BALB/c wild-type mice (8-week old females) were used as the subjects of all vaccine trials and as the source of all in vitro culture of primary cells. Experiments were approved by the Institutional Animal Care and Use Committee at Cornell University (Ithaca, NY), protocol number 2009-0096. For the macrophage knockout studies, MyD88, or TLR4, deficient macrophage cell lines (BEI resources) were cultured in Dulbeco’s modified essential medium supplemented with 10% (v/v) low endotoxin fetal bovine serum, 2 mM L-glutamine, 1 mM sodium pyruvate, 10 mM HEPES (complete DMEM) and 10 ug/ml ciprofloxacin [22]. Cells were stimulated with OMVs, or 100 ng/ml purified LPS as a control. For the TLR reconstitution assay, human embryonic kidney cells (HEK293) from the Leifer laboratory were cultured in complete DMEM supplemented with 50 U/ml penicillin and 50 ug/ml streptomycin. Cells were co-transfected in 96 well plates using TransIT (Muris) with the indicated TLRs, 5x-NF-kB-luciferase, and control vector to equal 200 ng/well total DNA. Cells were treated with OMVs, or PAM3CSK4 (TLR2), poly(I:C) (TLR3), LPS (TLR4), flagellin (TLR5), CpG DNA (TLR9), or profilin (TLR11). Cell lysates (5x Lysis buffer, Promega) were assayed for luciferase activity using the luciferase substrate as previously described [23].

nlpI and lpxM mutations were generated using P1 transduction of the nlpI::kan and lpxM::kan alleles, creating strains JH1 (ΔnlpI) and JH1-LpxM (ΔnlpIΔlpxM), from the Keio collection [24]. Briefly, E. coli Nissle 1917 bacteria were grown overnight and incubated with P1 lysates from appropriate Keio single mutants, as described elsewhere [25]. Transduction was performed using 50 mM CaCl₂ for 20 min at 37°C and 1 M Na-citrate for 40 min at room temp, and selective plating was done using medium containing 20 mM sodium citrate.

OMVs were grown and purified in accordance with previously established procedure [26]. Briefly, plasmid pBAD-ClyA-GFP, containing an arabinose promoter, was transformed via heat shock into chemically competent preparations of E. coli vesicle-overproducing strains JC8031 (EcJ) [27], JH1, and JH1-LpxM, and selected in LB-chloramphenicol or LB-kanamycin medium, respectively. Flasks containing 250 mL of medium were inoculated with overnight culture and allowed to grow at 37°C and 230 rpm until the OD₆₀₀ reached ∼0.5. Protein expression was induced at this point by addition of L-arabinose to a final concentration of 0.2%. Cell-free culture supernatants were collected 12 hours after induction (following centrifugation at 5000 g for 15 min) and then filtered through a 0.45 µm filter. Vesicles were isolated from all other soluble components by fractionation via ultracentrifugation (Beckman-Coulter; Ti SW28 rotor, 26000×g, 3 h, 4°C), resuspended in PBS, then stored at −20°C.

Visual characterization was conducted using a LEO 1550 FESEM, a FEI Tecnai F20 TEM, and an Olympus BX41 for SEM, TEM, and fluorescent microscopy, respectively. Additional quantitative fluorescence analysis [28] was conducted on a Gemini EM microplate spectrofluorometer (Molecular Devices). Dynamic light scattering measurements were conducted using a Nanosizer Nano ZS (Malvern Instruments), using the refractive index and viscosity of water (1.333 and 0.90 cP). Further protein characterization was conducted using the bicinchoninic-acid assay (BCA Protein Assay; Pierce) and anti-GFP Western blot (antibodies from Invitrogen and Jackson Immunoresearch), with control proteins grown in DH5 bacterial culture as described previously [29]. LPS content was analyzed using a KDO colorimetric assay [30]–[31] and proteomics were conducted using the isobaric tag for relative and absolute quantitation, or iTRAQ, method. Glysosylation analysis was performed using chromatography-facilitated mass spectrometry.

