Temporal change of DNA methylation subclasses between matched newly diagnosed and recurrent glioblastoma

Abstract

The longitudinal transition of phenotypes is pivotal in glioblastoma treatment resistance and DNA methylation emerged as an important tool for classifying glioblastoma phenotypes. We aimed to characterize DNA methylation subclass heterogeneity during progression and assess its clinical impact. Matched tissues from 47 glioblastoma patients were subjected to DNA methylation profiling, including CpG-site alterations, tissue and serum deconvolution, mass spectrometry, and immunoassay. Effects of clinical characteristics on temporal changes and outcomes were studied. Among 47 patients, 8 (17.0%) had non-matching classifications at recurrence. In the remaining 39 cases, 28.2% showed dominant DNA methylation subclass transitions, with 72.7% being a mesenchymal subclass. In general, glioblastomas with a subclass transition showed upregulated metabolic processes. Newly diagnosed glioblastomas with mesenchymal transition displayed increased stem cell-like states and decreased immune components at diagnosis and exhibited elevated immune signatures and cytokine levels in serum. In contrast, tissue of recurrent glioblastomas with mesenchymal transition showed increased immune components but decreased stem cell-like states. Survival analyses revealed comparable outcomes for patients with and without subclass transitions. This study demonstrates a temporal heterogeneity of DNA methylation subclasses in 28.2% of glioblastomas, not impacting patient survival. Changes in cell state composition associated with subclass transition may be crucial for recurrent glioblastoma targeted therapies.

Keywords: DNA methylation; Deconvolution; Glioma; Outcome; Subgroup; Temporal.

Fig. 1

Analysis of DNA methylation profiling between tumor tissue obtained from first and recurrent resection of IDH-wildtype glioblastoma. a Study workflow. b–d Sankey plots showing a possible transition of b DNA methylation subclasses, c calibrated scores, and d MGMT promoter methylation status. e T-distributed stochastic neighbor embedding shows methylation subclasses RTK I (gold), RTK II (red), and MES (green) from first resection, and tumors with a subclass transition (purple) at time of recurrence. f Gene set enrichment analysis of differentially methylated CpG sites in hypomethylated genes of newly diagnosed glioblastomas undergoing subclass transition compared to glioblastomas without transitions. g Gene set enrichment analysis of differentially methylated CpG sites in hypermethylated genes of newly diagnosed glioblastomas undergoing subclass transition compared to glioblastomas without transitions. RTK receptor tyrosine kinase, MES mesenchymal

Fig. 2

Cell state composition analysis from tissue and serum. a Cell state composition analysis of newly diagnosed glioblastoma separated to a potential subclass transition. b–e Immune cell signatures calculated from tumor tissue of first surgery. f–i Signatures of circulating serum levels of immune cells in patients with newly diagnosed IDH-wildtype glioblastoma. j Cell state composition analysis of recurrent glioblastoma tissue separated to a potential subclass transition. k–m Soluble factors with significantly different serum levels at time of diagnosis between glioblastoma with and without mesenchymal transition. MES mesenchymal

Fig. 3

Soluble factor analysis of patients’ serum at time of diagnosis and recurrence. a–c Serum levels of soluble factors TREM-2, IL-6, and IL-18 at time of diagnosis between tumors with a mesenchymal transition and without a subclass transition. d–f Comparison of serum levels of soluble factors TREM-2, IL-6, and IL-18 between first (blank dot) and recurrent (x-shaped dot) surgery with respect to a potential mesenchymal transition. MES mesenchymal, TREM-2 triggering receptor expressed on myeloid cells, IL interleukin

Fig. 4

Proteomic profiling of newly diagnosed IDH-wildtype glioblastomas with and without a subclass transition. a WCGNA analysis showed differentially correlated proteome modules between both subgroups. Tumors with a subclass transition showed a significantly enrichment of the module “skyblue1”, while non-transitioning tumors have higher protein abundance in module “coral1”. b Most abundant proteins for tumor with a subclass transition (referring to module “skyblue1”). c Most abundant proteins for tumor with a subclass transition (referring to module “skyblue1”). d Integrating public transcriptomic single-cell data showed an AC-/OPC- and MES-like character in tumors with a subclass transition. e Volcano plot of -log10 (p value) against log2 fold change representing the differently abundant proteins at time of diagnosis between tumors of with a subclass transition as compared to tumors without a transition. f Dot plot illustrating most significantly upregulated gene ontology terms at time of diagnosis in glioblastoma with a subclass transition. e–g Protein abundance of stem cell markers from tumor tissue of first surgery were compared between glioblastomas without transition and with mesenchymal transition. AC astrocytic, OPC oligodendrocyte precursor cell, MES mesenchymal, SOX Sex determining region Y-box 2, PROM prominin

Fig. 5

Kaplan Meier curves representing the survival outcome regarding DNA methylation subclass transition. a–d Survival outcome between patients with a methylation subclass change and without a subclass change, and e–h dependent on a potential mesenchymal subclass change