Pengelompokan Sekuens DNA menggunakan Metode K-Means dan Fitur N-mers Frequency

Abstract

Deoxyribo Nucleic Acid (DNA) is a nucleic acid that contains genetic instructions stored in the bodies of living organisms. Each species has a unique DNA. However, there are still similarity section among DNA from different species. The similarity information is useful to generate phylogenetic tree which can be developed from the clustering of DNA sequences. The purpose of this study is to implement K-Means clustering on DNA sequence to identify and distinguish species from another based on its common characteristics. Data used in this study consist of 70 species. Data are grouped using the K-Means clustering, and evaluated using the Davies Bouldin Index. The result shows that the best clustering is obtained with 3 clusters.