A joint-L2,1-norm-constraint-based semi-supervised feature extraction for RNA-Seq data analysis

Jin Xing Liu; Dong Wang; Ying Lian Gao; Chun Hou Zheng; Jun Liang Shang; Feng Liu; Yong Xu

doi:10.1016/j.neucom.2016.09.083

A joint-L_2,1-norm-constraint-based semi-supervised feature extraction for RNA-Seq data analysis

Jin Xing Liu
, Dong Wang
, Ying Lian Gao
, Chun Hou Zheng
, Jun Liang Shang
, Feng Liu
, Yong Xu

Research output: Contribution to journal › Article › peer-review

31 Scopus citations

Abstract

It is of urgency to effectively identify differentially expressed genes from RNA-Seq data. In this paper, we proposed a novel method, joint-L_2,1-norm-constraint-based semi-supervised feature extraction (L21SFE), to analyze RNA-Seq data. Our scheme was shown as follows. Firstly, we constructed a graph Laplacian matrix and refined it by using the labeled samples. Our graph construction method can make full use of a large number of unlabelled samples. Secondly, we found semi-supervised optimal maps by solving a generalized eigenvalue problem. Thirdly, we solved an optimal problem via the joint L_2,1-norm constraint to obtain a projection matrix. It can diminish the impact of noises and outliers by using the L_2,1-norm constraint and produce more precise results. Finally, we identified differentially expressed genes based on the projection matrix. The results on simulation and real RNA-Seq data sets demonstrated the feasibility and effectiveness of our method.

Original language	English
Pages (from-to)	263-269
Number of pages	7
Journal	Neurocomputing
Volume	228
DOIs	https://doi.org/10.1016/j.neucom.2016.09.083
State	Published - 8 Mar 2017
Externally published	Yes

Keywords

Feature extraction
L-norm constraint
RNA-Seq data analysis
Semi-supervised method
Spectral regression

Access to Document

10.1016/j.neucom.2016.09.083

Cite this

@article{e63b412eb9584f33a5f004eba1852f5e,

title = "A joint-L2,1-norm-constraint-based semi-supervised feature extraction for RNA-Seq data analysis",

abstract = "It is of urgency to effectively identify differentially expressed genes from RNA-Seq data. In this paper, we proposed a novel method, joint-L2,1-norm-constraint-based semi-supervised feature extraction (L21SFE), to analyze RNA-Seq data. Our scheme was shown as follows. Firstly, we constructed a graph Laplacian matrix and refined it by using the labeled samples. Our graph construction method can make full use of a large number of unlabelled samples. Secondly, we found semi-supervised optimal maps by solving a generalized eigenvalue problem. Thirdly, we solved an optimal problem via the joint L2,1-norm constraint to obtain a projection matrix. It can diminish the impact of noises and outliers by using the L2,1-norm constraint and produce more precise results. Finally, we identified differentially expressed genes based on the projection matrix. The results on simulation and real RNA-Seq data sets demonstrated the feasibility and effectiveness of our method.",

keywords = "Feature extraction, L-norm constraint, RNA-Seq data analysis, Semi-supervised method, Spectral regression",

author = "Liu, \{Jin Xing\} and Dong Wang and Gao, \{Ying Lian\} and Zheng, \{Chun Hou\} and Shang, \{Jun Liang\} and Feng Liu and Yong Xu",

note = "Publisher Copyright: {\textcopyright} 2016 Elsevier B.V.",

year = "2017",

month = mar,

day = "8",

doi = "10.1016/j.neucom.2016.09.083",

language = "英语",

volume = "228",

pages = "263--269",

journal = "Neurocomputing",

issn = "0925-2312",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - A joint-L2,1-norm-constraint-based semi-supervised feature extraction for RNA-Seq data analysis

AU - Liu, Jin Xing

AU - Wang, Dong

AU - Gao, Ying Lian

AU - Zheng, Chun Hou

AU - Shang, Jun Liang

AU - Liu, Feng

AU - Xu, Yong

PY - 2017/3/8

Y1 - 2017/3/8

N2 - It is of urgency to effectively identify differentially expressed genes from RNA-Seq data. In this paper, we proposed a novel method, joint-L2,1-norm-constraint-based semi-supervised feature extraction (L21SFE), to analyze RNA-Seq data. Our scheme was shown as follows. Firstly, we constructed a graph Laplacian matrix and refined it by using the labeled samples. Our graph construction method can make full use of a large number of unlabelled samples. Secondly, we found semi-supervised optimal maps by solving a generalized eigenvalue problem. Thirdly, we solved an optimal problem via the joint L2,1-norm constraint to obtain a projection matrix. It can diminish the impact of noises and outliers by using the L2,1-norm constraint and produce more precise results. Finally, we identified differentially expressed genes based on the projection matrix. The results on simulation and real RNA-Seq data sets demonstrated the feasibility and effectiveness of our method.

AB - It is of urgency to effectively identify differentially expressed genes from RNA-Seq data. In this paper, we proposed a novel method, joint-L2,1-norm-constraint-based semi-supervised feature extraction (L21SFE), to analyze RNA-Seq data. Our scheme was shown as follows. Firstly, we constructed a graph Laplacian matrix and refined it by using the labeled samples. Our graph construction method can make full use of a large number of unlabelled samples. Secondly, we found semi-supervised optimal maps by solving a generalized eigenvalue problem. Thirdly, we solved an optimal problem via the joint L2,1-norm constraint to obtain a projection matrix. It can diminish the impact of noises and outliers by using the L2,1-norm constraint and produce more precise results. Finally, we identified differentially expressed genes based on the projection matrix. The results on simulation and real RNA-Seq data sets demonstrated the feasibility and effectiveness of our method.

KW - Feature extraction

KW - L-norm constraint

KW - RNA-Seq data analysis

KW - Semi-supervised method

KW - Spectral regression

UR - https://www.scopus.com/pages/publications/85006856638

U2 - 10.1016/j.neucom.2016.09.083

DO - 10.1016/j.neucom.2016.09.083

M3 - 文章

AN - SCOPUS:85006856638

SN - 0925-2312

VL - 228

SP - 263

EP - 269

JO - Neurocomputing

JF - Neurocomputing

ER -

A joint-L_2,1-norm-constraint-based semi-supervised feature extraction for RNA-Seq data analysis

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this