A Tensor-based Bi-random Walks Model for Protein Function Prediction

Background: The accurate characterization of protein functions is key to understanding life at the molecular level and has a huge impact on biomedicine and pharmaceuticals. Computationally predicting protein functions has been studied in the past decades. Plagued by noise and errors in protein-protein interaction networks, researchers have begun to focus on the fusion of multi-omics data in recent years. A data model that appropriately integrates network topologies with biological data and preserves their intrinsic characteristics is still a bottleneck and an aspirational goal for function prediction. Results We propose RWRT to accomplish protein function prediction by applying bi-random walks on the tensor. RWRT firstly constructs a functional similarity tensor by combining protein interaction networks with multi-omics data derived from domain annotation and protein complex information. After this, RWRT extends the bi-random walk algorithm from a two-dimensional matrix to the tensor for scoring functional similarity between proteins. Finally, RWRT filters out possible pretenders based on the concept of cohesiveness coefficient and annotated target proteins with functions of the remaining functional partners. Experimental results indicate that RWRT performs significantly better than the state-of-the-art methods and improves the area under the receiver-operating curve (AUROC) by no less than 18%. Conclusions: Functional similarity tensor offers us an alternative, in that it is a collection of networks sharing the same nodes; however, the edges belong to different categories or represent interactions of different natures. We demonstrate that tensor-based random walk model can not only discover more partners with similar functions, but also effectively free from the constraints of errors in protein interaction networks. We conclude that the performance of function prediction depends greatly on whether we can extract and exploit proper functional similarity information from protein correlations.