CarsiDock: a deep learning paradigm for accurate protein–ligand docking and screening based on large-scale pre-training
Heng Cai, Chao Shen, Tianye Jian, Xujun Zhang, Tong Chen, Xiaoqi Han, Zhuo Yang, Wei Dang, Chang‐Yu Hsieh, Yu Kang, Peichen Pan, Xiangyang Ji, Jianfei Song, Tingjun Hou, Yafeng Deng
Abstract
, a deep learning model for the prediction of protein-ligand atomic distance matrices, and a translation, rotation and torsion-guided geometry optimization procedure to reconstruct the matrices into a credible binding pose. The pre-training and multiple innovative architectural designs facilitate the dramatically improved docking accuracy of our approach over the baselines in terms of multiple docking scenarios, thereby contributing to its outstanding early recognition performance in several retrospective virtual screening campaigns. Further explorations demonstrate that CarsiDock can not only guarantee the topological reliability of the binding poses but also successfully reproduce the crucial interactions in crystalized structures, highlighting its superior applicability.