Molecular diagnosis of eosinophilic esophagitis by gene expression profiling

Abstract

Background & aims: Gene expression profiling provides an opportunity for definitive diagnosis but has not yet been well applied to inflammatory diseases. Here we describe an approach for diagnosis of an emerging form of esophagitis, eosinophilic esophagitis (EoE), which is currently diagnosed by histology and clinical symptoms.

Methods: We developed an EoE diagnostic panel (EDP) comprising a 96-gene quantitative polymerase chain reaction array and an associated dual-algorithm that uses cluster analysis and dimensionality reduction using a cohort of randomly selected esophageal biopsy samples from pediatric patients with EoE (n = 15) or without EoE (non-EoE controls, n = 14) and subsequently vetted the EDP using a separate cohort of 194 pediatric and adult patient samples derived from both fresh or formalin-fixed, paraffin-embedded tissue: active EoE (n = 91), control (non-EoE and EoE remission, n = 57), histologically ambiguous (n = 34), and reflux (n = 12) samples.

Results: The EDP identified adult and pediatric patients with EoE with approximately 96% sensitivity and approximately 98% specificity, and distinguished patients with EoE in remission from controls, as well as identified patients exposed to swallowed glucorticoids. The EDP could be used with formalin-fixed, paraffin-embedded tissue RNA and distinguished patients with EoE from those with reflux esophagitis, identified by pH-impedance testing. Preliminary evidence showed that the EDP could identify patients likely to have disease relapse after treatment.

Conclusions: We developed a molecular diagnostic test (referred to as the EDP) that identifies patients with esophagitis in a fast, objective, and mechanistic manner, offering an opportunity to improve diagnosis and treatment, and a platform approach for other inflammatory diseases.

Keywords: AUC; Diagnostic Panel; EDP; EGID; EoE; EoE Transcriptome; Eosinophil; FFPE; Fluidic Card; GERD; GI; HPF; MII; NL; Nonerosive Reflux Disease; ROC; Signature; area under the curve; eosinophilic esophagitis; eosinophilic esophagitis diagnostic panel; eosinophilic gastrointestinal disorder; formalin-fixed, paraffin-embedded; gastroesophageal reflux disease; gastrointestinal; high-power field; multichannel intraluminal impedance; normal; receiver operating characteristic.

Figure 1. Graphic illustration of EDP standard operating procedures

The eosinophilic esophagitis (EoE) diagnostic panel (EDP) described in this report consists of three major steps, namely RNA extraction, EDP panel qPCR, and data analysis. RNA is extracted from a fresh patient esophageal biopsy or FFPE tissue sections. An aliquot of the RNA sample is subjected to reverse transcription reaction, and the resulting cDNA is loaded onto the 384-well fluidic card (4 patients) for qPCR amplification. The qPCR data are subjected to dual algorithms, namely signature analysis (heat map clustering) and dimensionality reduction (EoE score) to establish molecular EoE diagnosis, which forms the basis for the final diagnostic report with multiple disease pathogenesis component assessment. Th2: type 2 helper T cells; ΣΔCT, sum of normalized CT.

Figure 2. Dual EDP algorithms for molecular diagnosis of EoE

A, For the 94 EoE genes embedded, a statistical screening was performed between the 14 normal (NL) patients (blue branch) and 15 patients with EoE (red branch), resulting in 77 genes with FDR-corrected p < 0.05 and fold change > 2.0. Based on these 77 core genes, a heat map (red = upregulated) was created, with the hierarchical tree (dendrogram) established on both gene entities and sample conditions. On the x-axis, the first branch of the top tree is utilized to predict EoE vs. NL. B, The 77-gene/dimension expression data on 14 NL controls (blue) and 15 patients with EoE (red) were reduced to 3-D presentation by multi-dimensional scaling (MDS) analysis for visual presentation of the expression distance between samples. C, An EoE score was developed based on dimensionality reduction to distinguish EoE vs. NL and quantify EoE disease severity. A diagnosis cut-off at EoE score = 333 (dashed line) was derived from later, larger-scale studies by Receiver Operating Characteristic (ROC) analysis. D, ROC curve based on panel C and the EoE score = 333 cut-off, with an area under the curve (AUC) of 1.0. E, A linear correlation between eosinophils/HPF and EoE score, with Spearman r and p values shown. F, To demonstrate gene amplification accuracy, representative linear regressions regarding mast cell gene intra-correlation [CPA3 vs. Tryptase (TPSB2)], mast cell gene/eosinophil gene inter-correlation (CPA3 vs. CLC), and eosinophil gene/eosinophilia correlation (CLC vs. eosinophils/HPF) are shown in the left, middle, and right panels, respectively. All scatter plots were graphed as mean ± SEM.

