Home

Network Biology, 2018, 8(2): 65-82
[XML] [EndNote] [RefManager] [BibTex] [ Full PDF (887K)] [Comment/Review Article]

Article

Classification and prediction of dengue fever from microarray samples by LDA based on PPI network

Nahida Habib1, Kawsar Ahmed2,3, Md. Binyamin4, M. Mesbahuddin Sarker5, K. M. Akkas Ali5
1Department of Computer Science and Engineering, Mawlana Bhashani Science and Technology University, Santosh, Tangail-1902, Bangladesh
2Group of Bio-photomatix, Santosh, Tangail-1902, Bangladesh
3Department of Information and Communication Technology, Mawlana Bhashani Science and Technology University, Santosh, Tangail-1902, Bangladesh
4Department of Statistics, Mawlana Bhashani Science and Technology University, Santosh, Tangail-1902, Bangladesh
5Institute of Information Technology (IIT), Jahangirnagar University, Dhaka, Bangladesh

Received 6 December 2017;Accepted 10 January 2018;Published 1 June 2018
IAEES

Abstract
Modern Bioinformatics tools have a tremendous contribution in gene analysis, Protein-Protein Interaction (PPI) Network creation and Drug design. It's been a big challenge to pick out a small subset of informative data from a large microarray dataset and reach on an accurate classification. A successful and precise classification of any disease into its subtype is necessary for successful diagnosis and treatment of the disease. The NCBI Gene Expression Omnibus (GEO) is the extensive storage containing experimental microarray data. In this research, PPI networks and a common drug is designed for the unique DENGUE samples and Linear Discriminant Analysis (LDA) and Principle Component Analysis (PCA) techniques are applied for the classification of Dengue fever genes into its unique samples. Comparing to PCA, in LDA, LD1 classifies 96.2% while PC1 Classifies 46%. Using LDA, also a prediction is made to predict samples from gene variance. Moreover, LDA predicts approximately 73.21% accurate results. All of the calculation, comparison and gene analysis is performed using R tool and UniHi tool is used for the creation of PPI network and Drug design. Here, a common drug is designed which can be used for all of the sample type of the Dengue fever but in different proportion.

Keywords protein-protein interaction;drug design;gene expression omnibus;microarray data;Linear Discriminant Analysis;Principle Component Analysis.


International Academy of Ecology and Environmental Sciences. E-mail: office@iaees.org
Copyright © 2009-2024 International Academy of Ecology and Environmental Sciences. All rights reserved.
Web administrator: office@iaees.org, website@iaees.org; Last modified: 2024/4/16


Translate page to: