Detecting gene interactions within a Bayesian Network framework using external knowledge

Senol Isci, Umut Agyuz, Cengizhan Ozturk, Hasan H Otu

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

1 Citation (Scopus)

Abstract

Biological and clinical databases are increasing at a very high rate making a large volume of experimental data publicly available. In this paper, we propose a framework that makes use of external biological knowledge to predict if two given genes interact with each other. To this end, we utilize prior knowledge about interaction of two genes by generating a Bayesian Network using existing external biological knowledge. External knowledge types to be utilized are obtained from interaction databases such as BioGrid and Reac-tome and consist of protein-protein, protein-DNA/RNA, and gene interactions. We first built a naïve Bayesian Network to predict if two genes interact by employing parameter learning using known gene interactions. We propose that the resulting model will be incorporated into methods learning networks from high throughput biological data and interacting genes will be represented in the form of a network. In this process of network generation, the Bayesian Network model deducing gene interactions from external knowledge will be used to calculate the probability of candidate networks to enhance the structure learning task. Our simulations on both synthetic and real data sets show that proposed framework can successfully enhance identification of the true network and be used in predicting gene interactions.

Original languageEnglish (US)
Title of host publication2012 7th International Symposium on Health Informatics and Bioinformatics, HIBIT 2012
Pages82-87
Number of pages6
DOIs
StatePublished - Jun 29 2012
Event2012 7th International Symposium on Health Informatics and Bioinformatics, HIBIT 2012 - Cappadocia, Turkey
Duration: Apr 19 2012Apr 22 2012

Publication series

Name2012 7th International Symposium on Health Informatics and Bioinformatics, HIBIT 2012

Other

Other2012 7th International Symposium on Health Informatics and Bioinformatics, HIBIT 2012
CountryTurkey
CityCappadocia
Period4/19/124/22/12

Fingerprint

Genes
Learning
Databases
Proteins
RNA
DNA

ASJC Scopus subject areas

  • Health Informatics
  • Health Information Management

Cite this

Isci, S., Agyuz, U., Ozturk, C., & Otu, H. H. (2012). Detecting gene interactions within a Bayesian Network framework using external knowledge. In 2012 7th International Symposium on Health Informatics and Bioinformatics, HIBIT 2012 (pp. 82-87). [6209047] (2012 7th International Symposium on Health Informatics and Bioinformatics, HIBIT 2012). https://doi.org/10.1109/HIBIT.2012.6209047

Detecting gene interactions within a Bayesian Network framework using external knowledge. / Isci, Senol; Agyuz, Umut; Ozturk, Cengizhan; Otu, Hasan H.

2012 7th International Symposium on Health Informatics and Bioinformatics, HIBIT 2012. 2012. p. 82-87 6209047 (2012 7th International Symposium on Health Informatics and Bioinformatics, HIBIT 2012).

