The construction of protein-protein interaction network based on machine learning method

Protein-protein interactions (PPIs) are central to most biological processes. Although efforts have been devoted to the development of methodology for predicting PPIs and to construct protein interaction networks, the application of most existing methods is limited because of less and incomplete information. In the present work, we integrate multi-databases which contain protein information and apply for PPI prediction and construction of the interaction network. This process was based on several protein databases and a learning algorithm-support vector machine. The result suggests that the integrating multi-databases could be applied to the exploration of networks for any newly discovered protein with unknown biological relativity. In addition, supplementary experimental information can be added into the multi-databases and enhance the constructing ability of interaction network.