Differential DNA methylation analysis of breast cancer reveals the impact of immune signaling in radiation therapy

Abstract

Radiotherapy (RT) is a central treatment modality for breast cancer patients. The purpose of our study was to investigate the DNA methylation changes in tumors following RT, and to identify epigenetic markers predicting treatment outcome. Paired biopsies from patients with inoperable breast cancer were collected both before irradiation (n = 20) and after receiving 10-24 Gray (Gy) (n = 19). DNA methylation analysis was performed by using Illumina Infinium 27K arrays. Fourteen genes were selected for technical validation by pyrosequencing. Eighty-two differentially methylated genes were identified in irradiated (n = 11) versus nonirradiated (n = 19) samples (false discovery rate, FDR = 1.1%). Methylation levels in pathways belonging to the immune system were most altered after RT. Based on methylation levels before irradiation, a panel of five genes (H2AFY, CTSA, LTC4S, IL5RA and RB1) were significantly associated with clinical response (p = 0.041). Furthermore, the degree of methylation changes for 2,516 probes correlated with the given radiation dose. Within the 2,516 probes, an enrichment for pathways involved in cellular immune response, proliferation and apoptosis was identified (FDR < 5%). Here, we observed clear differences in methylation levels induced by radiation, some associated with response to treatment. Our study adds knowledge on the molecular mechanisms behind radiation response.

Keywords: breast cancer; dose dependent; immune response; irradiation; methylation.

Figure 1

(a) Hierarchical clustering of “before IR” and “after IR” samples. Red samples are irradiated (after IR) and nonirradiated (before IR) samples are shown in green. The beige boxes indicate samples clustering together as before IR/after IR pairs. The colored spots in the dendrogram reflect the beta-value from the 27K array. Yellow spots imply high levels, green intermediate, and blue low levels of methylation. (b) All the samples that were separated in the cluster are shown in the upper panel, while the samples clustering as pairs are displayed in the lower panel. The X-axis gives information about the given dose in each sample. The red circles are those after IR samples that were removed in the new reduced dataset. (c) Hierarchical clustering of the reduced dataset, where eight of the after IR samples are removed.

Figure 2

(a) The boxplot shows the median value (red line) of standardized methylation levels for all the five genes, in tumor samples before IR for good and poor responders, and in normal controls. The upper and black line of the box plot indicates 25th and 75th percentiles. (b) The boxplot shows the sum of relative z-score values for six genes in the tumor samples after irradiation for good and poor responders, and in normal controls. [Color figure can be viewed in the online issue, which is available at wileyonlinelibrary.com.]

Figure 3

(a) Difference in the percentage of methylation (before/after IR) positively correlated to the effective administered dose. This is performed on the top 100 positively correlated probes, and a mean value is calculated based on delta methylation level for these 100 probes. (b) Delta methylation level is based on the mean value for top 100 negatively correlated probes. The red line indicates a trend line for the values. [Color figure can be viewed in the online issue, which is available at wileyonlinelibrary.com.]