Secreted antigen A peptidoglycan hydrolase is essential for Enterococcus faecium cell separation and priming of immune checkpoint inhibitor therapy

Abstract

Enterococcus faecium is a microbiota species in humans that can modulate host immunity¹, but has also acquired antibiotic resistance and is a major cause of hospital-associated infections². Notably, diverse strains of E. faecium produce SagA, a highly conserved peptidoglycan hydrolase that is sufficient to promote intestinal immunity^3-5 and immune checkpoint inhibitor antitumor activity⁶. However, the functions of SagA in E. faecium were unknown. Here we report that deletion of sagA impaired E. faecium growth and resulted in bulged and clustered enterococci due to defective peptidoglycan cleavage and cell separation. Moreover, ΔsagA showed increased antibiotic sensitivity, yielded lower levels of active muropeptides, displayed reduced activation of the peptidoglycan pattern-recognition receptor NOD2, and failed to promote cancer immunotherapy. Importantly, plasmid-based expression of SagA, but not its catalytically-inactive mutant, restored ΔsagA growth, production of active muropeptides and NOD2 activation. SagA is therefore essential for E. faecium growth, stress resistance and activation of host immunity.

Extended Data Figure 1.. Analysis of E. faecium ΔsagA deletion and complementation studies.

a, PCR validation of ΔsagA deletion. b, ΔsagA cells are sedimented at the bottom of the tube compared to E. faecium WT and ΔsagA / psagA.

Extended Data Figure 2.. Antibiotic sensitivity of ΔsagA.

a, Approximate minimum inhibitory concentration (MIC) determinations via antibiotic test strips for E. faecium WT, ΔsagA and ΔsagA/ psagA. White arrows point to MIC values (summary of MIC determination is in Extended Data table 2). b, Liquid culture MIC determination for ampicillin. Growth curves of E. faecium WT, ΔsagA, and ΔsagA/ psagA in the presence of serially diluted ampicillin (n=3). Data are presented as mean value ± standard deviation. MIC is defined as minimum tested concentration at which no bacterial growth is observed.

Extended Data Figure 3.. E. faecium ΔsagA exhibits no defects in cell wall and septum thickness.

a, Representative cryo-ET images of E. faecium WT, ΔsagA, and ΔsagA/ psagA are shown in the top row. The cell wall, septum, divisome, and ribosome are indicated by white arrows. 3D segmentations are shown in the bottom row. The cell wall is annotated in blue, the membrane in green, and the divisome in magenta. Scale bar = 100 nm. b, The upper panel shows a diagram illustrating how measurements are collected. In the lower panel, a representative cryo-ET image of the septum is shown. Scale bar = 50 nm. c, Comparison of cell wall thickness. The violin plot displays the distribution of cell wall thickness, with E. faecium WT (n=66) shown in blue, ΔsagA (n=96) shown in red, and ΔsagA/ psagA (n=69) shown in magenta. Black dotted lines represent median (E. faecium WT: 47.48nm, ΔsagA: 50.11nm, ΔsagA/ psagA: 46.42nm) while the colored dotted lines represent quartiles. Welch’s t test was used to calculate statistical significance. ns, P ≥ 0.05. d, Comparison of septum thickness. The violin plot displays the distribution of septum thickness, with E. faecium WT (n=26) shown in blue, ΔsagA (n=62) shown in red, and ΔsagA/ psagA (n=16) shown in magenta. Black dotted lines represent median (E. faecium WT: 54.33nm, ΔsagA: 54.86nm, ΔsagA/ psagA: 57.50nm) while the colored dotted lines represent quartiles. Welch’s t test was used to calculate statistical significance. ns, P ≥ 0.05. (e) Comparison of divisome architecture. To assess potential alterations in the divisome architecture, the distance between the apical end of the septum and the membrane-proximal ring was divided by the distance between the apical end of the septum and the membrane-distal ring. The violin plot displays the distribution of the ratios, with E. faecium WT (n=31) shown in blue, ΔsagA (n=40) shown in red, and ΔsagA/ psagA (n=42) shown in magenta. Black dotted lines represent median (E. faecium WT: 0.5, ΔsagA: 0.5, ΔsagA/ psagA: 0.5) while the colored dotted lines represent quartiles. Welch’s t test was used to calculate statistical significance. ns, P ≥ 0.05.

