The molecular basis for oat intolerance in patients with celiac disease

Abstract

Background: Celiac disease is a small intestinal inflammatory disorder characterized by malabsorption, nutrient deficiency, and a range of clinical manifestations. It is caused by an inappropriate immune response to dietary gluten and is treated with a gluten-free diet. Recent feeding studies have indicated oats to be safe for celiac disease patients, and oats are now often included in the celiac disease diet. This study aimed to investigate whether oat intolerance exists in celiac disease and to characterize the cells and processes underlying this intolerance.

Methods and findings: We selected for study nine adults with celiac disease who had a history of oats exposure. Four of the patients had clinical symptoms on an oats-containing diet, and three of these four patients had intestinal inflammation typical of celiac disease at the time of oats exposure. We established oats-avenin-specific and -reactive intestinal T-cell lines from these three patients, as well as from two other patients who appeared to tolerate oats. The avenin-reactive T-cell lines recognized avenin peptides in the context of HLA-DQ2. These peptides have sequences rich in proline and glutamine residues closely resembling wheat gluten epitopes. Deamidation (glutamine-->glutamic acid conversion) by tissue transglutaminase was involved in the avenin epitope formation.

Conclusions: We conclude that some celiac disease patients have avenin-reactive mucosal T-cells that can cause mucosal inflammation. Oat intolerance may be a reason for villous atrophy and inflammation in patients with celiac disease who are eating oats but otherwise are adhering to a strict gluten-free diet. Clinical follow-up of celiac disease patients eating oats is advisable.

Figure 1. Histology of Intestinal Mucosa of Two of the Oat-Intolerant Patients

Small intestinal biopsies were obtained at diagnosis, after an ordinary gluten-free diet (remission), after introduction of oats, and after withdrawal of oats (recovery). For patient CD496, a biopsy was not taken after she started with a gluten-free diet. Biopsies were scored according to the modified Marsh criteria. Hematoxilin-eosin staining was used, and IEL counts are given in the corners of the photomicrographs. The remission biopsy from patient CD507 was poorly oriented. We therefore melted and reoriented this biopsy (insert). Original magnification: 100×.

Figure 2. Identification of an Epitope in Avenin Recognized by Intestinal T-Cells of Celiac Disease Patients

(A) Reverse-phase HPLC of a pepsin-trypsin digest of avenin. Peptides in fraction 25, obtained from gel filtration, were eluted by an acetonitrile gradient (straight line), and 41 fractions were collected. Fractions recognized by T-cell lines in subsequent experiments are indicated by the numbers above the peaks. (B) T-cell recognition of fractions obtained by reverse-phase HPLC. All 41 fractions obtained in (A) were tested for recognition by the intestinal T-cell line 422.2.4 (derived from an oat-intolerant celiac disease patient). The fractions were incubated with DR3-DQ2 homozygous antigen-presenting cells overnight before the T-cell line was added. Specific T-cell responses were measured by ³H-thymidine incorporation. Pepsin-trypsin-digested avenins, both TG2-treated and untreated, were used as control antigens. (C) Sequences of the peptides in the stimulatory fractions from reverse-phase HPLC identified by tandem mass spectrometry and overlapping synthetic peptides used for T-cell assays. For better comparison, the amino acid sequence of the avenin precursor protein JQ1047 (gi82331) is taken as a consensus sequence, and deviating residues are underlined.

Figure 3. HLA Restriction and Avenin Peptide Specificity of the Intestinal T-Cell Line 431.2 from Patient CD431

The avenin antigen (at 0.25 mg/ml) and peptides (at 10 μM), treated with TG2 when indicated, were incubated overnight with DR3-DQ2 homozygous antigen-presenting cells before T-cells were added. In the HLA restriction experiments, anti-DR or anti-DQ monoclonal antibodies were added 30 min prior to the T-cells. T-cell responses were measured by ³H-thymidine incorporation and are represented as SIs.

Figure 4. Reactivity of an HLA-DQ2-Restricted T-Cell Clone Derived from a T-Cell Line (CD496.2.3) Established by Avenin Stimulation of an Intestinal Biopsy of Patient CD496

T-cell responses were measured by ³H-thymidine incorporation and are represented as SIs. (A) The clone specifically recognizes the avenin peptide Av-α9B after treatment with TG2. The peptides were tested at 10 μM. (B) The clone recognizes avenin but not gluten antigen after treatment with TG2.

Figure 5. Amino Acid Sequence of an Avenin (gi 82331, JQ1047) and an α-Gliadin (α2-Gliadin, AJ133612)

The proline and glutamine residues are red and blue, respectively. In the avenin, the presumed 9-mer core region of the characterized T-cell epitope is underlined. In the α-gliadin, a 33-mer natural fragment containing six copies of three partly overlapping epitopes (DQ2-α-I, PFPQPQLPY; DQ2-α-II, PQPQLPYPQ; and DQ2-α-III, PYPQPQLPY) is underlined. Note the localization of all the epitopes to regions of the proteins rich in proline and glutamine residues and the high number of proline residues within the 9-mer core regions of the epitopes.