Mean ± s.d. of n = 6 independent experiments). Statistical significance tested between CC1-N wildtype and variants by one-way ANOVA with Dunnetts’s post-hoc test (WT vs. F29A *p = 0.0134, WT vs. I91A *p = 0.0122, WT vs. L95A *p = 0.0152, WT vs. V96A *p = 0.0471, WT vs. N97A *p = 0.0428). d A close-up view of the R28-IgI3 binding interface of CC1-N. e Alignment of CC1-N sequences. The critical residues required for binding of R28-IgI3 to human CC1 are highlighted by red boxes. f Binding of human, macaque, mouse or rat rCC1-HIS or rCC1-Fc proteins to R28-IgI3 (Mean ± s.d. of n = 4 independent experiments). Statistical significance tested by one-way ANOVA with Tukey’s post-hoc test (Fc-tag proteins, human CC1 vs. human CC8 *p = 0.0478, human CC1 vs. macaque CC1 *p = 0.0354, human CC1 vs. rat CC1 *p = 0.0353; HIS-tag proteins, human CC1 vs. human CC8 *p = 0.0489, human C1 vs. mouse CC1 *p = 0.0487). g Docking of R28-IgI3 onto human and macaque CC1-N variants, quantified as the binding-free energy (kcal/mol) (Mean ± s.d. of n = 10 in silico simulations). Binding-free energy for non-interacting proteins (R28-IgI3 and human CC1-N^F29A) is shown by a dashed line. Statistical significance tested by one-way ANOVA with Tukey’s post-hoc test (human CC1 vs. human CC1^F29A ****p < 0.0001, human CC1 vs. human CC1^F29I ***p < 0.0003, human CC1 vs. macaque CC1 ****p < 0.0001, macaque CC1 vs. macaque CC1I29F ***p = 0.0005). h Close-up of the R28-IgI3 binding interface of human and macaque CC1-N. R28-IgI3 residues required are shown in gray. F29 in human CC1-N and I29 in macaque CC1-N are shown in blue and yellow, respectively.

Fig. 4. R28 promotes adherence of S. pyogenes to human cervical epithelial cells and suppresses wound closure through a CEACAM1-dependent mechanism.

a Adherence of isogenic S. pyogenes AL368 strains to ME-180 cells at a multiplicity of infection (MOI) of 10, in the presence or absence a monoclonal antibody (mAb) specific to human CC1 and CC5 N-terminal (mean ± s.d. of n = 10 independent experiments). Statistical significance tested by one-way ANOVA with Tukey’s post-hoc test (+R28 vs. −R28 *p = 0.0142, +R28 vs. +R28 + anti-CC1/CC5 **p = 0.0071, +R28 + anti-CC1/CC5 vs. +R28 + IgG1 *p = 0.043). b, c Wound healing of ME-180 cell monolayers upon challenge with isogenic S. pyogenes AL368 strains. b Shows representative light microscopy images of ME-180 epithelia at ×10 magnification, in which the front of each scratch at 0 h is marked by a complete line and at 24 or 48 h by a dashed line. c shows the mean ± s.d. of at least n = 7 independent experiments. Statistical significance tested by one-way ANOVA with Tukey’s post-hoc test (24 h, Buffer vs. +R28 **p = 0.004, +R28 vs. −R28 ***p = 0.0002; 48 h, Buffer vs. +R28 **p = 0.0016, +R28 vs. −R28 **p = 0.0099). d Treatment of ME-180 cells with purified R28 protein suppresses wound repair (Mean ± s.d. of n = 8 independent experiments). Statistical significance tested by one-way ANOVA with Tukey’s post-hoc test (Buffer vs. R28 **p = 0.0012, R28 vs. Rib **p = 0.0056). e The impact of rR28-IgI3 protein treatment of ME-180 cell wound repair (mean ± s.d. of n = 8 independent experiments). Data generated using wildtype or mutant R28-IgI3 domains. Statistical significance tested by one-way ANOVA with Tukey’s post-hoc test (Buffer vs. WT *p = 0.0102, WT vs. Y61A **p = 0.009).

Fig. 5. S. pyogenes impairs the human immune response through R28-CEACAM1 interaction.

a Schematic representation of measurement of the cytokine and chemokine response of human cervical explants upon challenge with S. pyogenes strains or control buffer. b Quantification of the protein level production of cytokines and chemokines by wounded human cervical explants in response to infection with S. pyogenes strains. Samples were normalized against uninfected controls. Mean and s.d. from n = 7 independent human ecto-cervical explant donors. Statistical significance tested by two-tailed paired Student’s t test (IL-1β *p = 0.0334, GM-CSF *p = 0.0155, MIP-1β *p = 0.0139, SDF-1β **p = 0.0075, IL-12 ***p = 0.0006). c Activated human neutrophils bind purified R28. Data is representative of n = 3 independent replicates. d Survival of S. pyogenes after 2 h of incubation with human neutrophils at a multiplicity of infection (MOI) of 10 was quantified as the percentage of inoculum. Data are represented as mean ± s.d. of n = 12 data points from n = 6 independent donors. Statistical significance tested by two-tailed paired Student’s t test (R28 + vs. R28- ***p = 0.0003). e Replication of isogenic S. pyogenes AL368 strains in human whole blood was quantified after 3 h as the percentage of inoculum (mean ± s.d. from n = 10 independent experiments). Statistical significance tested by two-tailed unpaired t test (R28 + vs. R28- **p = 0.0063). f Pre-incubation of S. pyogenes with rCC1 suppresses the replication of S. pyogenes in human whole blood (Mean ± s.d. of n = 9 independent experiments). Statistical significance tested by two-tailed paired Friedman test with Dunn’s post-hoc test (Buffer vs. rCC1 *p = 0.0286, rCC1 vs. rCC8 **p = 0.0065).

Fig. 6. Model for the role of R28-CEACAM1 interaction in S. pyogenes puerperal sepsis pathogenesis.

The intact vaginal epithelium (left panel) is rarely colonized by S. pyogenes, but wounds introduced during childbirth provide opportunities for R28-expressing S. pyogenes to invade the mucosal tissue (right panel). Interaction of R28 with CEACAM1, present on the apical surface of the epithelial cells, impairs wound repair, and suppresses the proinflammatory immune response. This provides enhanced opportunities for S. pyogenes to invade the tissue. Moreover, binding of R28 to CEACAM1 on innate immune cells promotes the capacity of S. pyogenes to survive in blood, favoring the development of systemic infection. In contrast, an R28-negative mutant does not interact with CEACAM1 and will be less able to evade a proinflammatory response (middle panel).