development of an efficient hybrid method for motif discovery in dna sequences

this work presents a hybrid method for motif discovery in dna sequences. the proposed method called spso-lk, borrows the concept of chebyshev polynomials and uses the stochastic local search to improve the performance of the basic pso algorithm as a motif finder. the chebyshev polynomial concept encourages us to use a linear combination of previously discovered velocities beyond that proposed by the basic pso algorithm. under this method, to balance between exploration and exploitation, at each iteration step, a local region is associated with each candidate particle, and a local exploration performed in this blob. the stochastic local search employs an intelligent repulsion/attraction mechanism to navigate a particle to explore this local region beyond that defined by the search algorithm to achieve a better solution. over the successive iterations, the size of local region dynamically decreases. also a non-linear dynamic inertia weight is introduced to further improve the performance of spso-lk approach. the spso-lk is tested on different sets of simulated and real nucleotide sequences to discover implanted dna motifs. experimental results show that the spso-lk is effective, and provides competitive results in comparison with the performance of other algorithms investigated in this consideration.