The challenge of modeling protein assemblies: the CASP12-CAPRI experiment

Recent advances and challenges in protein complex model accuracy estimation

Estimation of model accuracy plays a crucial role in protein structure prediction, aiming to evaluate the quality of predicted protein structure models accurately and objectively. This process is not only key to screening candidate models that are close to the real structure, but also provides guidance for further optimization of protein structures. With the significant advancements made by AlphaFold2 in monomer structure, the problem of single-domain protein structure prediction has been widely solved. Correspondingly, the importance of assessing the quality of single-domain protein models decreased, and the research focus has shifted to estimation of model accuracy of protein complexes. In this review, our goal is to provide a comprehensive overview of the reference and statistical metrics, as well as representative methods, and the current challenges within four distinct facets (Topology Global Score, Interface Total Score, Interface Residue-Wise Score, and Tertiary Residue-Wise Score) in the field of complex EMA.

SurfPro-NN: A 3D point cloud neural network for the scoring of protein-protein docking models based on surfaces features and protein language models

Protein-protein interactions (PPI) play a crucial role in numerous key biological processes, and the structure of protein complexes provides valuable clues for in-depth exploration of molecular-level biological processes. Protein-protein docking technology is widely used to simulate the spatial structure of proteins. However, there are still challenges in selecting candidate decoys that closely resemble the native structure from protein-protein docking simulations. In this study, we introduce a docking evaluation method based on three-dimensional point cloud neural networks named SurfPro-NN, which represents protein structures as point clouds and learns interaction information from protein interfaces by applying a point cloud neural network. With the continuous advancement of deep learning in the field of biology, a series of knowledge-rich pre-trained models have emerged. We incorporate protein surface representation models and language models into our approach, greatly enhancing feature representation capabilities and achieving superior performance in protein docking model scoring tasks. Through comprehensive testing on public datasets, we find that our method outperforms state-of-the-art deep learning approaches in protein-protein docking model scoring. Not only does it significantly improve performance, but it also greatly accelerates training speed. This study demonstrates the potential of our approach in addressing protein interaction assessment problems, providing strong support for future research and applications in the field of biology.

Assembly of Protein Complexes in and on the Membrane with Predicted Spatial Arrangement Constraints

Membrane proteins play crucial roles in various cellular processes, and their interactions with other proteins in and on the membrane are essential for their proper functioning. While an increasing number of structures of more membrane proteins are being determined, the available structure data is still sparse. To gain insights into the mechanisms of membrane protein complexes, computational docking methods are necessary due to the challenge of experimental determination. Here, we introduce Mem-LZerD, a rigid-body membrane docking algorithm designed to take advantage of modern membrane modeling and protein docking techniques to facilitate the docking of membrane protein complexes. Mem-LZerD is based on the LZerD protein docking algorithm, which has been constantly among the top servers in many rounds of CAPRI protein docking assessment. By employing a combination of geometric hashing, newly constrained by the predicted membrane height and tilt angle, and model scoring accounting for the energy of membrane insertion, we demonstrate the capability of Mem-LZerD to model diverse membrane protein-protein complexes. Mem-LZerD successfully performed unbound docking on 13 of 21 (61.9%) transmembrane complexes in an established benchmark, more than shown by previous approaches. It was additionally tested on new datasets of 44 transmembrane complexes and 92 peripheral membrane protein complexes, of which it successfully modeled 35 (79.5%) and 15 (16.3%) complexes respectively. When non-blind orientations of peripheral targets were included, the number of successes increased to 54 (58.7%). We further demonstrate that Mem-LZerD produces complex models which are suitable for molecular dynamics simulation. Mem-LZerD is made available at https://lzerd.kiharalab.org.

Assessment of three-dimensional RNA structure prediction in CASP15

The prediction of RNA three-dimensional structures remains an unsolved problem. Here, we report assessments of RNA structure predictions in CASP15, the first CASP exercise that involved RNA structure modeling. Forty-two predictor groups submitted models for at least one of twelve RNA-containing targets. These models were evaluated by the RNA-Puzzles organizers and, separately, by a CASP-recruited team using metrics (GDT, lDDT) and approaches (Z-score rankings) initially developed for assessment of proteins and generalized here for RNA assessment. The two assessments independently ranked the same predictor groups as first (AIchemy_RNA2), second (Chen), and third (RNAPolis and GeneSilico, tied); predictions from deep learning approaches were significantly worse than these top ranked groups, which did not use deep learning. Further analyses based on direct comparison of predicted models to cryogenic electron microscopy (cryo-EM) maps and x-ray diffraction data support these rankings. With the exception of two RNA-protein complexes, models submitted by CASP15 groups correctly predicted the global fold of the RNA targets. Comparisons of CASP15 submissions to designed RNA nanostructures as well as molecular replacement trials highlight the potential utility of current RNA modeling approaches for RNA nanotechnology and structural biology, respectively. Nevertheless, challenges remain in modeling fine details such as noncanonical pairs, in ranking among submitted models, and in prediction of multiple structures resolved by cryo-EM or crystallography.

