DeepComplex: A Web Server of Predicting Protein Complex Structures by Deep Learning Inter-chain Contact Prediction and Distance-Based Modelling

Quadir, Farhan; Roy, Raj; Soltanikazemi, Elham; Cheng, Jianlin

doi:10.3389/fmolb.2021.716973

Cited by 20 publications

(16 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two residues from the two chains in a homodimer are considered an interchain contact if the Euclidean distance between any two heavy atoms of the two residues is less than or equal to 6 Å ( Ovchinnikov et al , 2014 ; Quadir et al , 2021a , b ; Zhou et al , 2018 ). Multiple homodimer datasets with known quaternary structures and interchain contacts are used to develop DRCon.…”

Section: Methodsmentioning

confidence: 99%

“…The DCA-based methods require a large number of sequences in MSAs to generate accurate interchain contact predictions, which are not available for most protein complexes because there are not many known protein complexes available. The problem is alleviated for protein homodimers (a protein complex consisting of two identical chains) because the MSA of a monomer (a single chain) in a homodimer contains both intrachain and interchain residue–residue co-evolutionary signals ( Quadir et al , 2021a , b ). The advantage of using the MSA of a monomer is that it is generally much deeper than the MSA of a protein complex.…”

Section: Introductionmentioning

confidence: 99%

“…The advantage of using the MSA of a monomer is that it is generally much deeper than the MSA of a protein complex. Recently several deep learning methods such as DNCON2_Inter ( Quadir et al , 2021a , b ) and DeepHomo ( Yan and Huang, 2021 ) use the MSA of a monomer in a homodimer to predict interchain contacts in homodimers, while another method, Glinter (Xie and Xu, 2021), uses the MSA of a dimer to perdict interchain contacts in both homodimers and heterodimers…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A deep dilated convolutional residual network for predicting interchain contacts of protein homodimers

et al. 2022

Self Cite

View full text Add to dashboard Cite

Motivation 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. Results 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. Availability The source code of DRCon is available at https://github.com/jianlin-cheng/DRCon.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A deep dilated convolutional residual network for predicting interchain contacts of protein homodimers

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Hou et al 2020;Quadir, Roy, Soltanikazemi, et al 2021;Quadir, Roy, Halfmann, et al 2021, 2;Yan and Huang 2021;Roy et al 2021;Xie and Xu 2021). The methods for quaternary structure prediction can be subdivided into two categories: ab-initio methods (Lyskov and Gray 2008;Pierce et al 2014;Quadir, Roy, Soltanikazemi, et al 2021;Evans et al 2021;Park et al 2021) and template-based methods (Tuncbag et al 2012;Guerler, Govindarajoo, and Zhang 2013). The template-based approach generally searches protein structure databases for similar templates for a target and predicts the quaternary structure of the target based on the template structures.…”

Section: Introductionmentioning

confidence: 99%

“…Despite the notable progress in tertiary structure prediction, the prediction of quaternary structure of protein complexes is still in the early stage of development (Zeng et al 2018; J. Hou et al 2020; Quadir, Roy, Soltanikazemi, et al 2021; Quadir, Roy, Halfmann, et al 2021, 2; Yan and Huang 2021; Roy et al 2021; Xie and Xu 2021). The methods for quaternary structure prediction can be subdivided into two categories: ab-initio methods(Lyskov and Gray 2008; Pierce et al 2014; Quadir, Roy, Soltanikazemi, et al 2021; Evans et al 2021; Park et al 2021) and template-based methods(Tuncbag et al 2012; Guerler, Govindarajoo, and Zhang 2013).…”

Section: Introductionmentioning

confidence: 99%

A deep reinforcement learning approach to reconstructing quaternary structures of protein dimers through self-learning

Soltanikazemi

Roy

Quadir

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Predicted interchain residue-residue contacts can be used to build the quaternary structure of protein complexes from scratch. However, only a small number of methods have been developed to reconstruct protein quaternary structures using predicted interchain contacts. Here, we present an agent-based self-learning method based on deep reinforcement learning (DRLComplex) to build protein complex structures using interchain contacts as distance constraints. We rigorously tested the DRLComplex on two standard datasets of homodimeric and heterodimeric dimers (the CASP-CAPRI homodimer dataset and Std_32 heterodimer dataset) using both true and predicted contacts. Utilizing true contacts as input, the DRLComplex achieved a high average TM-score of 0.9895 and 0.9881 and a low average interface RMSD (I_RMSD) of 0.2197 and 0.92 on the two datasets, respectively. When predicted contacts are used, the method achieves the TM-score of 0.73 and 0.76 for homodimers and heterodimers respectively. The accuracy of reconstructed quaternary structures depends on the accuracy of contact predictions. Compared with other optimization methods of reconstructing quaternary structures from interchain contacts, DRLComplex performs similarly to an advanced gradient descent method and better than a Markov Chain Monte Carlo simulation method and a simulated annealing-based method. The source code of DRLComplex is available at: https://github.com/jianlin-cheng/DRLComplex

show abstract

Distance‐based reconstruction of protein quaternary structures from inter‐chain contacts

et al. 2021

Self Cite

View full text Add to dashboard Cite

Predicting the quaternary structure of protein complex is an important problem. Interchain residue-residue contact prediction can provide useful information to guide the ab initio reconstruction of quaternary structures. However, few methods have been developed to build quaternary structures from predicted inter-chain contacts. Here, we develop the first method based on gradient descent optimization (GD) to build quaternary structures of protein dimers utilizing inter-chain contacts as distance restraints. We evaluate GD on several datasets of homodimers and heterodimers using true/predicted contacts and monomer structures as input. GD consistently performs better than both simulated annealing and Markov Chain Monte Carlo simulation. Starting from an arbitrarily quaternary structure randomly initialized from the tertiary structures of protein chains and using true inter-chain contacts as input, GD can reconstruct high-quality structural models for homodimers and heterodimers with average TM-score ranging from 0.92 to 0.99 and average interface root mean square distance from 0.72 Å to 1.64 Å. On a dataset of 115 homodimers, using predicted inter-chain contacts as restraints, the average TM-score of the structural models built by GD is 0.76. For 46% of the homodimers, high-quality structural models with TM-score ≥ 0.9 are reconstructed from predicted contacts. There is a strong correlation between the quality of the reconstructed models and the precision and recall of predicted contacts. Only a moderate precision or recall of inter-chain contact prediction is needed to build good structural models for most homodimers. Moreover, GD improves the quality of quaternary structures predicted by AlphaFold2 on a Critical Assessment of Techniques for Protein Structure Prediction-Critical Assessments of Predictions of Interactions dataset.

show abstract

DeepComplex: A Web Server of Predicting Protein Complex Structures by Deep Learning Inter-chain Contact Prediction and Distance-Based Modelling

Cited by 20 publications

References 35 publications

A deep dilated convolutional residual network for predicting interchain contacts of protein homodimers

A deep dilated convolutional residual network for predicting interchain contacts of protein homodimers

A deep reinforcement learning approach to reconstructing quaternary structures of protein dimers through self-learning

Distance‐based reconstruction of protein quaternary structures from inter‐chain contacts

Contact Info

Product

Resources

About