Ensemble learning of genetic networks from time-series expression data

Dougu Nam, Sung Ho Yoon, Jihyun F. Kim

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Motivation: Inferring genetic networks from time-series expression data has been a great deal of interest. In most cases, however, the number of genes exceeds that of data points which, in principle, makes it impossible to recover the underlying networks. To address the dimensionality problem, we apply the subset selection method to a linear system of difference equations. Previous approaches assign the single most likely combination of regulators to each target gene, which often causes over-fitting of the small number of data. Results: Here, we propose a new algorithm, named LEARNe, which merges the predictions from all the combinations of regulators that have a certain level of likelihood. LEARNe provides more accurate and robust predictions than previous methods for the structure of genetic networks under the linear system model. We tested LEARNe for reconstructing the SOS regulatory network of Escherichia coli and the cell cycle regulatory network of yeast from real experimental data, where LEARNe also exhibited better performances than previous methods.

Original languageEnglish
Pages (from-to)3225-3231
Number of pages7
JournalBioinformatics
Volume23
Issue number23
DOIs
Publication statusPublished - 2007 Dec 1

Fingerprint

Ensemble Learning
Genetic Network
Linear systems
Time series
Genes
Regulatory Networks
Learning
Regulator
Difference equations
Set theory
Linear Systems
Yeast
Escherichia coli
Gene
System of Difference Equations
Subset Selection
Genetic Structures
Prediction
Overfitting
Cells

All Science Journal Classification (ASJC) codes

  • Clinical Biochemistry
  • Computer Science Applications
  • Computational Theory and Mathematics

Cite this

Nam, Dougu ; Yoon, Sung Ho ; Kim, Jihyun F. / Ensemble learning of genetic networks from time-series expression data. In: Bioinformatics. 2007 ; Vol. 23, No. 23. pp. 3225-3231.
@article{33444b70259348e8b6eb81f64be0c83c,
title = "Ensemble learning of genetic networks from time-series expression data",
abstract = "Motivation: Inferring genetic networks from time-series expression data has been a great deal of interest. In most cases, however, the number of genes exceeds that of data points which, in principle, makes it impossible to recover the underlying networks. To address the dimensionality problem, we apply the subset selection method to a linear system of difference equations. Previous approaches assign the single most likely combination of regulators to each target gene, which often causes over-fitting of the small number of data. Results: Here, we propose a new algorithm, named LEARNe, which merges the predictions from all the combinations of regulators that have a certain level of likelihood. LEARNe provides more accurate and robust predictions than previous methods for the structure of genetic networks under the linear system model. We tested LEARNe for reconstructing the SOS regulatory network of Escherichia coli and the cell cycle regulatory network of yeast from real experimental data, where LEARNe also exhibited better performances than previous methods.",
author = "Dougu Nam and Yoon, {Sung Ho} and Kim, {Jihyun F.}",
year = "2007",
month = "12",
day = "1",
doi = "10.1093/bioinformatics/btm514",
language = "English",
volume = "23",
pages = "3225--3231",
journal = "Bioinformatics",
issn = "1367-4803",
publisher = "Oxford University Press",
number = "23",

}

Ensemble learning of genetic networks from time-series expression data. / Nam, Dougu; Yoon, Sung Ho; Kim, Jihyun F.

In: Bioinformatics, Vol. 23, No. 23, 01.12.2007, p. 3225-3231.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Ensemble learning of genetic networks from time-series expression data

AU - Nam, Dougu

AU - Yoon, Sung Ho

AU - Kim, Jihyun F.

PY - 2007/12/1

Y1 - 2007/12/1

N2 - Motivation: Inferring genetic networks from time-series expression data has been a great deal of interest. In most cases, however, the number of genes exceeds that of data points which, in principle, makes it impossible to recover the underlying networks. To address the dimensionality problem, we apply the subset selection method to a linear system of difference equations. Previous approaches assign the single most likely combination of regulators to each target gene, which often causes over-fitting of the small number of data. Results: Here, we propose a new algorithm, named LEARNe, which merges the predictions from all the combinations of regulators that have a certain level of likelihood. LEARNe provides more accurate and robust predictions than previous methods for the structure of genetic networks under the linear system model. We tested LEARNe for reconstructing the SOS regulatory network of Escherichia coli and the cell cycle regulatory network of yeast from real experimental data, where LEARNe also exhibited better performances than previous methods.

AB - Motivation: Inferring genetic networks from time-series expression data has been a great deal of interest. In most cases, however, the number of genes exceeds that of data points which, in principle, makes it impossible to recover the underlying networks. To address the dimensionality problem, we apply the subset selection method to a linear system of difference equations. Previous approaches assign the single most likely combination of regulators to each target gene, which often causes over-fitting of the small number of data. Results: Here, we propose a new algorithm, named LEARNe, which merges the predictions from all the combinations of regulators that have a certain level of likelihood. LEARNe provides more accurate and robust predictions than previous methods for the structure of genetic networks under the linear system model. We tested LEARNe for reconstructing the SOS regulatory network of Escherichia coli and the cell cycle regulatory network of yeast from real experimental data, where LEARNe also exhibited better performances than previous methods.

UR - http://www.scopus.com/inward/record.url?scp=36549040919&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36549040919&partnerID=8YFLogxK

U2 - 10.1093/bioinformatics/btm514

DO - 10.1093/bioinformatics/btm514

M3 - Article

VL - 23

SP - 3225

EP - 3231

JO - Bioinformatics

JF - Bioinformatics

SN - 1367-4803

IS - 23

ER -