Classification of gene expression levels using activator and repressor motifs

Huitao Sheng, Kishan Mehrotra, Chilukuri K Mohan, Ramesh Raina

Research output: Chapter in Book/Report/Conference proceedingConference 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 languageEnglish (US)
Title of host publicationProceedings - 2008 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW
Pages215-218
Number of pages4
DOIs
StatePublished - 2008
Event2008 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW - Philadelphia, PA, United States
Duration: Nov 3 2008Nov 5 2008

Other

Other2008 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW
CountryUnited States
CityPhiladelphia, PA
Period11/3/0811/5/08

Fingerprint

Gene expression
Gene Expression
Yeast
Support vector machines
Saccharomyces cerevisiae
Linear Models
Genes

ASJC Scopus subject areas

  • Molecular Biology
  • Information Systems
  • Biomedical Engineering

Cite this

Sheng, H., Mehrotra, K., Mohan, C. K., & 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). [4686239] https://doi.org/10.1109/BIBMW.2008.4686239

Classification of gene expression levels using activator and repressor motifs. / Sheng, Huitao; Mehrotra, Kishan; Mohan, Chilukuri K; Raina, Ramesh.

Proceedings - 2008 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW. 2008. p. 215-218 4686239.

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

Sheng, H, Mehrotra, K, Mohan, CK & 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, 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 CK, 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 https://doi.org/10.1109/BIBMW.2008.4686239
Sheng, Huitao ; Mehrotra, Kishan ; Mohan, Chilukuri K ; Raina, Ramesh. / Classification of gene expression levels using activator and repressor motifs. Proceedings - 2008 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW. 2008. pp. 215-218
@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 Mohan, {Chilukuri K} and Ramesh Raina",
year = "2008",
doi = "10.1109/BIBMW.2008.4686239",
language = "English (US)",
isbn = "9781424428908",
pages = "215--218",
booktitle = "Proceedings - 2008 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW",

}

TY - GEN

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

AU - Sheng, Huitao

AU - Mehrotra, Kishan

AU - Mohan, Chilukuri K

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

SP - 215

EP - 218

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

ER -