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.

Combining pairwise structural similarity and deep learning interface contact prediction to estimate protein complex model accuracy in CASP15

Estimating the accuracy of quaternary structural models of protein complexes and assemblies (EMA) is important for predicting quaternary structures and applying them to studying protein function and interaction. The pairwise similarity between structural models is proven useful for estimating the quality of protein tertiary structural models, but it has been rarely applied to predicting the quality of quaternary structural models. Moreover, the pairwise similarity approach often fails when many structural models are of low quality and similar to each other. To address the gap, we developed a hybrid method (MULTICOM_qa) combining a pairwise similarity score (PSS) and an interface contact probability score (ICPS) based on the deep learning inter-chain contact prediction for estimating protein complex model accuracy. It blindly participated in the 15th Critical Assessment of Techniques for Protein Structure Prediction (CASP15) in 2022 and performed very well in estimating the global structure accuracy of assembly models. The average per-target correlation coefficient between the model quality scores predicted by MULTICOM_qa and the true quality scores of the models of CASP15 assembly targets is 0.66. The average per-target ranking loss in using the predicted quality scores to rank the models is 0.14. It was able to select good models for most targets. Moreover, several key factors (i.e., target difficulty, model sampling difficulty, skewness of model quality, and similarity between good/bad models) for EMA are identified and analyzed. The results demonstrate that combining the multi-model method (PSS) with the complementary single-model method (ICPS) is a promising approach to EMA.

The impact of AI-based modeling on the accuracy of protein assembly prediction: Insights from CASP15

In CASP15, 87 predictors submitted around 11 000 models on 41 assembly targets. The community demonstrated exceptional performance in overall fold and interface contact predictions, achieving an impressive success rate of 90% (compared to 31% in CASP14). This remarkable accomplishment is largely due to the incorporation of DeepMind's AF2-Multimer approach into custom-built prediction pipelines. To evaluate the added value of participating methods, we compared the community models to the baseline AF2-Multimer predictor. In over 1/3 of cases, the community models were superior to the baseline predictor. The main reasons for this improved performance were the use of custom-built multiple sequence alignments, optimized AF2-Multimer sampling, and the manual assembly of AF2-Multimer-built subcomplexes. The best three groups, in order, are Zheng, Venclovas, and Wallner. Zheng and Venclovas reached a 73.2% success rate over all (41) cases, while Wallner attained 69.4% success rate over 36 cases. Nonetheless, challenges remain in predicting structures with weak evolutionary signals, such as nanobody-antigen, antibody-antigen, and viral complexes. Expectedly, modeling large complexes also remains challenging due to their high memory compute demands. In addition to the assembly category, we assessed the accuracy of modeling interdomain interfaces in the tertiary structure prediction targets. Models on seven targets featuring 17 unique interfaces were analyzed. Best predictors achieved a 76.5% success rate, with the UM-TBM group being the leader. In the interdomain category, we observed that the predictors faced challenges, as in the case of the assembly category, when the evolutionary signal for a given domain pair was weak or the structure was large. Overall, CASP15 witnessed unprecedented improvement in interface modeling, reflecting the AI revolution seen in CASP14.

Assembly of Protein Complexes In and On the Membrane with Predicted Spatial Arrangement Constraints

Membrane proteins play crucial roles in various cellular processes, and their interactions with other proteins in and on the membrane are essential for their proper functioning. While an increasing number of structures of more membrane proteins are being determined, the available structure data is still sparse. To gain insights into the mechanisms of membrane protein complexes, computational docking methods are necessary due to the challenge of experimental determination. Here, we introduce Mem-LZerD, a rigid-body membrane docking algorithm designed to take advantage of modern membrane modeling and protein docking techniques to facilitate the docking of membrane protein complexes. Mem-LZerD is based on the LZerD protein docking algorithm, which has been constantly among the top servers in many rounds of CAPRI protein docking assessment. By employing a combination of geometric hashing, newly constrained by the predicted membrane height and tilt angle, and model scoring accounting for the energy of membrane insertion, we demonstrate the capability of Mem-LZerD to model diverse membrane protein-protein complexes. Mem-LZerD successfully performed unbound docking on 13 of 21 (61.9%) transmembrane complexes in an established benchmark, more than shown by previous approaches. It was additionally tested on new datasets of 44 transmembrane complexes and 92 peripheral membrane protein complexes, of which it successfully modeled 35 (79.5%) and 15 (16.3%) complexes respectively. When non-blind orientations of peripheral targets were included, the number of successes increased to 54 (58.7%). We further demonstrate that Mem-LZerD produces complex models which are suitable for molecular dynamics simulation. Mem-LZerD is made available at https://lzerd.kiharalab.org.

