Establishment of fetomaternal tolerance through glycan-mediated B cell suppression

Abstract

Discrimination of self from non-self is fundamental to a wide range of immunological processes¹. During pregnancy, the mother does not recognize the placenta as immunologically foreign because antigens expressed by trophoblasts, the placental cells that interface with the maternal immune system, do not activate maternal T cells². Currently, these activation defects are thought to reflect suppression by regulatory T cells³. By contrast, mechanisms of B cell tolerance to trophoblast antigens have not been identified. Here we provide evidence that glycan-mediated B cell suppression has a key role in establishing fetomaternal tolerance in mice. B cells specific for a model trophoblast antigen are strongly suppressed through CD22-LYN inhibitory signalling, which in turn implicates the sialylated glycans of the antigen as key suppressive determinants. Moreover, B cells mediate the MHC-class-II-restricted presentation of antigens to CD4⁺ T cells, which leads to T cell suppression, and trophoblast-derived sialoglycoproteins are released into the maternal circulation during pregnancy in mice and humans. How protein glycosylation promotes non-immunogenic placental self-recognition may have relevance to immune-mediated pregnancy complications and to tumour immune evasion. We also anticipate that our findings will bolster efforts to harness glycan biology to control antigen-specific immune responses in autoimmune disease.

Extended Data Fig. 1 |. Experimental scheme.

To create an experimental model in which transmembrane OVA (mOVA) is expressed as a surrogate trophoblast antigen, we mated non-transgenic female mice (all C57BL/6-background) to C57BL/6 male mice hemizygous for the Act-mOVA (CAG-OVAL) transgene (right). This creates a pregnancy in which, on average, 50% of the concepti will bear the transgene. Due to the promoter/enhancer sequences of the transgene, these transgenic concepti (red) will ubiquitously express mOVA, but there is particularly high expression levels by placental trophoblasts that have invaded into uterine blood vessels and are thus directly exposed to the maternal circulation. Moreover, the topology of the mOVA constructs directs OVA expression to the external surface of the cell. Thus, the OVA protein itself is bathed in maternal blood. Although the mechanism remains elusive, previous work has established that mOVA is shed into the maternal circulation starting at about E10.5, and genetic experiments have established that its presentation to maternal CD4⁺ and CD8⁺ T cells is mediated exclusively by maternal APCs. As a negative control, females are mated to non-transgenic C57BL/6 males (left). At mid-gestation, the pregnant mice are injected with OVA-specific OT-I and/or OT-II TCR transgenic T cells, with or without adjuvants or c-OVA.

Extended Data Fig. 2 |. xmOVA pregnant mice show a mild, OVA-dependent expansion of OVA-specific Tregs, but Treg depletion does not alter their suppressed CD4⁺ T cell response to t-mOVA.

Treg depletion was accomplished through use of the Foxp3^DTR system, in which the gene for the diphtheria toxin receptor (DTR) is knocked into the X-linked Foxp3 locus, thus rendering Tregs sensitive to diphtheria toxin- (DT-) induced ablation. Since complete Treg ablation starting at mid-gestation is known to cause near-total pregnancy failure, our experiments employed Foxp3^DTR/WT female mice in which, due to random X-inactivation, ~50% of CD4⁺ T cells express a wild-type Foxp3 allele and the other ~50% express the DTR knock-in allele. DT administration thus causes a ~50% acute reduction in Treg frequencies. While this reduction is transient, it is still sufficient to induce a significant degree of fetal loss in allogeneic mating combinations. By contrast, partial Treg ablation in the syngeneic mating combinations employed here (C57BL/6 × C57BL/6, aside from the mOVA transgene) did not induce fetal loss. To prevent the transferred OT-II cells themselves from generating an OVA-specific Treg population, we also employed OT-II Foxp3^DTR/Y males as cell donors. All FOXP3⁺ OT-II cells from these mice are ablatable since they all express the Foxp3^DTR allele. a, Frequency of FOXP3⁺ Treg OT-II cells among total splenic OT-II cells 6 days after adoptive transfer into virgin mice or mid-gestational (E12.5–15.5) WT or Foxp3^DTR/WT mice mated as indicated. The Foxp3^DTR/WT mice received OT-II Foxp3^DTR/Y cells, and were injected daily with DT starting at E10.5, in line with previously work. Note that virtually none of the transferred cells in this latter group converted into Tregs. Adjusted P-values were determined by ordinary one-way ANOVA with Šídák’s multiple comparisons test applied to the four comparisons shown. ns, not significant. Data were accumulated from 5 individual experiments and all mice are shown. b, Confirmation of partial, DT-induced depletion of host FOXP3⁺ CD4⁺ cells in Foxp3^DTR/WT female mice. The frequency of FOXP3⁺ cells among total CD4⁺ lymphocytes in the spleens of virgin Foxp3^DTR/WT female mice was measured 24 h after DT administration. P-value was determined by two-tailed, unpaired t-test. Data are from 1 experiment and all mice are shown. c-f, Proliferation index (c), fold expansion (d), activation marker expression (e), and IFN-γ production (f) of CFSE-labeled Foxp3^DTR/Y OT-II cells 6 days after adoptive transfer on E12.5–15.5 into Foxp3^DTR/WT mice mated as indicated. The mice were injected daily with DT starting on E10.5, thus partially depleting endogenous Tregs and completely ablating all OT-II cells that have converted into Tregs, as described above. Some groups received i.v. adjuvants (poly(I:C)+anti-CD40 antibodies) ± c-OVA at the time of OT-II transfer. Adjusted P-values were determined by ordinary one-way ANOVA with Šídák’s multiple comparisons test. Each group was compared to the xB6 control group, and the xB6+c-OVA/Adj group was compared to the xmOVA+c-OVA/Adj group. Bars show mean±s.d. Data are from 4 independent experiments and all mice are shown.

