GDockScore: a graph-based protein–protein docking scoring function

Abstract

Protein complexes play vital roles in a variety of biological processes such as mediating biochemical reactions, the immune response, and cell signalling, with three-dimensional structure specifying function. Computational docking methods provide a means to determine the interface between two complexed polypeptide chains without using time-consuming experimental techniques. The docking process requires the optimal solution to be selected with a scoring function. Here we propose a novel graph-based deep learning model that utilizes mathematical graph representations of proteins to learn a scoring function (GDockScore). GDockScore was pre-trained on docking outputs generated with the Protein Data Bank (PDB) biounits and the RosettaDock protocol, and then fine-tuned on HADDOCK decoys generated on the ZDOCK Protein Docking Benchmark. GDockScore performs similarly to the Rosetta scoring function on docking decoys generated using the RosettaDock protocol. Furthermore, state-of-the-art is achieved on the CAPRI score set, a challenging dataset for developing docking scoring functions. The model implementation is available at https://gitlab.com/mcfeemat/gdockscore.

Human Cytokine and Coronavirus Nucleocapsid Protein Interactivity Using Large-Scale Virtual Screens

“…GDock Score. GDockScore, a graph-based deep learning model to assess the docking of two proteins, was included to evaluate AlphaFold2 models (12). The model was pretrained by the original authors on docking outputs generated from Protein Data Bank, RosettaDock, HADDOCK decoys, and the ZDOCK Protein Docking Benchmark-to include a wide variety of protein complexes and ensure generalization.…”

“…The in silico screen was set up on a high-performance computing system. AlphaFold2-Multimer (10) and HAD-DOCK (11) were utilized in parallel to predict cytokine binding sites on N, as GDockScore (12) and PRODIGY (13) were used to further assess the properties of the predicted cytokine binding. The goals were to identify the cytokine binding sites of the experimental cytokine hits and determine if their binding has been impacted by continuing evolution in the human host over the course of the pandemic.…”