SSIG: Single-Sample Information Gain Model for Integrating Multi-Omics Data to Identify Cancer Subtypes

ZHANG Yuanyuan; WANG Ziqi; WANG Shudong; KOU Chuanhua

doi:10.1049/cje.2021.01.011

Volume 30 Issue 2

Apr. 2021

Turn off MathJax

Article Contents

Article Navigation > Chinese Journal of Electronics > 2021 > 30(2): 303-312

ZHANG Yuanyuan, WANG Ziqi, WANG Shudong, et al., “SSIG: Single-Sample Information Gain Model for Integrating Multi-Omics Data to Identify Cancer Subtypes,” Chinese Journal of Electronics, vol. 30, no. 2, pp. 303-312, 2021, doi: 10.1049/cje.2021.01.011

Citation:

ZHANG Yuanyuan, WANG Ziqi, WANG Shudong, et al., “SSIG: Single-Sample Information Gain Model for Integrating Multi-Omics Data to Identify Cancer Subtypes,” Chinese Journal of Electronics, vol. 30, no. 2, pp. 303-312, 2021, doi: 10.1049/cje.2021.01.011

Citation:

PDF( 16749 KB)

SSIG: Single-Sample Information Gain Model for Integrating Multi-Omics Data to Identify Cancer Subtypes

doi: 10.1049/cje.2021.01.011

1.
School of Information and Control Engineering, Qingdao University of Technology, Qingdao 266520, China
2.
College of Computer Science and Technology, China University of Petroleum(East China), Qingdao 266580, China

Funds:

the National Natural Science Foundation of China 61902430

the National Natural Science Foundation of China 61873281

Natural Science Foundation of Shandong Province ZR2018PF004

More Information

Author Bio:
ZHANG Yuanyuan   received the B.S. and M.S. degrees from the Shandong University of Science and Technology, in 2008 and 2011, respectively, and the Ph.D. degree from Xidian University, Xi'an, China, in 2016. She is currently an associate professor at the School of Information and Control Engineering, Qingdao University of Technology. Her research interests include computational bioinformatics, complex networks, and network representation learning. (Email: yyzhang1217@163.com)

WANG Ziqi   is currently pursuing the master’s degree with the Qingdao University of Technology. Her current research interests include machine learning and network embedding

WANG Shudong   received the graduation degree from the Huazhong University of Science and Technology, Wuhan, in 2004. She is currently a professor at the China University of Petroleum, Qingdao, China. Her current research interests include biological computing and software engineering

KOU Chuanhua   is currently pursuing the master's degree with the Qingdao University of Technology. His current research interests include the mining of biological data
Received Date: 2020-08-21
Accepted Date: 2020-12-28
Publish Date: 2021-03-01

Abstract

Abstract

Different living environments of cancer samples lead to different molecular mechanisms of cancer development, which in turn leads to different cancer subtypes. How to identify cancer subtypes is a key issue for the realization of precision medicine. With the development of high-throughput technologies, multi-omics data which can better understand different causes of cancer have emerged. However, the current methods of analyzing cancer subtypes using multi-omics data is mostly derived from population cancer sample data and ignores the differences between different cancer samples. Therefore, the joint analysis of multi-omics based on a single sample may reveal more information about the differences between individual cancers. A strategy for identifying cancer subtypes is proposed based on Single-sample information gain (SSIG) which construct sample feature matrix by considering the heterogeneity of sample. Applying this strategy to current popular subtype identification methods, cancer subtypes can be identified more accurately and the mechanism of cancer can be found from the perspective of a single sample. By comparing different methods in different clustering measure, and using survival analysis, it is shown that SSIG is more suitable for cancer subtype identification than the original multi-omics data, and it is easier to mine the cancer subtype classification mechanism hidden behind the data.
- Cancer subtype,
- Multi-omics integration,
- Single-sample information gain

FullText(HTML)

References(23)

