Pengelompokan Sekuens DNA Menggunakan Algoritme Single Link dan Feature Vectors

Abstract

Clustering is a learning technique to find the the group automatically based on the characteristics. By separating the data into groups so the data will easy to understand. Clustering DNA sequences with feature vectors is the process of combining a group of DNA sequences with the same amount of nucleotides, the composition and distribution of nucleotide, will combine into the same group. There are 4 main stages of clustering DNA sequence: feature vectors, min max normalization, cosine similarity and single link clustering. This research consist of the 8 case and 5 experiment in each case, with the result of least average 86,7% and the best cluster found 100% in case 3 experiment 4. The most affecting for the result of DNA sequence clustering is the size and volume used in the research.