On predicting epithelial mesenchymal transition by integrating RNA-binding proteins and correlation data via L-1/2-regularization method
文献类型：期刊
作者：Qiu, Yushan[1]
机构：[1]Shenzhen Univ, Coll Math & Stat, Shenzhen 518060, Peoples R China.;
[2]Renmin Univ China, Sch Math, 59 Zhong Guan Cun St, Beijing, Peoples R China.;
[3]Univ Hong Kong, Dept Math, Pokfulam Rd, Hong Kong, Peoples R China.;
[4]Hong Kong Baptist Univ, Dept Math, Hong Kong, Peoples R China.;
通讯作者：Jiang, H (reprint author), Renmin Univ China, Sch Math, 59 Zhong Guan Cun St, Beijing, Peoples R China.
期刊名称：ARTIFICIAL INTELLIGENCE IN MEDICINE影响因子和分区
年：2019
卷：95
页码：96-103
收录情况：SCI(E)(WOS:000464091700009)
ISSN：0933-3657
关键词：L-1/2-regularization; Classification; RNA-binding proteins (RBPs); Epithelial-mesenchymal transition (EMT)
摘要：Identifying tumor metastasis signatures from gene expression data at the whole genome level remains an arduous challenge, particularly so when the number of genes is huge and the number of experimental samples is small. We focus on the prediction of the epithelial-mesenchymal transition (EMT), which is an underlying mechanism of tumor metastasis, here, rather than on tumor metastasis itself, to avoid confounding effects of uncertainties derived from various factors. We apply an extended LASSO mo ...More
Identifying tumor metastasis signatures from gene expression data at the whole genome level remains an arduous challenge, particularly so when the number of genes is huge and the number of experimental samples is small. We focus on the prediction of the epithelial-mesenchymal transition (EMT), which is an underlying mechanism of tumor metastasis, here, rather than on tumor metastasis itself, to avoid confounding effects of uncertainties derived from various factors. We apply an extended LASSO model, L-1/2-regularization model, as a feature selector, to identify significant RNA-binding proteins (RBPs) that contribute to regulating the EMT. We find that the L-1/2-regularization model significantly outperforms LASSO in the EMT regulation problem. Furthermore, remarkable improvement in L-1/2-regularization model classification performance can be achieved by incorporating extra information, specifically correlation values. We demonstrate that the L-1/2-regularization model is applicable for identifying significant RBPs in biological research. Identified RBPs will facilitate study of the underlying mechanisms of the EMT. ...Hide
DOI：10.1016/j.artmed.2018.09.005
百度学术：On predicting epithelial mesenchymal transition by integrating RNA-binding proteins and correlation data via L-1/2-regularization method
语言：外文
基金：Natural Science Foundation of SZU [2017058]; National Natural Science Foundation of China NSFCNational Natural Science Foundation of China [91730301]; Research Grants Council of Hong KongHong Kong Research Grants Council [15210815]; IMR; RAE Research Fund from Faculty of Science, the University of Hong Kong
作者其他论文
Nitration-Peroxidation of Alkenes: A Selective Approach to beta-Peroxyl Nitroalkanes.Chen, Yuanjin, Ma, Yangyang, Li, Liangkui, et al. .ORGANIC LETTERS. 2019, 21(5), 1480-1483.
Generation of Carbon Radical from Iron-Hydride/Alkene: Exchange-Enhanced Reactivity Selects the Reactive Spin State.Jiang, Hao, Lai, Wenzhen, Chen, Hui,.ACS CATALYSIS. 2019, 9(7), 6080-6086.
Exploring Observability of Attractor Cycles in Boolean Networks for Biomarker Detection.Qiu, Yushan, Huang, Yulong, Tan, Shaobo, et al. .IEEE ACCESS. 2019, 7, 127745-127753.
Discovery of metabolite biomarkers: flux analysis and reaction-reaction network approach.Li, Limin;Jiang, Hao;Qiu, Yushan,等.6th International Conference on Computational Systems Biology (ISB).2013,7.
On the Complexity of Inference and Completion of Boolean Networks from Given Singleton Attractors.Jiang, Hao;Tamura, Takeyuki;Ching, Wai-Ki,等.IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES.2013,E96A(11),2265-2274.