Figure 3. EDP is able to discriminate patients with EoE remission from normal patients

A, EoE transcriptome profiles from 17 patients with EoE remission [treated with swallowed fluticasone propionate (FP) n = 11 or budesonide (BUD) n = 6] were acquired by EDP. Statistical analysis between the normal (NL) cohort and the two EoE remission cohorts was performed (FDR corrected p < 0.05, fold change >2.0), which resulted in 22 significant genes present in both FP- and BUD-regulated gene sets. On the basis of this 22 remission genes, a double-clustered heat map was generated to evaluate the gene expression pattern of EoE remission (FP, green; BUD, light blue) compared to NL (blue) and EoE (red). B, The remission score (EoE R score) for each patient was calculated by 1-D reduction with the same formula for EoE score to differentiate the patients with EoE remission (FP R and BUD R, R = remission) from the NL ones quantitatively. C, A diagnostic cut-off line of EoE R score = 74 was derived from ROC analysis, which has an AUC of 1.00. D, On the basis of the 77 EoE diagnostic genes, EoE scores were also calculated to assess the EoE status of these remission patients. The EoE score = 333 cut-off line is indicated on the graph. All scatter plots were graphed as mean ± SEM.

Figure 4. EoE transcriptome pattern in the patient population with ambiguous eosinophil levels, 6–14 eosinophils/HPF

A, To acquire the esophageal signatures of 34 patients with noticeable eosinophilia that did not exceed the diagnostic cut-off [6 < eosinophils (EOS)/high-power field (HPF) < 15], EDP-based expression signatures were juxtaposed with the reference normal (NL, 0 eosinophils/HPF) and eosinophilic esophagitis (EoE, >15 eosinophils/HPF) cohorts. B, The EoE score algorithm was utilized to assess EoE signature within the population with ambiguous eosinophil levels of 6–14 eosinophils/HPF (6–14/HPF). The EoE score scatter plot indicates that ~ 47% (16/34) patients in this sub-diagnosis zone were EDP positive as determined by the 333 EoE diagnostic cut-off (dashed line). C, Multi-dimensional scaling (MDS) analysis was carried out to visualize the expression difference between the 6–14-eosinophil cohort (green) and NL (blue) and EoE (red) reference cohorts. D, The average (Avg) Euclid distances from the 6–14-eosinophil cohort to the NL and EoE cohorts, respectively, were graphed as mean ± 95% CI, revealing their collective Euclid distance to NL and EoE reference cohorts, respectively. (*** p < 0.001) E, All 34 patients with ambiguous eosinophil levels (6–14 eosinophils/HPF) were clinically followed for 2 years based on their medical record. The association between EDP results and subsequent active EoE (>15 eosinophils/HPF) (in 1.2 ± 0.5 years, Mean ± SD) was graphed in the χ² table. The odds ratio (OR) of 4.4 was calculated based on the relative risk factor for EoE development, EDP-positive (EoE score < 333) vs. EDP-negative result, with a significant p value = 0.039 by χ² test.

Figure 5. A pH impedance-guided EDP analysis aiming to discriminate NERD/GERD from EoE

The EDP was performed on a selected cohort of 38 patients who had pH-Multichannel Intraluminal Impedance (pH-MII) results from the time of endoscope procedure; they were categorized into four different cohorts based on pathology findings and pH-MII test. Expression heat map was generated based on 36 significant genes after a statistical screening between NL patients and patients with EoE (FDR corrected p < 0.05, fold change >2.0). Four study cohorts, namely NL, non-erosive reflux disease (NERD), GERD and EoE were juxtaposed for signature comparison. The overhead “Reflux episode” bars indicate the number of esophageal reflux episodes within 24 hours by pH-MII with a cut-off of 80 displayed. # = 2–6 eosinophils/HPF and/or with neutrophilia; EOS, eosinophils. EDP was performed on FFPE-derived RNA in this retrospective study.

Figure 6. Overall assessment of EDP merit

To assess the dual algorithms of the EDP on a larger scale, we collected EDP signatures for a total of 166 patients, in which there are 82 patients with EoE [≥ 15 eosinophils (EOS)/high-power field (HPF)] and 50 control patients (≤ 2 EOS) by histology. A, With the clustering algorithm by 1^st branch, a double-clustered heat map (red branch, EoE; blue branch, control) indicates that EDP clustering algorithm is highly competent at positive prediction, with only one control misdiagnosed as EoE (single blue branch in the EoE cluster on the left). B, EoE scores from histology-defined 50 control patients and 82 patients with EoE were plotted over the 333 diagnostic cut-off (determined herein and used throughout this report), resulting in an optimized balance between sensitivity and specificity. The scatter plots were graphed as mean ± SEM. C, The ROC curve of EDP diagnosis in B with 132 patients in reference to histological method. AUC: area under the curve. D, On the basis of the EoE score analysis in B and C with the histology as gold standard, the EDP’s diagnostic merit was summarized in specificity vs. sensitivity and PPV vs. NPV, reflecting the diagnosing power in clinical practice. E, The correlation between tissue eosinophilia (eosinophils/HPF) and EoE score was analyzed by LOWESS (Locally Weighted Scatterplot Smoothing) nonparametric regression and plotted with the predicted trend (red) and realistic values (blue), indicating a negative relationship with r² = 0.68 and reflecting disease severity.