Network-Regularized Sparse Logistic Regression Models for Clinical Risk Prediction and Biomarker Discovery

doi:10.1109/TCBB.2016.2640303

CORC > 数学与系统科学研究院 > 中国科学院数学与系统科学研究院 > 应用数学研究所

	Network-Regularized Sparse Logistic Regression Models for Clinical Risk Prediction and Biomarker Discovery
	Min, Wenwen 1; Liu, Juan 1; Zhang, Shihua2,3
刊名	IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
	2018-05-01
卷号	15 期号:3 页码:944-953
关键词	Sparse logistic regression network-regularized penalty survival risk prediction feature selection
ISSN号	1545-5963
DOI	10.1109/TCBB.2016.2640303
英文摘要	Molecular profiling data (e.g., gene expression) has been used for clinical risk prediction and biomarker discovery. However, it is necessary to integrate other prior knowledge like biological pathways or gene interaction networks to improve the predictive ability and biological interpretability of biomarkers. Here, we first introduce a general regularized Logistic Regression (LR) framework with regularized term lambda parallel to omega parallel to(1) + eta omega(T) M omega, which can reduce to different penalties, including Lasso, elastic net, and network regularized terms with different M. This framework can be easily solved in a unified manner by a cyclic coordinate descent algorithm which can avoid inverse matrix operation and accelerate the computing speed. However, if those estimated omega(i) and omega(j), have opposite signs, then the traditional network-regularized penalty may not perform well. To address it, we introduce a novel network-regularized sparse LR model with a new penalty lambda parallel to omega parallel to(1) + eta vertical bar omega vertical bar(T) M vertical bar omega vertical bar to consider the difference between the absolute values of the coefficients. We develop two efficient algorithms to solve it. Finally, we test our methods and compare them with the related ones using simulated and real data to show their efficiency.
资助项目	National Science Foundation of China[61379092] ; National Science Foundation of China[61422309] ; National Science Foundation of China[61621003] ; National Science Foundation of China[11661141019] ; Strategic Priority Research Program of the Chinese Academy of Sciences (CAS)[XDB13040600] ; Outstanding Young Scientist Program of CAS ; Key Research Program of Frontier Sciences, CAS[QYZDB-SSW-SYS008] ; Natural Science Foundation of Jiangsu Province[BK20161249] ; Open Research Funds of the State Key Laboratory of Software Engineering (SKLSE) ; Key Laboratory of Random Complex Structures and Data Science, CAS
WOS研究方向	Biochemistry & Molecular Biology ; Computer Science ; Mathematics
语种	英语
出版者	IEEE COMPUTER SOC
WOS记录号	WOS:000434295100024
内容类型	期刊论文
源URL	[http://ir.amss.ac.cn/handle/2S8OKBNM/30457]
专题	应用数学研究所
通讯作者	Min, Wenwen
作者单位	1.Wuhan Univ, Sch Comp, State Key Lab Software Engn, Wuhan 430072, Hubei, Peoples R China 2.Chinese Acad Sci, Acad Math & Syst Sci, Natl Ctr Math & Interdisciplinary Sci, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Math Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Min, Wenwen,Liu, Juan,Zhang, Shihua. Network-Regularized Sparse Logistic Regression Models for Clinical Risk Prediction and Biomarker Discovery[J]. IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS,2018,15(3):944-953.
APA	Min, Wenwen,Liu, Juan,&Zhang, Shihua.(2018).Network-Regularized Sparse Logistic Regression Models for Clinical Risk Prediction and Biomarker Discovery.IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS,15(3),944-953.
MLA	Min, Wenwen,et al."Network-Regularized Sparse Logistic Regression Models for Clinical Risk Prediction and Biomarker Discovery".IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 15.3(2018):944-953.