Ten groups (n = 10, each group) of 8-week old BALB/c mice (Charles River Laboratories) each were immunized s.c. with PBS (100 µL)containing purified protein or OMV preparations as described. The ten treatment groups were immunized with, respectively: PBS, 2.5 µg GFP, 2.5 µg ClyA, 2.5 µg GFP and ClyA mixture, 2.5 µg ClyA-GFP fusion, 2.5 µg alum and ClyA-GFP mixture (Alyhydrogel, 1.3% aluminum hydroxide [m/w]), and recombinant fluorescent equivalents of EcJ OMVs + ClyA-GFP, EcJ OMVs (with no recombinant antigen, or “empty”), EcN OMVs + ClyA-GFP, and EcN OMVs (empty). Two doses of vaccine (priming dose and boosting dose) were administered 4 weeks apart. Blood was collected from the mandibular sinus immediately before and 2 weeks after the first immunization, immediately before the boosting dose, and at 2 and 4 weeks after the boosting dose. Terminal splenectomies were performed on half (n = 5) of all ten groups immediately before administration of the boosting dose and on the other half (n = 5) following the final blood collection.

For bone marrow-derived macrophages and dendritic cells (DCs), bone marrow was obtained from mouse femurs and grown for 6 to 8 days in RPMI 1640 in the presence of 10% L929 conditioned medium [32] and collected 7 days later by scraping. Bone marrow-derived DCs were cultured in the presence of GM-CSF (20 ng/ml) and collected 6–8 days after culture [33]. For the splenic T-cells and B-cells, spleens were harvested, mechanically homogenized, and filtered through a 100 µm cell strainer (Falcon). Erythrocytes were lysed with cold ACK lysing buffer (Cellgro) for 5 min, and the cell suspension was washed with complete medium. T cells were purified with negative selection enrichment columns (R&D Systems) following the manufacturer’s recommendations. B cells were enriched by negative selection using magnetic isolation kits, as per manufacturer’s instructions (Miltenyi Biotec). This process resulted in cell purities of >97% as determined by flow cytometry.

Polystyrene microtiter 96-well plates (Maxisorp; Nunc Nalgene) were coated with GFP (5 µg/ml in carbonate buffer, pH 9.6) and incubated overnight at 4°C. Plates were blocked with 3% BSA in PBS containing 0.05% Tween-20 (PBST). Samples were serially diluted 2-fold in blocking buffer in a range of 1∶200–1∶3,276,800, added to the wells, and incubated for 2 hours at 37°C. Plates were washed six times with PBST, and biotinilated goat anti-mouse IgG, IgM (Sigma), or monoclonal IgG1 or IgG2 (BD Pharmingen) were added to the wells (1 µg/ml) for 1 hour at 37°C. Avidin-HRP (1∶1000; Sigma) was then added and incubation continued for 30 min at 37°C. After six additional washes with PBST, 3,3′,5,5′ tetramethylbenzidine substrate (1-Step TMB; Pierce) was added, and the enzyme reaction proceeded for 20 min. The reaction was stopped with 2 M H₂SO₄. The absorbance was quantified in a microplate spectrophotometer at a wavelength of 450 nm. Serum antibody titers were determined by measuring the last dilution that resulted in three standard deviations above background.

Cultured T-cells were trypsinized, centrifuged at 1000 rpm, and diluted to 1×10⁶ cells/mL in complete RPMI, then labeled with CFSE (Invitrogen). Cells (2×10⁵) were seeded into 96-well plates, incubated with GFP (30 µL, 100 µg/mL), and allowed to proliferate at 37°C for 4 days. FACS was used to assess loss of CFSE in proliferating cells.

Four groups (n = 4, all groups) of 8-week old BALB/c mice (Charles River Laboratories) each were injected s.d. in each ear with 10% of the vaccine dosage described previously for PBS, EcJ OMVs, EcN OMVs, and EcN-LpxM OMVs. Mice were euthanized 30 hours after injection, and their ears were resected and immediately fixed in 10% formalin. Tissue samples were processed routinely for histopathology and stained with H&E for light microscopy evaluation. Slides were read and graded in a blinded fashion by a licensed pathologist. For gross pathology, a 0–3 system was used: 0, no observable reaction; 1, slight redness only visible by parting fur, no touch sensitivity; 2, redness and swelling with touch sensitivity; 3, extreme inflammation leading to skin cracking/oozing, hair loss, and necrosis. For histological pathology scoring, a 1–5 system was used: 1, no observable change; 2, minor leukocyte recruitment; 3, leukocyte recruitment, apparent vasculature swelling and edema; 4, major leukocyte recruitment, vasculature swelling and edema, loss of structural order in tissue; 5, tissue remodeling and potential necrosis, vasculature rupture and extreme edema, plentiful neutrophils.

For the determination of cytokine secretion, appropriate cells were resuspended at a concentration of 2×10⁶ cells/well in medium RPMI 1640 (supplemented with FCS and antibiotics), seeded into 96-well plates and incubated for 48 h with GFP (5 µg). Cytokine levels of IFN-γ, IL-4, and IL-10 were measured in the supernatants as described above by using standard ELISA kits (eBioscience). For splenic cell analysis, T-cells from pre-boost (t = 4 wks) and post-boost (t = 8 wks) mice were both assessed, but no groups from pre-boost mice showed significant (p<0.05) stimulation; as such, only data from the post-boost mice is discussed below.

Cytokine expression analysis was conducted on primary mouse lymphocytes and macrophages. For splenic lymphocytes, cells were stimulated overnight with GFP (5 µg/ml), IL-2 (5 ng/ml) and anti-CD28 (10 µg/ml), and then cultured with brefeldin A. Cells were stained with fluorescent antibodies against the surface markers CD3 (clone 17A2) and CD4 (clone RM4–5), permeabilized, fixed and incubated with antibodies against the cytokines IFN-γ (clone XMG1.2) or IL-10. All incubations were carried out on ice for 30 min. All antibodies were purchased from BD Bioscience or eBioscience. For each sample, at least 50,000 cells were analyzed. The data were collected and analyzed using CELLQuest or FlowJo software and a FACScalibur flow cytometer (Becton Dickinson, San Jose, CA). For macrophages, cells were plated as above and also incubated with increasing concentrations of OMVs. Sixteen hours later, brefeldin A (10 µg/ml) was added and cells were incubated for 6 additional hours. Macrophages were then collected to be stained and analyzed by flow cytometry. Prior to staining, cells were incubated with an anti-Fcγ III/II receptor antibody (BD Biosciences) and 10% normal mouse serum (NMS) in PBS containing BSA (0.1%) and NaN₃ (0.01%). Cells were stained with antibodies against the surface marker CD11c (clone 223H7), fixed in 2% paraformaldehyde, permeabilized with saponin and then incubated with fluorescent antibodies against the cytokines IL-12 (clone C17.8), IL-10 (clone JES5–16E3) or IL-4 (clone 11B11). Incubations were carried out for 30 min on ice. All antibodies were purchased from BD Biosciences or eBioscience. Data was collected and analyzed as described above.

Bone marrow-derived macrophages were plated in 6-well plates (10⁶ cells/well) for 16 hours and incubated with increasing concentrations of ClyA-GFP(+) EcN or EcJ OMVs. Two hours after the addition of the OMVs, plates were washed vigorously; cells were collected and analyzed by flow cytometry to detect internalized GFP. The data were collected using a FACScalibur flow cytometer and analyzed in CELLQuest software (Becton Dickinson, San Jose, CA). For each sample, at least 30,000 cells were analyzed.

MyD88 or TLR4 deficient macrophages were cultured and stimulated as described above for 6 hours with OMVs or LPS, and media TNF was then measured by ELISA (Biolegend) according to the manufacturer. For the TLR reconstitution assay, single-TLR-expressing, NF-kB-luciferase(+) HEK293 cells were treated with OMVs or TLR agonist controls, with luciferase activity in lysates measured on a luminometer (Veritas).

BALB/c mice (n = 3) were injected s.c. between the scapulae with EcN OMVs (100 µg) and/or splenic DCs (1×10⁶ cells), stained with DiO and DiD respectively (Invitrogen), then euthanized after 4 days. After euthanasia, intact draining cervical lymph nodes were resected, placed in PBS, and immediately imaged via two-photon excited fluorescence microscopy on a custom setup. Imaging was conducted on a custom-designed microscope using a train of 830-nm, 90-MHz, 140-fs pulses from a Ti:sapphire laser oscillator (Chameleon; Coherent) for excitation. Laser scanning and data acquisition were controlled by ScanImage software [34]. For high-resolution imaging of labeled cells and particles respectively a 20X (numerical aperture: 1.0) water-immersion objective (Zeiss; W Plan-APO Chromat). Second harmonic generation from the extracellular matrix in lymph node was detected using a 417-nm centered wavelength filter. Fluorescence was detected using emission filters with 510-nm and 641-nm center wavelength with 65-nm bandwidth to image. Images shown are 20 µm stacks that were compiled using a maximum projection and a median filter was applied using Image J software (http://imagej.nih.gov/ij/).

