A gated graph transformer for protein complex structure quality assessment and its performance in CASP15

被引:8
作者
Chen, Xiao [1 ]
Morehead, Alex [1 ]
Liu, Jian [1 ]
Cheng, Jianlin [1 ]
机构
[1] Univ Missouri, Dept Elect Engn & Comp Sci, Columbia, MO 65201 USA
基金
美国国家科学基金会; 美国国家卫生研究院;
关键词
DOCKING; BENCHMARK; DESIGN;
D O I
10.1093/bioinformatics/btad203
中图分类号
Q5 [生物化学];
学科分类号
071010 ; 081704 ;
摘要
MotivationProteins interact to form complexes to carry out essential biological functions. Computational methods such as AlphaFold-multimer have been developed to predict the quaternary structures of protein complexes. An important yet largely unsolved challenge in protein complex structure prediction is to accurately estimate the quality of predicted protein complex structures without any knowledge of the corresponding native structures. Such estimations can then be used to select high-quality predicted complex structures to facilitate biomedical research such as protein function analysis and drug discovery.ResultsIn this work, we introduce a new gated neighborhood-modulating graph transformer to predict the quality of 3D protein complex structures. It incorporates node and edge gates within a graph transformer framework to control information flow during graph message passing. We trained, evaluated and tested the method (called DProQA) on newly-curated protein complex datasets before the 15th Critical Assessment of Techniques for Protein Structure Prediction (CASP15) and then blindly tested it in the 2022 CASP15 experiment. The method was ranked 3rd among the single-model quality assessment methods in CASP15 in terms of the ranking loss of TM-score on 36 complex targets. The rigorous internal and external experiments demonstrate that DProQA is effective in ranking protein complex structures.
引用
收藏
页码:i308 / i317
页数:10
相关论文
共 66 条
  • [1] Athanasios A, 2017, CURR DRUG METAB, V18, P5, DOI [10.2174/1389200217666161102150602, 10.2174/138920021801170119204832]
  • [3] DockQ: A Quality Measure for Protein-Protein Docking Models
    Basu, Sankar
    Wallner, Bjorn
    [J]. PLOS ONE, 2016, 11 (08):
  • [4] Finding correct protein-protein docking models using ProQDock
    Basu, Sankar
    Wallner, Bjorn
    [J]. BIOINFORMATICS, 2016, 32 (12) : 262 - 270
  • [5] Improved prediction of protein-protein interactions using AlphaFold2
    Bryant, P.
    Pozzati, G.
    Elofsson, A.
    [J]. NATURE COMMUNICATIONS, 2022, 13 (01)
  • [6] Energy-based graph convolutional networks for scoring protein docking models
    Cao, Yue
    Shen, Yang
    [J]. PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS, 2020, 88 (08) : 1091 - 1099
  • [7] 3D-equivariant graph neural networks for protein model quality assessment
    Chen, Chen
    Chen, Xiao
    Morehead, Alex
    Wu, Tianqi
    Cheng, Jianlin
    [J]. BIOINFORMATICS, 2023, 39 (01)
  • [8] Chen X.Z., 2020, IEEE ICCE, P1, DOI [10.1109/ICCE46568.2020.9043053, DOI 10.1109/icce46568.2020.9043053, 10.1145/3388440.3412469]
  • [9] Protein model accuracy estimation empowered by deep learning and inter-residue distance prediction in CASP14
    Chen, Xiao
    Liu, Jian
    Guo, Zhiye
    Wu, Tianqi
    Hou, Jie
    Cheng, Jianlin
    [J]. SCIENTIFIC REPORTS, 2021, 11 (01)
  • [10] cSurvival: a web resource for biomarker interactions in cancer outcomes and in cell lines
    Cheng, Xuanjin
    Liu, Yongxing
    Wang, Jiahe
    Chen, Yujie
    Robertson, Andrew Gordon
    Zhang, Xuekui
    Jones, Steven J. M.
    Taubert, Stefan
    [J]. BRIEFINGS IN BIOINFORMATICS, 2022, 23 (03)