OPUS-Rota5: A highly accurate protein side-chain modeling method with 3D-Unet and RotaFormer

Gang Xu; Zhenwei Luo; Yaming Yan; Qinghua Wang; Jianpeng Ma

doi:10.1016/j.str.2024.03.015

OPUS-Rota5: A highly accurate protein side-chain modeling method with 3D-Unet and RotaFormer

Structure. 2024 Apr 18:S0969-2126(24)00126-6. doi: 10.1016/j.str.2024.03.015. Online ahead of print.

Authors

Gang Xu¹, Zhenwei Luo¹, Yaming Yan², Qinghua Wang³, Jianpeng Ma⁴

Affiliations

¹ Multiscale Research Institute of Complex Systems, Fudan University, Shanghai 200433, China; Zhangjiang Fudan International Innovation Center, Fudan University, Shanghai 201210, China; Shanghai AI Laboratory, Shanghai 200030, China.
² Multiscale Research Institute of Complex Systems, Fudan University, Shanghai 200433, China; Zhangjiang Fudan International Innovation Center, Fudan University, Shanghai 201210, China.
³ Center for Biomolecular Innovation, Harcam Biomedicines, Shanghai 200131, China.
⁴ Multiscale Research Institute of Complex Systems, Fudan University, Shanghai 200433, China; Zhangjiang Fudan International Innovation Center, Fudan University, Shanghai 201210, China; Shanghai AI Laboratory, Shanghai 200030, China. Electronic address: jpma@fudan.edu.cn.

PMID: 38657613
DOI: 10.1016/j.str.2024.03.015

Abstract

Accurate protein side-chain modeling is crucial for protein folding and design. This is particularly true for molecular docking as ligands primarily interact with side chains. In this study, we introduce a two-stage side-chain modeling approach called OPUS-Rota5. It leverages a modified 3D-Unet to capture the local environmental features, including ligand information of each residue, and then employs the RotaFormer module to aggregate various types of features. Evaluation on three test sets, including recently released targets from CAMEO and CASP15, shows that OPUS-Rota5 significantly outperforms some other leading side-chain modeling methods. We also employ OPUS-Rota5 to refine the side chains of 25 G protein-coupled receptor targets predicted by AlphaFold2 and achieve a significantly improved success rate in a subsequent "back" docking of their natural ligands. Therefore, OPUS-Rota5 is a useful and effective tool for molecular docking, particularly for targets with relatively accurate predicted backbones but not side chains such as high-homology targets.