Combining clustering and bayesian network for gene network inference

Suhaila Zainudin, Safaai Deris

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

4 Citations (Scopus)

Abstract

Gene network reconstruction is a multidisciplinary research area involving datamining, machine learning, statistics, ontologies and others. Reconstructed gene network allows us to understand how genes interact with each other. However, network construction is very complex due to highly interactive nature of genes. A proposed approach to solve this complex problem is to cluster the genes according to similarity in their gene expression profiles. We applied k-means clustering with k = 10 to come up with ten clusters of genes. Then, we applied Bayesian Network structure learning with Hill- climbing search strategy and Akaike Information Criterion score to search for the best network. We compared inferred interactions to a reference positive interactions dataset and found similarities between our inferred interactions and the reference. We further study the gene interactions using Gene Ontology. From our findings, we conclude that the clustering step is essential in gene network reconstruction. Clustering produced better group of genes for Bayesian Network learning. Larger clusters also produced more gene interactions. Gene Ontology can be combined with clustering to produce better quality clusters to improve gene network construction.

Original languageEnglish
Title of host publicationProceedings - 8th International Conference on Intelligent Systems Design and Applications, ISDA 2008
Pages557-563
Number of pages7
Volume2
DOIs
Publication statusPublished - 2008
Event8th International Conference on Intelligent Systems Design and Applications, ISDA 2008 - Kaohsiung
Duration: 26 Nov 200828 Nov 2008

Other

Other8th International Conference on Intelligent Systems Design and Applications, ISDA 2008
CityKaohsiung
Period26/11/0828/11/08

Fingerprint

Bayesian networks
Genes
Ontology
Gene expression
Learning systems
Statistics

ASJC Scopus subject areas

  • Artificial Intelligence
  • Control and Systems Engineering

Cite this

Zainudin, S., & Deris, S. (2008). Combining clustering and bayesian network for gene network inference. In Proceedings - 8th International Conference on Intelligent Systems Design and Applications, ISDA 2008 (Vol. 2, pp. 557-563). [4696392] https://doi.org/10.1109/ISDA.2008.183

Combining clustering and bayesian network for gene network inference. / Zainudin, Suhaila; Deris, Safaai.

Proceedings - 8th International Conference on Intelligent Systems Design and Applications, ISDA 2008. Vol. 2 2008. p. 557-563 4696392.

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

Zainudin, S & Deris, S 2008, Combining clustering and bayesian network for gene network inference. in Proceedings - 8th International Conference on Intelligent Systems Design and Applications, ISDA 2008. vol. 2, 4696392, pp. 557-563, 8th International Conference on Intelligent Systems Design and Applications, ISDA 2008, Kaohsiung, 26/11/08. https://doi.org/10.1109/ISDA.2008.183
Zainudin S, Deris S. Combining clustering and bayesian network for gene network inference. In Proceedings - 8th International Conference on Intelligent Systems Design and Applications, ISDA 2008. Vol. 2. 2008. p. 557-563. 4696392 https://doi.org/10.1109/ISDA.2008.183
Zainudin, Suhaila ; Deris, Safaai. / Combining clustering and bayesian network for gene network inference. Proceedings - 8th International Conference on Intelligent Systems Design and Applications, ISDA 2008. Vol. 2 2008. pp. 557-563
@inproceedings{df545a6a470c4f869f3b2c9ffe6b407f,
title = "Combining clustering and bayesian network for gene network inference",
abstract = "Gene network reconstruction is a multidisciplinary research area involving datamining, machine learning, statistics, ontologies and others. Reconstructed gene network allows us to understand how genes interact with each other. However, network construction is very complex due to highly interactive nature of genes. A proposed approach to solve this complex problem is to cluster the genes according to similarity in their gene expression profiles. We applied k-means clustering with k = 10 to come up with ten clusters of genes. Then, we applied Bayesian Network structure learning with Hill- climbing search strategy and Akaike Information Criterion score to search for the best network. We compared inferred interactions to a reference positive interactions dataset and found similarities between our inferred interactions and the reference. We further study the gene interactions using Gene Ontology. From our findings, we conclude that the clustering step is essential in gene network reconstruction. Clustering produced better group of genes for Bayesian Network learning. Larger clusters also produced more gene interactions. Gene Ontology can be combined with clustering to produce better quality clusters to improve gene network construction.",
author = "Suhaila Zainudin and Safaai Deris",
year = "2008",
doi = "10.1109/ISDA.2008.183",
language = "English",
isbn = "9780769533827",
volume = "2",
pages = "557--563",
booktitle = "Proceedings - 8th International Conference on Intelligent Systems Design and Applications, ISDA 2008",

}

TY - GEN

T1 - Combining clustering and bayesian network for gene network inference

AU - Zainudin, Suhaila

AU - Deris, Safaai

PY - 2008

Y1 - 2008

N2 - Gene network reconstruction is a multidisciplinary research area involving datamining, machine learning, statistics, ontologies and others. Reconstructed gene network allows us to understand how genes interact with each other. However, network construction is very complex due to highly interactive nature of genes. A proposed approach to solve this complex problem is to cluster the genes according to similarity in their gene expression profiles. We applied k-means clustering with k = 10 to come up with ten clusters of genes. Then, we applied Bayesian Network structure learning with Hill- climbing search strategy and Akaike Information Criterion score to search for the best network. We compared inferred interactions to a reference positive interactions dataset and found similarities between our inferred interactions and the reference. We further study the gene interactions using Gene Ontology. From our findings, we conclude that the clustering step is essential in gene network reconstruction. Clustering produced better group of genes for Bayesian Network learning. Larger clusters also produced more gene interactions. Gene Ontology can be combined with clustering to produce better quality clusters to improve gene network construction.

AB - Gene network reconstruction is a multidisciplinary research area involving datamining, machine learning, statistics, ontologies and others. Reconstructed gene network allows us to understand how genes interact with each other. However, network construction is very complex due to highly interactive nature of genes. A proposed approach to solve this complex problem is to cluster the genes according to similarity in their gene expression profiles. We applied k-means clustering with k = 10 to come up with ten clusters of genes. Then, we applied Bayesian Network structure learning with Hill- climbing search strategy and Akaike Information Criterion score to search for the best network. We compared inferred interactions to a reference positive interactions dataset and found similarities between our inferred interactions and the reference. We further study the gene interactions using Gene Ontology. From our findings, we conclude that the clustering step is essential in gene network reconstruction. Clustering produced better group of genes for Bayesian Network learning. Larger clusters also produced more gene interactions. Gene Ontology can be combined with clustering to produce better quality clusters to improve gene network construction.

UR - http://www.scopus.com/inward/record.url?scp=67449128468&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67449128468&partnerID=8YFLogxK

U2 - 10.1109/ISDA.2008.183

DO - 10.1109/ISDA.2008.183

M3 - Conference contribution

AN - SCOPUS:67449128468

SN - 9780769533827

VL - 2

SP - 557

EP - 563

BT - Proceedings - 8th International Conference on Intelligent Systems Design and Applications, ISDA 2008

ER -