A deep dilated convolutional residual network for predicting interchain contacts of protein homodimers
Abstract
Deep learning has revolutionized protein tertiary structure prediction recently. The cutting-edge deep learning methods such as AlphaFold can predict high-accuracy tertiary structures for most individual protein chains. However, the accuracy of predicting quaternary structures of protein complexes consisting of multiple chains is still relatively low due to lack of advanced deep learning methods in the field. Because interchain residue–residue contacts can be used as distance restraints to guide quaternary structure modeling, here we develop a deep dilated convolutional residual network method (DRCon) to predict interchain residue–residue contacts in homodimers from residue–residue co-evolutionary signals derived from multiple sequence alignments of monomers, intrachain residue–residue contacts of monomers extracted from true/predicted tertiary structures or predicted by deep learning, and other sequence and structural features. Tested on three homodimer test datasets (Homo_std dataset, DeepHomo dataset and CASP-CAPRI dataset), the precision of DRCon for top L/5 interchain contact predictions (L: length of monomer in a homodimer) is 43.46%, 47.10% and 33.50% respectively at 6 Å contact threshold, which is substantially better than DeepHomo and DNCON2_inter and similar to Glinter. Moreover, our experiments demonstrate that using predicted tertiary structure or intrachain contacts of monomers in the unbound state as input, DRCon still performs well, even thoughmore »
- Authors:
- Publication Date:
- Research Org.:
- Univ. of Missouri, Columbia, MO (United States); Donald Danforth Plant Science Center, St. Louis, MO (United States)
- Sponsoring Org.:
- USDOE Advanced Research Projects Agency - Energy (ARPA-E); National Science Foundation (NSF); National Institutes of Health (NIH); Thompson Missouri Distinguished Professorship; USDOE Office of Science (SC), Biological and Environmental Research (BER)
- OSTI Identifier:
- 1859808
- Alternate Identifier(s):
- OSTI ID: 1904187; OSTI ID: 2278958; OSTI ID: 2318548
- Grant/Contract Number:
- AR0001213; SC0020400; SC0021303; AC05-00OR22725; DBI1759934; IIS1763246; R01GM093123
- Resource Type:
- Published Article
- Journal Name:
- Bioinformatics
- Additional Journal Information:
- Journal Name: Bioinformatics Journal Volume: 38 Journal Issue: 7; Journal ID: ISSN 1367-4803
- Publisher:
- Oxford University Press
- Country of Publication:
- United Kingdom
- Language:
- English
- Subject:
- 37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY; 59 BASIC BIOLOGICAL SCIENCES; 97 MATHEMATICS AND COMPUTING
Citation Formats
Roy, Raj S., Quadir, Farhan, Soltanikazemi, Elham, Cheng, Jianlin, and Xu, ed., Jinbo. A deep dilated convolutional residual network for predicting interchain contacts of protein homodimers. United Kingdom: N. p., 2022.
Web. doi:10.1093/bioinformatics/btac063.
Roy, Raj S., Quadir, Farhan, Soltanikazemi, Elham, Cheng, Jianlin, & Xu, ed., Jinbo. A deep dilated convolutional residual network for predicting interchain contacts of protein homodimers. United Kingdom. https://doi.org/10.1093/bioinformatics/btac063
Roy, Raj S., Quadir, Farhan, Soltanikazemi, Elham, Cheng, Jianlin, and Xu, ed., Jinbo. Fri .
"A deep dilated convolutional residual network for predicting interchain contacts of protein homodimers". United Kingdom. https://doi.org/10.1093/bioinformatics/btac063.
@article{osti_1859808,
title = {A deep dilated convolutional residual network for predicting interchain contacts of protein homodimers},
author = {Roy, Raj S. and Quadir, Farhan and Soltanikazemi, Elham and Cheng, Jianlin and Xu, ed., Jinbo},
abstractNote = {Deep learning has revolutionized protein tertiary structure prediction recently. The cutting-edge deep learning methods such as AlphaFold can predict high-accuracy tertiary structures for most individual protein chains. However, the accuracy of predicting quaternary structures of protein complexes consisting of multiple chains is still relatively low due to lack of advanced deep learning methods in the field. Because interchain residue–residue contacts can be used as distance restraints to guide quaternary structure modeling, here we develop a deep dilated convolutional residual network method (DRCon) to predict interchain residue–residue contacts in homodimers from residue–residue co-evolutionary signals derived from multiple sequence alignments of monomers, intrachain residue–residue contacts of monomers extracted from true/predicted tertiary structures or predicted by deep learning, and other sequence and structural features. Tested on three homodimer test datasets (Homo_std dataset, DeepHomo dataset and CASP-CAPRI dataset), the precision of DRCon for top L/5 interchain contact predictions (L: length of monomer in a homodimer) is 43.46%, 47.10% and 33.50% respectively at 6 Å contact threshold, which is substantially better than DeepHomo and DNCON2_inter and similar to Glinter. Moreover, our experiments demonstrate that using predicted tertiary structure or intrachain contacts of monomers in the unbound state as input, DRCon still performs well, even though its accuracy is lower than using true tertiary structures in the bound state are used as input. Finally, our case study shows that good interchain contact predictions can be used to build high-accuracy quaternary structure models of homodimers.},
doi = {10.1093/bioinformatics/btac063},
journal = {Bioinformatics},
number = 7,
volume = 38,
place = {United Kingdom},
year = {Fri Feb 04 00:00:00 EST 2022},
month = {Fri Feb 04 00:00:00 EST 2022}
}
https://doi.org/10.1093/bioinformatics/btac063
Works referenced in this record:
ZDOCK server: interactive docking prediction of protein-protein complexes and symmetric multimers
journal, February 2014
- Pierce, B. G.; Wiehe, K.; Hwang, H.
