Protein motif extraction with neuro-fuzzy optimization

Motivation: It is attempted to improve the speed and flexibility of protein motif identification. The proposed algorithm is able to extract both rigid and flexible protein motifs. Results: In this work, we present a new algorithm for extracting the consensus pattern, or motif, from a group of related protein sequences. This algorithm involves a statistical method to find short patterns with high frequency and then neural network training to optimize the final classification accuracies. Fuzzy logic is used to increase the flexibility of protein motifs. C2H2 Zinc Finger Protein and epidermal growth factor protein sequences are used to demonstrate the capability of the proposed algorithm in finding motifs. Availability: This program is freely available for academic use by request. Contact: bcch@mame.mu.oz.au sam@mame.mu.oz.au