Abstract
Medulloblastoma is a highly heterogeneous pediatric brain tumor with five molecular subtypes, Sonic Hedgehog TP53-mutant, Sonic Hedgehog TP53-wildtype, WNT, Group 3, and Group 4, defined by the World Health Organization. The current mechanism for classification into these molecular subtypes is through the use of immunostaining, methylation, and/or genetics. We surveyed the literature and identified a number of RNA-Seq and microarray datasets in order to develop, train, test, and validate a robust classifier to identify medulloblastoma molecular subtypes through the use of transcriptomic profiling data. We have developed a GPL-3 licensed R package and a Shiny Application to enable users to quickly and robustly classify medulloblastoma samples using transcriptomic data. The classifier utilizes a large composite microarray dataset (15 individual datasets), an individual microarray study, and an RNA-Seq dataset, using gene ratios instead of gene expression measures as features for the model. Discriminating features were identified using the limma R package and samples were classified using an unweighted mean of normalized scores. We utilized two training datasets and applied the classifier in 15 separate datasets. We observed a minimum accuracy of 85.71% in the smallest dataset and a maximum of 100% accuracy in four datasets with an overall median accuracy of 97.8% across the 15 datasets, with the majority of misclassification occurring between the heterogeneous Group 3 and Group 4 subtypes. We anticipate this medulloblastoma transcriptomic subtype classifier will be broadly applicable to the cancer research and clinical communities.
Highlights
Medulloblastoma (MB) is the most common of childhood brain tumors and accounts for nearly 20% of all pediatric CNS neoplasms [1]
This expression matrix was converted from a gene matrix to a gene expression ratios (GER) matrix and the limma R package was used to identify GERs specific to each subtype based on this dataset
We filtered to the 1,795 GERs and performed t-SNE analysis using the R package Rtsne using the following parameters: initial dimensions to be retained in the initial PCA step i.e. initial_dims set to 200, perplexity set to 10 and maximum iterations i.e. max_iter set to 500
Summary
Medulloblastoma (MB) is the most common of childhood brain tumors and accounts for nearly 20% of all pediatric CNS neoplasms [1]. In 2016, based on several profiling studies, five molecular subtypes of MB were recognized, Sonic HedgeHog (SHH) TP53 mutant, SHH TP53 wild-type, WNT, Group 3, and Group 4 [5,6] These subtypes were independently identified and demonstrated as concordant from multiple bioinformatic analyses of gene expression, comparative genomic hybridization, and DNA methylation microarray data: prediction analysis of microarrays [7], unsupervised two-way hierarchical clustering and bootstrap analysis [8], unsupervised SubMap [7], nonnegative matrix factorization [7,9]. We sought to develop a tool that can accurately predict the four major molecular subtypes of medulloblastoma, SHH, WNT, Group 3, and Group 4 using any type of transcriptomic data, including RNA-Seq, microarray data, or panel data from NanoString nCounter or HTG platforms. At the current time, we can only capture the four main subtypes of MB [11]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
