Neural network with K-means clustering via PCA for gene expression profile analysis

Thomas C. Chen; Sandeep Sanga; Tina Y. Chou; Vittorio Cristini; Mary E. Edgerton

doi:10.1109/CSIE.2009.945

Neural network with K-means clustering via PCA for gene expression profile analysis

Thomas C. Chen, Sandeep Sanga, Tina Y. Chou, Vittorio Cristini, Mary E. Edgerton

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Scopus citations

Abstract

Gene expression microarray data are highly multidimensional and contain high level of noise. Most of these data involve multiple heterogeneous dynamic patterns depending on disease under study. In addition, possible errors might also be introduced along data collection path if multiple sites and methods are used. In this paper a combined data mining method, i.e., neural network with K-means clustering via principal component analysis (PCA), is proposed to address the data complexity issues when conducting gene expression profile mining. The proposed method was tested on gene expression profile in lung adenocarcinoma, collected from multiple cancer research centers, for survival prediction and risk assessment. The results from the proposed method were analyzed, and further studies for future improvement of the proposed method were also recommended

Original language	English (US)
Title of host publication	2009 WRI World Congress on Computer Science and Information Engineering, CSIE 2009
Pages	670-673
Number of pages	4
Volume	3
DOIs	https://doi.org/10.1109/CSIE.2009.945
State	Published - Nov 12 2009
Event	2009 WRI World Congress on Computer Science and Information Engineering, CSIE 2009 - Los Angeles, CA, United States Duration: Mar 31 2009 → Apr 2 2009

Other

Other	2009 WRI World Congress on Computer Science and Information Engineering, CSIE 2009
Country	United States
City	Los Angeles, CA
Period	3/31/09 → 4/2/09

Keywords

Clustering analysis
Gene expression
K-mean
Lung cancer
Neural network
PCA

ASJC Scopus subject areas

Computer Science Applications
Hardware and Architecture
Information Systems
Software

Access to Document

10.1109/CSIE.2009.945

Fingerprint Dive into the research topics of 'Neural network with K-means clustering via PCA for gene expression profile analysis'. Together they form a unique fingerprint.

Cite this

Neural network with K-means clustering via PCA for gene expression profile analysis. / Chen, Thomas C.; Sanga, Sandeep; Chou, Tina Y.; Cristini, Vittorio; Edgerton, Mary E.

2009 WRI World Congress on Computer Science and Information Engineering, CSIE 2009. Vol. 3 2009. p. 670-673 5170925.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Chen, TC, Sanga, S, Chou, TY, Cristini, V & Edgerton, ME 2009, Neural network with K-means clustering via PCA for gene expression profile analysis. in 2009 WRI World Congress on Computer Science and Information Engineering, CSIE 2009. vol. 3, 5170925, pp. 670-673, 2009 WRI World Congress on Computer Science and Information Engineering, CSIE 2009, Los Angeles, CA, United States, 3/31/09. https://doi.org/10.1109/CSIE.2009.945

@inproceedings{4798eda8a5814aedb7106bb7dedea74f,

title = "Neural network with K-means clustering via PCA for gene expression profile analysis",

abstract = "Gene expression microarray data are highly multidimensional and contain high level of noise. Most of these data involve multiple heterogeneous dynamic patterns depending on disease under study. In addition, possible errors might also be introduced along data collection path if multiple sites and methods are used. In this paper a combined data mining method, i.e., neural network with K-means clustering via principal component analysis (PCA), is proposed to address the data complexity issues when conducting gene expression profile mining. The proposed method was tested on gene expression profile in lung adenocarcinoma, collected from multiple cancer research centers, for survival prediction and risk assessment. The results from the proposed method were analyzed, and further studies for future improvement of the proposed method were also recommended",

keywords = "Clustering analysis, Gene expression, K-mean, Lung cancer, Neural network, PCA",

author = "Chen, {Thomas C.} and Sandeep Sanga and Chou, {Tina Y.} and Vittorio Cristini and Edgerton, {Mary E.}",

year = "2009",

month = nov,

day = "12",

doi = "10.1109/CSIE.2009.945",

language = "English (US)",

isbn = "9780769535074",

volume = "3",

pages = "670--673",

booktitle = "2009 WRI World Congress on Computer Science and Information Engineering, CSIE 2009",

note = "2009 WRI World Congress on Computer Science and Information Engineering, CSIE 2009 ; Conference date: 31-03-2009 Through 02-04-2009",

}

TY - GEN

T1 - Neural network with K-means clustering via PCA for gene expression profile analysis

AU - Chen, Thomas C.

AU - Sanga, Sandeep

AU - Chou, Tina Y.

AU - Cristini, Vittorio

AU - Edgerton, Mary E.

PY - 2009/11/12

Y1 - 2009/11/12

N2 - Gene expression microarray data are highly multidimensional and contain high level of noise. Most of these data involve multiple heterogeneous dynamic patterns depending on disease under study. In addition, possible errors might also be introduced along data collection path if multiple sites and methods are used. In this paper a combined data mining method, i.e., neural network with K-means clustering via principal component analysis (PCA), is proposed to address the data complexity issues when conducting gene expression profile mining. The proposed method was tested on gene expression profile in lung adenocarcinoma, collected from multiple cancer research centers, for survival prediction and risk assessment. The results from the proposed method were analyzed, and further studies for future improvement of the proposed method were also recommended

AB - Gene expression microarray data are highly multidimensional and contain high level of noise. Most of these data involve multiple heterogeneous dynamic patterns depending on disease under study. In addition, possible errors might also be introduced along data collection path if multiple sites and methods are used. In this paper a combined data mining method, i.e., neural network with K-means clustering via principal component analysis (PCA), is proposed to address the data complexity issues when conducting gene expression profile mining. The proposed method was tested on gene expression profile in lung adenocarcinoma, collected from multiple cancer research centers, for survival prediction and risk assessment. The results from the proposed method were analyzed, and further studies for future improvement of the proposed method were also recommended

KW - Clustering analysis

KW - Gene expression

KW - K-mean

KW - Lung cancer

KW - Neural network

KW - PCA

UR - http://www.scopus.com/inward/record.url?scp=70449126766&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70449126766&partnerID=8YFLogxK

U2 - 10.1109/CSIE.2009.945

DO - 10.1109/CSIE.2009.945

M3 - Conference contribution

AN - SCOPUS:70449126766

SN - 9780769535074

VL - 3

SP - 670

EP - 673

BT - 2009 WRI World Congress on Computer Science and Information Engineering, CSIE 2009

T2 - 2009 WRI World Congress on Computer Science and Information Engineering, CSIE 2009

Y2 - 31 March 2009 through 2 April 2009

ER -