Biomarker identification by knowledge-driven multilevel ICA and motif analysis

Li Chen, Jianhua Xuan, Chen Wang, Yue Wang, Le Ming Shih, Tian Li Wang, Zhen Zhang, Robert Clarke, Eric P. Hoffman

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Traditional statistical methods often fail to identify biologically meaningful biomarkers from expression data alone. In this paper, we develop a novel strategy, namely knowledge-driven multi-level Independent Component Analysis (ICA), to infer regulatory signals and identify biomarkers based on clustering results and partial prior knowledge. A statistical test is designed to evaluate significance of transcription factor enrichment for extracted gene set based on motif information. The experimental results on an Rsf-1 (HBXAP) induced microarray data set show that our method can successfully extract biologically meaningful biomarkers related to ovarian cancer compared to other gene selection methods with or without prior knowledge.

Original languageEnglish (US)
Pages (from-to)365-381
Number of pages17
JournalInternational Journal of Data Mining and Bioinformatics
Volume3
Issue number4
DOIs
StatePublished - 2009
Externally publishedYes

Fingerprint

Independent component analysis
Biomarkers
statistical test
Genes
statistical method
knowledge
cancer
Transcription factors
Statistical tests
Microarrays
Ovarian Neoplasms
Cluster Analysis
Statistical methods
Transcription Factors

Keywords

  • Biomarker identification
  • Gene clustering
  • Gene regulatory networks
  • ICA
  • Independent component analysis
  • Microarray data analysis
  • Motif analysis
  • Multi-level ICA

ASJC Scopus subject areas

  • Library and Information Sciences
  • Information Systems
  • Biochemistry, Genetics and Molecular Biology(all)

Cite this

Biomarker identification by knowledge-driven multilevel ICA and motif analysis. / Chen, Li; Xuan, Jianhua; Wang, Chen; Wang, Yue; Shih, Le Ming; Wang, Tian Li; Zhang, Zhen; Clarke, Robert; Hoffman, Eric P.

In: International Journal of Data Mining and Bioinformatics, Vol. 3, No. 4, 2009, p. 365-381.

Research output: Contribution to journalArticle

Chen, Li ; Xuan, Jianhua ; Wang, Chen ; Wang, Yue ; Shih, Le Ming ; Wang, Tian Li ; Zhang, Zhen ; Clarke, Robert ; Hoffman, Eric P. / Biomarker identification by knowledge-driven multilevel ICA and motif analysis. In: International Journal of Data Mining and Bioinformatics. 2009 ; Vol. 3, No. 4. pp. 365-381.
@article{6de4beeefead4bda8b3f9a977a6a1499,
title = "Biomarker identification by knowledge-driven multilevel ICA and motif analysis",
abstract = "Traditional statistical methods often fail to identify biologically meaningful biomarkers from expression data alone. In this paper, we develop a novel strategy, namely knowledge-driven multi-level Independent Component Analysis (ICA), to infer regulatory signals and identify biomarkers based on clustering results and partial prior knowledge. A statistical test is designed to evaluate significance of transcription factor enrichment for extracted gene set based on motif information. The experimental results on an Rsf-1 (HBXAP) induced microarray data set show that our method can successfully extract biologically meaningful biomarkers related to ovarian cancer compared to other gene selection methods with or without prior knowledge.",
keywords = "Biomarker identification, Gene clustering, Gene regulatory networks, ICA, Independent component analysis, Microarray data analysis, Motif analysis, Multi-level ICA",
author = "Li Chen and Jianhua Xuan and Chen Wang and Yue Wang and Shih, {Le Ming} and Wang, {Tian Li} and Zhen Zhang and Robert Clarke and Hoffman, {Eric P.}",
year = "2009",
doi = "10.1504/IJDMB.2009.029201",
language = "English (US)",
volume = "3",
pages = "365--381",
journal = "International Journal of Data Mining and Bioinformatics",
issn = "1748-5673",
publisher = "Inderscience Enterprises Ltd",
number = "4",

}

TY - JOUR

T1 - Biomarker identification by knowledge-driven multilevel ICA and motif analysis

AU - Chen, Li

AU - Xuan, Jianhua

AU - Wang, Chen

AU - Wang, Yue

AU - Shih, Le Ming

AU - Wang, Tian Li

AU - Zhang, Zhen

AU - Clarke, Robert

AU - Hoffman, Eric P.

PY - 2009

Y1 - 2009

N2 - Traditional statistical methods often fail to identify biologically meaningful biomarkers from expression data alone. In this paper, we develop a novel strategy, namely knowledge-driven multi-level Independent Component Analysis (ICA), to infer regulatory signals and identify biomarkers based on clustering results and partial prior knowledge. A statistical test is designed to evaluate significance of transcription factor enrichment for extracted gene set based on motif information. The experimental results on an Rsf-1 (HBXAP) induced microarray data set show that our method can successfully extract biologically meaningful biomarkers related to ovarian cancer compared to other gene selection methods with or without prior knowledge.

AB - Traditional statistical methods often fail to identify biologically meaningful biomarkers from expression data alone. In this paper, we develop a novel strategy, namely knowledge-driven multi-level Independent Component Analysis (ICA), to infer regulatory signals and identify biomarkers based on clustering results and partial prior knowledge. A statistical test is designed to evaluate significance of transcription factor enrichment for extracted gene set based on motif information. The experimental results on an Rsf-1 (HBXAP) induced microarray data set show that our method can successfully extract biologically meaningful biomarkers related to ovarian cancer compared to other gene selection methods with or without prior knowledge.

KW - Biomarker identification

KW - Gene clustering

KW - Gene regulatory networks

KW - ICA

KW - Independent component analysis

KW - Microarray data analysis

KW - Motif analysis

KW - Multi-level ICA

UR - http://www.scopus.com/inward/record.url?scp=70549114783&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70549114783&partnerID=8YFLogxK

U2 - 10.1504/IJDMB.2009.029201

DO - 10.1504/IJDMB.2009.029201

M3 - Article

VL - 3

SP - 365

EP - 381

JO - International Journal of Data Mining and Bioinformatics

JF - International Journal of Data Mining and Bioinformatics

SN - 1748-5673

IS - 4

ER -