文献类型：期刊文献

英文题名：Subtype-WGME enables whole-genome-wide multi-omics cancer subtyping

作者：Yang, Hai[1];Zhao, Liang[1];Li, Dongdong[1];An, Congcong[1];Fang, Xiaoyang[2];Chen, Yiwen[3];Liu, Jingping[1];Xiao, Ting[1];Wang, Zhe[1]

机构：[1]East China Univ Sci & Technol, Dept Comp Sci & Engn, Shanghai 200237, Peoples R China;[2]Cornell Univ, Cornell Tech, New York, NY 14853 USA;[3]Natl Univ Singapore, Ctr Continuing & Lifelong Educ, Singapore 119077, Singapore

年份：2024

卷号：4

期号：6

外文期刊名：CELL REPORTS METHODS

收录：WOS:【ESCI(收录号:WOS:001259360700001)】；

基金：This work is supported by the National Key Research and Development Program of China under grant no. 2022YFB3203500, the Natural Science Foundation of China under grant nos. 61902126 and 62076094, the Shanghai Science and Technology Program's "Distributed and Generative FewShot Algorithm and Theory Research"under grant no. 20511100600, and the Shanghai Science and Technology Program's "Federated-Based Cross-Domain and Cross-Task Incremental Learning"under grant no. 21511100800.

语种：英文

摘要：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 wholegenome-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.