Identification of a DNA methylation signature to predict disease-free survival in locally advanced rectal cancer

Abstract

In locally advanced rectal cancer a preoperative predictive biomarker is necessary to adjust treatment specifically for those patients expected to suffer relapse. We applied whole genome methylation CpG island array analyses to an initial set of patients (n=11) to identify differentially methylated regions (DMRs) that separate a good from a bad prognosis group. Using a quantitative high-resolution approach, candidate DMRs were first validated in a set of 61 patients (test set) and then confirmed DMRs were further validated in additional independent patient cohorts (n=71, n=42). We identified twenty highly discriminative DMRs and validated them in the test set using the MassARRAY technique. Ten DMRs could be confirmed which allowed separation into prognosis groups (p=0.0207, HR=4.09). The classifier was validated in two additional cohorts (n=71, p=0.0345, HR=3.57 and n=42, p=0.0113, HR=3.78). Interestingly, six of the ten DMRs represented regions close to the transcriptional start sites of genes which are also marked by the Polycomb Repressor Complex component EZH2. In conclusion we present a classifier comprising 10 DMRs which predicts patient prognosis with a high degree of accuracy. These data may now help to discriminate between patients that may respond better to standard treatments from those that may require alternative modalities.

Figure 1. Study overview

Study design comprising four different independent cohorts (MCIp - Methyl-CpG immunoprecipitation, DMR – differentially methylated region, MassARRAY® (technique by Sequenome) - matrix-assisted laser desorption/ionization (MALDI) time-of-flight (TOF) mass spectrometry (MS), CRT – chemoradiotherapy, RT – radiotherapy, GER – German cohort, FRA – French cohort)

Figure 2. DFS of different patient cohorts

A) Methylation sites measured in the test-Set were filtered for their correlation with DFS using a Cox regression. Based on the filtered CpGs a clustering was performed which is shown on the heatmap. The dendrogram on the columns illustrates a hyper- and a hyopmethylated group. B) The Kaplan-Meier estimates of these groups were compared using a log-rank test indicating a significant difference between hyper- and hypomethylated tumors indicating a good and a bad prognosis groups. The patients from the validation set GER C) and FRA D) were assigned to one of the clusters based on their methylation pattern by means of the nearest centroid distance. The Kaplan-Meier curves of the resulting patient groups were again compared using a log-rank test. Correlation to DFS again revealed significant differences. (DFS – Diseas Free Survival)

Figure 3. Enrichment of EZH2 at rectal cancer DMRs

ChIP-seq data from H1 human embryonic stem cells, human umbilical vein endothelial cells, and normal human astrocytes obtained by the ENCODE consortium were analyzed for the occupancy of the Polycomb Repressor Complex-2 component EZH2 at the investigated rectal cancer-associated DMRs. As shown, significant signals of EZH2 occupancy were observed at the RNF220, ST6GALNAC5, BARHL2, ESRRG, ADRA1A and ERAS genes. The location of the DMRs is indicated by the black boxes located below the gene coordinates.