Bayesian network prior: Network analysis of biological data using external knowledge

Senol Isci, Haluk Dogan, Cengizhan Ozturk, Hasan H. Otu

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

Motivation: Reverse engineering GI networks from experimental data is a challenging task due to the complex nature of the networks and the noise inherent in the data. One way to overcome these hurdles would be incorporating the vast amounts of external biological knowledge when building interaction networks. We propose a framework where GI networks are learned from experimental data using Bayesian networks (BNs) and the incorporation of external knowledge is also done via a BN that we call Bayesian Network Prior (BNP). BNP depicts the relation between various evidence types that contribute to the event 'gene interaction' and is used to calculate the probability of a candidate graph (G) in the structure learning process.Results: Our simulation results on synthetic, simulated and real biological data show that the proposed approach can identify the underlying interaction network with high accuracy even when the prior information is distorted and outperforms existing methods.

Original languageEnglish (US)
Pages (from-to)860-867
Number of pages8
JournalBioinformatics
Volume30
Issue number6
DOIs
StatePublished - Mar 1 2014

Fingerprint

Network Analysis
Bayesian networks
Electric network analysis
Bayesian Networks
Noise
Learning
Genes
Interaction
Reverse engineering
Experimental Data
Structure Learning
Reverse Engineering
Prior Information
Learning Process
High Accuracy
Knowledge
Gene
Calculate
Graph in graph theory
Simulation

ASJC Scopus subject areas

  • Statistics and Probability
  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Computational Theory and Mathematics
  • Computational Mathematics

Cite this

Bayesian network prior : Network analysis of biological data using external knowledge. / Isci, Senol; Dogan, Haluk; Ozturk, Cengizhan; Otu, Hasan H.

In: Bioinformatics, Vol. 30, No. 6, 01.03.2014, p. 860-867.

Research output: Contribution to journalArticle

Isci, Senol ; Dogan, Haluk ; Ozturk, Cengizhan ; Otu, Hasan H. / Bayesian network prior : Network analysis of biological data using external knowledge. In: Bioinformatics. 2014 ; Vol. 30, No. 6. pp. 860-867.
@article{b4266846052d4abbb3a7edde43c4aaf8,
title = "Bayesian network prior: Network analysis of biological data using external knowledge",
abstract = "Motivation: Reverse engineering GI networks from experimental data is a challenging task due to the complex nature of the networks and the noise inherent in the data. One way to overcome these hurdles would be incorporating the vast amounts of external biological knowledge when building interaction networks. We propose a framework where GI networks are learned from experimental data using Bayesian networks (BNs) and the incorporation of external knowledge is also done via a BN that we call Bayesian Network Prior (BNP). BNP depicts the relation between various evidence types that contribute to the event 'gene interaction' and is used to calculate the probability of a candidate graph (G) in the structure learning process.Results: Our simulation results on synthetic, simulated and real biological data show that the proposed approach can identify the underlying interaction network with high accuracy even when the prior information is distorted and outperforms existing methods.",
author = "Senol Isci and Haluk Dogan and Cengizhan Ozturk and Otu, {Hasan H.}",
year = "2014",
month = "3",
day = "1",
doi = "10.1093/bioinformatics/btt643",
language = "English (US)",
volume = "30",
pages = "860--867",
journal = "Bioinformatics",
issn = "1367-4803",
publisher = "Oxford University Press",
number = "6",

}

TY - JOUR

T1 - Bayesian network prior

T2 - Network analysis of biological data using external knowledge

AU - Isci, Senol

AU - Dogan, Haluk

AU - Ozturk, Cengizhan

AU - Otu, Hasan H.

PY - 2014/3/1

Y1 - 2014/3/1

N2 - Motivation: Reverse engineering GI networks from experimental data is a challenging task due to the complex nature of the networks and the noise inherent in the data. One way to overcome these hurdles would be incorporating the vast amounts of external biological knowledge when building interaction networks. We propose a framework where GI networks are learned from experimental data using Bayesian networks (BNs) and the incorporation of external knowledge is also done via a BN that we call Bayesian Network Prior (BNP). BNP depicts the relation between various evidence types that contribute to the event 'gene interaction' and is used to calculate the probability of a candidate graph (G) in the structure learning process.Results: Our simulation results on synthetic, simulated and real biological data show that the proposed approach can identify the underlying interaction network with high accuracy even when the prior information is distorted and outperforms existing methods.

AB - Motivation: Reverse engineering GI networks from experimental data is a challenging task due to the complex nature of the networks and the noise inherent in the data. One way to overcome these hurdles would be incorporating the vast amounts of external biological knowledge when building interaction networks. We propose a framework where GI networks are learned from experimental data using Bayesian networks (BNs) and the incorporation of external knowledge is also done via a BN that we call Bayesian Network Prior (BNP). BNP depicts the relation between various evidence types that contribute to the event 'gene interaction' and is used to calculate the probability of a candidate graph (G) in the structure learning process.Results: Our simulation results on synthetic, simulated and real biological data show that the proposed approach can identify the underlying interaction network with high accuracy even when the prior information is distorted and outperforms existing methods.

UR - http://www.scopus.com/inward/record.url?scp=84897891549&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897891549&partnerID=8YFLogxK

U2 - 10.1093/bioinformatics/btt643

DO - 10.1093/bioinformatics/btt643

M3 - Article

C2 - 24215027

AN - SCOPUS:84897891549

VL - 30

SP - 860

EP - 867

JO - Bioinformatics

JF - Bioinformatics

SN - 1367-4803

IS - 6

ER -