DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

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

Journal Article · · Bioinformatics

Abstract Motivation Proteins 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. Results In 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. Availability and implementation The source code, data, and pre-trained models are available at https://github.com/jianlin-cheng/DProQA.

Research Organization:
Donald Danforth Plant Science Center, St. Louis, MO (United States)
Sponsoring Organization:
National Institutes of Health (NIH); National Science Foundation (NSF); USDOE
Grant/Contract Number:
AC05-00OR22725; AR0001213; SC0020400; SC0021303
OSTI ID:
1987926
Journal Information:
Bioinformatics, Journal Name: Bioinformatics Journal Issue: Supplement_1 Vol. 39; ISSN 1367-4803
Publisher:
Oxford University PressCopyright Statement
Country of Publication:
United Kingdom
Language:
English

References (45)

Dockground: A comprehensive data resource for modeling of protein complexes journal October 2017
Integrating atom-based and residue-based scoring functions for protein-protein docking journal August 2011
Scoring function for automated assessment of protein structure template quality journal January 2004
A combination of rescoring and refinement significantly improves protein docking performance: Rescoring and Refinement in Protein Docking journal January 2008
An iterative knowledge-based scoring function for protein-protein recognition journal February 2008
Score_set: A CAPRI benchmark for scoring protein complexes journal September 2014
Energy‐based graph convolutional networks for scoring protein docking models journal March 2020
Hierarchical, rotation‐equivariant neural networks to select structural models of protein complexes journal December 2020
Topology evaluation of models for difficult targets in the 14th round of the critical assessment of protein structure prediction (CASP14) journal July 2021
Dockground scoring benchmarks for protein docking journal February 2022
Protein–Protein Docking with Simultaneous Optimization of Rigid-body Displacement and Side-chain Conformations journal August 2003
GOAP: A Generalized Orientation-Dependent, All-Atom Statistical Potential for Protein Structure Prediction journal October 2011
Computational design of protein–protein interactions journal February 2004
Progress in computational protein design journal August 2007
Updates to the Integrated Protein–Protein Interaction Benchmarks: Docking Benchmark Version 5 and Affinity Benchmark Version 2 journal September 2015
Scoring by Intermolecular Pairwise Propensities of Exposed Residues (SIPPER): A New Efficient Potential for Protein−Protein Docking journal January 2011
HADDOCK:  A Protein−Protein Docking Approach Based on Biochemical or Biophysical Information journal February 2003
Small molecules, big targets: drug discovery faces the protein–protein interaction challenge journal April 2016
Prediction of inter-chain distance maps of protein complexes with 2D attention-based deep neural networks journal November 2022
Highly accurate protein structure prediction with AlphaFold journal July 2021
ProQ3: Improved model quality assessments using Rosetta energy terms journal October 2016
Accurate prediction of inter-protein residue–residue contacts for homo-oligomeric protein complexes journal March 2021
Fast and sensitive taxonomic assignment to metagenomic contigs journal March 2021
DeepRank-GNN: a graph neural network framework to learn patterns in protein–protein interfaces journal November 2022
3D-equivariant graph neural networks for protein model quality assessment journal January 2023
Dockground protein–protein docking decoy set journal September 2008
Biopython: freely available Python tools for computational molecular biology and bioinformatics journal March 2009
ProQ2: estimation of model accuracy implemented in Rosetta journal January 2016
Finding correct protein–protein docking models using ProQDock journal June 2016
The EVcouplings Python framework for coevolutionary sequence analysis journal October 2018
iScore: a novel graph kernel-based function for scoring protein–protein docking models journal June 2019
Protein docking model evaluation by 3D deep convolutional neural networks journal November 2019
GRAMM-X public web server for protein-protein docking journal July 2006
MM-align: a quick algorithm for aligning multiple-chain protein complex structures using iterative dynamic programming journal May 2009
Prediction and design of macromolecular structures and interactions journal February 2006
Distance-scaled, finite ideal-gas reference state improves structure-derived potentials of mean force for structure selection and stability prediction journal November 2002
Pcons: A neural-network-based consensus predictor that improves fold recognition journal November 2001
The scoring of poses in protein-protein docking: current capabilities and future directions journal January 2013
Benchmarking consensus model quality assessment for protein fold recognition journal September 2007
DISTEMA: distance map-based estimation of single protein model accuracy with attentive 2D convolutional neural network journal March 2022
Accelerating Protein Docking in ZDOCK Using an Advanced 3D Convolution Library journal September 2011
DockQ: A Quality Measure for Protein-Protein Docking Models journal August 2016
Protein-Protein Interaction (PPI) Network: Recent Advances in Drug Discovery journal January 2017
Quality Assessment of Protein Docking Models Based on Graph Neural Network journal August 2021
Evolution of In Silico Strategies for Protein-Protein Interaction Drug Discovery journal August 2018