Reconstructing gene regulatory networks from knock-out data using Gaussian Noise Model and Pearson Correlation Coefficient

Faridah Hani Mohamed Salleh, Shereena Mohd Arif, Suhaila Zainudin, Mohd Firdaus Mohd Raih

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

A gene regulatory network (GRN) is a large and complex network consisting of interacting elements that, over time, affect each other's state. The dynamics of complex gene regulatory processes are difficult to understand using intuitive approaches alone. To overcome this problem, we propose an algorithm for inferring the regulatory interactions from knock-out data using a Gaussian model combines with Pearson Correlation Coefficient (PCC). There are several problems relating to GRN construction that have been outlined in this paper. We demonstrated the ability of our proposed method to (1) predict the presence of regulatory interactions between genes, (2) their directionality and (3) their states (activation or suppression). The algorithm was applied to network sizes of 10 and 50 genes from DREAM3 datasets and network sizes of 10 from DREAM4 datasets. The predicted networks were evaluated based on AUROC and AUPR. We discovered that high false positive values were generated by our GRN prediction methods because the indirect regulations have been wrongly predicted as true relationships. We achieved satisfactory results as the majority of sub-networks achieved AUROC values above 0.5.

Original languageEnglish
JournalComputational Biology and Chemistry
DOIs
Publication statusAccepted/In press - 9 Sep 2014

Fingerprint

Pearson Correlation
Gene Regulatory Networks
Gene Regulatory Network
Gaussian Noise
Correlation coefficient
Genes
Gene
Regulator Genes
Gaussian Model
False Positive
Interaction
Model
Complex Networks
Activation
Intuitive
Complex networks
Predict
Prediction
Chemical activation
Datasets

Keywords

  • Bioinformatics
  • DREAM
  • Gaussian model
  • Gene regulatory network
  • Pearson Correlation Coefficient
  • Probability and statistics

ASJC Scopus subject areas

  • Biochemistry
  • Structural Biology
  • Organic Chemistry
  • Computational Mathematics

Cite this

@article{7850c226932440bcaa990c3167665955,
title = "Reconstructing gene regulatory networks from knock-out data using Gaussian Noise Model and Pearson Correlation Coefficient",
abstract = "A gene regulatory network (GRN) is a large and complex network consisting of interacting elements that, over time, affect each other's state. The dynamics of complex gene regulatory processes are difficult to understand using intuitive approaches alone. To overcome this problem, we propose an algorithm for inferring the regulatory interactions from knock-out data using a Gaussian model combines with Pearson Correlation Coefficient (PCC). There are several problems relating to GRN construction that have been outlined in this paper. We demonstrated the ability of our proposed method to (1) predict the presence of regulatory interactions between genes, (2) their directionality and (3) their states (activation or suppression). The algorithm was applied to network sizes of 10 and 50 genes from DREAM3 datasets and network sizes of 10 from DREAM4 datasets. The predicted networks were evaluated based on AUROC and AUPR. We discovered that high false positive values were generated by our GRN prediction methods because the indirect regulations have been wrongly predicted as true relationships. We achieved satisfactory results as the majority of sub-networks achieved AUROC values above 0.5.",
keywords = "Bioinformatics, DREAM, Gaussian model, Gene regulatory network, Pearson Correlation Coefficient, Probability and statistics",
author = "{Mohamed Salleh}, {Faridah Hani} and Arif, {Shereena Mohd} and Suhaila Zainudin and {Mohd Raih}, {Mohd Firdaus}",
year = "2014",
month = "9",
day = "9",
doi = "10.1016/j.compbiolchem.2015.04.012",
language = "English",
journal = "Computational Biology and Chemistry",
issn = "1476-9271",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Reconstructing gene regulatory networks from knock-out data using Gaussian Noise Model and Pearson Correlation Coefficient

AU - Mohamed Salleh, Faridah Hani

AU - Arif, Shereena Mohd

AU - Zainudin, Suhaila

AU - Mohd Raih, Mohd Firdaus

PY - 2014/9/9

Y1 - 2014/9/9

N2 - A gene regulatory network (GRN) is a large and complex network consisting of interacting elements that, over time, affect each other's state. The dynamics of complex gene regulatory processes are difficult to understand using intuitive approaches alone. To overcome this problem, we propose an algorithm for inferring the regulatory interactions from knock-out data using a Gaussian model combines with Pearson Correlation Coefficient (PCC). There are several problems relating to GRN construction that have been outlined in this paper. We demonstrated the ability of our proposed method to (1) predict the presence of regulatory interactions between genes, (2) their directionality and (3) their states (activation or suppression). The algorithm was applied to network sizes of 10 and 50 genes from DREAM3 datasets and network sizes of 10 from DREAM4 datasets. The predicted networks were evaluated based on AUROC and AUPR. We discovered that high false positive values were generated by our GRN prediction methods because the indirect regulations have been wrongly predicted as true relationships. We achieved satisfactory results as the majority of sub-networks achieved AUROC values above 0.5.

AB - A gene regulatory network (GRN) is a large and complex network consisting of interacting elements that, over time, affect each other's state. The dynamics of complex gene regulatory processes are difficult to understand using intuitive approaches alone. To overcome this problem, we propose an algorithm for inferring the regulatory interactions from knock-out data using a Gaussian model combines with Pearson Correlation Coefficient (PCC). There are several problems relating to GRN construction that have been outlined in this paper. We demonstrated the ability of our proposed method to (1) predict the presence of regulatory interactions between genes, (2) their directionality and (3) their states (activation or suppression). The algorithm was applied to network sizes of 10 and 50 genes from DREAM3 datasets and network sizes of 10 from DREAM4 datasets. The predicted networks were evaluated based on AUROC and AUPR. We discovered that high false positive values were generated by our GRN prediction methods because the indirect regulations have been wrongly predicted as true relationships. We achieved satisfactory results as the majority of sub-networks achieved AUROC values above 0.5.

KW - Bioinformatics

KW - DREAM

KW - Gaussian model

KW - Gene regulatory network

KW - Pearson Correlation Coefficient

KW - Probability and statistics

UR - http://www.scopus.com/inward/record.url?scp=84939857009&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84939857009&partnerID=8YFLogxK

U2 - 10.1016/j.compbiolchem.2015.04.012

DO - 10.1016/j.compbiolchem.2015.04.012

M3 - Article

JO - Computational Biology and Chemistry

JF - Computational Biology and Chemistry

SN - 1476-9271

ER -