文献类型：期刊文献

英文题名：Grouped Gene Selection of Cancer via Adaptive Sparse Group Lasso Based on Conditional Mutual Information

作者：Li, Juntao[1,2];Dong, Wenpeng[3];Meng, Deyuan[4,5]

第一作者：Li, Juntao

通讯作者：Meng, DY[1];Meng, DY[2]

机构：[1]Henan Univ Econ & Law, Coll Comp & Informat Engn, Zhengzhou 450002, Henan, Peoples R China;[2]Henan Normal Univ, Sch Math & Informat Sci, Xinxiang 453007, Peoples R China;[3]Henan Normal Univ, Sch Math & Informat Sci, Henan Engn Lab Big Data Stat Anal & Optimal Contr, Xinxiang 453007, Peoples R China;[4]Beihang Univ BUAA, Seventh Res Div, Beijing 100191, Peoples R China;[5]Beihang Univ BUAA, Sch Automat Sci & Elect Engn, Beijing 100191, Peoples R China

第一机构：河南财经政法大学计算机与信息工程学院

通讯机构：[1]corresponding author), Beihang Univ BUAA, Seventh Res Div, Beijing 100191, Peoples R China;[2]corresponding author), Beihang Univ BUAA, Sch Automat Sci & Elect Engn, Beijing 100191, Peoples R China.

年份：2018

卷号：15

期号：6

起止页码：2028-2038

外文期刊名：IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS

收录：;EI(收录号：20174304310354);Scopus(收录号：2-s2.0-85031897873);WOS:【SCI-EXPANDED(收录号:WOS:000453563100030)】；

基金：This work was supported by the Natural Science Foundation of China (61203293, 61374079, 61473010, 31700858), the Scientific and Technological Project of Henan Province (172102210047), the Foundation of Henan Educational Committee (18A520015), the Beijing Natural Science Foundation (4162036), and the Fundamental Research Funds for the Central Universities.

语种：英文

外文关键词：Cancer classification; grouped gene selection; conditional mutual information; group lasso; weighted gene co-expression network

摘要：This paper deals with the problems of cancer classification and grouped gene selection. The weighted gene co-expression network on cancer microarray data is employed to identify modules corresponding to biological pathways, based on which a strategy of dividing genes into groups is presented. Using the conditional mutual information within each divided group, an integrated criterion is proposed and the data-driven weights are constructed. They are shown with the ability to evaluate both the individual gene significance and the influence to improve correlation of all the other pairwise genes in each group. Furthermore, an adaptive sparse group lasso is proposed, by which an improved blockwise descent algorithm is developed. The results on four cancer data sets demonstrate that the proposed adaptive sparse group lasso can effectively perform classification and grouped gene selection.