Assessment of three-dimensional RNA structure prediction in CASP15

The prediction of RNA three-dimensional structures remains an unsolved problem. Here, we report assessments of RNA structure predictions in CASP15, the first CASP exercise that involved RNA structure modeling. Forty two predictor groups submitted models for at least one of twelve RNA-containing targets. These models were evaluated by the RNA-Puzzles organizers and, separately, by a CASP-recruited team using metrics (GDT, lDDT) and approaches (Z-score rankings) initially developed for assessment of proteins and generalized here for RNA assessment. The two assessments independently ranked the same predictor groups as first (AIchemy_RNA2), second (Chen), and third (RNAPolis and GeneSilico, tied); predictions from deep learning approaches were significantly worse than these top ranked groups, which did not use deep learning. Further analyses based on direct comparison of predicted models to cryogenic electron microscopy (cryo-EM) maps and X-ray diffraction data support these rankings. With the exception of two RNA-protein complexes, models submitted by CASP15 groups correctly predicted the global fold of the RNA targets. Comparisons of CASP15 submissions to designed RNA nanostructures as well as molecular replacement trials highlight the potential utility of current RNA modeling approaches for RNA nanotechnology and structural biology, respectively. Nevertheless, challenges remain in modeling fine details such as non-canonical pairs, in ranking among submitted models, and in prediction of multiple structures resolved by cryo-EM or crystallography.

The Impact of AI-Based Modeling on the Accuracy of Protein Assembly Prediction: Insights from CASP15

In CASP15, 87 predictors submitted around 11,000 models on 41 assembly targets. The community demonstrated exceptional performance in overall fold and interface contact prediction, achieving an impressive success rate of 90% (compared to 31% in CASP14). This remarkable accomplishment is largely due to the incorporation of DeepMind's AF2-Multimer approach into custom-built prediction pipelines. To evaluate the added value of participating methods, we compared the community models to the baseline AF2-Multimer predictor. In over 1/3 of cases the community models were superior to the baseline predictor. The main reasons for this improved performance were the use of custom-built multiple sequence alignments, optimized AF2-Multimer sampling, and the manual assembly of AF2-Multimer-built subcomplexes. The best three groups, in order, are Zheng, Venclovas and Wallner. Zheng and Venclovas reached a 73.2% success rate over all (41) cases, while Wallner attained 69.4% success rate over 36 cases. Nonetheless, challenges remain in predicting structures with weak evolutionary signals, such as nanobody-antigen, antibody-antigen, and viral complexes. Expectedly, modeling large complexes remains also challenging due to their high memory compute demands. In addition to the assembly category, we assessed the accuracy of modeling interdomain interfaces in the tertiary structure prediction targets. Models on seven targets featuring 17 unique interfaces were analyzed. Best predictors achieved the 76.5% success rate, with the UM-TBM group being the leader. In the interdomain category, we observed that the predictors faced challenges, as in the case of the assembly category, when the evolutionary signal for a given domain pair was weak or the structure was large. Overall, CASP15 witnessed unprecedented improvement in interface modeling, reflecting the AI revolution seen in CASP14.

PointDE: Protein Docking Evaluation Using 3D Point Cloud Neural Network

Protein-protein interactions (PPIs) play essential roles in many vital movements and the determination of protein complex structure is helpful to discover the mechanism of PPI. Protein-protein docking is being developed to model the structure of the protein. However, there is still a challenge to selecting the near-native decoys generated by protein-protein docking. Here, we propose a docking evaluation method using 3D point cloud neural network named PointDE. PointDE transforms protein structure to the point cloud. Using the state-of-the-art point cloud network architecture and a novel grouping mechanism, PointDE can capture the geometries of the point cloud and learn the interaction information from the protein interface. On public datasets, PointDE surpasses the state-of-the-art method using deep learning. To further explore the ability of our method in different types of protein structures, we developed a new dataset generated by high-quality antibody-antigen complexes. The result in this antibody-antigen dataset shows the strong performance of PointDE, which will be helpful for the understanding of PPI mechanisms.

Modeling protein-nucleic acid complexes with extremely large conformational changes using Flex-LZerD

Proteins and nucleic acids are key components in many processes in living cells, and interactions between proteins and nucleic acids are often crucial pathway components. In many cases, large flexibility of proteins as they interact with nucleic acids is key to their function. To understand the mechanisms of these processes, it is necessary to consider the 3D atomic structures of such protein-nucleic acid complexes. When such structures are not yet experimentally determined, protein docking can be used to computationally generate useful structure models. However, such docking has long had the limitation that the consideration of flexibility is usually limited to small movements or to small structures. We previously developed a method of flexible protein docking which could model ordered proteins which undergo large-scale conformational changes, which we also showed was compatible with nucleic acids. Here, we elaborate on the ability of that pipeline, Flex-LZerD, to model specifically interactions between proteins and nucleic acids, and demonstrate that Flex-LZerD can model more interactions and types of conformational change than previously shown.

