Structural templates for comparative protein docking

Assessment of Protein-Protein Docking Models Using Deep Learning

Protein-protein interactions are involved in almost all processes in a living cell and determine the biological functions of proteins. To obtain mechanistic understandings of protein-protein interactions, the tertiary structures of protein complexes have been determined by biophysical experimental methods, such as X-ray crystallography and cryogenic electron microscopy. However, as experimental methods are costly in resources, many computational methods have been developed that model protein complex structures. One of the difficulties in computational protein complex modeling (protein docking) is to select the most accurate models among many models that are usually generated by a docking method. This article reviews advances in protein docking model assessment methods, focusing on recent developments that apply deep learning to several network architectures.

Impact of AlphaFold on structure prediction of protein complexes: The CASP15-CAPRI experiment

We present the results for CAPRI Round 54, the 5th joint CASP-CAPRI protein assembly prediction challenge. The Round offered 37 targets, including 14 homodimers, 3 homo-trimers, 13 heterodimers including 3 antibody-antigen complexes, and 7 large assemblies. On average ~70 CASP and CAPRI predictor groups, including more than 20 automatics servers, submitted models for each target. A total of 21 941 models submitted by these groups and by 15 CAPRI scorer groups were evaluated using the CAPRI model quality measures and the DockQ score consolidating these measures. The prediction performance was quantified by a weighted score based on the number of models of acceptable quality or higher submitted by each group among their five best models. Results show substantial progress achieved across a significant fraction of the 60+ participating groups. High-quality models were produced for about 40% of the targets compared to 8% two years earlier. This remarkable improvement is due to the wide use of the AlphaFold2 and AlphaFold2-Multimer software and the confidence metrics they provide. Notably, expanded sampling of candidate solutions by manipulating these deep learning inference engines, enriching multiple sequence alignments, or integration of advanced modeling tools, enabled top performing groups to exceed the performance of a standard AlphaFold2-Multimer version used as a yard stick. This notwithstanding, performance remained poor for complexes with antibodies and nanobodies, where evolutionary relationships between the binding partners are lacking, and for complexes featuring conformational flexibility, clearly indicating that the prediction of protein complexes remains a challenging problem.

ComDock: A novel approach for protein-protein docking with an efficient fusing strategy

Protein-protein interaction plays an important role in studying the mechanism of protein functions from the structural perspective. Molecular docking is a powerful approach to detect protein-protein complexes using computational tools, due to the high cost and time-consuming of the traditional experimental methods. Among existing technologies, the template-based method utilizes the structural information of known homologous 3D complexes as available and reliable templates to achieve high accuracy and low computational complexity. However, the performance of the template-based method depends on the quality and quantity of templates. When insufficient or even no templates, the ab initio docking method is necessary and largely enriches the docking conformations. Therefore, it's a feasible strategy to fuse the effectivity of the template-based model and the universality of ab initio model to improve the docking performance. In this study, we construct a new, diverse, comprehensive template library derived from PDB, containing 77,685 complexes. We propose a template-based method (named TemDock), which retrieves the evolutionary relationship between the target sequence and samples in the template library and transfers similar structural information. Then, the target structure is built by superposing on the homologous template complex with TM-align. Moreover, we develop a consensus-based method (named ComDock) to integrate our TemDock and an existing ab initio method (ZDOCK). On 105 targets with templates from Benchmark 5.0, the TemDock and ComDock achieve a success rate of 68.57 % and 71.43 % in the top 10 conformations, respectively. Compared with the HDOCK, ComDock obtains better I-RMSD of hit configurations on 9 targets and more hit models in the top 100 conformations. As an efficient method for protein-protein docking, the ComDock is expected to study protein-protein recognition and reveal the various biological passways that are critical for developing drug discovery. The final results are stored at https://github.com/guofei-tju/mqz_ComDock_docking.

ComplexQA: a deep graph learning approach for protein complex structure assessment

MOTIVATION

In recent years, the end-to-end deep learning method for single-chain protein structure prediction has achieved high accuracy. For example, the state-of-the-art method AlphaFold, developed by Google, has largely increased the accuracy of protein structure predictions to near experimental accuracy in some of the cases. At the same time, there are few methods that can evaluate the quality of protein complexes at the residue level. In particular, evaluating the quality of residues at the interface of protein complexes can lead to a wide range of applications, such as protein function analysis and drug design. In this paper, we introduce a new deep graph neural network-based method ComplexQA, to evaluate the local quality of interfaces for protein complexes by utilizing the residue-level structural information in 3D space and the sequence-level constraints.

