Dataset Information

DNA methylation-based epigenetic signatures predict somatic genomic alterations in gliomas.

ABSTRACT: Molecular classification has improved diagnosis and treatment for patients with malignant gliomas. However, classification has relied on individual assays that are both costly and slow, leading to frequent delays in treatment. Here, we propose the use of DNA methylation, as an emerging clinical diagnostic platform, to classify gliomas based on major genomic alterations and provide insight into subtype characteristics. We show that using machine learning models, DNA methylation signatures can accurately predict somatic alterations and show improvement over existing classifiers. The established Unified Diagnostic Pipeline (UniD) we develop is rapid and cost-effective for genomic alterations and gene expression subtypes diagnostic at early clinical phase and improves over individual assays currently in clinical use. The significant relationship between genetic alteration and epigenetic signature indicates broad applicability of our approach to other malignancies.

SUBMITTER: Yang J

PROVIDER: S-EPMC9338285 | biostudies-literature | 2022 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

DNA methylation-based epigenetic signatures predict somatic genomic alterations in gliomas.

Yang Jie J Wang Qianghu Q Zhang Ze-Yan ZY Long Lihong L Ezhilarasan Ravesanker R Karp Jerome M JM Tsirigos Aristotelis A Snuderl Matija M Wiestler Benedikt B Wick Wolfgang W Miao Yinsen Y Huse Jason T JT Sulman Erik P EP

Nature communications 20220729 1

Molecular classification has improved diagnosis and treatment for patients with malignant gliomas. However, classification has relied on individual assays that are both costly and slow, leading to frequent delays in treatment. Here, we propose the use of DNA methylation, as an emerging clinical diagnostic platform, to classify gliomas based on major genomic alterations and provide insight into subtype characteristics. We show that using machine learning models, DNA methylation signatures can acc ...[more]

PMID: 35906213

Similar Datasets

Project description:BackgroundGlioma is the most common of all primary brain tumors with poor prognosis and high mortality. The 2016 World Health Organization classification of the tumors of central nervous system uses molecular parameters in addition to histology to redefine many tumor entities. The new classification scheme divides diffuse gliomas into low-grade glioma (LGG) and glioblastoma (GBM) as per histology. LGGs are further divided into isocitrate dehydrogenase (IDH) wild type or mutant, which is further classified into either oligodendroglioma that harbors 1p/19q codeletion or diffuse astrocytoma that has an intact 1p/19q loci but enriched for ATRX loss and TP53 mutation. GBMs are divided into IDH wild type that corresponds to primary or de novo GBMs and IDH mutant that corresponds to secondary or progressive GBMs. To make the 2016 WHO subtypes of diffuse gliomas more robust, we carried out Prediction Analysis of Microarrays (PAM) to develop DNA methylation signatures for these subtypes.ResultsIn this study, we applied PAM on a training set of diffuse gliomas derived from The Cancer Genome Atlas (TCGA) and identified DNA methylation signatures to classify LGG IDH wild type from LGG IDH mutant, LGG IDH mutant with 1p/19q codeletion from LGG IDH mutant with intact 1p/19q loci and GBM IDH wild type from GBM IDH mutant with an accuracy of 99-100%. The signatures were validated using the test set of diffuse glioma samples derived from TCGA with an accuracy of 96 to 99%. In addition, we also carried out additional validation of all three signatures using independent LGG and GBM cohorts. Further, the methylation signatures identified a fraction of samples as discordant, which were found to have molecular and clinical features typical of the subtype as identified by methylation signatures.ConclusionsThus, we identified methylation signatures that classified different subtypes of diffuse glioma accurately and propose that these signatures could complement 2016 WHO classification scheme of diffuse glioma.

Dataset Information

DNA methylation-based epigenetic signatures predict somatic genomic alterations in gliomas.

Publications

DNA methylation-based epigenetic signatures predict somatic genomic alterations in gliomas.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets