PROJECT TITLE :

A Fractal Dimension and Wavelet Transform Based Method for Protein Sequence Similarity Analysis

ABSTRACT:

One amongst the key tasks related to proteins is the similarity comparison of protein sequences in the area of bioinformatics and molecular biology, which helps the prediction and classification of protein structure and function. It's a significant and open issue to find similar proteins from a giant scale of protein database efficiently. This paper presents a replacement distance primarily based protein similarity analysis employing a new encoding method of protein sequence which is predicated on fractal dimension. The protein sequences are 1st represented into the 1-dimensional feature vectors by their biochemical quantities. A series of Hybrid methodology involving discrete Wavelet remodel, Fractal dimension calculation (HWF) with sliding window are then applied to create the feature vector. At last, through the similarity calculation, we tend to can acquire the distance matrix, by which, the phylogenic tree can be created. We apply this approach by analyzing the ND5 (NADH dehydrogenase subunit 5) protein cluster information set. The experimental results show that the proposed model is a lot of accurate than the present ones like Su's model, Zhang's model, Yao's model and MEGA software, and it is according to some known biological facts.