Graph based gene/protein prediction and clustering over uncertain medical databases.

Bano, Shahana; Rao, K. Rajasekhara

Abstract

Clustering over protein or gene data is now a popular issue in biomedical databases. In general, large sets of gene tags are clustered using high computation techniques over gene or protein distributed data. Most of the traditional clustering techniques are based on subspace, hierarchical and partitioning feature extraction. Various clustering techniques have been proposed in the literature with different cluster measures, but their performance is limited due to spatial noise and uncertainty. In this paper, an improved graph-based clustering technique is proposed for the generation of efficient gene or protein clusters over uncertain and noisy data. The proposed graph-based visualization can effectively identify different types of genes or proteins along with relational attributes. Experimental results show that the proposed graph model more effectively clusters complex gene or protein data when compared with conventional clustering approaches.

Citation

BANO, S. and RAO, K.R. 2015. Graph based gene/protein prediction and clustering over uncertain medical databases. Journal of theoretical and applied information technology [online], 82(3), pages 347-352. Available from: https://www.jatit.org/volumes/Vol82No3/2Vol82No3.pdf

• Journal Article Type: Article
• Acceptance Date: Dec 31, 2015
• Online Publication Date: Dec 31, 2015
• Publication Date: Dec 31, 2015
• Deposit Date: Sep 22, 2023
• Publicly Available Date: Sep 22, 2023
• Journal: Journal of theoretical and applied information technology
• Print ISSN: 1992-8645
• Electronic ISSN: 1817-3195
• Publisher: Journal of Theoretical and Applied Information Technology
• Peer Reviewed: Peer Reviewed
• Volume: 82
• Issue: 3
• Pages: 347-352
• Keywords: Data clustering; Biomedical data; Gene sequencing; Protein sequencing; Pattern recognition
• Public URL: https://rgu-repository.worktribe.com/output/2064136
• Publisher URL: https://www.jatit.org/volumes/Vol82No3/2Vol82No3.pdf