Extended Data Fig. 3 |. B cells present t-mOVA to maternal CD4⁺ T cells; t-mOVA presentation to CD8⁺ T cells is primarily mediated by dendritic cells.

a, Representative flow cytometry (n>4/group) for MHCII expression on splenic CD19⁺ B cells, CD11b⁺ cells, and CD11c⁺ cells in WT or H2-Ab^fl/flCd19-cre mice, demonstrating that H2-Ab^fl/flCd19-cre mice show loss of MHCII expression specifically on B cells. b, c, Proliferation index of CFSE-labeled OT-II (b) and OT-I (c) cells, measured 50 h after late-gestational transfer into xmOVA mated pregnant mice of the indicated genotypes. Adjusted P-values were determined by ordinary one-way ANOVA with Šídák’s multiple comparisons test. Each group was compared to the WT group. Bars show mean±s.d. Data were accumulated over 21 individual experiments and all mice are shown. d, e, Maternal CD4⁺ and CD8⁺ T cell recognition of t-mOVA does not require macrophages; serum does not restore CD4⁺ T cell recognition in B cell deficient mice. Proliferation index of CFSE-labeled OT-II (d) and OT-I (e) cells, measured 50 h after late-gestational transfer into xmOVA pregnant mice of the indicated genotypes. CD169-DTR mice received a single depleting dose of DT 48 h prior to cell transfer. Some WT mice received Clodronate Liposomes 24 h prior to cell transfer (WT + Clod Lip), and some μMT mice received 300 μl serum from late-gestational xmOVA-mated pregnant females administered in two separate doses (150 μl each) at 18 and 6 h prior to cell transfer (μMT + serum). Data for untreated WT and μMT mice are the same as in panels b and c. Adjusted P-values were determined by ordinary one-way ANOVA with Šídák’s multiple comparisons test. Each group was compared to the WT group. Bars show mean±s.d. All mice are shown. WT + Clod Lip mice, CD169-DTR mice, and μMT + serum mice data were accumulated from 2, 5, and 1 independent experiment(s), respectively. f, H2-Ab^fl/flCd19-cre mice retain the ability to present c-OVA to OT-II cells. Proliferation index of OT-II cells at 50 h after adoptive transfer into xB6-mated WT or H2-Ab^fl/flCd19-cre mice on E12.5–16.5. The mice were injected i.v. with c-OVA at the time of transfer. P-values were determined by two-tailed, unpaired t-test. Bars show mean±s.d. Data were accumulated from 3 independent experiments and all mice are shown.

