Rapid, reliable, and reproducible molecular sub-grouping of clinical medulloblastoma samples

Abstract

The diagnosis of medulloblastoma likely encompasses several distinct entities, with recent evidence for the existence of at least four unique molecular subgroups that exhibit distinct genetic, transcriptional, demographic, and clinical features. Assignment of molecular subgroup through routine profiling of high-quality RNA on expression microarrays is likely impractical in the clinical setting. The planning and execution of medulloblastoma clinical trials that stratify by subgroup, or which are targeted to a specific subgroup requires technologies that can be economically, rapidly, reliably, and reproducibly applied to formalin-fixed paraffin embedded (FFPE) specimens. In the current study, we have developed an assay that accurately measures the expression level of 22 medulloblastoma subgroup-specific signature genes (CodeSet) using nanoString nCounter Technology. Comparison of the nanoString assay with Affymetrix expression array data on a training series of 101 medulloblastomas of known subgroup demonstrated a high concordance (Pearson correlation r = 0.86). The assay was validated on a second set of 130 non-overlapping medulloblastomas of known subgroup, correctly assigning 98% (127/130) of tumors to the appropriate subgroup. Reproducibility was demonstrated by repeating the assay in three independent laboratories in Canada, the United States, and Switzerland. Finally, the nanoString assay could confidently predict subgroup in 88% of recent FFPE cases, of which 100% had accurate subgroup assignment. We present an assay based on nanoString technology that is capable of rapidly, reliably, and reproducibly assigning clinical FFPE medulloblastoma samples to their molecular subgroup, and which is highly suited for future medulloblastoma clinical trials.

Fig. 1

A nanoString CodeSet for medulloblastoma subgroup assignment. a Expression heatmaps for 22 medulloblastoma signature genes in a series of 101 primary medulloblastomas (training series) profiled by both the nanoString nCounter System (upper panel) and by Affymetrix exon array (lower panel). The 22 signature genes comprise the nanoString CodeSet used throughout the study. b Pearson correlation analysis of nanoString expression data versus Affymetrix expression data for the 22 signature genes shown in a across the training series of 101 medulloblastomas. r = Pearson correlation. c Virtual heatmap depicting results of cross-validation analysis for multiple class prediction algorithms evaluated on the training series for medulloblastoma subgroup prediction accuracy. Samples are ordered horizontally according to their known subgroup affiliation (‘Actual’). Results represent the consensus subgroup assignment following 10,000 iterations and discordant cases are labeled according to the subgroup in which they were erroneously classified. Samples labeled in grey represent those in which a single subgroup could not be reliably assigned. d Centroid plot for the nanoString CodeSet as determined by the PAM algorithm. Genes are grouped according to the subgroup for which they exhibit a positive centroid value

Fig. 2

Validation of nanoString assay on multiple published medulloblastoma cohorts with known subgroup affiliation. a–c Expression heatmaps of nanoString class-predicted medulloblastomas of known subgroup status as published by Remke et al. (a), Cho et al. [1] (b), and Kool et al. [6] (c). Samples were sorted according to subgroup prediction as determined by nanoString. nanoString predicted subgroup, known expression subgroup affiliation, and erroneously classified cases are marked above the heatmap. d Left chart Pie chart showing the known subgroup distribution of medulloblastomas from the three independent cohorts analyzed in a–c (n = 130) and the class-predicted subgroup assignments as determined by nanoString profiling. Misclassified cases are marked within each pie segment according to the subgroup in which they were erroneously classified. Right chart Pie chart showing the class prediction success rate (~98%, 127/130) for the validation series

Fig. 3

Cross-site validation of medulloblastoma classification using the nanoString CodeSet. a–c Forty-eight primary medulloblastomas of known subgroup affiliation were analyzed using the nanoString CodeSet at three independent facilities: Toronto, Canada (a), Miami, USA (b), and Geneva, Switzerland (c). Class prediction analysis of the data generated at the three independent nanoString facilities resulted in 100% sample classification accuracy. Heatmaps of the normalized nanoString data for the 48 cases are shown. d Scatterplot showing correlation of nanoString expression data generated in Toronto versus that generated at the two international validation sites (Miami, USA and Geneva, Switzerland). r = Pearson correlation

Fig. 4

Compatibility of nanoString classification assay with formalin-fixed paraffin embedded (FFPE) material from archival samples. a Plot of nanoString class prediction accuracy for all 280 validation samples according to PAM probability score. Vertical red line denotes threshold at which PAM classification becomes unreliable. b Plot of nanoString class prediction accuracy according to sample age of archival medulloblastomas stored as FFPE material (n = 84). Samples obtained within the past 8 years exhibit an accuracy of ≥95%, as demarcated by the red vertical line on the plot. Sample age range for the FFPE series was 1–33 years, with a median sample age of 10 years. c Heatmap of nanoString data showing class prediction results for FFPE cases ≤8 years of age confidently predicted by PAM (n = 28). 28/28 cases (100%) meeting the threshold were assigned to the correct subgroup. Samples were sorted according to subgroup prediction as determined by nanoString. d NanoString data for FFPE cases ≤8 years of age that failed to meet the PAM probability threshold for subgroup assignment (n = 4). 2/4 cases that failed to meet the PAM threshold, and were not assigned to the correct subgroup