FART Neural Network based Probabilistic Motif Discovery in Unaligned Biological Sequences

摘要

Finding Motif in bio-sequences is the most primitive operation in computational Biology. There are many computational requirements for a motif discovery algorithm such as computer memory space requirement and computational complexity. To overcome the complexity of motif discovery, an alternative solution is proposed by integrating genetic algorithm and Fuzzy Art machine learning approaches for eliminating multiple sequence alignment process. Problem statement: More than hundred methods have been proposed for motif discovery in recent years, representing very large variation with respect to both algorithmic approaches as well as the underlying models of regulatory regions. The aim of this study is to develop an alternative solution for motif discovery, which benefits from both data mining and genetic algorithm, and which at the same time eliminates the cost caused by use of multiple sequence alignment. Approach: Genetic algorithm based probabilistic Motif discovery model is designed to solve the problem. The proposed algorithm is implemented using Matlab and also tested with large DNA sequence data sets and synthetic data sets. Results: Results obtained by the proposed model to find the motif in terms of speed and length are compared with the existing method. This proposed method finds length of 11 in 18 sec and length of 15 in 24 sec but the existing methods finds length of 11 in 34 sec. When compared with other techniques the proposed method outperforms the popular existing method. Conclusion: In this study, a model is proposed to discover motif in large set of unaligned sequences in considerably minimum time. Length of motif in this study is also long when compared with existing methods. The proposed algorithm is implemented using Matlab and is tested with large DNA sequence data sets and synthetic data sets.