Design and implementation of bi-level artificial bee colony algorithm to train hidden Markov models for performing multiple sequence alignment of proteins

Multiple sequence alignment (MSA) is an NP-complete problem that is a challenging area from bioinformatics. Implementation of hidden Markov model (HMM) is one of the most effective approach for executing MSA, that performs training and testing of the sequence data so as to obtain alignment scores with accuracy. The training of HMM is again an NP-hard problem, hence it requires the implementation of metaheuristic methods. Proposed work presents a bi-level artificial bee colony (BL-ABC) algorithm to train hidden Markov models (HMMs) for MSA of proteins, i.e., BLABC-HMM. The trained stochastic model created by BL-ABC basically yields position-dependent probability matrices at higher prediction ratios. The performance of proposed algorithm is compared with the competitive state-of-the-art algorithms and different variants of particle swarm optimisation (PSO) algorithm on protein benchmark datasets from pfam and BAliBase database, and BLABC-HMM is found yielding better alignment scores and prediction accuracy.