Unveiling new interdependencies between significant DNA methylation sites, gene expression profiles and glioma patients survival

Abstract

In order to find clinically useful prognostic markers for glioma patients’ survival, we employed Monte Carlo Feature Selection and Interdependencies Discovery (MCFS-ID) algorithm on DNA methylation (HumanMethylation450 platform) and RNA-seq datasets from The Cancer Genome Atlas (TCGA) for 88 patients observed until death. The input features were ranked according to their importance in predicting patients’ longer (400+ days) or shorter (≤400 days) survival without prior classification of the patients. Interestingly, out of the 65 most important features found, 63 are methylation sites, and only two mRNAs. Moreover, 61 out of the 63 methylation sites are among those detected by the 450 k array technology, while being absent in the HumanMethylation27. The most important methylation feature (cg15072976) overlaps with the RE1 Silencing Transcription Factor (REST) binding site, and was confirmed to intersect with the REST binding motif in human U87 glioma cells. Six additional methylation sites from the top 63 overlap with REST sites. We found that the methylation status of the cg15072976 site affects transcription factor binding in U87 cells in gel shift assay. The cg15072976 methylation status discriminates ≤400 and 400+ patients in an independent dataset from TCGA and shows positive association with survival time as evidenced by Kaplan-Meier plots.

Global DNA Methylation Patterns in Human Gliomas and Their Interplay with Other Epigenetic Modifications

“…REST can bind directly to its own motifs or can be recruited by MeCP2 (methyl-CpG binding protein 2) [87]. It was shown recently, that DNA methylation may affect REST binding in human glioma and that its binding to specific cytosines may be prognostic for patients survival [88]. The effect of REST binding may go beyond simple TF-gene regulation scenario, since REST was shown to recruit many histone modifiers: 1) HDAC1/2—histone deacetylases known to be recruited as a part of both coREST and NcoR repressive complexes [87,89]; 2) KDM1A (LSD1)—a flavin dependent lysine 4 of histone protein H3 (H3-Lys4) demethylase recruited as a part of LSD1-CoREST/nucleosome complex [89], which removes methyl groups from histone 3 mono- or di-methylated at lysine 4 (H3K4me1, HSK4me2) [90,91]; 3) EHMT2—euchromatic histone lysine methyltransferase 2 (also known as site-specific histone methyltransferase G9a), which promotes dimethylation of histone 3 at lysine 9 (H3K9me2) [87,92,93]; 4) SUV39H1—suppressor of variegation 3–9 homolog 1, a histone methyltransferase that trimethylates lysine 9 of histone H3, which results in transcriptional gene silencing [94].…”

Tumor Heterogeneity in Glioblastomas: From Light Microscopy to Molecular Pathology

“…Epigenetic characterization of GBMs has provided great insight into inter-tumoral heterogeneity and glioma classification and prognosis [15,16]. DNA methylation of CpG islands in the gene promoter are associated with repression of gene expression [77]. These bear a close relationship with hypermethylated status conferred by IDH mutations in gliomas [15,16].…”

“…Notably, differences in DNA methylation between tumor areas as close as 5 mm apart were observed, both in IDH mutant and IDH wild-type gliomas [64]. For specific information about DNA methylation and its relationship with other epigenetic modifications in cancer, we recommend a recent review covering this topic [77].…”

DNA methylation-based profiling reveals distinct clusters with survival heterogeneity in high-grade serous ovarian cancer

“…Novel methods for tumour classification have been examined in recent years based on genome-wide DNA methylation data [10,11]. Several DNA methylation pattern analyses have been reported for many cancer types using The Cancer Genome Atlas (TCGA) data [12][13][14][15][16]. There is also increasing interest in the role of DNA methylation in defining molecular subtypes to assist in elucidating the clinical characteristics and prognosis of EOC [17][18][19].…”