Subtle Signal Discoveries in Unaligned Molecular Sequences Using Self-Organizing Neural Networks

In this paper, we study the problem of subtle signal discoveries in unaligned DNA and protein sequences. Motifs, also known as approximate common substrings, are good examples of subtle signals in DNA and protein sequences. The problem of motif identification in DNA and protein sequences has been studied for many years in the literature. Major hurdles at this point include computational complexity and reliability of the search algorithms. We propose a selforganizing neural network structure for solving the problem of motif identification in DNA and protein sequences. Our network contains several layers with each layer performing classifications at different level. The top layer divide the input space into a small number of regions and the bottom layer classifies all input patterns into motifs and non-motif patterns. Depending on the number of input patterns to be classified, several layers between the top layer and the bottom layer are needed to perform intermediate classifications. We maintain a low computational complexity through the use of the layered structure so that each pattern’s classification is performed with respect to a small subspace of the whole input space. We also maintain a high reliability using our self-organizing neural network since it will grow as needed to make sure all input patterns are considered and are given the same amount of attention. Finally, simulation results show that our algorithm significantly outperforms existing algorithms, especially in the reliability aspect. Our algorithm can identify motifs with higher accuracy than existing algorithms and our algorithm works well for long DNA sequences as well.