A Deep Learning–Based Framework for Supporting Clinical Diagnosis of Glioblastoma Subtypes
Open Access
- 28 March 2022
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Genetics
- Vol. 13, 855420
Abstract
Understanding molecular features that facilitate aggressive phenotypes in glioblastoma multiforme (GBM) remains a major clinical challenge. Accurate diagnosis of GBM subtypes, namely classical, proneural, and mesenchymal, and identification of specific molecular features are crucial for clinicians for systematic treatment. We develop a biologically interpretable and highly efficient deep learning framework based on a convolutional neural network for subtype identification. The classifiers were generated from high-throughput data of different molecular levels, i.e., transcriptome and methylome. Furthermore, an integrated subsystem of transcriptome and methylome data was also used to build the biologically relevant model. Our results show that deep learning model outperforms the traditional machine learning algorithms. Furthermore, to evaluate the biological and clinical applicability of the classification, we performed weighted gene correlation network analysis, gene set enrichment, and survival analysis of the feature genes. We identified the genotype–phenotype relationship of GBM subtypes and the subtype-specific predictive biomarkers for potential diagnosis and treatment.Keywords
Funding Information
- Cancer Prevention and Research Institute of Texas
This publication has 68 references indexed in Scilit:
- Age-Specific Signatures of Glioblastoma at the Genomic, Genetic, and Epigenetic LevelsPLOS ONE, 2013
- Deregulated Signaling Pathways in Glioblastoma Multiforme: Molecular Mechanisms and Therapeutic TargetsCancer Investigation, 2012
- Efficient Feature Selection and Multiclass Classification with Integrated Instance and Model Based LearningEvolutionary Bioinformatics, 2012
- Interobserver variation of the histopathological diagnosis in clinical trials on glioma: a clinician’s perspectiveActa Neuropathologica, 2010
- Widespread and tissue specific age-related DNA methylation changes in miceGenome Research, 2010
- Integrated Genomic Analysis Identifies Clinically Relevant Subtypes of Glioblastoma Characterized by Abnormalities in PDGFRA, IDH1, EGFR, and NF1Cancer Cell, 2010
- Identification of Survival Genes in Human Glioblastoma Cells by Small Interfering RNA ScreeningMolecular Pharmacology, 2009
- Cancer genome sequencing: a reviewHuman Molecular Genetics, 2009
- WGCNA: an R package for weighted correlation network analysisBMC Bioinformatics, 2008
- Characteristics of tumor-associated endothelial cells derived from glioblastoma multiformeNeurosurgical Focus, 2006