Investigation of the effects of imputation methods for gene regulatory networks modelling using dynamic bayesian networks

Sin Yi Lim; Mohd Saberi Mohamad; Lian En Chai; Safaai Deris; Weng Howe Chan; Sigeru Omatu; Juan Manuel Corchado; Muhammad Farhan Sjaugi; Muhammad Mahfuz Zainuddin; Gopinathaan Rajamohan; Zuwairie Ibrahim; Zulkifli Md Yusof

doi:10.1007/978-3-319-40162-1_45

Investigation of the effects of imputation methods for gene regulatory networks modelling using dynamic bayesian networks

Sin Yi Lim, Mohd Saberi Mohamad, Lian En Chai, Safaai Deris, Weng Howe Chan, Sigeru Omatu, Juan Manuel Corchado, Muhammad Farhan Sjaugi, Muhammad Mahfuz Zainuddin, Gopinathaan Rajamohan, Zuwairie Ibrahim, Zulkifli Md Yusof

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Citations (Scopus)

Abstract

DNA microarray technology plays an important role in advancing the analysis of gene expression and gene functions. However, gene expression data often contain missing values, which cause problems as most of the analysis methods of gene expression data require a complete matrix. Several missing value imputation methods have been developed to overcome the problems. In this paper, effects of the missing value imputation methods in modeling of gene regulatory network are investigated. Three missing value imputation methods are used, which are k-Nearest Neighbor (kNN), Iterated Local Least Squares (ILLsimpute), and Fixed Rank Approximation Algorithm (FRAA). Dataset used in this paper is E. coli. The results suggest that the performance of each missing value imputation method is influenced by the percentage and distribution of the missing values in the dataset, which subsequently affect the modeling of gene regulatory network using Dynamic Bayesian network.

Original language	English
Title of host publication	Distributed Computing and Artificial Intelligence, 13th International Conference
Editors	Julián A. García-García, Ali Semalat, Grzegorz Bocewicz, Paweł Sitek, Javier Bajo, Sigeru Omatu, Izabela Nielsen
Publisher	Springer Verlag
Pages	413-421
Number of pages	9
ISBN (Print)	9783319401614
DOIs	https://doi.org/10.1007/978-3-319-40162-1_45
Publication status	Published - 2016
Externally published	Yes
Event	13th International Conference on Distributed Computing and Artificial Intelligence, DCAI 2016 - Sevilla, Spain Duration: Jun 1 2016 → Jun 3 2016

Publication series

Name	Advances in Intelligent Systems and Computing
Volume	474
ISSN (Print)	2194-5357

Conference

Conference	13th International Conference on Distributed Computing and Artificial Intelligence, DCAI 2016
Country/Territory	Spain
City	Sevilla
Period	6/1/16 → 6/3/16

Keywords

Artificial intelligence
Bioinformatics
Dynamic bayesian network
Gene expression
Gene expression data
Gene regulatory network
Imputation methods
Missing values

ASJC Scopus subject areas

Control and Systems Engineering
General Computer Science

Access to Document

10.1007/978-3-319-40162-1_45

Cite this

Lim, S. Y., Mohamad, M. S., Chai, L. E., Deris, S., Chan, W. H., Omatu, S., Corchado, J. M., Sjaugi, M. F., Zainuddin, M. M., Rajamohan, G., Ibrahim, Z., & Yusof, Z. M. (2016). Investigation of the effects of imputation methods for gene regulatory networks modelling using dynamic bayesian networks. In J. A. García-García, A. Semalat, G. Bocewicz, P. Sitek, J. Bajo, S. Omatu, & I. Nielsen (Eds.), Distributed Computing and Artificial Intelligence, 13th International Conference (pp. 413-421). (Advances in Intelligent Systems and Computing; Vol. 474). Springer Verlag. https://doi.org/10.1007/978-3-319-40162-1_45

Investigation of the effects of imputation methods for gene regulatory networks modelling using dynamic bayesian networks. / Lim, Sin Yi; Mohamad, Mohd Saberi; Chai, Lian En et al.
Distributed Computing and Artificial Intelligence, 13th International Conference. ed. / Julián A. García-García; Ali Semalat; Grzegorz Bocewicz; Paweł Sitek; Javier Bajo; Sigeru Omatu; Izabela Nielsen. Springer Verlag, 2016. p. 413-421 (Advances in Intelligent Systems and Computing; Vol. 474).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Lim, SY, Mohamad, MS, Chai, LE, Deris, S, Chan, WH, Omatu, S, Corchado, JM, Sjaugi, MF, Zainuddin, MM, Rajamohan, G, Ibrahim, Z & Yusof, ZM 2016, Investigation of the effects of imputation methods for gene regulatory networks modelling using dynamic bayesian networks. in JA García-García, A Semalat, G Bocewicz, P Sitek, J Bajo, S Omatu & I Nielsen (eds), Distributed Computing and Artificial Intelligence, 13th International Conference. Advances in Intelligent Systems and Computing, vol. 474, Springer Verlag, pp. 413-421, 13th International Conference on Distributed Computing and Artificial Intelligence, DCAI 2016, Sevilla, Spain, 6/1/16. https://doi.org/10.1007/978-3-319-40162-1_45

Lim SY, Mohamad MS, Chai LE, Deris S, Chan WH, Omatu S et al. Investigation of the effects of imputation methods for gene regulatory networks modelling using dynamic bayesian networks. In García-García JA, Semalat A, Bocewicz G, Sitek P, Bajo J, Omatu S, Nielsen I, editors, Distributed Computing and Artificial Intelligence, 13th International Conference. Springer Verlag. 2016. p. 413-421. (Advances in Intelligent Systems and Computing). doi: 10.1007/978-3-319-40162-1_45

Lim, Sin Yi ; Mohamad, Mohd Saberi ; Chai, Lian En et al. / Investigation of the effects of imputation methods for gene regulatory networks modelling using dynamic bayesian networks. Distributed Computing and Artificial Intelligence, 13th International Conference. editor / Julián A. García-García ; Ali Semalat ; Grzegorz Bocewicz ; Paweł Sitek ; Javier Bajo ; Sigeru Omatu ; Izabela Nielsen. Springer Verlag, 2016. pp. 413-421 (Advances in Intelligent Systems and Computing).

@inproceedings{d9dcd8fff0744b91b7697736f72d618f,

title = "Investigation of the effects of imputation methods for gene regulatory networks modelling using dynamic bayesian networks",

abstract = "DNA microarray technology plays an important role in advancing the analysis of gene expression and gene functions. However, gene expression data often contain missing values, which cause problems as most of the analysis methods of gene expression data require a complete matrix. Several missing value imputation methods have been developed to overcome the problems. In this paper, effects of the missing value imputation methods in modeling of gene regulatory network are investigated. Three missing value imputation methods are used, which are k-Nearest Neighbor (kNN), Iterated Local Least Squares (ILLsimpute), and Fixed Rank Approximation Algorithm (FRAA). Dataset used in this paper is E. coli. The results suggest that the performance of each missing value imputation method is influenced by the percentage and distribution of the missing values in the dataset, which subsequently affect the modeling of gene regulatory network using Dynamic Bayesian network.",

keywords = "Artificial intelligence, Bioinformatics, Dynamic bayesian network, Gene expression, Gene expression data, Gene regulatory network, Imputation methods, Missing values",

author = "Lim, {Sin Yi} and Mohamad, {Mohd Saberi} and Chai, {Lian En} and Safaai Deris and Chan, {Weng Howe} and Sigeru Omatu and Corchado, {Juan Manuel} and Sjaugi, {Muhammad Farhan} and Zainuddin, {Muhammad Mahfuz} and Gopinathaan Rajamohan and Zuwairie Ibrahim and Yusof, {Zulkifli Md}",

note = "Publisher Copyright: {\textcopyright} Springer International Publishing Switzerland 2016.; 13th International Conference on Distributed Computing and Artificial Intelligence, DCAI 2016 ; Conference date: 01-06-2016 Through 03-06-2016",

year = "2016",

doi = "10.1007/978-3-319-40162-1_45",

language = "English",

isbn = "9783319401614",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer Verlag",

pages = "413--421",

editor = "Garc{\'i}a-Garc{\'i}a, {Juli{\'a}n A.} and Ali Semalat and Grzegorz Bocewicz and Pawe{\l} Sitek and Javier Bajo and Sigeru Omatu and Izabela Nielsen",

booktitle = "Distributed Computing and Artificial Intelligence, 13th International Conference",