Extended Data Fig. 4 |. Identification of endogenous OVA-specific B cells using fluorescently-conjugated OVA-tetramers.

a, Representative flow plots showing the gating scheme used to identify OVA-specific B cells. Spleen cell suspensions from a WT mouse were stained with OVA- and control (Ctrl)-tetramers followed by magnetic bead enrichment of tetramer⁺ cells (, see Methods). Briefly, SSC-H/W and FSC-H/W were used to exclude doublets, DAPI allowed for dead cell exclusion, and a dump channel consisting of Gr-1, CD11c, F4/80 and Thy1.2 was used to exclude non-B cells. Gating on the OVA-Tet⁺Ctrl-Tet^neg population identifies cells that bind to OVA and excludes those that recognize the non-OVA components of the tetramer reagent. b, Confirmation that OVA-Tet⁺Ctrl-Tet^neg B cells are OVA-specific. Whole spleen samples from WT mice were incubated in 300 μM of monomeric BSA or OVA beginning 20 min prior to tetramer staining (see Methods). Note the loss of the OVA-Tet⁺Ctrl-Tet^neg population in the preparation preincubated with monomeric OVA.

Extended Data Fig. 5 |. Antigen-specific B cell recognition of t-mOVA during pregnancy.

a, Total follicular (FO) splenic B cells from xB6 and xmOVA matings show a similar frequency of CD95^hiMHCII^hi cells at mid (E8.5–13.5) and late gestation (E14.5–18.5), demonstrating that the increased frequency of CD95^hiMHCII^hi cells among OVA-specific FO B cells in late gestation xmOVA mice (Fig. 2a, b) was antigen-driven. P-values were determined by two-tailed, unpaired t-test. Data were accumulated over 22 independent experiments and all mice are displayed. b–d, Phenotypic analysis of non-follicular splenic B cell subsets during mid- and late-gestation. Marginal zone (MZ) and CD93⁺ transitional splenic B cells were gated as DUMP^negCD19⁺IgM^hiCD21/35^hi and DUMP^negCD19⁺CD21/35^lo/negCD93⁺ cells, respectively, and then assessed for CD95 and MHCII expression. b, Representative flow plots (E17.5) are from n = 13 xB6 and n = 17 xmOVA late gestation pregnancies. c, d, Quantification of CD95/MHCII expression from xB6 and xmOVA pregnancies. For OVA-specific (OVA-Tet⁺) cells, there was variable but significant t-mOVA-driven CD95/MHCII upregulation at late gestation (E14.5–18.5) in CD93⁺ but not MZ B cells (left graphs). This upregulation was much less dramatic than that seen for follicular B cells (Fig. 2b). A similar frequency of CD95^hiMHCII^hi cells was seen for the total population of CD93⁺ and MZ B cells in xB6 and xmOVA pregnancies (right graphs). P-values were determined by two-tailed, unpaired t-test. Bars show mean±s.d. Data were accumulated over 22 independent experiments and all mice are displayed. e, f, OVA-specific (OVA-Tet⁺) B cells slightly expand in late gestation in xmOVA pregnancies. An increase in the absolute number (e) and frequency (f) of OVA-specific B cells becomes evident in late gestation (E14.5–18.5) only in xmOVA pregnancies. P-values were determined by two-tailed, unpaired t-test. Data were accumulated over 22 independent experiments and all mice are displayed. g, h, Antigen-specific B cell suppression by t-mOVA. Absolute number of total (g) or CD95⁺GL7⁺ GC phenotype (h) OVA-specific B cells 6 days after i.v. vaccination with 5×10⁴ OT-II cells ± c-OVA ± poly(I:C) (Adj) on E11.5 or E12.5. P_adj Adjusted P-values were determined by ordinary one-way ANOVA with Šídák’s multiple comparisons test. Each group was compared to the xB6 control group, and the xB6+c-OVA/Adj group was compared to the xmOVA+c-OVA/Adj group. Bars show mean±s.d. The dashed line (h) indicates the limit of detection. This analysis employed the same samples used for Fig. 2c, d. Data were accumulated over 26 independent experiments and all mice are displayed.

Extended Data Fig. 6 |. Although reduced in comparison to the response seen in virgin mice, c-OVA elicits similar levels of OT-II cell expansion and OT-II Tfh differentiation in xB6 and xmOVA pregnant mice, and does not induce OT-II Tfr differentiation.