RESULTS

We benchmark our method to other state-of-the-art quality assessment approaches on the HAF2 and DBM55-AF2 datasets (high-quality structural models predicted by AlphaFold-Multimer), and the BM5 docking dataset. The experimental results show that our proposed method achieves better or similar performance compared with other state-of-the-art methods, especially on difficult targets which only contain a few acceptable models. Our method is able to suggest a score for each interfac e residue, which demonstrates a powerful assessment tool for the ever-increasing number of protein complexes.

AVAILABILITY

https://github.com/Cao-Labs/ComplexQA.git. Contact: caora@plu.edu.

Discriminating physiological from non-physiological interfaces in structures of protein complexes: A community-wide study

Reliably scoring and ranking candidate models of protein complexes and assigning their oligomeric state from the structure of the crystal lattice represent outstanding challenges. A community-wide effort was launched to tackle these challenges. The latest resources on protein complexes and interfaces were exploited to derive a benchmark dataset consisting of 1677 homodimer protein crystal structures, including a balanced mix of physiological and non-physiological complexes. The non-physiological complexes in the benchmark were selected to bury a similar or larger interface area than their physiological counterparts, making it more difficult for scoring functions to differentiate between them. Next, 252 functions for scoring protein-protein interfaces previously developed by 13 groups were collected and evaluated for their ability to discriminate between physiological and non-physiological complexes. A simple consensus score generated using the best performing score of each of the 13 groups, and a cross-validated Random Forest (RF) classifier were created. Both approaches showed excellent performance, with an area under the Receiver Operating Characteristic (ROC) curve of 0.93 and 0.94, respectively, outperforming individual scores developed by different groups. Additionally, AlphaFold2 engines recalled the physiological dimers with significantly higher accuracy than the non-physiological set, lending support to the reliability of our benchmark dataset annotations. Optimizing the combined power of interface scoring functions and evaluating it on challenging benchmark datasets appears to be a promising strategy.

Quality Assessment of Protein Docking Models Based on Graph Neural Network

Protein docking provides a structural basis for the design of drugs and vaccines. Among the processes of protein docking, quality assessment (QA) is utilized to pick near-native models from numerous protein docking candidate conformations, and it directly determines the final docking results. Although extensive efforts have been made to improve QA accuracy, it is still the bottleneck of current protein docking systems. In this paper, we presented a Deep Graph Attention Neural Network (DGANN) to evaluate and rank protein docking candidate models. DGANN learns inter-residue physio-chemical properties and structural fitness across the two protein monomers in a docking model and generates their probabilities of near-native models. On the ZDOCK decoy benchmark, our DGANN outperformed the ranking provided by ZDOCK in terms of ranking good models into the top selections. Furthermore, we conducted comparative experiments on an independent testing dataset, and the results also demonstrated the superiority and generalization of our proposed method.

Protein Docking Model Evaluation by Graph Neural Networks

Physical interactions of proteins play key functional roles in many important cellular processes. To understand molecular mechanisms of such functions, it is crucial to determine the structure of protein complexes. To complement experimental approaches, which usually take a considerable amount of time and resources, various computational methods have been developed for predicting the structures of protein complexes. In computational modeling, one of the challenges is to identify near-native structures from a large pool of generated models. Here, we developed a deep learning-based approach named Graph Neural Network-based DOcking decoy eValuation scorE (GNN-DOVE). To evaluate a protein docking model, GNN-DOVE extracts the interface area and represents it as a graph. The chemical properties of atoms and the inter-atom distances are used as features of nodes and edges in the graph, respectively. GNN-DOVE was trained, validated, and tested on docking models in the Dockground database and further tested on a combined dataset of Dockground and ZDOCK benchmark as well as a CAPRI scoring dataset. GNN-DOVE performed better than existing methods, including DOVE, which is our previous development that uses a convolutional neural network on voxelized structure models.

