Distinguishing Glioblastoma Subtypes by Methylation Signatures

Frontiers in Genetics

Yu-Hang Zhang¹  Hao Li²  Zhandong Li²  Lei Chen³  Xiaoyong Pan⁴  Yu-Dong Cai⁵  Dejing Liu⁶  Tao Huang⁶  Tao Zeng⁷ 

[1] Channing Division of Network Medicine, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, United States;College of Food Engineering, Jilin Engineering Normal University, Changchun, China;College of Information Engineering, Shanghai Maritime University, Shanghai, China;Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, and Key Laboratory of System Control and Information Processing, Ministry of Education of China, Shanghai, China;School of Life Sciences, Shanghai University, Shanghai, China;Shanghai Institute of Nutrition and Health, Shanghai Institutes for Biological Sciences, Chinese Academy of Sciences, Shanghai, China;Shanghai Research Center for Brain Science and Brain-Inspired Intelligence, Shanghai, China;

关键词: glioblastoma;    methylation;    signature;    subtype;    classification;   

DOI  :  10.3389/fgene.2020.604336

来源: DOAJ

【 摘 要 】

Glioblastoma, also called glioblastoma multiform (GBM), is the most aggressive cancer that initiates within the brain. GBM is produced in the central nervous system. Cancer cells in GBM are similar to stem cells. Several different schemes for GBM stratification exist. These schemes are based on intertumoral molecular heterogeneity, preoperative images, and integrated tumor characteristics. Although the formation of glioblastoma is remarkably related to gene methylation, GBM has been poorly classified by epigenetics. To classify glioblastoma subtypes on the basis of different degrees of genes’ methylation, we adopted several powerful machine learning algorithms to identify numerous methylation features (sites) associated with the classification of GBM. The features were first analyzed by an excellent feature selection method, Monte Carlo feature selection (MCFS), resulting in a feature list. Then, such list was fed into the incremental feature selection (IFS), incorporating one classification algorithm, to extract essential sites. These sites can be annotated onto coding genes, such as CXCR4, TBX18, SP5, and TMEM22, and enriched in relevant biological functions related to GBM classification (e.g., subtype-specific functions). Representative functions, such as nervous system development, intrinsic plasma membrane component, calcium ion binding, systemic lupus erythematosus, and alcoholism, are potential pathogenic functions that participate in the initiation and progression of glioblastoma and its subtypes. With these sites, an efficient model can be built to classify the subtypes of glioblastoma.

【 授权许可】

Unknown