T-cell activation by stimulated DCs was assayed as described previously [35]–[36]. Briefly, 96-well plates were incubated overnight with anti-mouse CD3 (10 µg/mL, clone 145–2C11; BD Biosciences) at 4 C, after which plates were washed 3 times with complete RPMI. T cells were then labeled with CFSE as described and seeded into wells at 2×10⁵ cell/well. T-cells were co-incubated with DCs (4×10⁴ cell/well), anti-mouse CD28 (5 µg/mL, clone 37.51, Biolegend), and a range (1 to 100 µg/mL) EcJ or EcN OMVs. Samples prepared for flow cytometry analysis were incubated for 48 h at 37°C, then incubated for an additional 4–6 h with 25 ng/mL PMA, 1 µg/mL ionomycin, and 10 µg/mL brefeldin A. Samples prepared for proliferation analysis were incubated at 37 C for 7 days, then trypsinized and analyzed by flow cytometry for loss of CFSE staining.

Statistical significance was determined by unpaired two-tailed Student’s t-test or by ANOVA grouped test with supplemental Tukey’s HSD tests when appropriate. Significance was determined to be at a confidence interval of P<0.05. Proteomic data was cross-referenced between three E. coli proteome libraries to determine identifications at P<0.001.

Previously, we reported the successful expression and functional folding of a variety of recombinant antigens on the surface of K12 E. coli OMVs by inducing expression of a chimera consisting of the antigen fused to the C-terminus of enterobacterial cytotoxin ClyA [37]. For the present study, green fluorescent protein (GFP) was selected as the primary model antigen for two reasons. First, GFP’s natural fluorescence allowed simple quantitation of antigen content in all vaccine preparations, owing to the ClyA-antigen chimera’s capacity to retain proper antigen folding upon outer membrane insertion [29]. GFP’s second advantage was its poor immunogenicity in mice, which allowed for maximal demonstration of the vaccine carrier’s immunostimulatory potential. OMV overproduction was induced in EcN via genetic knockout of nlpI [37]–[38] to produce the antigen delivery platform (Fig. 1a). OMVs released by the hypervesiculating EcN mutants expressing ClyA-GFP exhibited uniform size and shape while retaining characteristic bilipid membrane structure (Fig. 1b) and carried fluorescent membrane-bound GFP (Fig. 1c). To demonstrate the effect of probiotic strain-selection on the immune response, similar GFP-containing OMVs (Fig. S2a–b in File S1) were produced as a control using the non-probiotic K12 E. coli strain JC8031 (abbreviated EcJ) [29], [37]. Western blot analysis confirmed comparable ClyA-GFP content in both OMV preparations (Fig. 1d), allowing for meaningful comparisons between the two strains’ abilities to trigger an immune response against the model antigen. To begin to better understand the molecular basis for the observed immune responses, we additionally investigated LPS, proteomic, and glycosyl differences between the EcJ and EcN OMV TLR-agonist composition. EcN and EcJ OMVs contained similar amounts of membrane-bound LPS (Fig. 1e), a known key contributor in OMV-induced immune responses [12]. In stark contrast, several major PAMP-rich peptide TLR agonists were substantially enriched in EcN OMVs, particularly the potent TLR5 agonist flagellin. Glycosyl analysis of sugar composition (Fig. 1f) revealed substantial enrichment of mannose in the EcN OMVs, an agonist of the mannose-binding lectin pathway. These compositional differences may form the molecular basis of the unique T_H1-biased immune response imparted by EcN OMVs that is described in the following section.