a, Representative flow plots (n = 5/group) showing the frequency of Bcl-6^hiPD-1^hi and CXCR5^hiPD-1^hi OT-II cells among total OT-II cells five days after adoptive transfer into virgin mice or on E11.5–12.5 into WT pregnant mice mated as indicated. All groups received the vaccination protocol used in Fig. 2c, d that generated a strong OVA-specific B cell response in control pregnancies (i.v. adjuvant [poly(I:C)] + c-OVA) at the time of OT-II transfer. Analysis on day 5 post-transfer was chosen for this experiment as it was the peak of OT-II expansion. b, Quantification of results from (a) showing that both the absolute number of OT-II cells and those with Tfh phenotype are diminished in pregnant mice compared to virgins. Presumably, this reflects an antigen non-specific effect of pregnancy. Adjusted P-values were determined by ordinary one-way ANOVA with Šídák’s multiple comparisons test. Each group was compared to the virgin+c-OVA/Adj group, and the xB6+c-OVA/Adj group was compared to the xmOVA+c-OVA/Adj group. Bars show mean±s.d. Data were accumulated over 4 independent experiments and all mice are shown. c, Representative flow plots showing the frequency of FOXP3⁺ cells among Bcl-6^hiPD-1^hi Tfh phenotype OT-II cells for the three groups shown in (a, b).

Extended Data Fig. 7 |. Additional characteristics of t-mOVA and demonstration of sialic acid at trophoblast membranes in contact with maternal blood.

a, b, Shed t-mOVA is present within the non-pelletable, non-exosomal fraction of maternal plasma. Equal volumes of plasma from xB6- and xmOVA-mated mice (E18.5) were subjected to differential centrifugation (see Methods) followed by either anti-OVA immunoprecipitation and anti-OVA immunoblotting (a) or immunoblotting for the exosome-specific marker CD9 (b). We analyzed three different fractions: “clarified plasma” (i.e., the plasma after an initial low-speed (10,000×g) centrifugation), and the “sup” and “pellet” fractions from 110,000×g ultracentrifugation. Anti-OVA immunoblotting identified mOVA in both the clarified plasma and 110,000xg “sup” fractions, but not in the 110,000×g “pellet” fraction where exosomes reside, as demonstrated by the anti-CD9 immunoblotting. Data are representative of 3 (a) and 2 (b) separate experiments. c, Shed t-mOVA contains N-glycolylneuraminic acid (Neu5Gc), the sialic acid variant required for strong α(2,6)-Sia binding to mouse CD22. Equal volumes of plasma respectively pooled from 3 xB6-mated and xmOVA-mated mice (E16.5–18.5) were subjected to differential centrifugation, anti-OVA immunoprecipitation on the 110,000×g supernatant, sialidase or mock digestion as indicated, and then anti-Neu5Gc immunoblotting. c-OVA was similarly immunoprecipitated and sialidase/mock-treated, or loaded directly onto the gel. As expected, Neu5Gc is absent from c-OVA. The non-specific (n.s.) band is likely free IgG heavy chain. Data are representative of 2 separate experiments. For gel source data, see Supplementary Fig. 1. d–i, Distribution of α(2,6)-Sia and Neu5Gc in the mouse placental labyrinth. Placental sections prepared from mice on E12.5 were stained with SNA-I (d–f) or anti-Neu5Gc antibodies (g–i). For the SNA-I control (f), the adjacent section was pretreated with neuraminidase A; for the anti-Neu5Gc control (i), free Neu5Gc was added in with the primary antibody. Fetal and maternal blood spaces were respectively identified by the presence of DAPI⁺ (blue counterstain) nucleated or DAPI^neg enucleated RBCs, both of which are autofluorescent on the green channel. Note the SNA-I staining on trophoblast membranes in direct contact with maternal blood (arrowheads). This staining was not as continuous as the staining for Neu5Gc, which was present in all trophoblast membranes in contact with maternal blood. The small round structures showing strong Neu5Gc staining are morphologically consistent with platelets. Images are representative of 3 independent experiments.

Extended Data Fig. 8 |. CD22 and LYN mediate B cell suppression to t-mOVA.

