Identifikasi DNA Bakteri Menggunakan Metode Ekstraksi Ciri Rantai Markov dengan Probabilistic Neural Network Sebagai Classifier

Abstract

Genetic differences among organisms motivate many research in DNA identification system. DNA identification system has two main parts: Feature Extraction Method and Classification Method. This study aims to identify the DNA with feature extraction using first order and second order Markov chain combined with Probabilistic Neural Network (PNN) classification method. DNA sequence is derived from the genus Bacillus, Clostridium, Lactobacillus, Mycobacterium, and Staphylococcus with sequence lengths of 100 bp, 200 bp, 400 bp, 800 bp, and 1000 bp. These data were obtained from the National Center for Biotechnology Information (NCBI). The results of this research show that the best sensitivity value is 0.7136 and the best specificity value is 0.9284. These results were obtained when the length of the sequence is 1000 bp and the feature extraction method used is second order Markov Chain. The greater the length of the sequence, the greater the sensitivity and specificity values.