Effects of In Vivo Gluten Challenge on PBMC Gene Expression Profiles in Diet Treated Celiac Disease

Abstract

The pathological mechanisms that lead to the onset and reactivation of celiac disease (CD) remain largely unknown. While gluten free diet (GFD) improves the intestinal damage and associated clinical symptoms in majority of cases, it falls short of providing full recovery. Additionally, late or misdiagnosis is also common as CD presents with a wide range of symptoms. Clear understanding of CD pathogenesis is thus critical to address both diagnostic and treatment concerns. We aimed to study the molecular impact of short gluten exposure in GFD treated CD patients, as well as identify biological pathways that remain altered constitutively in CD regardless of treatment. Using RNAseq profiling of PBMC samples collected from treated CD patients and gluten challenged patient and healthy controls, we explored the peripheral transcriptome in CD patients following a short gluten exposure. Short gluten exposure of just three days was enough to alter the genome-wide PBMC transcriptome of patients. Pathway analysis revealed gluten-induced upregulation of mainly immune response related pathways, both innate and adaptive, in CD patients. We evaluated the perturbation of biological pathways in sample-specific manner. Compared to gluten exposed healthy controls, pathways related to tight junction, olfactory transduction, metabolism of unsaturated fatty acids (such as arachidonic acid), metabolism of amino acids (such as cysteine and glutamate), and microbial infection were constitutively altered in CD patients regardless of treatment, while GFD treatment appears to mostly normalize immune response pathways to "healthy" state. Upstream regulator prediction analysis using differentially expressed genes identified constitutively activated regulators relatively proximal to previously reported CD associated loci, particularly SMARCA4 on 19p13.2 and CSF2 on 5q31. We also found constitutively upregulated genes in CD that are in CD associated genetic loci such as MEF2BNB-MEF2B (BORCS8-MEF2B) on 19p13.11 and CSTB on 21q22.3. RNAseq revealed strong effects of short oral gluten challenge on whole PBMC fraction and constitutively altered pathways in CD PBMC suggesting important factors other than gluten in CD pathogenesis.

Keywords: celiac disease; celiac disease RNA sequencing; celiac disease gene expression analysis; celiac disease transcriptomics; pathway analysis, gluten challenge.

Figure 1

Differential gene expression in PBMC of CD patients following short gluten challenge. (A) Multidimensional scaling (MDS) plot of the total gene expression profile segregates pre-challenge patients (from day 0 shown in blue) from post-gluten challenge patients (day 6 samples in red). Gluten challenged healthy controls (in green) largely cluster with treated patients. (B) Top 20 differentially expressed genes from all three analysis are used to make a heatmap. The top 20 genes segregate samples by their health status. Gene clusters I and III appear to be altered genes following the 3-day gluten exposure, with I significantly upregulated and III downregulated in gluten exposed samples of day 6. Gene cluster II is downregulated in healthy controls following gluten exposure while remaining relatively highly expressed across patient samples from day 6 and particularly day 0. Rows are centered and unit variance scaling is applied to rows. Both genes and samples are clustered using hierarchical clustering with euclidean distance and ward linkage. (C) Venn diagram of DEGs from the three analyses is shown for all DEGs, differentially upregulated genes, and downregulated genes respectively. CD, celiac disease; HC, healthy control; d0, day0; d6, day6.

Figure 2

Pathways with significant enrichment scores from GSEA analyses. The normalized pathway enrichment scores (NES) of significantly perturbed KEGG pathways (p-values < 0.05) is used to draw a heat map across the three analyses. Row clustering of the KEGG pathways groups the pathways into CD relevant pathways regardless of treatment, and gluten exposure associated pathways in patients.

Figure 3

Sample-specific pathway deregulation analysis. (A) pathways in Cluster IV that appear “normalized” in treated day 0 (unchallenged) CD patient samples with pathway deregulation scores (PDS) close to the average in the healthy samples is shown. These pathways are deregulated in gluten exposed day 6 CD samples. (B) Pathways in Cluster II that show constitutive deregulation in CD patients regardless of treatment are shown. Clustering of the samples based on their PDS across pathways shows the similarity of samples over these pathways. Clusters IV and II are shown here, for the complete result see Figure S3. (C) PCA plot of the complete sample versus pathways deregulation score matrix data. The PCA shows clear separation of sample types by gluten exposure and health status. Gluten exposed CD patient samples have the most within cluster variation. CD, celiac disease; HC, healthy control; d0, day0; d6, day6.