Support vector machines for predicting protein-protein interactions using domains and hydrophobicity features

Since proteins work in the context of many other proteins and rarely work in isolation, it is highly important to study protein-protein interactions to understand proteins functions. The interactions data that have been identified by high-throughput technologies like the yeast two-hybrid system are known to yield many false positives. As a result, methods for computational prediction of protein-protein interactions based on sequence information are becoming increasingly important. In this study, computational prediction of protein-protein interactions (PPI) from domain structure and hydrophobicity properties is presented. Protein domain structure and hydrophobicity properties are used separately as the sequence feature for the support vector machines (SYM) as a learning system. Both features achieved accuracy of about 80%. But domains structure had receiver operating characteristic (ROC) score of 0.8480 with running time of 34 seconds, while hydrophobicity had ROC score of 0.8159 with running time of 20,571 seconds (5.7 hours). These results indicate that protein-protein interaction can be predicted from domain structure with reliable accuracy and acceptable running time.