Critical Assessment of Methods for Predicting the 3D Structure of Proteins and Protein Complexes

Advances in a scientific discipline are often measured by small, incremental steps. In this review, we report on two intertwined disciplines in the protein structure prediction field, modeling of single chains and modeling of complexes, that have over decades emulated this pattern, as monitored by the community-wide blind prediction experiments CASP and CAPRI. However, over the past few years, dramatic advances were observed for the accurate prediction of single protein chains, driven by a surge of deep learning methodologies entering the prediction field. We review the mainscientific developments that enabled these recent breakthroughs and feature the important role of blind prediction experiments in building up and nurturing the structure prediction field. We discuss how the new wave of artificial intelligence-based methods is impacting the fields of computational and experimental structural biology and highlight areas in which deep learning methods are likely to lead to future developments, provided that major challenges are overcome.

Combining pairwise structural similarity and deep learning interface contact prediction to estimate protein complex model accuracy in CASP15

Estimating the accuracy of quaternary structural models of protein complexes and assemblies (EMA) is important for predicting quaternary structures and applying them to studying protein function and interaction. The pairwise similarity between structural models is proven useful for estimating the quality of protein tertiary structural models, but it has been rarely applied to predicting the quality of quaternary structural models. Moreover, the pairwise similarity approach often fails when many structural models are of low quality and similar to each other. To address the gap, we developed a hybrid method (MULTICOM_qa) combining a pairwise similarity score (PSS) and an interface contact probability score (ICPS) based on the deep learning inter-chain contact prediction for estimating protein complex model accuracy. It blindly participated in the 15th Critical Assessment of Techniques for Protein Structure Prediction (CASP15) in 2022 and ranked first out of 24 predictors in estimating the global accuracy of assembly models. The average per-target correlation coefficient between the model quality scores predicted by MULTICOM_qa and the true quality scores of the models of CASP15 assembly targets is 0.66. The average per-target ranking loss in using the predicted quality scores to rank the models is 0.14. It was able to select good models for most targets. Moreover, several key factors (i.e., target difficulty, model sampling difficulty, skewness of model quality, and similarity between good/bad models) for EMA are identified and analayzed. The results demonstrate that combining the multi-model method (PSS) with the complementary single-model method (ICPS) is a promising approach to EMA. The source code of MULTICOM_qa is available at https://github.com/BioinfoMachineLearning/MULTICOM_qa .

G-RANK: an equivariant graph neural network for the scoring of protein-protein docking models

Motivation

Protein complex structure prediction is important for many applications in bioengineering. A widely used method for predicting the structure of protein complexes is computational docking. Although many tools for scoring protein-protein docking models have been developed, it is still a challenge to accurately identify near-native models for unknown protein complexes. A recently proposed model called the geometric vector perceptron-graph neural network (GVP-GNN), a subtype of equivariant graph neural networks, has demonstrated success in various 3D molecular structure modeling tasks.

Results

Herein, we present G-RANK, a GVP-GNN-based method for the scoring of protein-protein docking models. When evaluated on two different test datasets, G-RANK achieved a performance competitive with or better than the state-of-the-art scoring functions. We expect G-RANK to be a useful tool for various applications in biological engineering.

Availability and implementation

Source code is available at https://github.com/ha01994/grank.

Contact

kds@kaist.ac.kr.

Supplementary information

Supplementary data are available at Bioinformatics Advances online.

Improving classification of correct and incorrect protein-protein docking models by augmenting the training set

Motivation

Protein-protein interactions drive many relevant biological events, such as infection, replication and recognition. To control or engineer such events, we need to access the molecular details of the interaction provided by experimental 3D structures. However, such experiments take time and are expensive; moreover, the current technology cannot keep up with the high discovery rate of new interactions. Computational modeling, like protein-protein docking, can help to fill this gap by generating docking poses. Protein-protein docking generally consists of two parts, sampling and scoring. The sampling is an exhaustive search of the tridimensional space. The caveat of the sampling is that it generates a large number of incorrect poses, producing a highly unbalanced dataset. This limits the utility of the data to train machine learning classifiers.

Results

Using weak supervision, we developed a data augmentation method that we named hAIkal. Using hAIkal, we increased the labeled training data to train several algorithms. We trained and obtained different classifiers; the best classifier has 81% accuracy and 0.51 Matthews' correlation coefficient on the test set, surpassing the state-of-the-art scoring functions.

Availability and implementation

Docking models from Benchmark 5 are available at https://doi.org/10.5281/zenodo.4012018. Processed tabular data are available at https://repository.kaust.edu.sa/handle/10754/666961. Google colab is available at https://colab.research.google.com/drive/1vbVrJcQSf6\_C3jOAmZzgQbTpuJ5zC1RP?usp=sharing.