Structural motifs in protein cores and at protein-protein interfaces are different

Structures of proteins and protein-protein complexes are determined by the same physical principles and thus share a number of similarities. At the same time, there could be differences because in order to function, proteins interact with other molecules, undergo conformations changes, and so forth, which might impose different restraints on the tertiary versus quaternary structures. This study focuses on structural properties of protein-protein interfaces in comparison with the protein core, based on the wealth of currently available structural data and new structure-based approaches. The results showed that physicochemical characteristics, such as amino acid composition, residue-residue contact preferences, and hydrophilicity/hydrophobicity distributions, are similar in protein core and protein-protein interfaces. On the other hand, characteristics that reflect the evolutionary pressure, such as structural composition and packing, are largely different. The results provide important insight into fundamental properties of protein structure and function. At the same time, the results contribute to better understanding of the ways to dock proteins. Recent progress in predicting structures of individual proteins follows the advancement of deep learning techniques and new approaches to residue coevolution data. Protein core could potentially provide large amounts of data for application of the deep learning to docking. However, our results showed that the core motifs are significantly different from those at protein-protein interfaces, and thus may not be directly useful for docking. At the same time, such difference may help to overcome a major obstacle in application of the coevolutionary data to docking-discrimination of the intramolecular information not directly relevant to docking.

Protein docking model evaluation by 3D deep convolutional neural networks

MOTIVATION

Many important cellular processes involve physical interactions of proteins. Therefore, determining protein quaternary structures provide critical insights for understanding molecular mechanisms of functions of the complexes. To complement experimental methods, many computational methods have been developed to predict structures of protein complexes. One of the challenges in computational protein complex structure prediction is to identify near-native models from a large pool of generated models.

RESULTS

We developed a convolutional deep neural network-based approach named DOcking decoy selection with Voxel-based deep neural nEtwork (DOVE) for evaluating protein docking models. To evaluate a protein docking model, DOVE scans the protein-protein interface of the model with a 3D voxel and considers atomic interaction types and their energetic contributions as input features applied to the neural network. The deep learning models were trained and validated on docking models available in the ZDock and DockGround databases. Among the different combinations of features tested, almost all outperformed existing scoring functions.

AVAILABILITY AND IMPLEMENTATION

Codes available at http://github.com/kiharalab/DOVE, http://kiharalab.org/dove/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Application of docking methodologies to modeled proteins

Protein docking is essential for structural characterization of protein interactions. Besides providing the structure of protein complexes, modeling of proteins and their complexes is important for understanding the fundamental principles and specific aspects of protein interactions. The accuracy of protein modeling, in general, is still less than that of the experimental approaches. Thus, it is important to investigate the applicability of docking techniques to modeled proteins. We present new comprehensive benchmark sets of protein models for the development and validation of protein docking, as well as a systematic assessment of free and template-based docking techniques on these sets. As opposed to previous studies, the benchmark sets reflect the real case modeling/docking scenario where the accuracy of the models is assessed by the modeling procedure, without reference to the native structure (which would be unknown in practical applications). We also expanded the analysis to include docking of protein pairs where proteins have different structural accuracy. The results show that, in general, the template-based docking is less sensitive to the structural inaccuracies of the models than the free docking. The near-native docking poses generated by the template-based approach, typically, also have higher ranks than those produces by the free docking (although the free docking is indispensable in modeling the multiplicity of protein interactions in a crowded cellular environment). The results show that docking techniques are applicable to protein models in a broad range of modeling accuracy. The study provides clear guidelines for practical applications of docking to protein models.

How to choose templates for modeling of protein complexes: Insights from benchmarking template-based docking

Comparative docking is based on experimentally determined structures of protein-protein complexes (templates), following the paradigm that proteins with similar sequences and/or structures form similar complexes. Modeling utilizing structure similarity of target monomers to template complexes significantly expands structural coverage of the interactome. Template-based docking by structure alignment can be performed for the entire structures or by aligning targets to the bound interfaces of the experimentally determined complexes. Systematic benchmarking of docking protocols based on full and interface structure alignment showed that both protocols perform similarly, with top 1 docking success rate 26%. However, in terms of the models' quality, the interface-based docking performed marginally better. The interface-based docking is preferable when one would suspect a significant conformational change in the full protein structure upon binding, for example, a rearrangement of the domains in multidomain proteins. Importantly, if the same structure is selected as the top template by both full and interface alignment, the docking success rate increases 2-fold for both top 1 and top 10 predictions. Matching structural annotations of the target and template proteins for template detection, as a computationally less expensive alternative to structural alignment, did not improve the docking performance. Sophisticated remote sequence homology detection added templates to the pool of those identified by structure-based alignment, suggesting that for practical docking, the combination of the structure alignment protocols and the remote sequence homology detection may be useful in order to avoid potential flaws in generation of the structural templates library.

