Title :
ANN Based Classification of Unknown Genome Fragments Using Chaos Game Representation
Author :
Nair, Vrinda V. ; Vijayan, Karthika ; Gopinath, Deepa P. ; Nair, Achuthsankar S.
Author_Institution :
Dept. of Electron. & Commun. Eng., Gov. Eng. Coll., Thrissur, India
Abstract :
Classification of organisms into different categories using their genomic sequences has found importance in study of evolutionary characteristics, specific identification of previously unknown organisms, study of mutual relationships between organisms and many other aspects in the study of living things. Chaos game representation (CGR) uniquely represents DNA sequences and reveals hidden patterns in it. Frequency-CGR (FCGR) derived from CGR, shows the frequency of sub-sequences present in the DNA sequence. In this paper, a novel method for classification of organisms based on a combination of FCGR and Artificial Neural network (ANN) is proposed. Eight categories from the taxonomical distribution of Eukaryotic organisms are taken and ANN is used for classification. Different configurations of ANN are tested and good accuracy is obtained. The way the fractal nature of DNA helps in classification, is also investigated.
Keywords :
DNA; chaos; evolutionary computation; fractals; game theory; genomics; medical computing; microorganisms; molecular biophysics; neural nets; pattern classification; ANN; DNA sequences; Eukaryotic organisms; FCGR; artificial neural network; chaos game representation; evolutionary characteristics; frequency CGR; genome fragments classification; taxonomical distribution; Artificial neural networks; Bioinformatics; Chaos; DNA; Fractals; Frequency; Genomics; Organisms; Sequences; Testing; ANN; CGR; DNA sequence; FCGR;
Conference_Titel :
Machine Learning and Computing (ICMLC), 2010 Second International Conference on
Conference_Location :
Bangalore
Print_ISBN :
978-1-4244-6006-9
Electronic_ISBN :
978-1-4244-6007-6
DOI :
10.1109/ICMLC.2010.56
