Novel epigenetic network biomarkers for early detection of esophageal cancer

Abstract

Background: Early detection of esophageal cancer is critical to improve survival. Whilst studies have identified biomarkers, their interpretation and validity is often confounded by cell-type heterogeneity.

Results: Here we applied systems-epigenomic and cell-type deconvolution algorithms to a discovery set encompassing RNA-Seq and DNA methylation data from esophageal adenocarcinoma (EAC) patients and matched normal-adjacent tissue, in order to identify robust biomarkers, free from the confounding effect posed by cell-type heterogeneity. We identify 12 gene-modules that are epigenetically deregulated in EAC, and are able to validate all 12 modules in 4 independent EAC cohorts. We demonstrate that the epigenetic deregulation is present in the epithelial compartment of EAC-tissue. Using single-cell RNA-Seq data we show that one of these modules, a proto-cadherin module centered around CTNND2, is inactivated in Barrett's Esophagus, a precursor lesion to EAC. By measuring DNA methylation in saliva from EAC cases and controls, we identify a chemokine module centered around CCL20, whose methylation patterns in saliva correlate with EAC status.

Conclusions: Given our observations that a CCL20 chemokine network is overactivated in EAC tissue and saliva from EAC patients, and that in independent studies CCL20 has been found to be overactivated in EAC tissue infected with the bacterium F. nucleatum, a bacterium that normally inhabits the oral cavity, our results highlight the possibility of using DNAm measurements in saliva as a proxy for changes occurring in the esophageal epithelium. Both the CTNND2/CCL20 modules represent novel promising network biomarkers for EAC that merit further investigation.

Keywords: Barrett’s esophagus; Biological networks; DNA methylation; Esophageal adenocarcinoma; Saliva; Single-cell RNA-Seq.

Fig. 1

Identification of network biomarkers in EAC. a Using the TCGA DNA methylation and mRNA expression datasets for EAC, we identify gene-modules of joint epigenetic and expression deregulation in EAC compared to normal-adjacent tissue, using our Functional Epigenetic Modules (FEM) algorithm whilst adjusting for stromal heterogeneity. The latter is accomplished by estimating total epithelial, total immune cell and total fibroblast fractions in the TCGA samples using our HEpiDISH algorithm. FEM searches for gene-modules in the context of a PPI network. Subsequently, we apply our CellDMC algorithm to ascertain if the DNA methylation changes underlying the inferred gene modules are happening in the epithelial compartment of the tissue. Finally, we validate inferred modules in independent DNA methylation and mRNA expression EAC datasets. b Modules validating in (a) are then explored for their potential utility as early detection markers. This is done in two ways. In one case we analyse scRNA-Seq data from Barrett’s and normal esophagus to explore if any modules are deregulated in Barrett’s. In the second case, we explore if promising gene-modules exhibit variable DNA methylation patterns in saliva from cohorts containing both EAC and healthy subjects, where we also apply cell-type deconvolution methods to estimate epithelial fractions in saliva

Fig. 2

FEM-modules derived from TCGA EAC cohort. Barplot lists the significant FEM-modules labeled by the seed-gene with the number of genes in each module given in brackets. Length of bars indicate the number of genes within the module that are significantly differentially methylated (DM), significantly differentially expressed (DR), jointly differentially methylated and differentially expressed (DM & DR) and the subset of these that exhibit anticorrelation between promoter DNAm and gene-expression. We display 3 modules defined by seed-genes, CTNND2, CCL20 and NCAM1. The node color indicates differential DNAm, with the border color indicating differential expression, as specified in the color-bars

Fig. 3

Validation of our EAC modules in independent DNAm cohorts. Violin plots comparing predicted FEM-scores for each of the 12 EAC modules in each of two independent DNAm EAC cohorts. Validation cohort-1 is from GSE72872. Validation cohort-2 is from GSE89181. P values are from a one-tailed Wilcoxon rank sum test

Fig. 4

The CTNND2 module is altered in the epithelial cells of EAC and Barrett’s Esophagus. a Barplot displaying the number of differentially methylated genes (DMG), and the subset of these that are specifically differentially methylated in the epithelial (Epi), fibroblast (Fib) and immune cells (IC) for each of the 12 EAC FEM-modules, as determined in the EAC TCGA DNAm dataset. b tSNE diagrams for the 2009 epithelial single cells profiled in samples derived from 4 patients diagnosed with BE. The first panel displays the inferred 6 clusters. The middle panel labels the cells by the site of sampling (tissue): BE = Barrett’s Esophagus, DuoD = duodenum, Gastric = gastroesophageal junction, Oesoph = adjacent normal squamous cells from oesophagus. The right panel labels the cells by the patient they derived from. The Chi-Square statistics and associated P values were derived from a contingency table test, assessing how unevenly tissue and patient are distributed among the inferred clusters. c Violin plots displaying the FEM cancer-score for the CTNND2 module in a scRNA-Seq dataset comparing epithelial cells from Barrett’s Esophagus lesions (BE) to adjacent normal squamous epithelial cells for each of 4 different patients diagnosed with BE. Last panel is for the case where all cells from all patients are merged. P values are from a one-tailed Wilcoxon rank sum test

Fig. 5

Correlation of CCL20 module with EAC status in saliva. a Violin plots displaying the total epithelial fraction (fEPI, y-axis), as estimated using HEpiDISH with our Epithelial-Fibroblast-ImmuneCell DNAm reference, against disease stage (x-axis) in the two saliva cohorts, as indicated. P values derive from a one-tailed Wilcoxon rank sum test, comparing each disease stage to the normal-state. N = normal, NDBE = non-dysplastic Barrett’s Esophagus, HGD = high grade dysplasia, C = Esophageal Adenocarcinoma. b Scatterplot of the estimated total epithelial fraction (fEPI, y-axis) vs the estimated squamous buccal epithelium fraction (x-axis). Pearson correlation coefficient (PCC) and P value are given. Samples have been colored according to disease stage using same coloring scheme as in (a). c As (b), but now displaying the estimated esophageal adenoma carcinoma cell fraction along the x-axis. d Violin plots displaying the FEM EAC score (y-axis) versus disease stage (x-axis), for the CCL20-module in the two saliva cohorts. P values derive from a one-tailed Wilcoxon rank sum test, comparing each disease stage to the normal-state