To test the ability of EcN OMVs to generate a strong adaptive response to GFP, we immunized BALB/c mice via subcutaneous injection with formulations of OMVs containing ClyA-GFP and free of additional adjuvant (Fig. 2a). To ensure the presence of a substantially competitive positive control, we separately injected vesicle-free ClyA-GFP adsorbed onto the aluminum hydroxide (alum) adjuvant delivery system, Alhydrogel. IgG titers assayed four weeks after the final boost indicated induction of a strong humoral response by both EcN and EcJ OMVs comparable to the gold standard of alum (Fig. 2b), consistent with previous work [29] and reflective of progressive generation of a robust response. However, IgM titers showed some divergence in the humoral responses (Fig. 2c), with lower IgM levels generated by EcN OMVs indicating either early class-switching or a discrepancy in B-leukocyte stimulation by membranous endotoxins. Further divergence could be seen in IgG1 versus IgG2a titers (Fig. 2d). The EcN OMVs elicited an IgG2a-dominant humoral response, which taken together with the relative decrease in final IgM titer suggests induction of a T_H1-facilitated immune response consistent with heightened cellular immunity stimulation [39]. In contrast, EcJ OMVs mirrored the alum-positive control with a larger IgG1 fraction, suggesting a response more in line with standard adjuvants. As a result, these data not only indicate that the EcN OMVs can function as an effective antigen carrier for stimulating humoral immunity, but additionally suggest a strain-dependent advantage conferred by EcN in stimulating a traditionally elusive T_H1 response.

Further analysis of the mice’s OMV-induced adaptive immunity revealed a favorable T-cell response reflective of the EcN OMVs’ unique humoral response. Specifically, spleen-derived T-cells from post-boost mice vaccinated with ClyA-GFP EcN OMVs had proliferation responses to antigen restimulation comparable to the alum-positive ClyA-GFP control and significantly greater than that triggered by EcJ OMVs (Fig. 2e). This result is generally indicative of a significant immunostimulatory effect on naïve T-cell populations, and is in direct agreement with the driving hypothesis that the EcN membrane may be privileged as an adjuvant material in its ability to actively target T cells. Moreover, EcN but not EcJ OMVs promoted a similarly dramatic increase in antigen-restimulated T-cell IFN-γ secretion (Fig. 2f) and expression levels (Fig. 2g). Taken together, these results highlight the ability of EcN OMVs to induce a strong cellular immune response, which correlates well with the T_H1 response suggested by the IgG2a:IgG1 ratio. Depressed IL-4 levels (Fig. 2h) relative to IFN-γ further support the induction of a favorable T_H1-biased response by EcN OMVs. This level of T_H1-indicative IFN- γ/IL-4 discrepancy has rarely been reported in the literature for adjuvant-free subunuit vaccine carriers, making it of particular interest in this study. Importantly, this also sets the EcN OMV carrier apart from standard adjuvants such as alum, which produce a mixed T_H1/T_H2 (T_H2 dominant) response that is often insufficient at leveraging the advantage of T_H1 immunity against certain intracellular pathogens. Also of note was the observation that IL-10 secretory activity from EcN OMV restimulation was elevated relative to EcJ OMVs and the alum-positive control (Fig. 2i), despite the overall T-cell population participating in IL-10 secretion not being as dramatically elevated. Considering the successful induction of elevated T-cell IFN-γ levels, this suggests a unique (though possibly minor) use of IL-10 in a supplementary and indirectly beneficial role in generating a favorable and non-detrimental T-cell response [40], though further study is required to determine if this might have a practical role in modulating either adaptive immunity or associated inflammatory responses (discussed below). Taken together, the antigen-specific humoral and cellular immunity induced by the EcN OMV carriers are indicative both of a protective vaccine response [41] and, more importantly, a response tuned toward potential use against pathogens that are most effectively neutralized by the more elusive T_H1-biased response [42].

A key determining factor in adaptive immune response generation by a vaccine is the extent to which innate immunity is engaged [2]. While on a macroscopic level OMV vaccine inflammation was observed to be similar to that of the alum control in duration and recovery time (Fig. 3a), such observations are not necessarily reflective of an adjuvant’s capacity for local immune cell engagement and recruitment. Hence, we further explored the capacity of EcN OMVs to robustly induce an innate response. Using a subdermal ear injection model in BALB/c mice, and subsequent histological analysis, we assessed the acute inflammatory response generated by both EcN and EcJ OMVs. The resulting inflammopathology revealed surprisingly marked differences. At 30 h post-injection, EcN OMVs dramatically remodeled the dermal tissue, caused local vasculature swelling, and recruited dense populations of leukocytes (Fig. 3d) relative to a blank PBS control (Fig. 3b). Such a reaction is an established sign of an adjuvanting material capable of stimulating the required innate immunity activation for a good vaccine response [2], [43]. EcJ OMVs, on the other hand, stimulated a much less dramatic inflammatory response with an equivalent OMV dosage (Fig. 3c). Taken together, these data imply that the probiotic strain-dependent nature of EcN OMVs’ unique immune response is in part dependent on a strong stimulation of innate immunity.

