DWT Based Cancer Identification Using EIIP

Abstract

Nowadays, the challenges facing by researchers is to classify the cancer disease accurately without involving biological experiments so that early treatment is possible. With the recent advances in Genomic signal processing (GSP) domain, researchers have been applying digital signal processing (DSP) techniques in raw genomic data for extracting the hidden features and periodicities within the fragments of DNA. In this paper, we have incorporated Electron ion interaction potential (EIIP) method for mapping of DNA sequence into digital signal and Discrete wavelet transform (DWT) power spectrum methods in our algorithm to predict the abnormalities present in the protein coding region. This technique also reduces the noise present in the signal as well as compressed the large sample data. This crucial region plays an important role for analyzing cancerous and non-cancerous cell. The aim of this research paper is to discover families of genes or gene products that can be used to classify disease, thereby leading to molecular-based diagnosis and prognosis. In this work, algorithm is implemented using MATLAB R2012a which supports bioinformatics toolbox. The proposed algorithm is tested for several normal and abnormal DNA sequences of Homosapien chromosomes available in National center of Biotechnology Information (NCBI) database, PubMed, Uniprot, HMR195 and BG570 database.