Biomarker identification by knowledge-driven multi-level ICA and motif analysis

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

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

1 Citation (Scopus)

Abstract

Many statistical methods often fail to identify biologically meaningful biomarkers related to a specific disease under study 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 biologically relevant biomarkers from microarray data. Specifically, based on multi-level clustering results and partial prior knowledge, we apply ICA to find stable disease specific linear regulatory modes and then extract associated biomarker genes. A statistical test is designed to evaluate the significance of transcription factor enrichment for extracted gene set based on motif information. The experimental results on an Rsf-1 induced microarray data set show that our knowledgedriven method can extract more biologically meaningful biomarkers with significant enrichment of transcription factors related to ovarian cancer compared to other gene selection methods with/without prior knowledge.

Original languageEnglish (US)
Title of host publicationProceedings - 6th International Conference on Machine Learning and Applications, ICMLA 2007
Pages560-566
Number of pages7
DOIs
StatePublished - 2007
Externally publishedYes
Event6th International Conference on Machine Learning and Applications, ICMLA 2007 - Cincinnati, OH, United States
Duration: Dec 13 2007Dec 15 2007

Other

Other6th International Conference on Machine Learning and Applications, ICMLA 2007
CountryUnited States
CityCincinnati, OH
Period12/13/0712/15/07

Fingerprint

Independent component analysis
Biomarkers
Transcription factors
Genes
Microarrays
Statistical tests
Statistical methods

ASJC Scopus subject areas

  • Computer Science Applications
  • Human-Computer Interaction
  • Control and Systems Engineering

Cite this

Chen, L., Wang, C., Shih, I. M., Wang, T. L., Zhang, Z., Wang, Y., ... Xuan, J. (2007). Biomarker identification by knowledge-driven multi-level ICA and motif analysis. In Proceedings - 6th International Conference on Machine Learning and Applications, ICMLA 2007 (pp. 560-566). [4457289] https://doi.org/10.1109/ICMLA.2007.24

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

Proceedings - 6th International Conference on Machine Learning and Applications, ICMLA 2007. 2007. p. 560-566 4457289.

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

Chen, L, Wang, C, Shih, IM, Wang, TL, Zhang, Z, Wang, Y, Clarke, R, Hoffman, E & Xuan, J 2007, Biomarker identification by knowledge-driven multi-level ICA and motif analysis. in Proceedings - 6th International Conference on Machine Learning and Applications, ICMLA 2007., 4457289, pp. 560-566, 6th International Conference on Machine Learning and Applications, ICMLA 2007, Cincinnati, OH, United States, 12/13/07. https://doi.org/10.1109/ICMLA.2007.24
Chen L, Wang C, Shih IM, Wang TL, Zhang Z, Wang Y et al. Biomarker identification by knowledge-driven multi-level ICA and motif analysis. In Proceedings - 6th International Conference on Machine Learning and Applications, ICMLA 2007. 2007. p. 560-566. 4457289 https://doi.org/10.1109/ICMLA.2007.24
Chen, Li ; Wang, Chen ; Shih, Ie Ming ; Wang, Tian Li ; Zhang, Zhen ; Wang, Yue ; Clarke, Robert ; Hoffman, Eric ; Xuan, Jianhua. / Biomarker identification by knowledge-driven multi-level ICA and motif analysis. Proceedings - 6th International Conference on Machine Learning and Applications, ICMLA 2007. 2007. pp. 560-566
@inproceedings{a75bb159b5d44e859ea25b91c52390c5,
title = "Biomarker identification by knowledge-driven multi-level ICA and motif analysis",
abstract = "Many statistical methods often fail to identify biologically meaningful biomarkers related to a specific disease under study 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 biologically relevant biomarkers from microarray data. Specifically, based on multi-level clustering results and partial prior knowledge, we apply ICA to find stable disease specific linear regulatory modes and then extract associated biomarker genes. A statistical test is designed to evaluate the significance of transcription factor enrichment for extracted gene set based on motif information. The experimental results on an Rsf-1 induced microarray data set show that our knowledgedriven method can extract more biologically meaningful biomarkers with significant enrichment of transcription factors related to ovarian cancer compared to other gene selection methods with/without prior knowledge.",
author = "Li Chen and Chen Wang and Shih, {Ie Ming} and Wang, {Tian Li} and Zhen Zhang and Yue Wang and Robert Clarke and Eric Hoffman and Jianhua Xuan",
year = "2007",
doi = "10.1109/ICMLA.2007.24",
language = "English (US)",
isbn = "0769530699",
pages = "560--566",
booktitle = "Proceedings - 6th International Conference on Machine Learning and Applications, ICMLA 2007",

}

TY - GEN

T1 - Biomarker identification by knowledge-driven multi-level ICA and motif analysis

AU - Chen, Li

AU - Wang, Chen

AU - Shih, Ie Ming

AU - Wang, Tian Li

AU - Zhang, Zhen

AU - Wang, Yue

AU - Clarke, Robert

AU - Hoffman, Eric

AU - Xuan, Jianhua

PY - 2007

Y1 - 2007

N2 - Many statistical methods often fail to identify biologically meaningful biomarkers related to a specific disease under study 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 biologically relevant biomarkers from microarray data. Specifically, based on multi-level clustering results and partial prior knowledge, we apply ICA to find stable disease specific linear regulatory modes and then extract associated biomarker genes. A statistical test is designed to evaluate the significance of transcription factor enrichment for extracted gene set based on motif information. The experimental results on an Rsf-1 induced microarray data set show that our knowledgedriven method can extract more biologically meaningful biomarkers with significant enrichment of transcription factors related to ovarian cancer compared to other gene selection methods with/without prior knowledge.

AB - Many statistical methods often fail to identify biologically meaningful biomarkers related to a specific disease under study 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 biologically relevant biomarkers from microarray data. Specifically, based on multi-level clustering results and partial prior knowledge, we apply ICA to find stable disease specific linear regulatory modes and then extract associated biomarker genes. A statistical test is designed to evaluate the significance of transcription factor enrichment for extracted gene set based on motif information. The experimental results on an Rsf-1 induced microarray data set show that our knowledgedriven method can extract more biologically meaningful biomarkers with significant enrichment of transcription factors related to ovarian cancer compared to other gene selection methods with/without prior knowledge.

UR - http://www.scopus.com/inward/record.url?scp=47349121988&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=47349121988&partnerID=8YFLogxK

U2 - 10.1109/ICMLA.2007.24

DO - 10.1109/ICMLA.2007.24

M3 - Conference contribution

SN - 0769530699

SN - 9780769530697

SP - 560

EP - 566

BT - Proceedings - 6th International Conference on Machine Learning and Applications, ICMLA 2007

ER -