A Novel Method for Functional Prediction of Proteins from a Protein-Protein Interaction Network

Functional prediction of unannotated proteins is one of the most important tasks in yeast genomics. Analysis of a protein-protein interaction network leads to a better understanding of the functions of unannotated proteins. Much research has been performed for the functional prediction of unannotated proteins from a protein-protein interaction network. A chi-square method is one of the existing methods for the functional prediction of unannotated proteins from a protein- protein interaction network, but the method does not consider the topology of network. In this paper, we propose a novel method that is able to predict specific molecular functions for unanno- tated proteins from a protein-protein interaction network. To do this, we investigated all protein interaction databases of yeast in public sites such as MIPS, DIP and SGD. For the prediction of unannotated proteins, we employed a modified chi-square measure based on neighborhood counting and we assessed the prediction accuracy of the protein function from a protein-protein interaction network. KCI Citation Count: 0