The nature of statistical learning theory
The nature of statistical learning theory
Making large-scale support vector machine learning practical
Advances in kernel methods
A Tutorial on Support Vector Machines for Pattern Recognition
Data Mining and Knowledge Discovery
Epitope Prediction Algorithms for Peptide based Vaccine Design
CSB '03 Proceedings of the IEEE Computer Society Conference on Bioinformatics
| Hi-index | 0.00 |
Protein-protein interactions play a central role in many cellular functions, and as whole-genome data accumulates, computational methods for predicting these interactions become increasingly important. Computational methods have already proven to be a useful first step for rapid genome-wide identification of putative protein structure and function, but research on the problem of computationally determining biologically relevant partners for given protein sequences is just beginning. In this paper, we approach the problem of predicting protein-protein interactions by focusing on the 2- stranded coiled-coil motif. We introduce a computational method for predicting coiled-coil protein interactions, and give a novel framework that is able to use both genomic sequence data and experimental data in making these predictions. Cross-validation tests show that the method is able to predict many aspects of protein-protein interactions mediated by the coiled-coil motif, and suggest that this methodology can be used as the basis for genome-wide prediction of coiled-coil protein interactions.