Prediction of Protein-Protein Interaction Sites Using Granularity Computing of Quotient Space Theory

Proteins function through interactions with other proteins, compounds, RNA and DNA. Prediction of protein interface sites is the key process for providing clues to the function of a protein, and is becoming increasing relevant to drug discovery. In this paper, combining the protein features with the theory of granular computing of quotient space based on protein-protein interaction sites classification algorithm is proposed, (i.e. PPI-GS Model). Such algorithm uses the support vector machine (SVM) with better generalization ability to get different classification results, and construct different quotient space by using these results. The final result is got by granularity synthesis method to organize these quotient spaces. The experiment suggests that this new method is in effect. Also, the potency of the granular computing of quotient space in the application of protein-protein interaction sites prediction and processing is demonstrated.