Importantly, the different innate immune stimulation from the EcN and EcJ strains resulted from equivalent doses of OMV-bound LPS, generally considered to be the most important innate bacterial immunomodulator [12]. This result implies that the immunostimulatory mechanism for the EcN OMVs is not fully dependent on the LPS. Therefore, we next investigated whether or not direct reduction of LPS-induced endotoxicity would substantially attenuate the enhanced innate response observed with EcN OMVs. A genetic knockout of the lpxM gene in E. coli inactivates the msbB lipid A acyltransferase and is known to minimize LPS-based endotoxicity [44]; therefore, lpxM was knocked out in the EcN nlpl mutant to generate mutant EcN OMVs (Fig. S2c–d in File S1) and allow investigation of the influence of LPS on the activation of the innate response. Following identical subdermal mouse ear injections, the previously observed inflammopathology was partially attenuated but ultimately still reflective of an appreciable inflammatory response (Fig. 3e), both on the tissue (Fig. 3f) and cellular (Fig. 3g) levels. Follow-up studies of vaccine efficacy in BALB/c mice under identical conditions as those described above additionally demonstrated that the lpxM mutation did not eliminate the ability of EcN OMVs to stimulate strong anti-GFP humoral immunity (Fig. S3 in File S1). As a result, it would appear that a non-endotoxicity-dependent, strain-dependent advantage in innate immunity stimulation is conferred by using EcN as an OMV source, possibly due to the presence of other highly active immunostimulatory membranous PAMPs [45] and TLR agonists, as suggested by the proteomic analysis discussed above.

Analysis of EcN OMV macrophage stimulation, an important cellular component of innate immunity, provided additional support for an enhanced mechanism of innate immunity stimulation provided by the EcN source. When bone marrow-derived mouse macrophages (BMMs) from wild-type BALB/c mice were incubated with equivalent amounts of ClyA-GFP-containing EcN and EcJ OMVs, they internalized a significantly greater number of the former at a variety of OMV concentrations (Fig. 3h). These results suggest that the EcN outer membrane is a more potent activator of macrophage phagocytosis. Further analysis of BMM cytokine expression profiles following OMV incubation additionally revealed a significant discrepancy in IL-12 and IL-4 expression induced by EcN and EcJ OMVs (Fig. 3i). Specifically, EcN OMVs stimulated elevated IL-12 but not IL-4 expression relative to EcJ OMVs, indicating a propensity for EcN OMVs to facilitate T_H1 dominance during the adaptive immunity transition. In addition, the elevated IL-10 levels likely indicate a more potent general stimulation of phagocytic activity on the part of the EcN OMVs [46]. This may highlight a synergistic coupling of enhanced targeting via superior PAMP-dependent TLR crosslinking and subsequent intracellular delivery of membranous and soluble bacterial factors [12]. The opposite expression levels induced by EcJ OMVs in turn suggests facilitation of a mechanism more in line with T_H2 bias [47], though without additional studies this facet of the response is primarily useful as in highlighting a general discrepancy in immunity bias as being crucial to the mechanistic benefits conferred by using the EcN OMVs.