Supplementary information

Supplementary data are available at Bioinformatics Advances online.

DeepHomo2.0: improved protein-protein contact prediction of homodimers by transformer-enhanced deep learning

Protein-protein interactions play an important role in many biological processes. However, although structure prediction for monomer proteins has achieved great progress with the advent of advanced deep learning algorithms like AlphaFold, the structure prediction for protein-protein complexes remains an open question. Taking advantage of the Transformer model of ESM-MSA, we have developed a deep learning-based model, named DeepHomo2.0, to predict protein-protein interactions of homodimeric complexes by leveraging the direct-coupling analysis (DCA) and Transformer features of sequences and the structure features of monomers. DeepHomo2.0 was extensively evaluated on diverse test sets and compared with eight state-of-the-art methods including protein language model-based, DCA-based and machine learning-based methods. It was shown that DeepHomo2.0 achieved a high precision of >70% with experimental monomer structures and >60% with predicted monomer structures for the top 10 predicted contacts on the test sets and outperformed the other eight methods. Moreover, even the version without using structure information, named DeepHomoSeq, still achieved a good precision of >55% for the top 10 predicted contacts. Integrating the predicted contacts into protein docking significantly improved the structure prediction of realistic Critical Assessment of Protein Structure Prediction homodimeric complexes. DeepHomo2.0 and DeepHomoSeq are available at http://huanglab.phys.hust.edu.cn/DeepHomo2/.

MetaScore: A Novel Machine-Learning-Based Approach to Improve Traditional Scoring Functions for Scoring Protein-Protein Docking Conformations

Protein-protein interactions play a ubiquitous role in biological function. Knowledge of the three-dimensional (3D) structures of the complexes they form is essential for understanding the structural basis of those interactions and how they orchestrate key cellular processes. Computational docking has become an indispensable alternative to the expensive and time-consuming experimental approaches for determining the 3D structures of protein complexes. Despite recent progress, identifying near-native models from a large set of conformations sampled by docking-the so-called scoring problem-still has considerable room for improvement. We present MetaScore, a new machine-learning-based approach to improve the scoring of docked conformations. MetaScore utilizes a random forest (RF) classifier trained to distinguish near-native from non-native conformations using their protein-protein interfacial features. The features include physicochemical properties, energy terms, interaction-propensity-based features, geometric properties, interface topology features, evolutionary conservation, and also scores produced by traditional scoring functions (SFs). MetaScore scores docked conformations by simply averaging the score produced by the RF classifier with that produced by any traditional SF. We demonstrate that (i) MetaScore consistently outperforms each of the nine traditional SFs included in this work in terms of success rate and hit rate evaluated over conformations ranked among the top 10; (ii) an ensemble method, MetaScore-Ensemble, that combines 10 variants of MetaScore obtained by combining the RF score with each of the traditional SFs outperforms each of the MetaScore variants. We conclude that the performance of traditional SFs can be improved upon by using machine learning to judiciously leverage protein-protein interfacial features and by using ensemble methods to combine multiple scoring functions.

Pairwise and Multi-chain Protein Docking Enhanced Using LZerD Web Server

Interactions of proteins with other macromolecules have important structural and functional roles in the basic processes of living cells. To understand and elucidate the mechanisms of interactions, it is important to know the 3D structures of the complexes. Proteomes contain numerous protein-protein complexes, for which experimentally determined structures often do not exist. Computational techniques can be a practical alternative to obtain useful complex structure models. Here, we present a web server that provides access to the LZerD and Multi-LZerD protein docking tools, which can perform both pairwise and multi-chain docking. The web server is user-friendly, with options to visualize the distribution and structures of binding poses of top-scoring models. The LZerD web server is available at https://lzerd.kiharalab.org . This chapter dictates the algorithm and step-by-step procedure to model the monomeric structures with AttentiveDist, and also provides the detail of pairwise LZerD docking, and multi-LZerD. This also provided case studies for each of the three modules.

Protein-protein interaction prediction methods: from docking-based to AI-based approaches

Protein-protein interactions (PPIs), such as protein-protein inhibitor, antibody-antigen complex, and supercomplexes play diverse and important roles in cells. Recent advances in structural analysis methods, including cryo-EM, for the determination of protein complex structures are remarkable. Nevertheless, much room remains for improvement and utilization of computational methods to predict PPIs because of the large number and great diversity of unresolved complex structures. This review introduces a wide array of computational methods, including our own, for estimating PPIs including antibody-antigen interactions, offering both historical and forward-looking perspectives.

