Mapping of DNA sequences using hidden Markov model self organizing maps

Recently next generation sequencing techniques have begun to produce huge amounts of sequencing data. To analyze these data, an efficient method that can handle large amounts of information is required. In this paper, we proposed a method for classifying sets of DNA sequences by using a hidden Markov model self-organizing map. For this purpose, a learning algorithm that requires low computational costs was developed. The availability of this method was examined in experiments classifying DNA sequences of various types of genes.