Reconstructing gene regulatory networks from homozygous and heterozygous deletion data using Gaussian noise model

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

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

Abstract

A transcription network 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, many research studies have been conducted for reconstructing gene regulatory networks (GRN). In this research study, we propose an algorithm for inferring the regulatory interactions from homozygous and heterozygous deletion data using a Gaussian model. Using simulated gene expression data on networks of known connectivity, we investigate the ability of the proposed algorithm to predict the presence of regulatory interactions between genes and the signed edges (activation or suppression). The algorithm is applied to network sizes of 10 genes and 50 genes for two E.coli subgroups and three S.cerevisiae/Yeast subgroups. The predicted networks were evaluated on the basis of two scoring metrics, area under the ROC curve (AUROC) and area under the precision-recall curve (AUPR). The algorithm has reconstructed the networks with a reasonably low error rate. Our AUPR and AUROC values are consistently higher than the other method compared in this study. The Gaussian model distinguishes real signals from random fluctuations using an iterative method. The analysis of the experiment results reveals that our method can reconstruct networks and predict signed edges with a wide range of network types, connectivity, and noise levels with a reasonable error rate.

Original languageEnglish
Title of host publicationProceedings - 1st International Conference on Artificial Intelligence, Modelling and Simulation, AIMS 2013
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages74-80
Number of pages7
ISBN (Print)9781479932511
DOIs
Publication statusPublished - 14 Nov 2014
Event1st International Conference on Artificial Intelligence, Modelling and Simulation, AIMS 2013 - Kota Kinabalu, Sabah
Duration: 3 Dec 20135 Dec 2013

Other

Other1st International Conference on Artificial Intelligence, Modelling and Simulation, AIMS 2013
CityKota Kinabalu, Sabah
Period3/12/135/12/13

Fingerprint

Gene Regulatory Network
Gaussian Noise
Deletion
Genes
Gene
Receiver Operating Characteristic Curve
Gaussian Model
Signed
Error Rate
Model
Connectivity
Complex networks
Transcription
Subgroup
Iterative methods
Gene expression
Yeast
Escherichia coli
Predict
Curve

Keywords

  • Genetic regulatory networks
  • reverse engineering
  • statistical method

ASJC Scopus subject areas

  • Computer Science(all)
  • Modelling and Simulation

Cite this

Salleh, F. H. M., Arif, S. M., Zainuddin, S., & Mohd Raih, M. F. (2014). Reconstructing gene regulatory networks from homozygous and heterozygous deletion data using Gaussian noise model. In Proceedings - 1st International Conference on Artificial Intelligence, Modelling and Simulation, AIMS 2013 (pp. 74-80). [6959897] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AIMS.2013.19

Reconstructing gene regulatory networks from homozygous and heterozygous deletion data using Gaussian noise model. / Salleh, Faridah Hani Mohamed; Arif, Shereena Mohd; Zainuddin, Suhaila; Mohd Raih, Mohd Firdaus.

Proceedings - 1st International Conference on Artificial Intelligence, Modelling and Simulation, AIMS 2013. Institute of Electrical and Electronics Engineers Inc., 2014. p. 74-80 6959897.