- Bioinformatics, Vol. 30, Issue 12
Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model
journal, January 2017
- Wang, Sheng; Sun, Siqi; Li, Zhen
- PLOS Computational Biology, Vol. 13, Issue 1
TM-align: a protein structure alignment algorithm based on the TM-score
journal, April 2005
- Zhang, Y.
- Nucleic Acids Research, Vol. 33, Issue 7
DeepMSA: constructing deep multiple sequence alignment to improve contact prediction and fold-recognition for distant-homology proteins
journal, November 2019
- Zhang, Chengxin; Zheng, Wei; Mortuza, S. M.
- Bioinformatics, Vol. 36, Issue 7
Scoring function for automated assessment of protein structure template quality
journal, January 2004
- Zhang, Yang; Skolnick, Jeffrey
- Proteins: Structure, Function, and Bioinformatics, Vol. 57, Issue 4
Predicting protein residue–residue contacts using deep networks and boosting
journal, October 2012
- Eickholt, Jesse; Cheng, Jianlin
- Bioinformatics, Vol. 28, Issue 23
The RosettaDock server for local protein-protein docking
journal, May 2008
- Lyskov, S.; Gray, J. J.
- Nucleic Acids Research, Vol. 36, Issue Web Server
Improved protein structure prediction using potentials from deep learning
journal, January 2020
- Senior, Andrew W.; Evans, Richard; Jumper, John
- Nature, Vol. 577, Issue 7792
Prediction of protein assemblies, the next frontier: The CASP14‐CAPRI experiment
journal, September 2021
- Lensink, Marc F.; Brysbaert, Guillaume; Mauri, Théo
- Proteins: Structure, Function, and Bioinformatics, Vol. 89, Issue 12
DockQ: A Quality Measure for Protein-Protein Docking Models
journal, August 2016
- Basu, Sankar; Wallner, Björn
- PLOS ONE, Vol. 11, Issue 8
PSICOV: precise structural contact prediction using sparse inverse covariance estimation on large multiple sequence alignments
journal, November 2011
- Jones, David T.; Buchan, Daniel W. A.; Cozzetto, Domenico
- Bioinformatics, Vol. 28, Issue 2
Protein-protein docking using region-based 3D Zernike descriptors
journal, January 2009
- Venkatraman, Vishwesh; Yang, Yifeng D.; Sael, Lee
- BMC Bioinformatics, Vol. 10, Issue 1
Protein–Protein Docking with Simultaneous Optimization of Rigid-body Displacement and Side-chain Conformations
journal, August 2003
- Gray, Jeffrey J.; Moughon, Stewart; Wang, Chu
- Journal of Molecular Biology, Vol. 331, Issue 1
Sequence co-evolution gives 3D contacts and structures of protein complexes
journal, September 2014
- Hopf, Thomas A.; Schärfe, Charlotta P. I.; Rodrigues, João P. G. L. M.
- eLife, Vol. 3
DNCON2_Inter: predicting interchain contacts for homodimeric and homomultimeric protein complexes using multiple sequence alignments of monomers and deep learning
journal, June 2021
- Quadir, Farhan; Roy, Raj S.; Halfmann, Randal
- Scientific Reports, Vol. 11, Issue 1
Critical assessment of methods of protein structure prediction (CASP)—Round XIII
journal, August 2019
- Kryshtafovych, Andriy; Schwede, Torsten; Topf, Maya
- Proteins: Structure, Function, and Bioinformatics, Vol. 87, Issue 12
Highly accurate protein structure prediction for the human proteome
journal, July 2021
- Tunyasuvunakool, Kathryn; Adler, Jonas; Wu, Zachary
- Nature, Vol. 596, Issue 7873
Accurate prediction of protein structures and interactions using a three-track neural network
journal, July 2021
- Baek, Minkyung; DiMaio, Frank; Anishchenko, Ivan
- Science, Vol. 373, Issue 6557
DeepDist: real-value inter-residue distance prediction with deep residual convolutional network
journal, January 2021
- Wu, Tianqi; Guo, Zhiye; Hou, Jie
- BMC Bioinformatics, Vol. 22, Issue 1
Critical assessment of methods of protein structure prediction: Progress and new directions in round XI: Progress in CASP XI
journal, June 2016
- Moult, John; Fidelis, Krzysztof; Kryshtafovych, Andriy
- Proteins: Structure, Function, and Bioinformatics, Vol. 84
InterPep2: global peptide–protein docking using interaction surface templates
journal, January 2020
- Johansson-Åkhe, Isak; Mirabello, Claudio; Wallner, Björn
- Bioinformatics, Vol. 36, Issue 8
Hidden Markov model speed heuristic and iterative HMM search procedure
journal, August 2010
