ABSTRACT

Modern biological science produces vast amount of genomic progression data. Genome contains the hereditary information of creatures. Huge amount of DNA sequences are stored in DNA databases like GenBank. In consequence, decreasing the Data storage costs for DNA sequences has become an essential. Standard general purpose compression algorithms are unsuccessful to get a good compression ratio. This paper presents a Pattern Recognition based DNA Sequence Compression algorithm which compresses the DNA sequences with 80% of reduction in its storage space.