Domain-Based Protein Docking with Extremely Large Conformational Changes

Proteins are key components in many processes in living cells, and physical interactions with other proteins and nucleic acids often form key parts of their functions. In many cases, large flexibility of proteins as they interact is key to their function. To understand the mechanisms of these processes, it is necessary to consider the 3D structures of such protein complexes. When such structures are not yet experimentally determined, protein docking has long been present to computationally generate useful structure models. However, protein docking has long had the limitation that the consideration of flexibility is usually limited to very small movements or very small structures. Methods have been developed which handle minor flexibility via normal mode or other structure sampling, but new methods are required to model ordered proteins which undergo large-scale conformational changes to elucidate their function at the molecular level. Here, we present Flex-LZerD, a framework for docking such complexes. Via partial assembly multidomain docking and an iterative normal mode analysis admitting curvilinear motions, we demonstrate the ability to model the assembly of a variety of protein-protein and protein-nucleic acid complexes.

Fast protein structure comparison through effective representation learning with contrastive graph neural networks

Protein structure alignment algorithms are often time-consuming, resulting in challenges for large-scale protein structure similarity-based retrieval. There is an urgent need for more efficient structure comparison approaches as the number of protein structures increases rapidly. In this paper, we propose an effective graph-based protein structure representation learning method, GraSR, for fast and accurate structure comparison. In GraSR, a graph is constructed based on the intra-residue distance derived from the tertiary structure. Then, deep graph neural networks (GNNs) with a short-cut connection learn graph representations of the tertiary structures under a contrastive learning framework. To further improve GraSR, a novel dynamic training data partition strategy and length-scaling cosine distance are introduced. We objectively evaluate our method GraSR on SCOPe v2.07 and a new released independent test set from PDB database with a designed comprehensive performance metric. Compared with other state-of-the-art methods, GraSR achieves about 7%-10% improvement on two benchmark datasets. GraSR is also much faster than alignment-based methods. We dig into the model and observe that the superiority of GraSR is mainly brought by the learned discriminative residue-level and global descriptors. The web-server and source code of GraSR are freely available at www.csbio.sjtu.edu.cn/bioinf/GraSR/ for academic use.

The size and shape of protein structures vary considerably. Accurate protein structure comparison usually relies on structure alignment algorithms. However, superimposing two protein structures is relatively time-consuming, which makes it inappropriate for large-scale protein structure retrieval. Alignment-free algorithms are proposed for efficient protein structure comparison over the last few decades. These algorithms first transform the coordinates of atoms in two proteins to fixed-length vectors. Then, the comparison can be done by measuring the distance or similarity between two vectors, which is much faster than alignment. In this study, we propose a novel protein structure representation method for efficient structure comparison. Compared with other state-of-the-art alignment-free methods, our method achieves better performance on both ranking and multi-class classification tasks due to the powerful representation ability of deep graph neural networks. We dig into the model and observe that the superiority of our method is mainly brought by the learned discriminative residue-level and global descriptors.

TRScore: a three-dimensional RepVGG-based scoring method for ranking protein docking models

MOTIVATION

Protein-protein interactions (PPI) play important roles in cellular activities. Due to the technical difficulty and high cost of experimental methods, there are considerable interests towards the development of computational approaches, such as protein docking, to decipher PPI patterns. One of the important and difficult aspects in protein docking is recognizing near-native conformations from a set of decoys, but unfortunately traditional scoring functions still suffer from limited accuracy. Therefore, new scoring methods are pressingly needed in methodological and/or practical implications.

RESULTS

We present a new deep learning-based scoring method for ranking protein-protein docking models based on a three-dimensional (3D) RepVGG network, named TRScore. To recognize near-native conformations from a set of decoys, TRScore voxelizes the protein-protein interface into a 3D grid labeled by the number of atoms in different physicochemical classes. Benefiting from the deep convolutional RepVGG architecture, TRScore can effectively capture the subtle differences between energetically favorable near-native models and unfavorable non-native decoys without needing extra information. TRScore was extensively evaluated on diverse test sets including protein-protein docking benchmark 5.0 update set, DockGround decoy set, as well as realistic CAPRI decoy set, and overall obtained a significant improvement over existing methods in cross validation and independent evaluations.

AVAILABILITY

Codes available at: https://github.com/BioinformaticsCSU/TRScore.

Application of Homology Modeling by Enhanced Profile-Profile Alignment and Flexible-Fitting Simulation to Cryo-EM Based Structure Determination

Application of cryo-electron microscopy (cryo-EM) is crucially important for ascertaining the atomic structure of large biomolecules such as ribosomes and protein complexes in membranes. Advances in cryo-EM technology and software have made it possible to obtain data with near-atomic resolution, but the method is still often capable of producing only a density map with up to medium resolution, either partially or entirely. Therefore, bridging the gap separating the density map and the atomic model is necessary. Herein, we propose a methodology for constructing atomic structure models based on cryo-EM maps with low-to-medium resolution. The method is a combination of sensitive and accurate homology modeling using our profile–profile alignment method with a flexible-fitting method using molecular dynamics simulation. As described herein, this study used benchmark applications to evaluate the model constructions of human two-pore channel 2 (one target protein in CASP13 with its structure determined using cryo-EM data) and the overall structure of Enterococcus hirae V-ATPase complex.