Dockground Tool for Development and Benchmarking of Protein Docking Procedures

Databases of protein-protein complexes are essential for the development of protein modeling/docking techniques. Such databases provide a knowledge base for docking algorithms, intermolecular potentials, search procedures, scoring functions, and refinement protocols. Development of docking techniques requires systematic validation of the modeling protocols on carefully curated benchmark sets of complexes. We present a description and a guide to the DOCKGROUND resource ( http://dockground.compbio.ku.edu ) for structural modeling of protein interactions. The resource integrates various datasets of protein complexes and other data for the development and testing of protein docking techniques. The sets include bound complexes, experimentally determined unbound, simulated unbound, model-model complexes, and docking decoys. The datasets are available to the user community through a Web interface.

Efficient flexible backbone protein-protein docking for challenging targets

Motivation

Binding-induced conformational changes challenge current computational docking algorithms by exponentially increasing the conformational space to be explored. To restrict this search to relevant space, some computational docking algorithms exploit the inherent flexibility of the protein monomers to simulate conformational selection from pre-generated ensembles. As the ensemble size expands with increased flexibility, these methods struggle with efficiency and high false positive rates.

Results

Here, we develop and benchmark RosettaDock 4.0, which efficiently samples large conformational ensembles of flexible proteins and docks them using a novel, six-dimensional, coarse-grained score function. A strong discriminative ability allows an eight-fold higher enrichment of near-native candidate structures in the coarse-grained phase compared to RosettaDock 3.2. It adaptively samples 100 conformations each of the ligand and the receptor backbone while increasing computational time by only 20-80%. In local docking of a benchmark set of 88 proteins of varying degrees of flexibility, the expected success rate (defined as cases with ≥50% chance of achieving 3 near-native structures in the 5 top-ranked ones) for blind predictions after resampling is 77% for rigid complexes, 49% for moderately flexible complexes and 31% for highly flexible complexes. These success rates on flexible complexes are a substantial step forward from all existing methods. Additionally, for highly flexible proteins, we demonstrate that when a suitable conformer generation method exists, the method successfully docks the complex.

Availability and implementation

As a part of the Rosetta software suite, RosettaDock 4.0 is available at https://www.rosettacommons.org to all non-commercial users for free and to commercial users for a fee.

Supplementary information

Supplementary data are available at Bioinformatics online.

Gene ontology improves template selection in comparative protein docking

Structural characterization of protein-protein interactions is essential for our ability to study life processes at the molecular level. Computational modeling of protein complexes (protein docking) is important as the source of their structure and as a way to understand the principles of protein interaction. Rapidly evolving comparative docking approaches utilize target/template similarity metrics, which are often based on the protein structure. Although the structural similarity, generally, yields good performance, other characteristics of the interacting proteins (eg, function, biological process, and localization) may improve the prediction quality, especially in the case of weak target/template structural similarity. For the ranking of a pool of models for each target, we tested scoring functions that quantify similarity of Gene Ontology (GO) terms assigned to target and template proteins in three ontology domains-biological process, molecular function, and cellular component (GO-score). The scoring functions were tested in docking of bound, unbound, and modeled proteins. The results indicate that the combined structural and GO-terms functions improve the scoring, especially in the twilight zone of structural similarity, typical for protein models of limited accuracy.

Inhibition of protein interactions: co-crystalized protein-protein interfaces are nearly as good as holo proteins in rigid-body ligand docking

Modulating protein interaction pathways may lead to the cure of many diseases. Known protein-protein inhibitors bind to large pockets on the protein-protein interface. Such large pockets are detected also in the protein-protein complexes without known inhibitors, making such complexes potentially druggable. The inhibitor-binding site is primary defined by the side chains that form the largest pocket in the protein-bound conformation. Low-resolution ligand docking shows that the success rate for the protein-bound conformation is close to the one for the ligand-bound conformation, and significantly higher than for the apo conformation. The conformational change on the protein interface upon binding to the other protein results in a pocket employed by the ligand when it binds to that interface. This proof-of-concept study suggests that rather than using computational pocket-opening procedures, one can opt for an experimentally determined structure of the target co-crystallized protein-protein complex as a starting point for drug design.

