Identification of genes important in predicting the overall survival in patients with follicular lymphoma

Li Xiao, Kai Fu, Javeed Iqbal, Wing C. Chan, Simon Sherman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this work, we propose to use the class comparison methods of median absolute deviation (MAD), Significance Analysis of Microarray (SAM) and Principal Component Analysis (PCA) for selecting important genes related to survival in lymphoma gene expression profiles. MAD is applied for selecting the genes whose expression values have maximal variation across the samples. SAM identifies genes with statistically significant changes in expression by assimilating a set of gene-specific t tests. Principal Component Analysis (PCA) is a linear projection method that defines a new dimensional space (samples by principal components) that captures the maximum information present in the initial data set (samples by genes). It is demonstrated that the expression measurement of the selected genes has a strong relation to the survival time. The selected genes can be used as features in building the class predication model.

Original languageEnglish (US)
Title of host publicationProceedings of the 2005 International Conference on Data Mining, DMIN'05
Pages181-186
Number of pages6
StatePublished - Dec 1 2005
Event2005 International Conference on Data Mining, DMIN'05 - Las Vegas, NV, United States
Duration: Jun 20 2005Jun 23 2005

Publication series

NameProceedings of the 2005 International Conference on Data Mining, DMIN'05

Conference

Conference2005 International Conference on Data Mining, DMIN'05
CountryUnited States
CityLas Vegas, NV
Period6/20/056/23/05

Fingerprint

Genes
Microarrays
Gene expression
Principal component analysis

Keywords

  • Follicular lymphoma
  • Gene expression
  • Principal component analysis
  • Significance analysis

ASJC Scopus subject areas

  • Computer Science Applications
  • Software

Cite this

Xiao, L., Fu, K., Iqbal, J., Chan, W. C., & Sherman, S. (2005). Identification of genes important in predicting the overall survival in patients with follicular lymphoma. In Proceedings of the 2005 International Conference on Data Mining, DMIN'05 (pp. 181-186). (Proceedings of the 2005 International Conference on Data Mining, DMIN'05).

Identification of genes important in predicting the overall survival in patients with follicular lymphoma. / Xiao, Li; Fu, Kai; Iqbal, Javeed; Chan, Wing C.; Sherman, Simon.

Proceedings of the 2005 International Conference on Data Mining, DMIN'05. 2005. p. 181-186 (Proceedings of the 2005 International Conference on Data Mining, DMIN'05).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Xiao, L, Fu, K, Iqbal, J, Chan, WC & Sherman, S 2005, Identification of genes important in predicting the overall survival in patients with follicular lymphoma. in Proceedings of the 2005 International Conference on Data Mining, DMIN'05. Proceedings of the 2005 International Conference on Data Mining, DMIN'05, pp. 181-186, 2005 International Conference on Data Mining, DMIN'05, Las Vegas, NV, United States, 6/20/05.
Xiao L, Fu K, Iqbal J, Chan WC, Sherman S. Identification of genes important in predicting the overall survival in patients with follicular lymphoma. In Proceedings of the 2005 International Conference on Data Mining, DMIN'05. 2005. p. 181-186. (Proceedings of the 2005 International Conference on Data Mining, DMIN'05).
Xiao, Li ; Fu, Kai ; Iqbal, Javeed ; Chan, Wing C. ; Sherman, Simon. / Identification of genes important in predicting the overall survival in patients with follicular lymphoma. Proceedings of the 2005 International Conference on Data Mining, DMIN'05. 2005. pp. 181-186 (Proceedings of the 2005 International Conference on Data Mining, DMIN'05).
@inproceedings{a3329c6454404381a6a2754796f75b97,
title = "Identification of genes important in predicting the overall survival in patients with follicular lymphoma",
abstract = "In this work, we propose to use the class comparison methods of median absolute deviation (MAD), Significance Analysis of Microarray (SAM) and Principal Component Analysis (PCA) for selecting important genes related to survival in lymphoma gene expression profiles. MAD is applied for selecting the genes whose expression values have maximal variation across the samples. SAM identifies genes with statistically significant changes in expression by assimilating a set of gene-specific t tests. Principal Component Analysis (PCA) is a linear projection method that defines a new dimensional space (samples by principal components) that captures the maximum information present in the initial data set (samples by genes). It is demonstrated that the expression measurement of the selected genes has a strong relation to the survival time. The selected genes can be used as features in building the class predication model.",
keywords = "Follicular lymphoma, Gene expression, Principal component analysis, Significance analysis",
author = "Li Xiao and Kai Fu and Javeed Iqbal and Chan, {Wing C.} and Simon Sherman",
year = "2005",
month = "12",
day = "1",
language = "English (US)",
isbn = "9781932415797",
series = "Proceedings of the 2005 International Conference on Data Mining, DMIN'05",
pages = "181--186",
booktitle = "Proceedings of the 2005 International Conference on Data Mining, DMIN'05",

}

TY - GEN

T1 - Identification of genes important in predicting the overall survival in patients with follicular lymphoma

AU - Xiao, Li

AU - Fu, Kai

AU - Iqbal, Javeed

AU - Chan, Wing C.

AU - Sherman, Simon

PY - 2005/12/1

Y1 - 2005/12/1

N2 - In this work, we propose to use the class comparison methods of median absolute deviation (MAD), Significance Analysis of Microarray (SAM) and Principal Component Analysis (PCA) for selecting important genes related to survival in lymphoma gene expression profiles. MAD is applied for selecting the genes whose expression values have maximal variation across the samples. SAM identifies genes with statistically significant changes in expression by assimilating a set of gene-specific t tests. Principal Component Analysis (PCA) is a linear projection method that defines a new dimensional space (samples by principal components) that captures the maximum information present in the initial data set (samples by genes). It is demonstrated that the expression measurement of the selected genes has a strong relation to the survival time. The selected genes can be used as features in building the class predication model.

AB - In this work, we propose to use the class comparison methods of median absolute deviation (MAD), Significance Analysis of Microarray (SAM) and Principal Component Analysis (PCA) for selecting important genes related to survival in lymphoma gene expression profiles. MAD is applied for selecting the genes whose expression values have maximal variation across the samples. SAM identifies genes with statistically significant changes in expression by assimilating a set of gene-specific t tests. Principal Component Analysis (PCA) is a linear projection method that defines a new dimensional space (samples by principal components) that captures the maximum information present in the initial data set (samples by genes). It is demonstrated that the expression measurement of the selected genes has a strong relation to the survival time. The selected genes can be used as features in building the class predication model.

KW - Follicular lymphoma

KW - Gene expression

KW - Principal component analysis

KW - Significance analysis

UR - http://www.scopus.com/inward/record.url?scp=60749098516&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=60749098516&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:60749098516

SN - 9781932415797

T3 - Proceedings of the 2005 International Conference on Data Mining, DMIN'05

SP - 181

EP - 186

BT - Proceedings of the 2005 International Conference on Data Mining, DMIN'05

ER -