NetLoc: Network Based Protein Localization Prediction Using Protein-Protein Interaction, Genetic Interaction, and Co-expression Networks

Recent study shows that protein-protein interaction network based features can significantly improve the prediction of protein subcellular localization. However, it is unclear whether network prediction models or other types of protein-protein correlation networks would also improve localization prediction. We present NetLoc, a novel network based algorithm for predicting protein subcellular localization using four types of protein networks including physical protein-protein interaction (PPPI) network, genetic interaction network (GPPI), and co-expression network (COEXP). Diffusion kernel-based logistic regression (KLR) is used to develop the prediction model. We applied NetLoc to yeast protein localization prediction. The results showed that protein networks can provide rich information for protein localization prediction, achieving prediction performance up to AUC score of 0.93. We also showed that networks with high connectivity and high percentage of interacting protein pairs targeting the same location lead to better prediction performance. In terms of localization prediction performance, PPPI is better than GPPI which is better than COEXP. The classification performance (AUC) with PPPI network ranges between 0.71 and 0.93 for 7 locations. The overall balanced performance is 0.82 which is significantly better than the performance (0.49 and 0.57) of the previous network feature based classification algorithm evaluated on the same yeast dataset using leave-one-out crossvalidation.