Extended Data Figure 4.. Deletion of sagA alters the position of cell division.

a, Cartoon model depicting cell division site in the xy coordinate plane (left) and xz coordinate plane (right). The two boxes shown in right represent the cryo-focused ion beam (cryo-FIB) milling patterns used to generate thin sections of E. faecium for subsequent cryo-electron tomography (cryo-ET) imaging. b-d, Representative tomographic slices (n=2) of E. faecium strains: E. faecium WT (b), ΔsagA (c), and ΔsagA/ psagA. (d). The upper panels show view of dividing cells in the xy coordinate plane and, while the corresponding bottom panels show the divisome complex (annotated with white arrows) at the highlighted areas in the corresponding upper panels in the xz coordinate plane, obtained by rotating the cell 90° along the highlighted axis. Scale bar = 100 nm. e, A diagram indicating how measurements were collected. f, Comparison of membrane to proximal ring distance. The violin plot displays the distribution of distance between the apical end of septum membrane to the proximal ring, with E. faecium WT (n=31) shown in blue, ΔsagA (n=40) shown in red, and ΔsagA/ psagA (n=42) shown in magenta. Black dotted lines represent median (E. faecium WT: 7.39nm, ΔsagA: 7.39nm, ΔsagA/ psagA: 7.39nm) while the colored dotted lines represent quartiles. Welch’s t test was used to calculate statistical significance. ns, P ≥ 0.05. g, Comparison of membrane to distal ring distance. The violin plot displays the distribution of distance between the apical end of septum membrane to the distal ring, with E. faecium WT (n=31) shown in blue, ΔsagA (n=40) shown in red, and ΔsagA/ psagA (n=42) shown in magenta. Black dotted lines represent median (E. faecium WT: 14.77nm, ΔsagA: 15.83nm, ΔsagA/ psagA: 15.83nm) while the colored dotted lines represent quartiles. Welch’s t test was used to calculate statistical significance. *, P < 0.05.

Extended Data Figure 5.. Peptidoglycan profile of E. faecium ΔsagA by LC-MS.

a, Representative LC-MS chromatograms of mutanolysin-digested peptidoglycan isolated from sacculi of E. faecium WT (top), ΔsagA (middle), and ΔsagA/ psagA (bottom). Numbers correspond to each muropeptide annotated in the table (b). b, Composition of mutanolysin-digested peptidoglycan isolated from E. faecium sacculi. ^a. Peak numbers refer to (a). ^b. GM, disaccharide (GlcNAc-MurNAc); 2GM, disaccharide-disaccharide (GlcNAc-MurNAc-GlcNAc-MurNAc); 3GM, disaccharide-disaccharide-disaccharide (GlcNAc-MurNAc-GlcNAc-MurNAc-GlcNAc-MurNAc); GM-Tri, disaccharide tripeptide (L-Ala-D-iGln-L-Lys); GM-Tetra, disaccharide tetrapeptide (L-Ala-D-iGln-L-Lys-D-Ala); GM-Penta, disaccharide pentapeptide (L-Ala-D-iGln-L-Lys-D-Ala -D-Ala). ^c. The assignment of the amide and the hydroxyl functions to either peptide stem is arbitrary.

Extended Data Figure 6.. Gating strategy used for flow cytometry analysis of TILs.

We first identified total tumor infiltrating cells by forward and side scatter gating. We then selected single cells using forward scatter area (FSC-A) versus forward scatter height (FSC-H) parameters and side scatter area (SSC-A) versus side scatter height (SSC-H) parameters respectively. From the single cell population, we selected live cells by gating on LIVE/DEAD dye events. Then, we selected total leukocytes from live cells, using the pan-leukocyte marker CD45. From the total leukocytes, we identified T cells and NK cells using the pan-T cell marker CD3 and the NK cell marker NK1.1. We then split T cells (CD3⁺ NK1.1⁻) into CD4⁺ and CD8⁺ populations using CD4 and CD8 expression. From the total CD8⁺ T cells, we further gated GranzymeB⁺CD8⁺ cytotoxic T cells, Ki67⁺CD8⁺ T cells, and PD-1⁺CD8⁺ T cells. From the total CD4⁺ T cells, FoxP3⁺ CD4⁺ T cells were identified as regulatory T cells. We also gated the GranzymeB⁺ NK cells from NK (CD3⁻NK1.1⁺) cells.

Extended Data Figure 7.. Summary of SagA function in E. faecium and impact on host immunity during ICI cancer therapy.

Deletion of sagA impairs peptidoglycan remodeling and cell separation in E. faecium and limits the activation of NOD2 in mammalian cells to promote immune checkpoint inhibitor cancer therapy in mouse models. Created with BioRender.com.

Figure 1.. Growth and morphology phenotypes of wild type, ΔsagA and psagA complemented E. faecium Com15 strains.

a, Growth curves of E. faecium WT, ΔsagA, and complementation strains with functional and nonfunctional sagA genes (n=3). Data are presented as mean value ± standard deviation. b, α-SagA Western Blot of E. faecium WT, ΔsagA, and complementation strains with functional and nonfunctional sagA genes, on both whole cell lysate (pellets) and total secreted proteins (secreted). Bottom panel shows total protein loading visualized by Stain-free^™ imaging and serves as protein loading control. c, DIC microscopy of E. faecium WT, ΔsagA and ΔsagA/ psagA complemented strains. White arrows point to cell clusters. Scale bar = 5 μm. d, Transmission electron microscopy (TEM) of E. faecium WT Com15, ΔsagA, and ΔsagA/ psagA complemented strains. White arrows point to failed cell separation in ΔsagA. Green arrow points to undegraded peptidoglycan in ΔsagA. Scale bar = 0.2 μm.

