Abstract

DNA is the identity of a living organism through which we know the characteristics of an organism. DNA is a big data that need to be processed, so as to obtains accurate results of a prediction and classification, a new trends of Machine learning processing technique. This study is part of applied application of bioinformatics contained many applications, sequences alignments, clustering and classification. This application is very important to bioinformatics scientists for disease detection and tracking, mutations Detection, Forensic medicine, agriculture, and proof of lineage. 
This study is devoted to process Sequences Alignment and find the similarity matrix. An algorithm was proposed and compared with three algorithms in terms of time (hamming, Levenshtein, and rank). The proposed algorithm was the fastest in terms of time.