Analysis of nucleotide sequence with normal and affected cancer liver cells using Hidden Markov model

The nucleotide sequence of biological databases is growing long terms of quantity, memory and complexity, managing these databases is becoming very complex. In this paper focuses Hidden Markov Model (HMM), has increased on the Pattern recognition domain primarily because of its strong mathematical basis and the ability to adapt to unknown of nucleotide sequence of normal and cancer affected liver cells as are pictorially represented by finite state machine. It is a finite automaton with a fixed number of states which are trained to maximize the probability of the observation sequence by using viterbi algorithm and forward algorithm. The work will be focused and analyzed about performance of DNA gene liver cancer database and normal liver cell data set from ncbi DNA data set. Each amino acid can have character variables and also assigned numeric number and its corresponding pair combination of sequence are represented in a graph. The proposed HMM system is validated with two different nucleotide values for analyse the performance and get the simulated output using viterbi and forward algorithms implemented in Mat Lab Tool.