Protein Structural Domain Boundary Prediction

Revision with unchanged content. The prediction of protein structural domains and their boundaries from amino acid sequence data is an open problem of interest to the bio­informatics community. Determining a protein's structural domains experi­mentally can be very difficult. The assignment of structural domains relies on the time-consuming process of determining the three-dimensional structure. There is a strong potential for computational methods to aid in this and other tasks in structural molecular biology. Efforts from other researchers, along with the results presented here indicate that boundaries can indeed be predicted from amino acid sequence alone. A new machine-learning based architecture is introduced to predict structural domain boundaries, the key feature of which is a Mixture of Experts (MoE) model. The MoE provides the ability to combine the predictions of individual classifiers, such as artificial neural networks, support vector machines, and naïve Bayes classifiers, so as to optimize prediction accuracy. This book is addressed to students and researchers in both computer science and bioinformatics.