OUP accepted manuscript

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 and implementation

The source code of DRCon is available at https://github.com/jianlin-cheng/DRCon. The datasets are available at https://zenodo.org/record/5998532#.YgF70vXMKsB.

Supplementary information

Supplementary data are available at Bioinformatics online.

A random forest classifier for protein-protein docking models

Herein, we present the results of a machine learning approach we developed to single out correct 3D docking models of protein-protein complexes obtained by popular docking software. To this aim, we generated 3 × 10 4 docking models for each of the 230 complexes in the protein-protein benchmark, version 5, using three different docking programs (HADDOCK, FTDock and ZDOCK), for a cumulative set of ≈ 7 × 10 6 docking models. Three different machine learning approaches (Random Forest, Supported Vector Machine and Perceptron) were used to train classifiers with 158 different scoring functions (features). The Random Forest algorithm outperformed the other two algorithms and was selected for further optimization. Using a features selection algorithm, and optimizing the random forest hyperparameters, allowed us to train and validate a random forest classifier, named COnservation Driven Expert System (CoDES). Testing of CoDES on independent datasets, as well as results of its comparative performance with machine learning methods recently developed in the field for the scoring of docking decoys, confirm its state-of-the-art ability to discriminate correct from incorrect decoys both in terms of global parameters and in terms of decoys ranked at the top positions.

Supplementary information

Supplementary data are available at Bioinformatics Advances online.

Software and data availability statement

The docking models are available at https://doi.org/10.5281/zenodo.4012018. The programs underlying this article will be shared on request to the corresponding authors.

Prediction of protein assemblies, the next frontier: The CASP14-CAPRI experiment

We present the results for CAPRI Round 50, the fourth joint CASP-CAPRI protein assembly prediction challenge. The Round comprised a total of twelve targets, including six dimers, three trimers, and three higher-order oligomers. Four of these were easy targets, for which good structural templates were available either for the full assembly, or for the main interfaces (of the higher-order oligomers). Eight were difficult targets for which only distantly related templates were found for the individual subunits. Twenty-five CAPRI groups including eight automatic servers submitted ~1250 models per target. Twenty groups including six servers participated in the CAPRI scoring challenge submitted ~190 models per target. The accuracy of the predicted models was evaluated using the classical CAPRI criteria. The prediction performance was measured by a weighted scoring scheme that takes into account the number of models of acceptable quality or higher submitted by each group as part of their five top-ranking models. Compared to the previous CASP-CAPRI challenge, top performing groups submitted such models for a larger fraction (70-75%) of the targets in this Round, but fewer of these models were of high accuracy. Scorer groups achieved stronger performance with more groups submitting correct models for 70-80% of the targets or achieving high accuracy predictions. Servers performed less well in general, except for the MDOCKPP and LZERD servers, who performed on par with human groups. In addition to these results, major advances in methodology are discussed, providing an informative overview of where the prediction of protein assemblies currently stands.

Protein-Protein Docking: Past, Present, and Future

The biological significance of proteins attracted the scientific community in exploring their characteristics. The studies shed light on the interaction patterns and functions of proteins in a living body. Due to their practical difficulties, reliable experimental techniques pave the way for introducing computational methods in the interaction prediction. Automated methods reduced the difficulties but could not yet replace experimental studies as the field is still evolving. Interaction prediction problem being critical needs highly accurate results, but none of the existing methods could offer reliable performance that can parallel with experimental results yet. This article aims to assess the existing computational docking algorithms, their challenges, and future scope. Blind docking techniques are quite helpful when no information other than the individual structures are available. As more and more complex structures are being added to different databases, information-driven approaches can be a good alternative. Artificial intelligence, ruling over the major fields, is expected to take over this domain very shortly.

Integrative Modeling of PROTAC-Mediated Ternary Complexes

Proteolysis-targeting chimeras (PROTACs), which selectively induce targeted protein degradation, represent an emerging drug discovery technology. Although numerous PROTACs have been reported, designing potent PROTACs still remains a great challenge, to some extent, due to insufficient structural data of Target-PROTAC-E3 ternary complexes. In this work, PROTAC-Model, an integrative computational method by combining the FRODOCK-based protocol and RosettaDock-based refinement, was developed to predict PROTAC-mediated ternary complex structures and tested on 14 cases. The quality of the models was evaluated using the criteria of the critical assessment of predicted interactions (CAPRI). Using the unbound structures, the FRODOCK-based protocol can generate the ternary complex structures with medium or high quality for 8 cases out of 14. With the refinement by RosettaDock, the cases with medium or high quality increase to 12. Compared with PRosettaC and the method developed by Drummond et al., PROTAC-Model shows better performance. In summary, PROTAC-Model should be useful for the rational design of PROTACs.

