An automatic motif recognition algorithm in DNA sequences based on particle swarm optimization and random projection

Abstract

Motif recognition plays a significant role for understanding the biological meanings of sequences. In this paper, a particle swarm optimization and random projection based algorithm (PSORPS) is proposed for recognizing DNA motifs. First, noise subsequences are filtered by a random projection strategy for constructing objective space. Then the PSO is used to automatically search the motifs of DNA sequences in the constructed l-mer objective space. Finally, the operators of independent drift and associated drift are conducted on the optimization results to alleviate base deviation. The experiments are carried out on real-world biological datasets, and the results validate the effectiveness of the proposed algorithm.