The IDH1 Mutation-Induced Oncometabolite, 2-Hydroxyglutarate, May Affect DNA Methylation and Expression of PD-L1 in Gliomas

Abstract

Background: Malignant gliomas are heterogeneous brain tumors with the potential for aggressive disease progression, as influenced by suppressive immunoediting. Given the success and enhanced potential of immune-checkpoint inhibitors in immunotherapy, we focused on the connections between genetic alterations affected by IDH1 mutations and immunological landscape changes and PDL-1 expression in gliomas. Methods: Paired surgically resected tumors from lower-grade gliomas (LGGs) and glioblastomas (GBM) were investigated, and a genetic analysis of patients' primary tumor samples culled from TCGA datasets was performed. Results: The results demonstrate that when compared with IDH1-mutant tumors, IDH1 wildtype tumors represent an immunosuppression landscape and elevated levels of PD-L1 expression. DNA hypo-methylation of the PD-L1 gene, as well as high gene and protein expressions, were observed in the wildtype tumors. We also found that quantitative levels of IDH1 mutant proteins were positively associated with recurrence-free survival (RFS). A key product of the IDH1 mutation (2-hydroxyglutarate) was found to transiently increase DNA methylation and suppress PD-L1 expression. Conclusions: IDH1 mutations impact the immune landscape of gliomas by affecting immune infiltrations and manipulating checkpoint ligand PD-L1 expression. Applications of immune checkpoint inhibitors may be beneficial for chemoradiation-insensitive IDH1-wildtype gliomas.

Keywords: 2-hydroxyglutarate; DNA methylation; IDH mutation; PD-L1; gliomas; immune checkpoint.

Figure 1

The immunological gene profile in primary LGG subgroups and GBMs with or without IDH1 mutations. (A) Hierarchical cluster of cancer immune-related genes among three LGG subgroups (left panel) and GBMs with or without an IDH1 mutation (right panel). RNA-Seq data from TCGA were analyzed and 750 cancer immune-associated genes (Cesano, 2015) were used to perform the hierarchical clustering according to the nCounter® PanCancer Immune Profiling Panel. These genes were imported to log2 normalization and centered by the mean gene expression value. (B,C) Differences in local immune infiltrates and cytolytic activity in the tumors was based on the terminology and data analysis used in a previous report (Rooney et al., 2015) for the three subgroups of LGGs and GBMs with or without the mutation. These tumor-related, local immune cell subtype/process-associated genes were clustered using Pearson's correlation among the subtypes. The enrichment scores (Z-scores) of each subgroup were plotted. The LGG patients were subdivided according to IDH1 mutation status and complete deletion of chromosome 1p/19q. Asterisks (^*) indicate a significant difference found between the IDH1wildtype and -mutant tumors. We used mixed-effects analysis of variance (ANOVA) to screen across 14 cell types to assess differences in response among tumor types. The subject was modeled as a random effect nested within tumor type, and tumor type and cell type were both modeled as fixed effects. We specifically compared the IDH-WT tumor type mean to the average of the two IDH-mutated tumor type means within each cell type and assessed FDR-adjusted P-values at FDR = 1%.

Figure 2

There were fewer immune-suppressive cell infiltrates in tumors with the IDH1 mutation compared with the IDH1 wildtype in primary and recurrent/secondary tumors. (A,B) Identification of the IDH1 mutation by DNA sequencing and antibody staining. A representative result of the IDH1 mutation, as determined by the anti-IDH1 mutation (R132H)-specific antibody and DNA sequence. (C–F) The immune infiltrates between patients with and without IDH1 mutation in primary LGG (pLGG) and GBM (pGBM) for CD4+, CD8+, and Foxp3+ T cells and CD68 and CD163 macrophages. (G–J) The immune infiltrates differ between patients with and without IDH1 mutations in recurrent LGG (rLGG) and GBM (rGBM) for the same markers. A total of 35 pairs of LGGs and 15 pairs of GBMs (pre- and post-tumor progression, as described in Table S2) were analyzed by immunohistochemistry staining for T cell subset makers (CD4, CD8, and Foxp3+ cells) and macrophage markers (CD68 and CD163). The immune infiltrates in the tumors were counted in three large regions. In each region, a mean of 10 consecutive high-power fields was recorded by experienced pathologists who were blinded to the patients' clinical information. The average counts of the three regions were used for the final report. The difference among the three groups was analyzed using one-way ANOVA. Any difference among group means and post hoc pairwise comparisons among tumor types were performed using FDR-adjusted P-values.

Figure 3

Elevated levels of a mutant IDH1 protein associated with clinical outcomes in gliomas. (A,B) Recurrent tumors, including LGG-LGG and LGG-GBM, were evaluated for correlations between mutant IDH1 protein changes (before and after recurrence) and RFS/OS. (C,D) The data only show recurrent LGG-GBM tumors. Quantitation of mutant IDH1 protein expression in tumor samples was performed using Image Plus Premier 9.1 software. The relative values of the mutant protein in each tumor are the mean density of ten 20× magnification fields. The IDH1 increase was the difference between recurrent and primary tumors featuring the IDH1 mutant protein. We used linear regression to estimate linear trend lines and R2 to test the strength of the association.

Figure 4

The association between PD-L1 gene expression (PD-L1) and OS in gliomas and wildtype tumors expressed a higher level of PD-L1. (A) The PD-L1 expression is inversely correlated with OS in pLGGs; (B) no similar trend was found in pGBMs. The RNAseq data of 282 primary LGGs and 151 primary GBMs with IDH mutation status and patients' OS culled from TCGA were analyzed. Median values were used as a cut-off point in each comparison. The Kaplan–Meier survival curves and the log-rank test were used to compare the groups in terms of OS and hazard ratios (HRs). (C,D) PD-L1 gene and PD-L1 expression among three LGG subgroups, as well as GBM with (WT) or without (M) IDH mutation. (E,F) IHC staining of PD-L1. Surgically resected tumors of mutant (n = 13) or wildtype (n = 14) LGGs were stained with a PD-L1 antibody; the quantitation of PD-L1 was analyzed using Image Plus Premier 9.1 software. (G) The PD-L1 expression on primary glioma lines; the PD-L1 expression on these cell lines was determined by FACS analysis and positivity was calculated using the isotype as a control. The difference between the two groups was analyzed using the Mann–Whitney U-test.

Figure 5

The differential DNA methylation of PD-L1 between IDH1 mutant and wildtype tumors in primary gliomas. (A) Hierarchical cluster of DNA methylation (cg15837913, cg19724470) measured by the β-values between IDH1 mutant and wildtype tumors is shown. (B,C) Quantitative β-values in different subgroups of primary gliomas. DNA methylation and IDH mutation/1p/19q codeletion information of primary LGG and GBM patients were derived from a TCGA Human Methylation 450k Array, as well as using the supplementary data from a previous publication (Suzuki et al., 2015). The β-values of each methylation probe were already offset by −0.5. (D) Adding 2-HG in vitro increased the DNA methylations of PD-L1. U87, an IDH wildtype, and a PD-L1-positive GBM line was cultured in medium containing indicated concentrations of 2HG, and the DNA was isolated at 24 and 48 h, respectively; the levels of methylation at baseline and 24 h were determined by pyrosequencing. (E,F) Adding 2HG transiently reduced gene (24 h) and protein (48 h) expression of PD-L1. The same cells described in (D) were also prepared for mRNA-qPCR and FACS analysis, and the experiments were repeated three times. The difference was determined using paired t-tests.