A Deep Learning-Based Framework for Supporting Clinical Diagnosis of Glioblastoma Subtypes

被引:13
作者
Munquad, Sana [1 ]
Si, Tapas [2 ]
Mallik, Saurav [3 ]
Das, Asim Bikas [1 ]
Zhao, Zhongming [3 ,4 ,5 ]
机构
[1] Natl Inst Technol Warangal, Dept Biotechnol, Warangal, India
[2] Bankura Unnayani Inst Engn, Dept Comp Sci & Engn, Bankura, India
[3] Univ Texas Hlth Sci Ctr Houston, Ctr Precis Hlth, Sch Biomed Informat, Houston, TX 77030 USA
[4] Univ Texas Hlth Sci Ctr Houston, Human Genet Ctr, Sch Publ Hlth, Houston, TX 77030 USA
[5] Univ Texas Hlth Sci Ctr Houston, McGovern Med Sch, Dept Pathol & Lab Med, Houston, TX 77030 USA
关键词
deep learning; glioblastoma multiforme; biomarkers; co-expression gene module; machine learning; DNA METHYLATION; GENE-EXPRESSION; WEB SERVER; GLIOMA; CANCER; MICROARRAY;
D O I
10.3389/fgene.2022.855420
中图分类号
Q3 [遗传学];
学科分类号
071007 ; 090102 ;
摘要
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.
引用
收藏
页数:15
相关论文
共 70 条
[1]   Gap junctions and cancer: communicating for 50 years [J].
Aasen, Trond ;
Mesnil, Marc ;
Naus, Christian C. ;
Lampe, Paul D. ;
Laird, Dale W. .
NATURE REVIEWS CANCER, 2016, 16 (12) :775-788
[2]  
Afifi S, 2017, IEEE ENG MED BIO, P270, DOI 10.1109/EMBC.2017.8036814
[3]   DNA methylation of distal regulatory sites characterizes dysregulation of cancer genes [J].
Aran, Dvir ;
Sabato, Sivan ;
Hellman, Asaf .
GENOME BIOLOGY, 2013, 14 (03)
[4]   A Survey and Comparative Study of Statistical Tests for Identifying Differential Expression from Microarray Data [J].
Bandyopadhyay, Sanghamitra ;
Mallik, Saurav ;
Mukhopadhyay, Anirban .
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS, 2014, 11 (01) :95-115
[5]   Epigenetic reprogramming of cell identity: lessons from development for regenerative medicine [J].
Basu, Amitava ;
Tiwari, Vijay K. .
CLINICAL EPIGENETICS, 2021, 13 (01)
[6]   Sox2 Promotes Malignancy in Glioblastoma by Regulating Plasticity and Astrocytic Differentiation [J].
Berezovsky, Artem D. ;
Poisson, Laila M. ;
Cherba, David ;
Webb, Craig P. ;
Transou, Andrea D. ;
Lemke, Nancy W. ;
Hong, Xin ;
Hasselbach, Laura A. ;
Irtenkauf, Susan M. ;
Mikkelsen, Tom ;
deCarvalho, Ana C. .
NEOPLASIA, 2014, 16 (03) :193-206.e25
[7]   RAB38 Facilitates Energy Metabolism and Counteracts Cell Death in Glioblastoma Cells [J].
Bianchetti, Elena ;
Bates, Sierra J. ;
Nguyen, Trang T. T. ;
Siegelin, Markus D. ;
Roth, Kevin A. .
CELLS, 2021, 10 (07)
[8]   Age-Specific Signatures of Glioblastoma at the Genomic, Genetic, and Epigenetic Levels [J].
Bozdag, Serdar ;
Li, Aiguo ;
Riddick, Gregory ;
Kotliarov, Yuri ;
Baysan, Mehmet ;
Iwamoto, Fabio M. ;
Cam, Margaret C. ;
Kotliarova, Svetlana ;
Fine, Howard A. .
PLOS ONE, 2013, 8 (04)
[9]   The Somatic Genomic Landscape of Glioblastoma [J].
Brennan, Cameron W. ;
Verhaak, Roel G. W. ;
McKenna, Aaron ;
Campos, Benito ;
Noushmehr, Houtan ;
Salama, Sofie R. ;
Zheng, Siyuan ;
Chakravarty, Debyani ;
Sanborn, J. Zachary ;
Berman, Samuel H. ;
Beroukhim, Rameen ;
Bernard, Brady ;
Wu, Chang-Jiun ;
Genovese, Giannicola ;
Shmulevich, Ilya ;
Barnholtz-Sloan, Jill ;
Zou, Lihua ;
Vegesna, Rahulsimham ;
Shukla, Sachet A. ;
Ciriello, Giovanni ;
Yung, W. K. ;
Zhang, Wei ;
Sougnez, Carrie ;
Mikkelsen, Tom ;
Aldape, Kenneth ;
Bigner, Darell D. ;
Van Meir, Erwin G. ;
Prados, Michael ;
Sloan, Andrew ;
Black, Keith L. ;
Eschbacher, Jennifer ;
Finocchiaro, Gaetano ;
Friedman, William ;
Andrews, David W. ;
Guha, Abhijit ;
Iacocca, Mary ;
O'Neill, Brian P. ;
Foltz, Greg ;
Myers, Jerome ;
Weisenberger, Daniel J. ;
Penny, Robert ;
Kucherlapati, Raju ;
Perou, Charles M. ;
Hayes, D. Neil ;
Gibbs, Richard ;
Marra, Marco ;
Mills, Gordon B. ;
Lander, Eric ;
Spellman, Paul ;
Wilson, Richard .
CELL, 2013, 155 (02) :462-477
[10]   Harnessing the Activation of RIG-I Like Receptors to Inhibit Glioblastoma Tumorigenesis [J].
Bufalieri, Francesca ;
Basili, Irene ;
Di Marcotullio, Lucia ;
Infante, Paola .
FRONTIERS IN MOLECULAR NEUROSCIENCE, 2021, 14