}

TY - GEN

T1 - Investigation of the effects of imputation methods for gene regulatory networks modelling using dynamic bayesian networks

AU - Lim, Sin Yi

AU - Mohamad, Mohd Saberi

AU - Chai, Lian En

AU - Deris, Safaai

AU - Chan, Weng Howe

AU - Omatu, Sigeru

AU - Corchado, Juan Manuel

AU - Sjaugi, Muhammad Farhan

AU - Zainuddin, Muhammad Mahfuz

AU - Rajamohan, Gopinathaan

AU - Ibrahim, Zuwairie

AU - Yusof, Zulkifli Md

N1 - Publisher Copyright: © Springer International Publishing Switzerland 2016.

PY - 2016

Y1 - 2016

N2 - DNA microarray technology plays an important role in advancing the analysis of gene expression and gene functions. However, gene expression data often contain missing values, which cause problems as most of the analysis methods of gene expression data require a complete matrix. Several missing value imputation methods have been developed to overcome the problems. In this paper, effects of the missing value imputation methods in modeling of gene regulatory network are investigated. Three missing value imputation methods are used, which are k-Nearest Neighbor (kNN), Iterated Local Least Squares (ILLsimpute), and Fixed Rank Approximation Algorithm (FRAA). Dataset used in this paper is E. coli. The results suggest that the performance of each missing value imputation method is influenced by the percentage and distribution of the missing values in the dataset, which subsequently affect the modeling of gene regulatory network using Dynamic Bayesian network.

AB - DNA microarray technology plays an important role in advancing the analysis of gene expression and gene functions. However, gene expression data often contain missing values, which cause problems as most of the analysis methods of gene expression data require a complete matrix. Several missing value imputation methods have been developed to overcome the problems. In this paper, effects of the missing value imputation methods in modeling of gene regulatory network are investigated. Three missing value imputation methods are used, which are k-Nearest Neighbor (kNN), Iterated Local Least Squares (ILLsimpute), and Fixed Rank Approximation Algorithm (FRAA). Dataset used in this paper is E. coli. The results suggest that the performance of each missing value imputation method is influenced by the percentage and distribution of the missing values in the dataset, which subsequently affect the modeling of gene regulatory network using Dynamic Bayesian network.

KW - Artificial intelligence

KW - Bioinformatics

KW - Dynamic bayesian network

KW - Gene expression

KW - Gene expression data

KW - Gene regulatory network

KW - Imputation methods

KW - Missing values

UR - http://www.scopus.com/inward/record.url?scp=84975521332&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84975521332&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-40162-1_45

DO - 10.1007/978-3-319-40162-1_45

M3 - Conference contribution

AN - SCOPUS:84975521332

SN - 9783319401614

T3 - Advances in Intelligent Systems and Computing

SP - 413

EP - 421

BT - Distributed Computing and Artificial Intelligence, 13th International Conference

A2 - García-García, Julián A.

A2 - Semalat, Ali

A2 - Bocewicz, Grzegorz

A2 - Sitek, Paweł

A2 - Bajo, Javier

A2 - Omatu, Sigeru

A2 - Nielsen, Izabela

PB - Springer Verlag

T2 - 13th International Conference on Distributed Computing and Artificial Intelligence, DCAI 2016

Y2 - 1 June 2016 through 3 June 2016

ER -

Investigation of the effects of imputation methods for gene regulatory networks modelling using dynamic bayesian networks

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this