Immunomodulation of antigen presenting cells promotes natural regulatory T cells that prevent autoimmune diabetes in NOD mice

Abstract

Progression towards type 1 diabetes (T1D) in susceptible patients is linked to a progressive decline in the capacity of regulatory T cells (Treg) to maintain tolerance. As such, therapies aimed at redressing the failing Treg compartment have been the subject of intense investigation. Treg dysfunction in T1D has recently been linked to a reduced capacity of antigen presenting cells (APCs) to maintain Treg function rather than Treg intrinsic defects. This suggests that therapies aimed simply at addressing the failing Treg compartment are unlikely to provide long-term protection. Here, we demonstrate that modulation of the inflammatory status of CD11b+CD11c- APCs favors the upregulation of protective Tregs in a mouse model of T1D. We further demonstrate that reduced expression of the costimulatory molecule CD40 plays a role in this increased immunoregulatory capacity. Strikingly, Treg upregulation resulted exclusively from an increase in natural Tregs rather than the peripheral conversion of conventional T cells. This suggests that modulation of CD11b+ CD11c- APCs inflammatory properties favors the establishment of natural Treg responses that, unlike adaptive Treg responses, are likely to maintain tolerance to a broad range of antigens. As such, modulation of this APC subset represents a potential therapeutic avenue to reestablish peripheral tolerance and protect from autoimmune diseases such as T1D.

Figure 1. CD11b+CD11c− APCs produce lower levels of inflammatory cytokines following CB4 infection in the context of TGF-β.

Ex vivo production of A, B) TNF-α or C,D) IL-6 from CD11b+CD11c− APCs FACS sorted from CB4 infected NOD (black bar) or NODTGFβ (white bar) mice. Cytokine levels were measured from culture supernatants following 24 hours of incubation. Panels A,C are representative data from one experiment with pooled mice of each genotype while panels B,D represent mean + s.e.m of cytokine levels from 6 separate experiments normalized to the cytokine levels produced by WT NOD mice infected with CB4 in each separate experiments.

Figure 2. CB4 infection does not increase expression of type II monocyte/macrophages markers on CD11b+CD11c-APCs.

A) Percentage of CD11b+CD11c− APCs from mock-infected NOD (black bars) or NODTGFβ (white bars) mice positive for surface expression of CD204, CD206 or CD204 and CD206. B) Percentage of CD11b+CD11c− APCs from NOD (black bars) or NODTGFβ (white bars) mice positive for surface expression of CD204, CD206 or CD204 and CD206 7 days following CB4 infection. Data represent mean + s.e.m from 3 separate experiments, n = 9 per group.

Figure 3. Adoptive transfer of CD11b+CD11c− APCs from CB4-infected NODTGFβ mice is sufficient to increase Treg levels in uninfected NOD mice.

Average percentage of CD4+ T cells expressing Foxp3 in A, B) the PLNs or C) the pancreas of 10–12 week uninfected NOD recipients mock-transferred with DMEM (grey bars) or adoptively transferred with CD11b+CD11c− APCs FACS sorted from A) mock-infected NODTGFβ mice (white bars) or B, C) CB4 infected NODTGFβ (white bars) or NOD mice (black bars). Data represent mean + s.e.m. from at least 3 separate experiments (n = at least 6 mice per group).

Figure 4. Absence of CD40 on CD11b+CD11c− APCs is sufficient to increase Treg levels following CB4 infection.

Average percentage of CD4 T cells expressing Foxp3 in the A) PLNs or B) pancreas of NODCD40KO mice mock-infected with DMEM (white bars) or infected with CB4 (black bars) (n = at least 10 per group). C) Average percentage of CD4+ T cells expressing Foxp3 in the PLNs of uninfected 10–12 week old NOD mice mock-transferred with DMEM (white bar) or adoptively transferred with CD11b+CD11c− FACS sorted from CB4 infected NODCD40KO (black bar) or mock-infected NODCD40KO mice (grey bars). Data represent mean + s.e.m from at least 3 separate experiments (n = at least 7 per group).

Figure 5. CB4 infection in the context of TGF-β does not induce conversion of naïve T cells to adaptive Tregs but rather increases the levels of natural Tregs.

A) Representative flow cytometry plots of Foxp3 and Helios expression by CD4+ T cells from the PLNs of mock-infected (left panel) or CB4-infected NODTGFβ mice at day 7PI. B) Average percentage of Helios+ cells among CD4+Foxp3+ Tregs from the PLNs of NODTGFβ mice with increased Treg levels at day 7 PI with CB4 (black bars) or mock-infection with DMEM (white bars). C) Average percentage of Helios- cells among CD4+Foxp3+ Tregs from the PLNs of NODTGFβ mice with increased Treg levels at day 7 PI with CB4 (black bars) or mock-infection with DMEM (white bars). Data represent mean + s.e.m from at least 2 separate experiments (n = at least 4 per group). D) Representative flow cytometry plots of CD4 and GFP (Foxp3) expression of donor (Thy1.1+) cells recovered from the spleen (left panels) or PLNs (right panels) of NOD (top panels) or NODTGF-β (bottom panels) recipient mice at day 7 following infection with CB4. Data is representative of 2 separate experiments, n = 3 for NOD recipients and n = 6 for NODTGFβ recipients.