A Novel Attention-Mechanism Based Cox Survival Model by Exploiting Pan-Cancer Empirical Genomic Information

doi:10.3390/cells11091421

	A Novel Attention-Mechanism Based Cox Survival Model by Exploiting Pan-Cancer Empirical Genomic Information
	Meng, Xiangyu 1; Wang, Xun 1,2; Zhang, Xudong 1; Zhang, Chaogang 1; Zhang, Zhiyuan 1; Zhang, Kuijie 1; Wang, Shudong 1
	2022-05-01
发表期刊	CELLS
卷号	11 期号:9 页码:18
摘要	Cancer prognosis is an essential goal for early diagnosis, biomarker selection, and medical therapy. In the past decade, deep learning has successfully solved a variety of biomedical problems. However, due to the high dimensional limitation of human cancer transcriptome data and the small number of training samples, there is still no mature deep learning-based survival analysis model that can completely solve problems in the training process like overfitting and accurate prognosis. Given these problems, we introduced a novel framework called SAVAE-Cox for survival analysis of high-dimensional transcriptome data. This model adopts a novel attention mechanism and takes full advantage of the adversarial transfer learning strategy. We trained the model on 16 types of TCGA cancer RNA-seq data sets. Experiments show that our module outperformed state-of-the-art survival analysis models such as the Cox proportional hazard model (Cox-ph), Cox-lasso, Cox-ridge, Cox-nnet, and VAECox on the concordance index. In addition, we carry out some feature analysis experiments. Based on the experimental results, we concluded that our model is helpful for revealing cancer-related genes and biological functions.
关键词	deep learning survival analysis neural networks Cox regression cancer prognosis
DOI	10.3390/cells11091421
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61873280] ; National Natural Science Foundation of China[61873281] ; National Natural Science Foundation of China[61972416] ; Natural Science Foundation of Shandong Province[ZR2019MF012]
WOS研究方向	Cell Biology
WOS类目	Cell Biology
WOS记录号	WOS:000794779100001
出版者	MDPI
引用统计	被引频次：6[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/19543
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Wang, Shudong
作者单位	1.China Univ Petr, Coll Comp Sci & Technol, Qingdao Inst Software, Qingdao 266580, Peoples R China 2.Chinese Acad Sci, China High Performance Comp Res Ctr, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Meng, Xiangyu,Wang, Xun,Zhang, Xudong,et al. A Novel Attention-Mechanism Based Cox Survival Model by Exploiting Pan-Cancer Empirical Genomic Information[J]. CELLS,2022,11(9):18.
APA	Meng, Xiangyu.,Wang, Xun.,Zhang, Xudong.,Zhang, Chaogang.,Zhang, Zhiyuan.,...&Wang, Shudong.(2022).A Novel Attention-Mechanism Based Cox Survival Model by Exploiting Pan-Cancer Empirical Genomic Information.CELLS,11(9),18.
MLA	Meng, Xiangyu,et al."A Novel Attention-Mechanism Based Cox Survival Model by Exploiting Pan-Cancer Empirical Genomic Information".CELLS 11.9(2022):18.