Distance-based Reconstruction of Protein Quaternary Structures from Inter-Chain Contacts

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

doi:10.22541/au.162696617.75074967/v1

Cited by 7 publications

(10 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 3 visualizes the top L /5 interchain contact predictions for a target (PDB code: 1DR0) from the Homo_std test dataset and the quaternary structure reconstructed from the interchain contacts predicted by DRcon and the known tertiary structure of a chain in the dimer. The quaternary structure is built by GD ( Soltanikazemi et al , 2022 ), which applies the gradient descent optimization to build quaternary structures by using interchain contacts as distance restraints.…”

Section: Resultsmentioning

confidence: 99%

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: Resultsmentioning

confidence: 99%

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

“…We compare DRLComplex with four existing methods namely GD (gradient descent)(Soltanikazemi et al 2022), MC (Markov Chain Monte Carlo simulation), Equidock(Ganea et al 2022) and CNS(Brünger et al 1998; Brunger 2007) (the simulated annealing simulation used in ConComplex)(Quadir, Roy, Soltanikazemi, et al 2021) that constructs quaternary structures. It is worth noting that Equidock is an equivariant neural network method of directly predicting quaternary structures of dimers without using interchain contacts as input.…”

Section: Resultsmentioning

confidence: 99%

“…The methods are evaluated on two standard protein dimer datasets: CASP_CAPRI and Std_32. The CASP_CAPRI dataset consists of 28 homodimer(Yan and Huang 2021) targets and the Std_32 contains 32 heterodimer targets(Soltanikazemi et al 2022). It is worth noting that only 31 out of the 32 targets of the Std_32 are used because one target (1IXRA_1IXRC) has no interchain contact between its ligand and receptor.…”

Section: Resultsmentioning

confidence: 99%

“…Zdock (Pierce et al 2014) uses a combination of various potential scoring criteria to select the quaternary structure models generated by the Fourier transformation. Recently, a gradient descent structure optimization method - GD (Soltanikazemi et al 2022) and a simulated annealing method - ConComplex (Quadir, Roy, Soltanikazemi, et al 2021) have been developed to build quaternary structures from predicted interchain residue-residue contacts and tertiary structures of protein chains. Due to the recent development of more accurate deep learning methods for interchain contact prediction such as DRCon(Roy et al 2021) and GLINTER(Xie and Xu 2021), these approaches can generate high-quality quaternary structures for some proteins.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

“…We conduct all subsequent experiments for model evaluation on two standard protein dimer datasets: CASP_CAPRI and Std_32. The CASP_CAPRI dataset consists of 28 homodimer [15] targets, and the Std_32 contains 32 heterodimer targets [22]. We note that we exclude one of the Std_32 targets from our experiments, as this target (PDB Code: 1IXRA_1IXRC) contains no inter-chain contacts between its ligand and receptor structures.…”

Section: Evaluation Setupmentioning

confidence: 99%

DRLComplex: Reconstruction of protein quaternary structures using deep reinforcement learning

Soltanikazemi¹,

Roy²,

Quadir³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Predicted inter-chain 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 inter-chain contacts. Here, we present an agent-based self-learning method based on deep reinforcement learning (DRLCOMPLEX) to build protein complex structures using inter-chain contacts as distance constraints. We rigorously tested DRLCOMPLEX on two standard datasets of homodimeric and heterodimeric protein complexes (i.e., the CASP-CAPRI homodimer and Std_32 heterodimer datasets) using both true and predicted interchain contacts as inputs. Utilizing true contacts as input, DRLCOMPLEX achieved high average TM-scores 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 TM-scores of 0.73 and 0.76 for homodimers and heterodimers, respectively. Our experiments find that the accuracy of reconstructed quaternary structures depends on the accuracy of the contact predictions. Compared to other optimization methods for reconstructing quaternary structures from inter-chain contacts, DRLCOMPLEX performs similar to an advanced gradient descent method and better than a Markov Chain Monte Carlo simulation method and a simulated annealing-based method, validating the effectiveness of DRLCOMPLEX for quaternary reconstruction of protein complexes. * Equal Contribution † Equal Contribution Preprint. Under review.

show abstract

Distance-based Reconstruction of Protein Quaternary Structures from Inter-Chain Contacts

Cited by 7 publications

References 0 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

DRLComplex: Reconstruction of protein quaternary structures using deep reinforcement learning

Contact Info

Product

Resources

About