The HLA-DQ2 gene dose effect in celiac disease is directly related to the magnitude and breadth of gluten-specific T cell responses

Abstract

In patients with celiac disease, inflammatory T cell responses to HLA-DQ2-bound gluten peptides are thought to cause disease. Two types of HLA-DQ2 molecules exist, termed HLA-DQ2.5 and HLA-DQ2.2. Whereas HLA-DQ2.5 predisposes to celiac disease, HLA-DQ2.2 does not. We now provide evidence that the disease-associated HLA-DQ2.5 molecule presents a large repertoire of gluten peptides, whereas the non-disease-associated HLA-DQ2.2 molecule can present only a subset of these. Moreover, gluten presentation by HLA-DQ2 homozygous antigen-presenting cells was superior to presentation by HLA-DQ2/non-DQ2 heterozygous antigen-presenting cells in terms of T cell proliferation and cytokine secretion. Gluten presentation by HLA-DQ2.5/2.2 heterozygous antigen-presenting cells induced intermediate T cell stimulation. These results correlated with peptide binding to the antigen-presenting cells. Finally, we demonstrate that HLA-DQ trans dimers formed in HLA-DQ2.5/2.2 heterozygous individuals have properties identical with HLA-DQ2.5 dimers. Our findings explain the strongly increased risk of disease development for HLA-DQ2.5 homozygous and HLA-DQ2.2/2.5 heterozygous individuals, and they are indicative of a quantitative model for disease development, where HLA-DQ expression and the available number of T cell-stimulatory gluten peptides are critical limiting factors. This model may have important implications for disease prevention.

Fig. 1.

Gene dose effect in stimulation of gluten-specific T cell clones. Stimulation of two gluten-specific T cell clones with the gluten epitopes glia-α9(A and B) and glt-17 (C and D) is shown. Five concentrations of the epitopes were tested in the range from 0.2 μg/ml (light-gray bars) to 20 μg/ml (black bars). Peripheral blood mononuclear cells (PBMC) of various HLA-DQ2⁺ healthy individuals were used as APC (x axis). The epitopes were tested as deamidated peptides. T cell stimulation was determined by measurement of proliferation (A and C) and IFN-γ production (B and D). Production of tumor necrosis factor α, IL-10, IL-5, and IL-4 correlated with the levels of IFN-γ secreted (data not shown). The percentage of HLA class II-expressing cells in the PBMCs was determined by FACS analysis and was similar for each donor (data not shown). These results are representative of three independent experiments using PBMCs from various donors.

Fig. 2.

Peptide binding to a panel of HLA-DQ combinations. Shown is the binding of a concentration range of the indicator peptides MHCIα46-63 (A and B) and glia-α9(C and D) to HLA-DQ molecules isolated from HLA-homozygous and -heterozygous EBV-transformed B cell lines. The results shown are representative of at least three independent experiments.

Fig. 3.

Functional expression of HLA-DQ2.5 in cis and in trans. (Upper) Absence of HLA-DQ2 on an HLA class II negative B cell line (thin line), and presence of HLA-DQ2 on the cell line transduced with HLA-DQα*0501 and DQβ*0201 (solid gray), and HLA-DQα*0501 and DQβ*0202 (black line). (Lower) T cell stimulation by the glia-α9 epitope in the context of the untransduced HLA class II-negative cell line (wt), and transduced cell lines with the HLA-DQ2 molecules in cis (DQα*0501 and DQβ*0201) and in trans (DQα*0501 and DQβ*0202). Five concentrations of the glia-α9 epitope were tested in the range from 0.2 μg/ml (light-gray bars) to 20 μg/ml (black bars).

Fig. 4.

Model for the impact of the HLA-gene dose on the formation of immunogenic HLA-DQ2-gluten peptide complexes. With an increase in the number of available gluten peptides (x axis), the number of immunogenic HLA-DQ-peptide complexes (y axis) rises the strongest in HLA-DR3-DQ2.5-homozygous individuals, breaking through a hypothetical threshold when relatively few gluten peptides are present. HLA-heterozygous individuals need to recognize a larger group of gluten peptides before they reach the threshold. HLA-DQ2.5/2.2 individuals are in between.