a–d, Absolute number of total (a, c) and GL7⁺CD95⁺ GC phenotype (b, d) OVA-specific B cells in pregnant Cd22^−/− and Lyn^−/− mice 6 days after i.v. vaccination with 5×10⁴ OT-II cells ± c-OVA ± poly(I:C) (Adj) on E11.5 or E12.5. Adjusted P-values were determined by ordinary one-way ANOVA with Šídák’s multiple comparisons test. Each group was compared to the xB6 control group, and the xB6+c-OVA/Adj group was compared to the xmOVA+c-OVA/Adj group. Bars show mean±s.d. This analysis employed the same samples used for Fig. 3c, d. The Lyn^−/− and Cd22^−/− data were accumulated over 14 and 11 independent experiments, respectively, and all mice are displayed. See Extended Data Fig. 5g, h for corresponding WT data. Note that in Lyn^−/− but not WT nor Cd22^−/− mice, the number of GC phenotype OVA-specific B cells in xmOVA pregnancies approaches that seen in xB6 pregnancies following c-OVA/Adj immunization. The dashed line (b, d) indicates the limit of detection. e-i, Antigen-specific B cell suppression to t-mOVA in pregnant Fcgr2b^−/− mice. Representative flow plots (e), frequencies of total (f) or GL7⁺CD95⁺ GC phenotype (g) OVA-specific B cells, and absolute number of total (h) or GL7⁺CD95⁺ GC phenotype (i) OVA-specific B cells in pregnant WT or Fcgr2b^−/− mice 6 days after i.v. vaccination with 5×10⁴ OT-II cells ± c-OVA ± poly(I:C) (Adj) on E11.5 or E12.5. WT data are from Fig. 2c, d and Extended Data Fig. 5g, h and were accumulated over 26 independent experiments. Fcgr2b^−/− data were accumulated over 4 independent experiments. All mice are shown. The flow plots show OVA-tetramer⁺ B cells gated from a fixed number of total B cells across all groups. P-values were determined by two-tailed, unpaired t-test. Bars show mean±s.d.

Extended Data Fig. 9 |. Analysis of sialylated glycopeptides in pregnant mouse and human plasma.

a, Workflow. Plasma (n = 3/group) from non-pregnant or pregnant mice (E15.5–17.5) and humans (collected at delivery) was first run over species-specific Multiple Affinity Removal System (MARS) columns to remove high abundance proteins, whose presence would obscure the detection of other glycopeptides. In one analysis (top), the MARS-depleted plasma was analyzed by mass spectrometry to identify endogenous proteins of potential placental origin bearing N-linked glycans with terminal α(2,6)-Sia. Specifically, the depleted plasma was first subjected to trypsin digestion followed by SNA-I lectin chromatography to isolate α(2,6)-Sia containing glycopeptides. These peptides were then deglycosylated using PNGase F and then subjected to LC-MS/MS. Detected peptides representing true N-glycosites were identified as those bearing the consensus N-X-S/T/C motif with an asparagine → aspartic acid substitution, which occurs as a result of the PNGase F digestion. In addition (bottom), the depleted plasma was subjected to SNA-I and MAL-I lectin blotting, to reveal the overall pattern and prevalence of α(2,6)- and α(2,3)-linked sialylated glycoproteins, respectively. b, Identification of proteins unique to pregnant plasma that contain N-linked glycans with α(2,6)-Sia. Peptides with N-glycosites present in at least one pregnant specimen but absent from all three non-pregnant specimens were tallied. For mice, there were 30 such peptides, corresponding to 26 proteins, and for humans, there were 68 such peptides, corresponding to 53 proteins. For the mouse proteins, database queries (biogps.org) identified 7 (27% of total) of the encoding genes to be likely expressed primarily if not exclusively by the conceptus. These genes and corresponding representative peptide species are shown in the table (with the N-glycosites colored red), and include Lepr (encoding the Leptin receptor), a recently identified marker of sinusoidal trophoblast giant cells, Lifr (LIF receptor alpha subunit), which is expressed by a number of trophoblast subtypes, Ceacam11 and Ceacam12, which are expressed by spongiotrophoblasts, and Afp (α-fetoprotein), which is expressed by the yolk sac and fetal liver^,. The pregnant mice were from xmOVA matings but OVA sequences were not identified, suggesting that this mass spectrometry experiment identified only a subset of the shed proteins, perhaps only those with high abundance or with favorable ionization properties. For the human proteins, we found that 7 of the encoding genes were likely expressed primarily if not exclusively by the placenta. These included PSG1/2/7/5/9/11, i.e., members of the PSG gene family encoding Pregnancy Specific Glycoproteins, which are known to be the most abundant protein species released from the trophoblasts into maternal blood. Peptide assignments were redundant due to shared sequences. PSG1 has recently been shown to carry primarily α(2,3)-Sia with a small amount of α(2,6)-Sia. Both mouse and human pregnant plasma contained unique peptides derived from fibronectin (Fn1 and FN1). While fibronectin is abundant in non-pregnant plasma, fibronectin isolated from the human placenta is more heavily glycosylated, carrying polylactosamine chains. Of note, many of the sialoglycopeptides unique to pregnancy but not obviously derived from the conceptus appeared instead to be produced by the liver (not shown), suggesting that the endocrine state of pregnancy might systemically alter protein sialylation. Complete data is available at the ProteomeXchange under identifier PXD029966 (http://proteomecentral.proteomexchange.org). c–i, Lectin blotting. Volumes of MARS column eluates corresponding to equivalent volumes of starting plasma were subjected to SDS-PAGE followed by lectin blotting, Neu5Gc immunoblotting, and silver staining. Although sialylated glycoproteins were more abundant in pregnant plasma specimens, it is important to emphasize that these blotting experiments alone do not demonstrate that the corresponding proteins were derived from the placenta. Many were likely derived from the liver, in accord with our mass spectrometry data. For gel source data, see Supplementary Fig. 1. The experiment was performed once.

