Development of hybrid model for improving the prediction of dengue-human protein interaction for anti-viral drug discovery. (9th September 2020)

• Record Type: Journal Article
• Authors: Revathy, R.; Fathima, A. Jainul; Balamurali, S.; Murugaboopathi, G.
• Is Part Of: International journal of intelligent information and database systems. Volume 13:Number 2/4(2020)
• Page Start: 479
• Page End: 490
• Publication Date: 2020-09-09
• Subjects: FFBPN -- firefly optimisation -- protein-protein interaction -- PPI -- anti-viral drug discovery; Database management -- Computer programs -- Periodicals; Information retrieval -- Computer programs -- Periodicals; Information storage and retrieval systems -- Computer programs -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Intelligent agents (Computer software) -- Periodicals; 006.33
• Languages: English
• ISSNs: 1751-5858

Abstract

Dengue fever is the most common viral disease caused by mosquitoes. Due to the lack of curable drugs, there is an urgent need to develop anti-viral against dengue disease. Several innovative computational approaches were incorporated for the discovery of a new lead molecule that acts on the dengue virus target. The target can be a viral or host protein. Predicting the type of interaction between the virus and human protein will give better knowledge in developing therapeutics against the dengue disease. The main objective of this study is to propose a hybrid model which combines feed forward back propagation neural network (FFBPNN) with firefly algorithm to predict the dengue-human protein interaction. The novelty in this study is to focus on optimising the weights and bias of the artificial neural network to improve the efficiency of algorithm. While comparing with existing C4.5 and FFBPNN classification algorithms, the results show that the proposed hybrid method fitted the interaction data efficiently and predicts the interaction type which leads to the development of anti-viral drugs. The accuracy of the classification gained by C4.5 is 88%, FFBPNN is 97% and hybrid FFBPNN is 99%.