MAIN


©1996-2018 All Rights Reserved. Online Journal of Bioinformatics . You may not store these pages in any form except for your own personal use. All other usage or distribute on is illegal under international copyright treaties. Permission to use any of these pages in any other way besides the  before mentioned must be gained in writing from the publisher. This article is exclusively copyrighted in its entirety to OJB publications. This article may be copied once but may not be, reproduced or  re-transmitted without the express permission of the editors. This journal satisfies the refereeing requirements (DEST) for the Higher Education Research Data Collection (Australia). Linking:To link to this page or any pages linking to this page you must link directly to this page only here rather than put up your own page.


 

OJBTM

Online Journal of Bioinformatics

Volume 19 (2):1235-145, 2018.


 Fuzzy Neural Network for Classification of Protein Domains into SCOP Superfamily

 

UB Angadi1, M Venkatesulu2.

 

1National Institute of Animal Nutrition and Physiology, Bangalore, and 2Department of Computer Applications, Kalasalingam University, Tamil Nadu, India.

 

ABSTRACT

Angadi UB, Venkatesulu M., Fuzzy Neural Network for Classification of Protein Domains into SCOP Superfamily., Onl J Bioinform., 19 (2):135-145, 2018. One of the major research directions in bioinformatics is that of predicting the protein superfamily in large database and classifying a given set of protein domains in superfamilies. The classification reflects the structural, evolutionary and functional relatedness. These relationships are embodied in hierarchical classification such Structural Classification of Protein (SCOP), which is manually curated. Such classification is essential for the structural and functional analysis of proteins. A large numbers of proteins remain unclassified and there is a greater need to develop more efficient, accurate and automated classification methods to cope up with the speed with which new sequences are generated. We propose an unsupervised machine learning fuzzy neural network algorithm to classify a given set of proteins into SCOP superfamilies. The proposed method, construct a similarity matrix from p-values of BLAST all-against-all, train the network with a simple unsupervised max-min fuzzy neural network learning algorithm using the similarity matrix as input vectors and finally the trained network offers SCOP superfamily level classification. The proposed method has compared with other techniques on different datasets and shown that the trained network is able to classify a given set of sequences at high accuracy.

 

Key words: Protein classification; SCOP; fuzzy neural network; unsupervised learning.


MAIN

FULL-TEXT (SUBSCRIBE OR PURCHASE TITLE $25USD)