Extended Data Fig. 10 |. LYN deficiency allows for partial OT-II cell priming in response to t-mOVA.

a, b, Analysis of CD44 and CD62L expression. Representative flow plots (n ≥ 5 mice/group) (a) showing the frequency of CD44^hiCD62L^lo OT-II cells among total OT-II cells 6 days after adoptive transfer into WT or Lyn^−/− pregnant mice mated as indicated; the CD44^hiCD62L^lo gate was set based upon host CD4 cells for each cytometry run, which is shown in (b). Some groups received i.v. adjuvants (poly(I:C)+anti-CD40 antibodies) ± c-OVA at the time of OT-II transfer. See Fig. 4c for summary data. c–f, Assessment of the immunogenicity of Endoglycosidase H- (Endo H-) deglycosylated c-OVA. The extent of deglycosylation in Endo H- or mock (−)-treated c-OVA was determined via Concanavalin A (Con A) lectin blotting (c). Proliferation index (d), activation marker expression (e), and IFN-γ production (f) of CFSE-labeled OT-II cells were determined 6 days after transfer into virgin WT and μMT females, with 300 μg mock-treated or deglycosylated c-OVA given i.p. together with adjuvants (poly(I:C)+anti-CD40 antibodies) on the same day as the OT-II transfer. Bars show mean±s.d. P-values were determined by two-tailed, unpaired t-test. Data were accumulated from 3 independent experiments and all mice are shown. g–j, Upregulation of CD80 and CD86 by antigen-specific B cells is suppressed by t-mOVA in WT and Lyn^−/− pregnant mice. Frequency of CD80^hi or CD86^hi OVA-Tetramer⁺ (g, i) or total (h, j) B cells 6 days after i.v. vaccination with 5×10⁴ OT-II cells ± c-OVA ± poly(I:C) (Adj) on E11.5 or E12.5. Adjusted P-values were determined by ordinary one-way ANOVA with Šídák’s multiple comparisons test. Each group was compared to the control xB6 group, and the xB6+c-OVA/Adj group was compared to the xmOVA+c-OVA/Adj group. Bars show mean±s.d. Data were accumulated over 39 independent experiments and all mice are shown.

Fig. 1 |. B cells present t-mOVA to CD4⁺ T cells, which leads to impaired CD4⁺ T-cell priming and suppressed responses to c-OVA.

a–e, Proliferation index (a), fold expansion (b), activation marker expression (c), IFNγ production (d) and representative flow plots (e) of carboxyfluorescein diacetate succinimidyl ester (CFSE)-labelled OT-II cells 6 days after transfer on embryonic day (E) 12.5–E15.5 into WT females mated as indicated. Some groups received intravenous injections of adjuvants (Adj; comprised of poly(I:C) and anti-CD40 antibodies) with or without c-OVA at the time of OT-II transfer. Adjusted P values were determined by ordinary one-way analysis of variance (ANOVA) with Sidak’s multiple comparisons test. Each group was compared to the xB6 control group, and the xB6 + c-OVA/Adj group was compared to the xmOVA + c-OVA/Adj group. NS, not significant. Bars show mean ± s.d. Data were accumulated over 11 independent experiments and all mice are displayed. f, Representative CFSE dilution profiles (n ≥ 6 per group) indicating the extent of OT-II (top row) and OT-I (bottom row) cell proliferation 50 h after late-gestational transfer into xmOVA pregnant mice of the indicated genotypes. See Extended Data Fig. 3b, c for summary data.

Fig. 2 |. Antigen-specific B cell suppression by t-mOVA.

a, b, Phenotypic analysis of OVA-specific B cells from xB6 and xmOVA pregnancies showing t-mOVA-driven CD95 and MHCII upregulation at late gestation (E14.5–E18.5) in follicular (FO) cells, which were gated as DUMP^negCD19⁺CD21/CD35^lo-medCD93^neg. a, Representative contour plots on E17.5 are from n = 13 xB6 and n = 17 mOVA late gestation pregnancies. Ctrl-Tet, control-tetramer; OVA-Tet, OVA-tetramer. b, P values were determined by two-tailed, unpaired t-test. Bars show mean ± s.d. Data were accumulated over 22 independent experiments and all mice are displayed. c, d, Frequencies of total (c) or GL7⁺CD95⁺ GC phenotype (d) OVA-specific B cells 6 days after intravenous injection of 5 × 10⁴ OT-II cells with or without c-OVA and with or without poly(I:C) (Adj) on E11.5 or E12.5. Adjusted P values were determined by ordinary one-way ANOVA with Sidak’s multiple comparisons test as described in Fig. 1. Bars show mean ± s.d; dashed line shows limit of detection. Data were accumulated over 26 independent experiments and all mice are displayed. e, Representative flow plots of OVA-Tet⁺ B cells gated from a fixed number of total B cells across all groups.

Fig. 3 |. CD22 and LYN mediate t-mOVA-induced B cell suppression.

a, Extensive N-linked glycosylation of t-mOVA. Equal volumes of pooled plasma (n = 3 mice per group (E16.5–E18.5)) were subjected to anti-OVA immunoprecipitation, deglycosylation by PNGase F digestion as indicated, then anti-OVA immunoblotting. c-OVA was analysed in parallel. b, t-mOVA sialylation. OVA from various sources was subjected to anti-OVA immunoprecipitation, sialidase digestion as indicated, then lectin blotting. Plasma came from n = 3–4 pooled xB6 pregnant WT, xmOVA pregnant WT (both E15.5–E17.5) or non-pregnant Act-mOVA (mOVA⁺) transgenic females; skin came from non-pregnant mOVA⁺ transgenic females. Each lectin blot was stripped and re-probed with anti-OVA antibodies. A nonspecific (NS) species and the sialidase itself was detected on the lectin blots. c, α(2,6)-Sia prevalence on mOVA from various tissues of Act-mOVA mice. OVA was immunoprecipitated from tissue homogenates or plasma (as in b) and subjected to SNA-I blotting, then anti-OVA immunoblotting. Blots in a–c are each representative of two to three experiments, each with independent biological replicates. For gel source data, see Supplementary Fig. 1.d–f, Representative flow plots (f), frequencies of total (d) or GL7⁺CD95⁺ GC phenotype (e) OVA-specific B cells 6 days after vaccination as described in Fig. 2c–e. WT data are from Fig. 2c, d. The flow plots show OVA-Tet⁺ B cells gated from a fixed number of total B cells across all groups. Adjusted P values were determined by ordinary one-way ANOVA with Sidak’s multiple comparisons test as described in Fig. 1. Bars show mean ± s.d. Lyn^−/− and Cd22^−/− data were accumulated over 14 and 11 independent experiments, respectively, and all mice are displayed. g, B cell responses to presumptive endogenous trophoblast antigens. For pregnant mice, splenic B cells were analysed on E18.5 and combine data from n = 5–9 xB6 mice and n = 5 xmOVA mice per group. Adjusted P values were determined by ordinary one-way ANOVA with Sidak’s multiple comparisons test. Bars show mean ± s.d.

Fig. 4 |. CD4⁺ T-cell priming to t-mOVA in Lyn^−/− mice.

a–e, Proliferation index (a), fold expansion (b), activation marker expression (c), IFNγ production (d) and representative flow plots (e) of CFSE-labelled OT-II cells 6 days after transfer on E12.5–15.5 cells into pregnant WT (top row, e) or Lyn^−/− (bottom row, e) mice mated as indicated. Some groups received intravenous injections of adjuvants (poly(I:C) and anti-CD40 antibodies) with or without c-OVA at the time of OT-II transfer. Data for untreated WT xB6 and untreated WT xmOVA mice are the same as in Fig. 1. Adjusted P values were determined by ordinary one-way ANOVA with Sidkak’s multiple comparisons test as described in Fig. 1. Bars show mean ± s.d. Data were accumulated over eight independent experiments and all mice are displayed.