DNA methylation, transcriptome and genetic copy number signatures of diffuse cerebral WHO grade II/III gliomas resolve cancer heterogeneity and development

Abstract

Background: Diffuse lower WHO grade II and III gliomas (LGG) are slowly progressing brain tumors, many of which eventually transform into a more aggressive type. LGG is characterized by widespread genetic and transcriptional heterogeneity, yet little is known about the heterogeneity of the DNA methylome, its function in tumor biology, coupling with the transcriptome and tumor microenvironment and its possible impact for tumor development.

Methods: We here present novel DNA methylation data of an LGG-cohort collected in the German Glioma Network containing about 85% isocitrate dehydrogenase (IDH) mutated tumors and performed a combined bioinformatics analysis using patient-matched genome and transcriptome data.

Results: Stratification of LGG based on gene expression and DNA-methylation provided four consensus subtypes. We characterized them in terms of genetic alterations, functional context, cellular composition, tumor microenvironment and their possible impact for treatment resistance and prognosis. Glioma with astrocytoma-resembling phenotypes constitute the largest fraction of nearly 60%. They revealed largest diversity and were divided into four expression and three methylation groups which only partly match each other thus reflecting largely decoupled expression and methylation patterns. We identified a novel G-protein coupled receptor and a cancer-related 'keratinization' methylation signature in in addition to the glioma-CpG island methylator phenotype (G-CIMP) signature. These different signatures overlap and combine in various ways giving rise to diverse methylation and expression patterns that shape the glioma phenotypes. The decrease of global methylation in astrocytoma-like LGG associates with higher WHO grade, age at diagnosis and inferior prognosis. We found analogies between astrocytoma-like LGG with grade IV IDH-wild type tumors regarding possible worsening of treatment resistance along a proneural-to-mesenchymal axis. Using gene signature-based inference we elucidated the impact of cellular composition of the tumors including immune cell bystanders such as macrophages.

Conclusions: Genomic, epigenomic and transcriptomic factors act in concert but partly also in a decoupled fashion what underpins the need for integrative, multidimensional stratification of LGG by combining these data on gene and cellular levels to delineate mechanisms of gene (de-)regulation and to enable better patient stratification and individualization of treatment.

Keywords: Astrocytoma; Cellular composition; DNA methylation; Epigenetics; Glioma; Molecular subtypes; Prognosis; Tumor microenvironment.

Fig. 1

Characteristics of molecular subtypes of glioma. Samples were grouped into gene expression groups E1 – E8 (E-classes) or DNA methylation groups M1 – M6 (M-classes) using the sample expression and methylation data, respectively. A) The pairwise sample correlation heatmaps visualize the correlation coefficient between all pairwise combinations of sample-portraits. Intra-class similarities between samples are evident as brown quadratic areas along the diagonal while inter-class relations are seen either as brown or blue off-diagonal regions for positively and negatively correlated data landscapes, respectively. B) Genetic, methylation and clinical characteristics (see text). C) We sorted samples in each E-group according to their M-group membership and in each M-group according to their E-group membership to better recognize pattern due to methylation and expression effects, respectively (see the two color bars above the heatmap). The color code for molecular groups are used throughout the paper. Mutual relations between the E- and M-groups were estimated based on mutual memberships of the samples giving rise to four consensus subtypes C1- C4 which are characterized by IDH-wild type astrocytoma-like (IDH-wt), IDH-mutated astrocytoma-like (IDH-A) and oligodendroglioma-like (IDH-O) and a neuronal-like (NL) phenotypes, respectively

Fig. 2

Gene set analysis associates the E- and M-subtypes with previous glioma expression and methylation signatures (see Additional file 1: Table S6 for details). The expression and methylation levels of the signature sets are shown as bar-code profiles where each bar refers to one sample. Correlation plots between expression and methylation levels in GSZ-scale reflect predominantly repressive effects of promoter methylation on the expression of the downstream genes (right part)

Fig. 3

Gene set analysis of functional and epigenetic signatures: a Bar-code profiles of expression and methylation levels of functional and epigenetic signatures and the correlation plots of subtype averaged values (see legend of Fig. 2). b Schematic overview about the basic functional, genetic and glioma characteristics extracted from the gene-signature analysis

Fig. 4

Cell type, micro-environmental immune cell and treatment-resistance characteristics. a Heatmaps of expression and methylation levels of single-cell signatures taken from [59] reveal subtype-specific activation of astrocyte-, oligodendrocyte- and stem cell-like characteristics. b Digital immune cell-type decomposition of glioma transcriptomes using CIBERSORT [46] (see Fig. S21 for the full set of cells considered) on sample (above) and mean subtype levels for selected leukocyte cells across the expression subtypes. c The boxplots of expression and methylation levels of a transcriptomic drug and radiation resistance signature containing 50 genes [54] suggest largest resistance effects in E3 and E1. Expression and methylation levels of the subgroups anti-correlate (right part)

Fig. 5

Schematic summary: a The major glioma subtypes arise after specific genetic hits. The tumor phenotypes are then shaped by the tumor microenvironment (TME), its cell composition, epigenetics and additional genetic defects. Different methylation patterns develop in a subtype specific fashion upon tumor progression (left part). On a cellular level, astrocyte-like and oligodendrocyte-like gliomas are both primarily composed of proliferating stem cells, oligodendrocytes and astrocytes, however in different amounts, which associates with different immune cell compositions in the TME and metabolic expression signatures, which partly are affected by methylation effects. b Phenotypic trees provide similarity relations between the expression and methylation subtypes (top), which were simplified as one-dimensional sequences of subtypes and associated with selected transcriptional programs, methylation patterns and prognosis (bottom)