Subtype-WGME enables whole-genome-wide multi-omics cancer subtyping

Hai Yang; Liang Zhao; Dongdong Li; Congcong An; Xiaoyang Fang; Yiwen Chen; Jingping Liu; Ting Xiao; Zhe Wang

doi:10.1016/j.crmeth.2024.100781

Subtype-WGME enables whole-genome-wide multi-omics cancer subtyping

Cell Rep Methods. 2024 May 14:100781. doi: 10.1016/j.crmeth.2024.100781. Online ahead of print.

Authors

Hai Yang¹, Liang Zhao¹, Dongdong Li¹, Congcong An¹, Xiaoyang Fang², Yiwen Chen³, Jingping Liu¹, Ting Xiao¹, Zhe Wang⁴

Affiliations

¹ Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai 200237, China.
² Cornell Tech, Cornell University, New York, NY 14853, USA.
³ Center for Continuing and Lifelong Education, National University of Singapore, Singapore 119077, Singapore.
⁴ Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai 200237, China. Electronic address: wangzhe@ecust.edu.cn.

PMID: 38761803
DOI: 10.1016/j.crmeth.2024.100781

Abstract

We present an innovative strategy for integrating whole-genome-wide multi-omics data, which facilitates adaptive amalgamation by leveraging hidden layer features derived from high-dimensional omics data through a multi-task encoder. Empirical evaluations on eight benchmark cancer datasets substantiated that our proposed framework outstripped the comparative algorithms in cancer subtyping, delivering superior subtyping outcomes. Building upon these subtyping results, we establish a robust pipeline for identifying whole-genome-wide biomarkers, unearthing 195 significant biomarkers. Furthermore, we conduct an exhaustive analysis to assess the importance of each omic and non-coding region features at the whole-genome-wide level during cancer subtyping. Our investigation shows that both omics and non-coding region features substantially impact cancer development and survival prognosis. This study emphasizes the potential and practical implications of integrating genome-wide data in cancer research, demonstrating the potency of comprehensive genomic characterization. Additionally, our findings offer insightful perspectives for multi-omics analysis employing deep learning methodologies.

Keywords: CP: Cancer biology; CP: Systems biology; cancer biomarkers; deep learning methods; molecular subtyping; multi-omics data integration; whole-genome.