Link prediction with continuous-time classical and quantum walks
This addresses the challenge of inferring missing interactions in PPI networks, which are costly and error-prone to obtain, but the approach is incremental as it builds on existing random walk methods.
The paper tackled the problem of incomplete protein-protein interaction (PPI) networks by proposing novel link prediction methods based on continuous-time classical and quantum random walks, achieving performance that rivals the state of the art on four real-world PPI datasets.
Protein-protein interaction (PPI) networks consist of the physical and/or functional interactions between the proteins of an organism. Since the biophysical and high-throughput methods used to form PPI networks are expensive, time-consuming, and often contain inaccuracies, the resulting networks are usually incomplete. In order to infer missing interactions in these networks, we propose a novel class of link prediction methods based on continuous-time classical and quantum random walks. In the case of quantum walks, we examine the usage of both the network adjacency and Laplacian matrices for controlling the walk dynamics. We define a score function based on the corresponding transition probabilities and perform tests on four real-world PPI datasets. Our results show that continuous-time classical random walks and quantum walks using the network adjacency matrix can successfully predict missing protein-protein interactions, with performance rivalling the state of the art.