References

[1]	Prasad V, Fojo T and Brada M, "Precision oncology: Origins, optimism, and potential", The Lancet Oncology, Vol. 17, No. 2, pp. 81-86, 2016. doi: 10.1016/S1470-2045(15)00620-8
[2]	Akbani R, Ng KS, Werner HM, et al., "A pan-cancer proteomic analysis of the cancer genome atlas (TCGA) project", Cancer research, Vol. 74, No. 19, pp. 4262-4262, 2014. http://cancerres.aacrjournals.org/content/74/19_Supplement/4262
[3]	Zhao J, Xie XJ, Xu X, et al., "Multi-view learning overview: Recent progress and new challenges", Inform Fusion, Vol. 38, No. 2, pp. 43-54, 2017. http://www.sciencedirect.com/science/article/pii/S1566253516302032
[4]	Rappoport N and Shamir R, "NEMO: Cancer subtyping by integration of partial multi-omic data", Bioinformatics, Vol. 35, No. 18, pp. 3348-3356, 2019. doi: 10.1093/bioinformatics/btz058
[5]	Suzan A, Sorin D and Nguyen. T, "Integrated cancer subtyping using heterogeneous genome-scale molecular datasets", Pac Symp Biocomput, Vol. 38, No. 25, pp. 551-562, 2020. http://www.researchgate.net/publication/338301137_Integrated_Cancer_Subtyping_using_Heterogeneous_Genome-Scale_Molecular_Datasets
[6]	Rappoport N and Shamir R, "Multi-omic and multi-view clustering algorithms: Review and cancer benchmark", Nucleic Acids Research, Vol. 47, No. 2, pp: 1044-1044, 2019. doi: 10.1093/nar/gky1226
[7]	Wang B, Mezlini AM, Demir F, et al., "Similarity network fusion for aggregating data types on a genomic scale", Nature methods, Vol. 11, No. 3, pp: 333-337, 2014. doi: 10.1038/nmeth.2810
[8]	Ma T and Zhang A, "Affinity network fusion and semi-supervised learning for cancer patient clustering", Methods, Vol. 145, No. 8, pp. 16-24, 2018. http://europepmc.org/abstract/MED/29807109
[9]	Guo Y, Zheng J, Shang X, et al., "A similarity regression fusion model for integrating multi-omics data to identify cancer subtypes", Genes, Vol. 9, No. 7, pp. 314-322, 2018. doi: 10.3390/genes9070314
[10]	Jiang L, Xiao Y, Ding Y, et al., "Discovering cancer subtypes via an accurate fusion strategy on multiple profile data", Frontiers in Genetics, Vol. 20, No. 5, pp. 10-20, 2019. http://www.ncbi.nlm.nih.gov/pubmed/30804977
[11]	Nguyen T, Tagett R, Diaz D, et al., "A novel approach for data integration and disease subtyping", Genome Research, Vol. 27, No. 12, pp. 2025-2039, 2017. doi: 10.1101/gr.215129.116
[12]	Liu XP, Wang YT, Ji HB, et al., "Personalized characterization of diseases using sample-Specific networks", Nucleic Acids Research, Vol. 44, No. 22, pp. 164-164, 2016. doi: 10.1093/nar/gkw772
[13]	Rappoport N and Shamir R, "Multi-omic and multi-view clustering algorithms: Review and cancer benchmark", Nucleic Acids Research, Vol. 47, No. 2, pp. 1044-1044, 2019. doi: 10.1093/nar/gky1226
[14]	Duan R, Gao L, Xu H, et al., "CEPICS: A comparison and evaluation platform for integration methods in cancer subtyping", Frontiers in Genetics, Vol. 19, No. 10, pp. 966-978, 2019. http://www.ncbi.nlm.nih.gov/pubmed/31649733
[15]	Cancer Genome Atlas Research N, Weinstein JN, Collisson EA, et al., "The cancer genome atlas pan-cancer analysis project", Nature Genetics, Vol. 45, No. 10, pp. 1113-1120, 2013. doi: 10.1038/ng.2764
[16]	Hidalgo SJT and Ma SG, "Clustering multilayer omics data using muncut", BMC Genomics, Vol. 19, No. 1, pp. 198-198, 2018. doi: 10.1186/s12864-018-4580-6
[17]	Peter J. Rousseeuw, "Silhouettes: A graphical aid to the interpretation and validation of cluster analysis", Journal of Computational and Applied Mathematics, Vol. 20, No. 1, pp. 53-65, 1987. http://www.sciencedirect.com/science/article/pii/0377042787901257
[18]	Estevez PA, Tesmer M, Perez CA, et al., "Normalized mutual information feature selection", IEEE Transactions on Neural Networks, Vol. 20, No. 2, pp. 189-201, 2009. doi: 10.1109/TNN.2008.2005601
[19]	Steinley D, "Properties of the Hubert-Arabie adjusted Rand index", Psychological Methods, Vol. 9, No. 3, pp. 386-396, 2004. doi: 10.1037/1082-989X.9.3.386
[20]	Richardson M, Garner P and Donegan S, "Cluster randomised trials in cochrane reviews: Evaluation of methodological and reporting practice", PloS one, Vol. 11, No. 3, pp. 53-65, 2016. http://europepmc.org/articles/PMC4794236/
[21]	Zhang SL, Wang X, Li ZM, et al., "Score for the overall survival probability of patients with first-diagnosed distantly metastatic cervical cancer: A novel nomogram-based risk assessment system", Frontiers in Oncology, Vol. 5, No. 9, pp. 1106-1106, 2019. http://www.ncbi.nlm.nih.gov/pubmed/31750238
[22]	Henshall SM, Afar DE, Hiller J, et al., "Survival analysis of genome-wide gene expression profiles of prostate cancers identifies new prognostic targets of disease relapse", Cancer Research, Vol. 63, No. 14, pp. 4196-4203, 2003. http://carcin.oxfordjournals.org/cgi/ijlink?linkType=ABST&journalCode=canres&resid=63/14/4196
[23]	Shi Q, Zhang C, Peng M, et al., "Pattern fusion analysis by adaptive alignment of multiple heterogeneous omics data", Bioinformatics, Vol. 33, No. 17, pp. 2706-2714, 2017. doi: 10.1093/bioinformatics/btx176