A self-organizing neural network approach for the identification of motifs with insertions and deletions in protein sequences

Current popular algorithms of motif identification in protein sequences face two difficulties, large computation and insertions and deletions of letters. In this paper, we provide a new strategy that solves this problem in a more efficient and effective way. We build a self-organizing neural network with multiple levels of subnetworks to classify subsequences obtained from the protein sequences. We maintain a low computational complexity through the use of this multi-level structure so that the classification of each subsequence is performed with respect to a small subspace of the whole input space. The new definition of pairwise distance between motif patterns provided in this paper can deal with more insertions/deletions allowed in a motif than other algorithms. In the simulation result, our algorithm significantly outperforms existing algorithms in both accuracy and reliability aspects.