Figure 2.. Deletion of sagA changes the angle of growing septum.

a-c, Representative tomographic slices (n=3) of E. faecium strains: E. faecium WT (a), ΔsagA (b), and ΔsagA/ psagA (c). Cell division septa are indicated by white arrows. Scale bar = 100 nm. d, A diagram indicating how septum angle measurements were collected. Acute angles are recorded for further analysis. e, Comparison of septum angle. The violin plot displays the distribution of septum angle, with E. faecium WT (n=40) shown in blue, ΔsagA (n=49) shown in red, and ΔsagA/ psagA (n=37) shown in magenta. Black dotted lines represent median (E. faecium WT: 88°, ΔsagA: 79°, ΔsagA/ psagA: 87°) while the colored dotted lines represent quartiles. Welch’s t test was used to calculate statistical significance. *, P < 0.05; ****, P < 0.0001. f, Pairwise comparison of septum angle in opposing septa. The paired plot displays the distribution of septum angle, with E. faecium WT (n=18) shown in blue, ΔsagA (n=16) shown in red, and ΔsagA/ psagA (n=16) shown in magenta. Two septum angles from opposing septa are linked with straight lines. Paired t test was used to calculate statistical significance. ns, P ≥ 0.05.

Figure 3.. Peptidoglycan profile and NOD2 activation of E. faecium ΔsagA.

a, Relative abundance of muropeptides isolated from mutanolysin-digested sacculi of E. faecium strains and analyzed by LC-MS (n=6). Green asterisks highlight changes in abundance of small muropeptides, purple asterisks highlight changes in abundance of crosslinked peptidoglycan fragments. Numbers correspond to different muropeptides from LC-MS analysis listed in legend. b, Composition of muropeptides from E. faecium sacculi. ^a. Peak numbers refer to (a). ^b.GM, disaccharide (GlcNAc-MurNAc); 2GM, disaccharide-disaccharide (GlcNAc-MurNAc-GlcNAc-MurNAc); 3GM, disaccharide-disaccharide-disaccharide (GlcNAc-MurNAc-GlcNAc-MurNAc-GlcNAc-MurNAc); GM-Tri, disaccharide tripeptide (L-Ala-D-iGln-L-Lys); GM-Tetra, disaccharide tetrapeptide (L-Ala-D-iGln-L-Lys-D-Ala); GM-Penta, disaccharide pentapeptide (L-Ala-D-iGln-L-Lys-D-Ala -D-Ala). ^c. The assignment of the amide and the hydroxyl functions to either peptide stem is arbitrary. c, Relative abundance of GMDP relative to WT from LC-MS chromatograms (n=6). d, NF-κB responses of HEK-Blue^™ hNOD2 cells to live E. faecium strains (MOI=1, n=6). NOD2 activation is expressed as fold change relative to untreated control. e, Colony forming units (CFU) of E. faecium strains (MOI = 1) internalized in HEK-Blue^™ hNOD2 cells (n=6). Dashed line indicates Limit of Detection (LOD). Data for a, c-e represent mean value ± standard deviation and analyzed with one-way ANOVA and Tukey’s multiple comparison post hoc test. *p≤0.05; **p≤0.01; ***p≤0.005; ****p≤0.001; ns, not significant.

Figure 4.. Immune checkpoint inhibitor antitumor activity and tumor immune profile of E. faecium ΔsagA colonized mice.

a, Schematic of tumor growth experiment: mice were provided water containing antibiotics for one week and started drinking bacteria three days before tumor implantation. Once the tumor reaches ~100 mm³, the measurement starts and two days after treated with anti-PD-1 (MC38) or anti-PD-L1 (B16F10) every other day. b, MC-38 tumor growth in Nod2^+/− or Nod2^−/− mice that were colonized with E. faecium WT and treated with anti-PD-1 starting at day 7. n=10 for Nod2^+/− mice, n=6 for Nod2^−/− mice. c, B16F10 tumor growth in C57BL/6 mice that were colonized with E. faecium WT or ΔsagA and treated with anti-PD-L1 starting at day 6. No bacterial colonization group as a control (black). n=7-8 mice per group. d, Fecal CFU analysis of E. faecium on HiCrome^™ Enterococcus faecium agar plates from c at day 6. n=6 per group. Each dot represents one mouse. The line indicates the limit of detection (LOD, 4000 CFU g⁻¹). Nd, not detected. Data represent means ± 95% confidence interval. e-j, Quantification of tumor infiltrating CD45⁺ cells (e), FoxP3⁺ cells (f), CD3⁺ CD8⁺ cells (g), GranzymeB⁺ CD8⁺ T cells (h), Ki67⁺ CD8⁺ T cells (i) and PD-1⁺ CD8⁺ T cells (j). For f, h-j, fluorescence minus one (FMO) control was used to define gates. n=7 mice per group. Data for b and c represent mean ± SEM and were analyzed using a mixed effects model with Tukey’s multiple comparisons post hoc test. Data for e-j represent mean ± SEM and were analyzed by the Mann-Whitney U (one-tail) test. *P < 0.05, **P < 0.01, ***P < 0.001, ****P < 0.0001; ns, not significant.