Reason-A Technical Journal (Formerly Reason-A Technical Magazine)

Open Access Open Access  Restricted Access Subscription Access

Construction and Comparison of Gene Regulatory Networks of Human Hiv-1 VPR Microarray Datasets by Radial Basis Neural Network Approach


Affiliations
1 Department of Electronics and Communication Engineering, Kalyani Government Engineering College, Kalyani- 741235, Dist. Nadia, West Bengal, India
 

Gene Regulatory Network (GRN) construction by using neural network approach is very important and useful approach for analyzing microarray gene expression microarray datasets. The human HIV-1 Vpr mutant microarray time series gene expression value carries the experimentally validated interaction records. Firstly, the subtractive clustering approach is used to cluster the microarray data. Secondly, GRN is constructed within cluster centers of HIV-1 Vpr mutant dataset using Radial Basis Neural Network approach. The optimized output of genetic network is found using genetic algorithm. Then the influence of range of cluster centers of data clusters and also GRN outputs are compared. It is found that proximity of gene expressed values in wild type cell line HIV-1 is higher than other two HIV-1 Vpr mutants. In this paper, the nature of network output functions are also identified.

Keywords

AIDS, HIV-1 Vpr Mutants, Time Series Microarray Data, Subtractive Clustering, Genetic Network, Radial Basis Neural Network, Genetic Algorithm.
User
Notifications
Font Size


  • Zhao, R.Y.,Bukrinsky, M. and Elder, R.T., HIV-1 viral protein R (Vpr) and host cellular responses, The Indian Journal of Medical Research, Vol. 121, No.4, pp. 270-286, 2005.

  • Yao, X.J.,Rougeau, N. and Duisit, G., Analysis of HIV-1 Vpr determinantsresponsible for cell growth arrest in Saccharomyces cerevisiae, Retrovirology, Vol. 1, No.21, 2004.

  • Kogan, M. and Rappaport, J., HIV1Accessory ProteinVpr: Relevance in the pathogenesisof HIV and potential for therapeutic intervention, Retrovirology, Vol. 8, No.25, pp. 25-44, 2011.

  • Sarafianos, S.G., Das, K. and Tantillo, C., Crystal structure of HIV-1 reversetranscriptase in complex with a polypurine tract RNA:DNA, The EMBO Journal, Vol.20, No.6, pp.1449-1461, 2001.

  • Doan , C.D.,Liong, S.Y. and Karunasinghe, D. S.K., Derivation of ef fective and efficientdata set with subtractive clustering method and genetic algorithm, Journal of Hydroinformatics,Vol. 7, No.4, pp. 219-233, 2005.

  • Bataineh, K.M., Najia, M. and Saqera, M., A Comparison Study between VariousFuzzy Clustering Algorithms’, Jordan Journal ofMechanical and Industrial Engineering, Vol. 5(4), pp. 335-343, 2011.

  • Priyono, A.,Ridwan, M. and Alias, A. J., Generation of Fuzzy Rules with Subtractive Clustering, Journal Teknologi, Vol. 43, pp. 143-153, 2007.

  • Goyal, S. and Goyal, G.K., Radial Basis (Exact Fit) Artif icialNeural Network Techniquefor Estimating Shelf Life of Burfi, Advances in Computer Science and its Applications, Vol. 1, No.2, pp.93-96, 2012.

  • Orr, M.J.L., Introduction to radial basis function networks, Technical Report,Centre for Cognitive Science, University of Edinburgh, Scotland, 1996.

  • Fiszelew, A., Britos, P. and Ochoa, A., Finding Optimal Neural Network ArchitectureUsing Genetic Algorithms’, Advances in Computer Science and Engineering Research in Computing Science,Vol. 27, pp. 15-24, 2007.

  • Zhang, B.T. and Muhlenbein, H., Evolving Optimal Neural Networks Using GeneticAlgorithms with Occams’ Razor’, Complex Systems, Vol. 7, No.3, pp. 199220, 1993.

  • Sug, H., Generating Better Radial Basis Function Network for Large Data Set of Census,International Journal of Software Engineering and Its Applications, Vol. 4 (2), pp. 15-22, 2010.

  • Barman, B. and Mukhopadhyay, A., Construction of GA-optimized Radial Basis Neural Network from HIV-1 Vpr Mutant Microarray Gene Expression Data, Proceedings of International Conference on Computational Intelligence: Modeling, Techniques and Applications (CIMTA 2013),Kalyani, India, Procedia Technology, Vol. 10, pp. 450-456, 2013.

  • Barman, B.,Biswas, P. and Mukhopadhyay, A., Comparison of gene regulatory networks usingadaptive neural network and selforganising map approach over Huh7 hepatoma cell microarray datamatrix, International Journal of Bio-Inspired Computation, Vol. 8, No.4, pp. 240-247, 2016.


Abstract Views: 447

PDF Views: 160




  • Construction and Comparison of Gene Regulatory Networks of Human Hiv-1 VPR Microarray Datasets by Radial Basis Neural Network Approach

Abstract Views: 447  |  PDF Views: 160

Authors

Bandana Barman
Department of Electronics and Communication Engineering, Kalyani Government Engineering College, Kalyani- 741235, Dist. Nadia, West Bengal, India

Abstract


Gene Regulatory Network (GRN) construction by using neural network approach is very important and useful approach for analyzing microarray gene expression microarray datasets. The human HIV-1 Vpr mutant microarray time series gene expression value carries the experimentally validated interaction records. Firstly, the subtractive clustering approach is used to cluster the microarray data. Secondly, GRN is constructed within cluster centers of HIV-1 Vpr mutant dataset using Radial Basis Neural Network approach. The optimized output of genetic network is found using genetic algorithm. Then the influence of range of cluster centers of data clusters and also GRN outputs are compared. It is found that proximity of gene expressed values in wild type cell line HIV-1 is higher than other two HIV-1 Vpr mutants. In this paper, the nature of network output functions are also identified.

Keywords


AIDS, HIV-1 Vpr Mutants, Time Series Microarray Data, Subtractive Clustering, Genetic Network, Radial Basis Neural Network, Genetic Algorithm.

References





DOI: https://doi.org/10.21843/reas%2F2016%2F61-69%2F158777