A new approach of training Hidden Markov Model by PSO algorithm for gene Sequence Modeling

Sequence Modeling is one of the most important problems in bioinformatics. In the sequential data modeling, Hidden Markov Models(HMMs) have been widely used to find similarity between sequences, since the performance of HMMs are suitable for handling of sequence patterns with various lengths. In this paper, a new approach for biological sequence modeling scheme based on HMMs optimized by Particle Swarm Optimization(PSO) algorithm is introduced. In this approach, each sequence is described by a specific HMM, and then for each model, its probability to generate individual sequence is evaluated. Then, the generated sequence is compared with actual sequence. Experiments carried out on gene sequences dataset show that the proposed approach can be successfully utilized for sequence modeling.