- Johnson, L. Steven; Eddy, Sean R.; Portugaly, Elon
- BMC Bioinformatics, Vol. 11, Issue 1
DeepComplex: A Web Server of Predicting Protein Complex Structures by Deep Learning Inter-chain Contact Prediction and Distance-Based Modelling
journal, August 2021
- Quadir, Farhan; Roy, Raj S.; Soltanikazemi, Elham
- Frontiers in Molecular Biosciences, Vol. 8
HHblits: lightning-fast iterative protein sequence searching by HMM-HMM alignment
journal, December 2011
- Remmert, Michael; Biegert, Andreas; Hauser, Andreas
- Nature Methods, Vol. 9, Issue 2
Highly accurate protein structure prediction with AlphaFold
journal, July 2021
- Jumper, John; Evans, Richard; Pritzel, Alexander
- Nature
Assessment of protein model structure accuracy estimation in CASP14 : Old and new challenges
journal, August 2021
- Kwon, Sohee; Won, Jonghun; Kryshtafovych, Andriy
- Proteins: Structure, Function, and Bioinformatics, Vol. 89, Issue 12
Protein-Protein Interaction Interface Residue Pair Prediction Based on Deep Learning Architecture
journal, September 2019
- Zhao, Zhenni; Gong, Xinqi
- IEEE/ACM Transactions on Computational Biology and Bioinformatics, Vol. 16, Issue 5
Prediction of homoprotein and heteroprotein complexes by protein docking and template‐based modeling: A CASP‐CAPRI experiment
journal, June 2016
- Lensink, Marc F.; Velankar, Sameer; Kryshtafovych, Andriy
- Proteins: Structure, Function, and Bioinformatics, Vol. 84, Issue S1
CCMpred—fast and precise prediction of protein residue–residue contacts from correlated mutations
journal, July 2014
- Seemayer, Stefan; Gruber, Markus; Söding, Johannes
- Bioinformatics, Vol. 30, Issue 21
CASP prediction center infrastructure and evaluation measures in CASP10 and CASP ROLL: CASP Prediction Center
journal, October 2013
- Kryshtafovych, Andriy; Monastyrskyy, Bohdan; Fidelis, Krzysztof
- Proteins: Structure, Function, and Bioinformatics, Vol. 82
Robust and accurate prediction of residue–residue interactions across protein interfaces using evolutionary information
journal, May 2014
- Ovchinnikov, Sergey; Kamisetty, Hetunandan; Baker, David
- eLife, Vol. 3
Improved protein structure prediction using predicted interresidue orientations
journal, January 2020
- Yang, Jianyi; Anishchenko, Ivan; Park, Hahnbeom
- Proceedings of the National Academy of Sciences, Vol. 117, Issue 3
SCRATCH: a protein structure and structural feature prediction server
journal, July 2005
- Cheng, J.; Randall, A. Z.; Sweredoski, M. J.
- Nucleic Acids Research, Vol. 33, Issue Web Server
UniRef clusters: a comprehensive and scalable alternative for improving sequence similarity searches
journal, November 2014
- Suzek, B. E.; Wang, Y.; Huang, H.
- Bioinformatics, Vol. 31, Issue 6
The challenge of modeling protein assemblies: the CASP12-CAPRI experiment
journal, November 2017
- Lensink, Marc F.; Velankar, Sameer; Baek, Minkyung
- Proteins: Structure, Function, and Bioinformatics, Vol. 86
3D Complex: A Structural Classification of Protein Complexes
journal, January 2006
- Levy, Emmanuel D.; Pereira-Leal, Jose B.; Chothia, Cyrus
- PLoS Computational Biology, Vol. 2, Issue 11
Protein structure prediction using multiple deep neural networks in the 13th Critical Assessment of Protein Structure Prediction (CASP13)
journal, August 2019
- Senior, Andrew W.; Evans, Richard; Jumper, John
- Proteins: Structure, Function, and Bioinformatics, Vol. 87, Issue 12
Accurate prediction of inter-protein residue–residue contacts for homo-oligomeric protein complexes
journal, March 2021
- Yan, Yumeng; Huang, Sheng-You
- Briefings in Bioinformatics, Vol. 22, Issue 5
Deep graph learning of inter-protein contacts
journal, November 2021
- Xie, Ziwei; Xu, Jinbo
- Bioinformatics, Vol. 38, Issue 4
Protein docking prediction using predicted protein-protein interface
journal, January 2012
- Li, Bin; Kihara, Daisuke
- BMC Bioinformatics, Vol. 13, Issue 1
CONFOLD: Residue-residue contact-guided ab initio protein folding: Contact-Guided Protein Folding
journal, June 2015
- Adhikari, Badri; Bhattacharya, Debswapna; Cao, Renzhi
- Proteins: Structure, Function, and Bioinformatics, Vol. 83, Issue 8