SnapDock-template-based docking by Geometric Hashing

Motivation

A highly efficient template-based protein–protein docking algorithm, nicknamed SnapDock, is presented. It employs a Geometric Hashing-based structural alignment scheme to align the target proteins to the interfaces of non-redundant protein–protein interface libraries. Docking of a pair of proteins utilizing the 22 600 interface PIFACE library is performed in < 2 min on the average. A flexible version of the algorithm allowing hinge motion in one of the proteins is presented as well.

Results

To evaluate the performance of the algorithm a blind re-modelling of 3547 PDB complexes, which have been uploaded after the PIFACE publication has been performed with success ratio of about 35%. Interestingly, a similar experiment with the template free PatchDock docking algorithm yielded a success rate of about 23% with roughly 1/3 of the solutions different from those of SnapDock. Consequently, the combination of the two methods gave a 42% success ratio.

Availability and implementation

A web server of the application is under development.

Modeling CAPRI targets 110-120 by template-based and free docking using contact potential and combined scoring function

The paper presents analysis of our template-based and free docking predictions in the joint CASP12/CAPRI37 round. A new scoring function for template-based docking was developed, benchmarked on the Dockground resource, and applied to the targets. The results showed that the function successfully discriminates the incorrect docking predictions. In correctly predicted targets, the scoring function was complemented by other considerations, such as consistency of the oligomeric states among templates, similarity of the biological functions, biological interface relevance, etc. The scoring function still does not distinguish well biological from crystal packing interfaces, and needs further development for the docking of bundles of α-helices. In the case of the trimeric targets, sequence-based methods did not find common templates, despite similarity of the structures, suggesting complementary use of structure- and sequence-based alignments in comparative docking. The results showed that if a good docking template is found, an accurate model of the interface can be built even from largely inaccurate models of individual subunits. Free docking however is very sensitive to the quality of the individual models. However, our newly developed contact potential detected approximate locations of the binding sites.

Improved performance in CAPRI round 37 using LZerD docking and template-based modeling with combined scoring functions

We report our group's performance for protein-protein complex structure prediction and scoring in Round 37 of the Critical Assessment of PRediction of Interactions (CAPRI), an objective assessment of protein-protein complex modeling. We demonstrated noticeable improvement in both prediction and scoring compared to previous rounds of CAPRI, with our human predictor group near the top of the rankings and our server scorer group at the top. This is the first time in CAPRI that a server has been the top scorer group. To predict protein-protein complex structures, we used both multi-chain template-based modeling (TBM) and our protein-protein docking program, LZerD. LZerD represents protein surfaces using 3D Zernike descriptors (3DZD), which are based on a mathematical series expansion of a 3D function. Because 3DZD are a soft representation of the protein surface, LZerD is tolerant to small conformational changes, making it well suited to docking unbound and TBM structures. The key to our improved performance in CAPRI Round 37 was to combine multi-chain TBM and docking. As opposed to our previous strategy of performing docking for all target complexes, we used TBM when multi-chain templates were available and docking otherwise. We also describe the combination of multiple scoring functions used by our server scorer group, which achieved the top rank for the scorer phase.

Dockground: A comprehensive data resource for modeling of protein complexes

Characterization of life processes at the molecular level requires structural details of protein interactions. The number of experimentally determined structures of protein-protein complexes accounts only for a fraction of known protein interactions. This gap in structural description of the interactome has to be bridged by modeling. An essential part of the development of structural modeling/docking techniques for protein interactions is databases of protein-protein complexes. They are necessary for studying protein interfaces, providing a knowledge base for docking algorithms, and developing intermolecular potentials, search procedures, and scoring functions. Development of protein-protein docking techniques requires thorough benchmarking of different parts of the docking protocols on carefully curated sets of protein-protein complexes. We present a comprehensive description of the Dockground resource (http://dockground.compbio.ku.edu) for structural modeling of protein interactions, including previously unpublished unbound docking benchmark set 4, and the X-ray docking decoy set 2. The resource offers a variety of interconnected datasets of protein-protein complexes and other data for the development and testing of different aspects of protein docking methodologies. Based on protein-protein complexes extracted from the PDB biounit files, Dockground offers sets of X-ray unbound, simulated unbound, model, and docking decoy structures. All datasets are freely available for download, as a whole or selecting specific structures, through a user-friendly interface on one integrated website.

