Comparative molecular characterization of typical and exceptional responders in glioblastoma

Abstract

Glioblastoma (GBM) is the most common and the deadliest type of primary brain tumor, with a median survival time of only 15 months despite aggressive treatment. Although most patients have an extremely poor prognosis, a relatively small number of patients survive far beyond the median survival time. Investigation of these exceptional responders has sparked a great deal of interest and is becoming an important focus in the field of cancer research. To investigate the molecular differences between typical and exceptional responders in GBM, comparative analyses of somatic mutations, copy number, methylation, and gene expression datasets from The Cancer Genome Atlas were performed, and the results of these analyses were integrated via gene ontology and pathway analyses to assess the functional significance of the differential aberrations. Less severe copy number loss of CDKN2A, lower expression of CXCL8, and FLG mutations are all associated with an exceptional response. Typical responders are characterized by upregulation of NF-κB signaling and of pro-inflammatory cytokines, while exceptional responders are characterized by upregulation of Alzheimer's and Parkinson's disease pathways as well as of genes involved in synaptic transmission. The upregulated pathways and processes in typical responders are consistently associated with more aggressive tumor phenotypes, while those in the exceptional responders suggest a retained ability in tumor cells to undergo cell death in response to treatment. With the upcoming launch of the National Cancer Institute's Exceptional Responders Initiative, similar studies with much larger sample sizes will likely become possible, hopefully providing even more insight into the molecular differences between typical and exceptional responders.

Keywords: TCGA; exceptional responders; glioblastoma; integrative analysis; survival analysis.

Figure 1. Survival curve for TCGA GBM dataset

This curve includes the 408 TCGA GBM patients that met the inclusion criteria. The curve is characterized by a steep drop off centered around the median of 345 days, with a relatively small number of patients surviving beyond approximately 2.5 years. Typical responders are labeled in blue and exceptional responders are labeled in green.

Figure 2. Copy number alterations in typical and exceptional responders relative to normal

Mean log₂ ratios for typical (blue) and exceptional (green) responders are shown. (A) Mean log₂ ratios assessed at approximately 40,000 probes genome-wide, excluding sex chromosomes. The most prominent alterations are gains in chromosome 7 and losses in chromosome 9p and 10. Peaks tend to be of a greater magnitude in the typical response group. (B) Mean log₂ ratios in regions that include differential copy number alterations between typical and exceptional responders. Both groups are characterized by gains in 7p11.2 and losses in 9p21.2 and 9p21.3, but in both cases the magnitude is greater in typical responders. Genes in bold (VSTM2A, VSTM2A-OT1, and CDKN2A-AS1) have differential mean log₂ ratios that reach statistical significance.

Figure 3. Differential methylation patterns between typical and exceptional responders

Typical responders are shown in blue, exceptional in green, and normal in grey. (A) Modified volcano plot of significantly differentially methylated CpG sites between typical and exceptional responders. Each axis is skewed to reflect the cutoffs made to assess significance (p > 0.05 and ∆β > 0.2). Sites with a lower degree of methylation in typical responders are shown in blue and sites with a lower degree of methylation in exceptional responders are shown in green. Sites with the largest ∆β values and smallest p values are labeled with their associated gene name. (B) Histograms of β values in normal glial cells and each response group. The response group histograms include mean β values for the 45 CpG sites with ∆β values larger than 0.2, and the normal histogram includes β values for 41 of those sites (the remaining 4 sites were not assessed in the normal arrays). The distribution of β values in typical responders closely resembles the distribution for normal glial cells, while the exceptional responders are characterized by a shift towards larger β values. (C) Kolmogorov-Smirnov (KS) tests and cumulative distribution plots of β values. KS tests indicate that the distribution of β values for the CpG sites with ∆β > 0.2 is significantly different from both the typical and normal distributions (p < 0.0001). There is no difference between the distributions for the typical and normal groups. Cumulative distribution plots are shown for each of the three groups, indicating a clear shift in exceptional responders toward higher β values.