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

Salleh, FHM, Arif, SM, Zainuddin, S & Mohd Raih, MF 2014, Reconstructing gene regulatory networks from homozygous and heterozygous deletion data using Gaussian noise model. in Proceedings - 1st International Conference on Artificial Intelligence, Modelling and Simulation, AIMS 2013., 6959897, Institute of Electrical and Electronics Engineers Inc., pp. 74-80, 1st International Conference on Artificial Intelligence, Modelling and Simulation, AIMS 2013, Kota Kinabalu, Sabah, 3/12/13. https://doi.org/10.1109/AIMS.2013.19
Salleh FHM, Arif SM, Zainuddin S, Mohd Raih MF. Reconstructing gene regulatory networks from homozygous and heterozygous deletion data using Gaussian noise model. In Proceedings - 1st International Conference on Artificial Intelligence, Modelling and Simulation, AIMS 2013. Institute of Electrical and Electronics Engineers Inc. 2014. p. 74-80. 6959897 https://doi.org/10.1109/AIMS.2013.19
Salleh, Faridah Hani Mohamed ; Arif, Shereena Mohd ; Zainuddin, Suhaila ; Mohd Raih, Mohd Firdaus. / Reconstructing gene regulatory networks from homozygous and heterozygous deletion data using Gaussian noise model. Proceedings - 1st International Conference on Artificial Intelligence, Modelling and Simulation, AIMS 2013. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 74-80
@inproceedings{3532c6a047c74a4895225c95b8851e95,
title = "Reconstructing gene regulatory networks from homozygous and heterozygous deletion data using Gaussian noise model",
abstract = "A transcription network 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, many research studies have been conducted for reconstructing gene regulatory networks (GRN). In this research study, we propose an algorithm for inferring the regulatory interactions from homozygous and heterozygous deletion data using a Gaussian model. Using simulated gene expression data on networks of known connectivity, we investigate the ability of the proposed algorithm to predict the presence of regulatory interactions between genes and the signed edges (activation or suppression). The algorithm is applied to network sizes of 10 genes and 50 genes for two E.coli subgroups and three S.cerevisiae/Yeast subgroups. The predicted networks were evaluated on the basis of two scoring metrics, area under the ROC curve (AUROC) and area under the precision-recall curve (AUPR). The algorithm has reconstructed the networks with a reasonably low error rate. Our AUPR and AUROC values are consistently higher than the other method compared in this study. The Gaussian model distinguishes real signals from random fluctuations using an iterative method. The analysis of the experiment results reveals that our method can reconstruct networks and predict signed edges with a wide range of network types, connectivity, and noise levels with a reasonable error rate.",
keywords = "Genetic regulatory networks, reverse engineering, statistical method",
author = "Salleh, {Faridah Hani Mohamed} and Arif, {Shereena Mohd} and Suhaila Zainuddin and {Mohd Raih}, {Mohd Firdaus}",
year = "2014",
month = "11",
day = "14",
doi = "10.1109/AIMS.2013.19",
language = "English",
isbn = "9781479932511",
pages = "74--80",
booktitle = "Proceedings - 1st International Conference on Artificial Intelligence, Modelling and Simulation, AIMS 2013",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Reconstructing gene regulatory networks from homozygous and heterozygous deletion data using Gaussian noise model

AU - Salleh, Faridah Hani Mohamed

AU - Arif, Shereena Mohd

AU - Zainuddin, Suhaila

AU - Mohd Raih, Mohd Firdaus

PY - 2014/11/14

Y1 - 2014/11/14

N2 - A transcription network 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, many research studies have been conducted for reconstructing gene regulatory networks (GRN). In this research study, we propose an algorithm for inferring the regulatory interactions from homozygous and heterozygous deletion data using a Gaussian model. Using simulated gene expression data on networks of known connectivity, we investigate the ability of the proposed algorithm to predict the presence of regulatory interactions between genes and the signed edges (activation or suppression). The algorithm is applied to network sizes of 10 genes and 50 genes for two E.coli subgroups and three S.cerevisiae/Yeast subgroups. The predicted networks were evaluated on the basis of two scoring metrics, area under the ROC curve (AUROC) and area under the precision-recall curve (AUPR). The algorithm has reconstructed the networks with a reasonably low error rate. Our AUPR and AUROC values are consistently higher than the other method compared in this study. The Gaussian model distinguishes real signals from random fluctuations using an iterative method. The analysis of the experiment results reveals that our method can reconstruct networks and predict signed edges with a wide range of network types, connectivity, and noise levels with a reasonable error rate.

AB - A transcription network 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, many research studies have been conducted for reconstructing gene regulatory networks (GRN). In this research study, we propose an algorithm for inferring the regulatory interactions from homozygous and heterozygous deletion data using a Gaussian model. Using simulated gene expression data on networks of known connectivity, we investigate the ability of the proposed algorithm to predict the presence of regulatory interactions between genes and the signed edges (activation or suppression). The algorithm is applied to network sizes of 10 genes and 50 genes for two E.coli subgroups and three S.cerevisiae/Yeast subgroups. The predicted networks were evaluated on the basis of two scoring metrics, area under the ROC curve (AUROC) and area under the precision-recall curve (AUPR). The algorithm has reconstructed the networks with a reasonably low error rate. Our AUPR and AUROC values are consistently higher than the other method compared in this study. The Gaussian model distinguishes real signals from random fluctuations using an iterative method. The analysis of the experiment results reveals that our method can reconstruct networks and predict signed edges with a wide range of network types, connectivity, and noise levels with a reasonable error rate.

KW - Genetic regulatory networks

KW - reverse engineering

KW - statistical method

UR - http://www.scopus.com/inward/record.url?scp=84917680934&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84917680934&partnerID=8YFLogxK

U2 - 10.1109/AIMS.2013.19

DO - 10.1109/AIMS.2013.19

M3 - Conference contribution

AN - SCOPUS:84917680934

SN - 9781479932511

SP - 74

EP - 80

BT - Proceedings - 1st International Conference on Artificial Intelligence, Modelling and Simulation, AIMS 2013

PB - Institute of Electrical and Electronics Engineers Inc.

ER -