Modeling complexes of modeled proteins

Structural characterization of proteins is essential for understanding life processes at the molecular level. However, only a fraction of known proteins have experimentally determined structures. This fraction is even smaller for protein-protein complexes. Thus, structural modeling of protein-protein interactions (docking) primarily has to rely on modeled structures of the individual proteins, which typically are less accurate than the experimentally determined ones. Such "double" modeling is the Grand Challenge of structural reconstruction of the interactome. Yet it remains so far largely untested in a systematic way. We present a comprehensive validation of template-based and free docking on a set of 165 complexes, where each protein model has six levels of structural accuracy, from 1 to 6 Å Cα RMSD. Many template-based docking predictions fall into acceptable quality category, according to the CAPRI criteria, even for highly inaccurate proteins (5-6 Å RMSD), although the number of such models (and, consequently, the docking success rate) drops significantly for models with RMSD > 4 Å. The results show that the existing docking methodologies can be successfully applied to protein models with a broad range of structural accuracy, and the template-based docking is much less sensitive to inaccuracies of protein models than the free docking. Proteins 2017; 85:470-478. © 2016 Wiley Periodicals, Inc.

Structural quality of unrefined models in protein docking

Structural characterization of protein-protein interactions is essential for understanding life processes at the molecular level. However, only a fraction of protein interactions have experimentally resolved structures. Thus, reliable computational methods for structural modeling of protein interactions (protein docking) are important for generating such structures and understanding the principles of protein recognition. Template-based docking techniques that utilize structural similarity between target protein-protein interaction and cocrystallized protein-protein complexes (templates) are gaining popularity due to generally higher reliability than that of the template-free docking. However, the template-based approach lacks explicit penalties for intermolecular penetration, as opposed to the typical free docking where such penalty is inherent due to the shape complementarity paradigm. Thus, template-based docking models are commonly assumed to require special treatment to remove large structural penetrations. In this study, we compared clashes in the template-based and free docking of the same proteins, with crystallographically determined and modeled structures. The results show that for the less accurate protein models, free docking produces fewer clashes than the template-based approach. However, contrary to the common expectation, in acceptable and better quality docking models of unbound crystallographically determined proteins, the clashes in the template-based docking are comparable to those in the free docking, due to the overall higher quality of the template-based docking predictions. This suggests that the free docking refinement protocols can in principle be applied to the template-based docking predictions as well. Proteins 2016; 85:39-45. © 2016 Wiley Periodicals, Inc.

Assessment of refinement of template-based models in CASP11

CASP11 (the 11th Meeting on the Critical Assessment of Protein Structure Prediction) ran a blind experiment in the refinement of protein structure predictions, the fourth such experiment since CASP8. As with the previous experiments, the predictors were provided with one starting structure from the server models of each of a selected set of template-based modeling targets and asked to refine the coordinates of the starting structure toward native. We assessed the refined structures with the Z-scores of the standard CASP measures, which compare the model-target similarities of the models from all the predictors. Furthermore, we assessed the refined structures with "relative measures," which compare the improvement in accuracy of each model with respect to the starting structure. The latter provides an assessment of the extent to which each predictor group is able to improve the starting structures toward native. We utilized heat maps to display improvements in the Calpha-Calpha distance matrix for each model. The heat maps labeled with each element of secondary structure helped us to identify regions of refinement toward native in each model. Most positively scoring models show modest improvements in multiple regions of the structure, while in some models we were able to identify significant repositioning of N/C-terminal segments and internal elements of secondary structure. The best groups were able to improve more than 70% of the targets from the starting models, and by an average of 3-5% in the standard CASP measures. Proteins 2016; 84(Suppl 1):260-281. © 2016 Wiley Periodicals, Inc.