Past studies of wild-type EcN bacteria suggest that its immunomodulatory capacity is derived from TLR-dependent stimulation of antigen-presenting cells and T-cells that makes use of a variety of enriched TLR agonists [48]. Building on the above findings concerning innate immunity stimulation, macrophages were selected to determine a potential connection between TLR pathway stimulation and enhanced EcN OMV adjuvancy. First, we confirmed the presence of both TLR4-dependent and TLR4-independent stimulation in the EcN OMVs’ adjuvancy using MyD88 and TLR4 macrophage knockouts (Fig. 3j). Further testing with cell lines genetically restricted to single-TLR expression was then used to characterize the implied broadened stimulation spectrum unique to the EcN OMVs (Fig. 3k). Uniquely strong stimulation of TLR2, TLR3, TLR4, TLR5, TLR9, and TLR11 were all seen with observed via the EcN OMVs. TLR2/4 stimulation is consistent with E. coli bacterial membranes, while TLR5 and TLR9 stimulation (likely via enriched EcN membrane components such as flagellin) were also expected due to previous evidence of retained EcN-derived immunostimulation [17], [19], [20]. The TLR3 expression is more challenging to immediately understand without further study, and could have resulted either from intracellular delivery of some unknown bacterial factor or possibly cross-activation via residual TLR5 pathway expression. Regardless, these two experiments together revealed that TLR2/4-dependent, TLR5-dependent, and non-TLR2/4/5 MyD88-dependent mechanisms had all been harnessed by EcN OMVs. These results correlate well with past in vitro mechanistic studies on intact EcN bacteria [19], [20], [48], and support the premise that the EcN OMVs’ T_H1-biasing capacity is derived from the acellular isolation of EcN’s unique probiotic immunity.

An important link between a heightened inflammatory response and the development of a strong adaptive T-cell response are antigen-loaded dendritic cells (DCs) that migrate from the site of inflammation to local lymph nodes [9]. Two-photon microscopy of extracted lymph nodes was used to confirm that OMVs drained into lymph nodes following subcutaneous injection, where they spatially overlapped with adoptively transferred dendritic cells (DCs) (Fig. 4a–c). These results confirm that the OMV carriers and their delivered antigens are available to lymphoid-localized DCs, T-cells, and B-cells [49]. Subsequent in vitro stimulation of separately purified murine splenic DCs revealed that while both EcN and EcJ OMVs substantially upregulated CD86, EcN OMVs had a greater capacity to additionally upregulate CD80 as well (Fig. 4d). This is promising, as CD80 has been implicated in modulating regulatory immunity in addition to traditional stimulatory cellular immunity [50].

Similar studies using murine DC and naïve splenic T-cell coculture (Fig. 4e) demonstrated stronger DC-facilitated T-cell stimulation by EcN OMVs as well. Specifically, the pronounced increase in naïve T-cell activation by BMDCs primed with a variety of EcN OMV concentrations relative to those primed with EcJ OMVs suggests that the selection of EcN as the OMV source improved the ability of the OMVs to effectively interface with and stimulate APCs. Additionally, the ability of the EcJ OMV control to also stimulate T-cells through BMDC-dependent activation, albeit to a lesser extent than EcN OMVs, helps rule out the possibility that they caused a DC-dependent T-cell suppression [17], which would have made conclusions concerning a strain-dependent T_H1/T_H2-bias discrepancy difficult.

Taken together, the enhanced stimulation of both macrophages and DCs by EcN OMVs builds a strong case for a PAMP-dependent mechanism for enhanced activation of professional APCs as a crucial component of the robust induction of adaptive immunity to a recombinant antigen. These data led us to consider that the EcN OMVs’ immunomodulatory capability might take advantage of similarly improved interactions with the third major APC, namely B-cells. Accordingly, we measured induced proliferation of splenic mouse B-cells via incubation with EcN and EcJ OMVs. This analysis revealed that EcN OMVs possessed significant potential for type 1 T-cell independent B-cell activation due to their ability to stimulate B-cell proliferation in the absence of T-cell helper factors at a variety of OMV concentrations (Fig. 4f). Such activation is not uncommon in pathogen infection [51], and likely resulted from a combination of the presence of EcN PAMPs and OMV nanoscale avidity enhancement [5], [52], possibly facilitated by the elevated TLR9 stimulation noted previously. Interestingly, this phenomenon was in strong contrast to the EcJ OMV control’s ability to activate B-cells, which was entirely dependent on the addition of T-cell helper factors IL-4 and anti-CD40. Such a strong discrepancy further highlights the important benefit EcN provides to E. coli OMV antigen carriers, potentially providing robust humoral immunity through a supplemental T-cell independent mechanism that can work in parallel to, and perhaps even uniquely enhance, the establishment of a T_H1-biased adaptive response.