Classification of gene expression levels using activator and repressor motifs

Huitao Sheng; Kishan Mehrotra; Chilukuri Mohan; Ramesh Raina

doi:10.1109/BIBMW.2008.4686239

Classification of gene expression levels using activator and repressor motifs

Huitao Sheng, Kishan Mehrotra, Chilukuri Mohan, Ramesh Raina

Research output: Chapter in Book/Entry/Poem › Conference contribution

Abstract

Gene expression levels are influenced significantly by the presence or absence of cis-regulatory elements or motifs. This paper presents classification systems in which the occurrences of both activator and repressor motifs constitute important inputs in predicting whether a gene will be upregulated, down-regulated, or neither (neutral). We have experimented with several approaches for classification using these input data, and best performance was obtained using Support Vector Machine (SVM) models with linear kernels and a hierarchical structure. On Saccharomyces cerevisiae data, this approach yielded 71% accuracy (on test data) for 3-category classification.

Original language	English (US)
Title of host publication	Proceedings - 2008 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW
Pages	215-218
Number of pages	4
DOIs	https://doi.org/10.1109/BIBMW.2008.4686239
State	Published - 2008
Event	2008 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW - Philadelphia, PA, United States Duration: Nov 3 2008 → Nov 5 2008

Publication series

Name	Proceedings - 2008 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW

Other

Other	2008 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW
Country/Territory	United States
City	Philadelphia, PA
Period	11/3/08 → 11/5/08

ASJC Scopus subject areas

Molecular Biology
Information Systems
Biomedical Engineering

Access to Document

10.1109/BIBMW.2008.4686239

Cite this

Sheng, H., Mehrotra, K., Mohan, C., & Raina, R. (2008). Classification of gene expression levels using activator and repressor motifs. In Proceedings - 2008 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW (pp. 215-218). Article 4686239 (Proceedings - 2008 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW). https://doi.org/10.1109/BIBMW.2008.4686239

Classification of gene expression levels using activator and repressor motifs. / Sheng, Huitao; Mehrotra, Kishan; Mohan, Chilukuri et al.
Proceedings - 2008 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW. 2008. p. 215-218 4686239 (Proceedings - 2008 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW).

Research output: Chapter in Book/Entry/Poem › Conference contribution

Sheng, H, Mehrotra, K, Mohan, C & Raina, R 2008, Classification of gene expression levels using activator and repressor motifs. in Proceedings - 2008 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW., 4686239, Proceedings - 2008 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW, pp. 215-218, 2008 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW, Philadelphia, PA, United States, 11/3/08. https://doi.org/10.1109/BIBMW.2008.4686239

Sheng H, Mehrotra K, Mohan C , Raina R. Classification of gene expression levels using activator and repressor motifs. In Proceedings - 2008 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW. 2008. p. 215-218. 4686239. (Proceedings - 2008 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW). doi: 10.1109/BIBMW.2008.4686239

@inproceedings{90bea4f9d015404dbadb886e2c80d5eb,

title = "Classification of gene expression levels using activator and repressor motifs",

abstract = "Gene expression levels are influenced significantly by the presence or absence of cis-regulatory elements or motifs. This paper presents classification systems in which the occurrences of both activator and repressor motifs constitute important inputs in predicting whether a gene will be upregulated, down-regulated, or neither (neutral). We have experimented with several approaches for classification using these input data, and best performance was obtained using Support Vector Machine (SVM) models with linear kernels and a hierarchical structure. On Saccharomyces cerevisiae data, this approach yielded 71% accuracy (on test data) for 3-category classification.",

author = "Huitao Sheng and Kishan Mehrotra and Chilukuri Mohan and Ramesh Raina",

year = "2008",

doi = "10.1109/BIBMW.2008.4686239",

language = "English (US)",

isbn = "9781424428908",

series = "Proceedings - 2008 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW",

pages = "215--218",

booktitle = "Proceedings - 2008 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW",

note = "2008 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW ; Conference date: 03-11-2008 Through 05-11-2008",

}

TY - GEN

T1 - Classification of gene expression levels using activator and repressor motifs

AU - Sheng, Huitao

AU - Mehrotra, Kishan

AU - Mohan, Chilukuri

AU - Raina, Ramesh

PY - 2008

Y1 - 2008

N2 - Gene expression levels are influenced significantly by the presence or absence of cis-regulatory elements or motifs. This paper presents classification systems in which the occurrences of both activator and repressor motifs constitute important inputs in predicting whether a gene will be upregulated, down-regulated, or neither (neutral). We have experimented with several approaches for classification using these input data, and best performance was obtained using Support Vector Machine (SVM) models with linear kernels and a hierarchical structure. On Saccharomyces cerevisiae data, this approach yielded 71% accuracy (on test data) for 3-category classification.

AB - Gene expression levels are influenced significantly by the presence or absence of cis-regulatory elements or motifs. This paper presents classification systems in which the occurrences of both activator and repressor motifs constitute important inputs in predicting whether a gene will be upregulated, down-regulated, or neither (neutral). We have experimented with several approaches for classification using these input data, and best performance was obtained using Support Vector Machine (SVM) models with linear kernels and a hierarchical structure. On Saccharomyces cerevisiae data, this approach yielded 71% accuracy (on test data) for 3-category classification.

UR - http://www.scopus.com/inward/record.url?scp=58049181393&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=58049181393&partnerID=8YFLogxK

U2 - 10.1109/BIBMW.2008.4686239

DO - 10.1109/BIBMW.2008.4686239

M3 - Conference contribution

AN - SCOPUS:58049181393

SN - 9781424428908

T3 - Proceedings - 2008 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW

SP - 215

EP - 218

BT - Proceedings - 2008 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW

T2 - 2008 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW

Y2 - 3 November 2008 through 5 November 2008

ER -

Classification of gene expression levels using activator and repressor motifs

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this