Background: Many important cellular processes are carried out by protein complexes. To provide physical pictures\r\nof interacting proteins, many computational protein-protein prediction methods have been developed in the past.\r\nHowever, it is still difficult to identify the correct docking complex structure within top ranks among alternative\r\nconformations.\r\nResults: We present a novel protein docking algorithm that utilizes imperfect protein-protein binding interface\r\nprediction for guiding protein docking. Since the accuracy of protein binding site prediction varies depending on\r\ncases, the challenge is to develop a method which does not deteriorate but improves docking results by using a\r\nbinding site prediction which may not be 100% accurate. The algorithm, named PI-LZerD (using Predicted Interface\r\nwith Local 3D Zernike descriptor-based Docking algorithm), is based on a pair wise protein docking prediction\r\nalgorithm, LZerD, which we have developed earlier. PI-LZerD starts from performing docking prediction using the\r\nprovided protein-protein binding interface prediction as constraints, which is followed by the second round of\r\ndocking with updated docking interface information to further improve docking conformation. Benchmark results\r\non bound and unbound cases show that PI-LZerD consistently improves the docking prediction accuracy as\r\ncompared with docking without using binding site prediction or using the binding site prediction as post-filtering.\r\nConclusion: We have developed PI-LZerD, a pairwise docking algorithm, which uses imperfect protein-protein\r\nbinding interface prediction to improve docking accuracy. PI-LZerD consistently showed better prediction accuracy\r\nover alternative methods in the series of benchmark experiments including docking using actual docking interface\r\nsite predictions as well as unbound docking cases.
Loading....