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

Isci, S, Agyuz, U, Ozturk, C & Otu, HH 2012, Detecting gene interactions within a Bayesian Network framework using external knowledge. in 2012 7th International Symposium on Health Informatics and Bioinformatics, HIBIT 2012., 6209047, 2012 7th International Symposium on Health Informatics and Bioinformatics, HIBIT 2012, pp. 82-87, 2012 7th International Symposium on Health Informatics and Bioinformatics, HIBIT 2012, Cappadocia, Turkey, 4/19/12. https://doi.org/10.1109/HIBIT.2012.6209047
Isci S, Agyuz U, Ozturk C, Otu HH. Detecting gene interactions within a Bayesian Network framework using external knowledge. In 2012 7th International Symposium on Health Informatics and Bioinformatics, HIBIT 2012. 2012. p. 82-87. 6209047. (2012 7th International Symposium on Health Informatics and Bioinformatics, HIBIT 2012). https://doi.org/10.1109/HIBIT.2012.6209047
Isci, Senol ; Agyuz, Umut ; Ozturk, Cengizhan ; Otu, Hasan H. / Detecting gene interactions within a Bayesian Network framework using external knowledge. 2012 7th International Symposium on Health Informatics and Bioinformatics, HIBIT 2012. 2012. pp. 82-87 (2012 7th International Symposium on Health Informatics and Bioinformatics, HIBIT 2012).
@inproceedings{fd1724429f7a482480708b11a8bb93e7,
title = "Detecting gene interactions within a Bayesian Network framework using external knowledge",
abstract = "Biological and clinical databases are increasing at a very high rate making a large volume of experimental data publicly available. In this paper, we propose a framework that makes use of external biological knowledge to predict if two given genes interact with each other. To this end, we utilize prior knowledge about interaction of two genes by generating a Bayesian Network using existing external biological knowledge. External knowledge types to be utilized are obtained from interaction databases such as BioGrid and Reac-tome and consist of protein-protein, protein-DNA/RNA, and gene interactions. We first built a na{\"i}ve Bayesian Network to predict if two genes interact by employing parameter learning using known gene interactions. We propose that the resulting model will be incorporated into methods learning networks from high throughput biological data and interacting genes will be represented in the form of a network. In this process of network generation, the Bayesian Network model deducing gene interactions from external knowledge will be used to calculate the probability of candidate networks to enhance the structure learning task. Our simulations on both synthetic and real data sets show that proposed framework can successfully enhance identification of the true network and be used in predicting gene interactions.",
author = "Senol Isci and Umut Agyuz and Cengizhan Ozturk and Otu, {Hasan H}",
year = "2012",
month = "6",
day = "29",
doi = "10.1109/HIBIT.2012.6209047",
language = "English (US)",
isbn = "9781467308786",
series = "2012 7th International Symposium on Health Informatics and Bioinformatics, HIBIT 2012",
pages = "82--87",
booktitle = "2012 7th International Symposium on Health Informatics and Bioinformatics, HIBIT 2012",

}

TY - GEN

T1 - Detecting gene interactions within a Bayesian Network framework using external knowledge

AU - Isci, Senol

AU - Agyuz, Umut

AU - Ozturk, Cengizhan

AU - Otu, Hasan H

PY - 2012/6/29

Y1 - 2012/6/29

N2 - Biological and clinical databases are increasing at a very high rate making a large volume of experimental data publicly available. In this paper, we propose a framework that makes use of external biological knowledge to predict if two given genes interact with each other. To this end, we utilize prior knowledge about interaction of two genes by generating a Bayesian Network using existing external biological knowledge. External knowledge types to be utilized are obtained from interaction databases such as BioGrid and Reac-tome and consist of protein-protein, protein-DNA/RNA, and gene interactions. We first built a naïve Bayesian Network to predict if two genes interact by employing parameter learning using known gene interactions. We propose that the resulting model will be incorporated into methods learning networks from high throughput biological data and interacting genes will be represented in the form of a network. In this process of network generation, the Bayesian Network model deducing gene interactions from external knowledge will be used to calculate the probability of candidate networks to enhance the structure learning task. Our simulations on both synthetic and real data sets show that proposed framework can successfully enhance identification of the true network and be used in predicting gene interactions.

AB - Biological and clinical databases are increasing at a very high rate making a large volume of experimental data publicly available. In this paper, we propose a framework that makes use of external biological knowledge to predict if two given genes interact with each other. To this end, we utilize prior knowledge about interaction of two genes by generating a Bayesian Network using existing external biological knowledge. External knowledge types to be utilized are obtained from interaction databases such as BioGrid and Reac-tome and consist of protein-protein, protein-DNA/RNA, and gene interactions. We first built a naïve Bayesian Network to predict if two genes interact by employing parameter learning using known gene interactions. We propose that the resulting model will be incorporated into methods learning networks from high throughput biological data and interacting genes will be represented in the form of a network. In this process of network generation, the Bayesian Network model deducing gene interactions from external knowledge will be used to calculate the probability of candidate networks to enhance the structure learning task. Our simulations on both synthetic and real data sets show that proposed framework can successfully enhance identification of the true network and be used in predicting gene interactions.

UR - http://www.scopus.com/inward/record.url?scp=84862726762&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862726762&partnerID=8YFLogxK

U2 - 10.1109/HIBIT.2012.6209047

DO - 10.1109/HIBIT.2012.6209047

M3 - Conference contribution

SN - 9781467308786

T3 - 2012 7th International Symposium on Health Informatics and Bioinformatics, HIBIT 2012

SP - 82

EP - 87

BT - 2012 7th International Symposium on Health Informatics and Bioinformatics, HIBIT 2012

ER -