LZerD Protein-Protein Docking Webserver Enhanced With de novo Structure Prediction

Protein-protein docking is a useful tool for modeling the structures of protein complexes that have yet to be experimentally determined. Understanding the structures of protein complexes is a key component for formulating hypotheses in biophysics regarding the functional mechanisms of complexes. Protein-protein docking is an established technique for cases where the structures of the subunits have been determined. While the number of known structures deposited in the Protein Data Bank is increasing, there are still many cases where the structures of individual proteins that users want to dock are not determined yet. Here, we have integrated the AttentiveDist method for protein structure prediction into our LZerD webserver for protein-protein docking, which enables users to simply submit protein sequences and obtain full-complex atomic models, without having to supply any structure themselves. We have further extended the LZerD docking interface with a symmetrical homodimer mode. The LZerD server is available at https://lzerd.kiharalab.org/.

Assessment of the CASP14 assembly predictions

In CASP14, 39 research groups submitted more than 2500 3D models on 22 protein complexes. In general, the community performed well in predicting the fold of the assemblies (for 80% of the targets), although it faced significant challenges in reproducing the native contacts. This is especially the case for the complexes without whole-assembly templates. The leading predictor, BAKER-experimental, used a methodology combining classical techniques (template-based modeling, protein docking) with deep learning-based contact predictions and a fold-and-dock approach. The Venclovas team achieved the runner-up position with template-based modeling and docking. By analyzing the target interfaces, we showed that the complexes with depleted charged contacts or dominating hydrophobic interactions were the most challenging ones to predict. We also demonstrated that if AlphaFold2 predictions were at hand, the interface prediction challenge could be alleviated for most of the targets. All in all, it is evident that new approaches are needed for the accurate prediction of assemblies, which undoubtedly will expand on the significant improvements in the tertiary structure prediction field.

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 Design and Analysis of the RHOA-ARHGEF1 Binding Mode: Challenges and Applications for Protein-Protein Interface Prediction

The interaction between two proteins may involve local movements, such as small side-chains re-positioning or more global allosteric movements, such as domain rearrangement. We studied how one can build a precise and detailed protein-protein interface using existing protein-protein docking methods, and how it can be possible to enhance the initial structures using molecular dynamics simulations and data-driven human inspection. We present how this strategy was applied to the modeling of RHOA-ARHGEF1 interaction using similar complexes of RHOA bound to other members of the Rho guanine nucleotide exchange factor family for comparative assessment. In parallel, a more crude approach based on structural superimposition and molecular replacement was also assessed. Both models were then successfully refined using molecular dynamics simulations leading to protein structures where the major data from scientific literature could be recovered. We expect that the detailed strategy used in this work will prove useful for other protein-protein interface design. The RHOA-ARHGEF1 interface modeled here will be extremely useful for the design of inhibitors targeting this protein-protein interaction (PPI).

Experimental determination and data-driven prediction of homotypic transmembrane domain interfaces

•

Homotypic TMD interfaces identified by different techniques share strong similarities.

•

The GxxxG motif is the feature most strongly associated with interfaces.

•

Other features include conservation, polarity, coevolution, and depth in the membrane

•

The role of each of each feature strongly depends on the individual protein.

•

Machine-learning helps predict interfaces from evolutionary sequence data

Interactions between their transmembrane domains (TMDs) frequently support the assembly of single-pass membrane proteins to non-covalent complexes. Yet, the TMD-TMD interactome remains largely uncharted. With a view to predicting homotypic TMD-TMD interfaces from primary structure, we performed a systematic analysis of their physical and evolutionary properties. To this end, we generated a dataset of 50 self-interacting TMDs. This dataset contains interfaces of nine TMDs from bitopic human proteins (Ire1, Armcx6, Tie1, ATP1B1, PTPRO, PTPRU, PTPRG, DDR1, and Siglec7) that were experimentally identified here and combined with literature data. We show that interfacial residues of these homotypic TMD-TMD interfaces tend to be more conserved, coevolved and polar than non-interfacial residues. Further, we suggest for the first time that interface positions are deficient in β-branched residues, and likely to be located deep in the hydrophobic core of the membrane. Overrepresentation of the GxxxG motif at interfaces is strong, but that of (small)xxx(small) motifs is weak. The multiplicity of these features and the individual character of TMD-TMD interfaces, as uncovered here, prompted us to train a machine learning algorithm. The resulting prediction method, THOIPA (www.thoipa.org), excels in the prediction of key interface residues from evolutionary sequence data.

Integrating ab initio and template-based algorithms for protein-protein complex structure prediction

MOTIVATION

Template-based and template-free methods have both been widely used in predicting the structures of protein-protein complexes. Template-based modeling is effective when a reliable template is available, while template-free methods are required for predicting the binding modes or interfaces that have not been previously observed. Our goal is to combine the two methods to improve computational protein-protein complex structure prediction.

RESULTS

Here, we present a method to identify and combine high-confidence predictions of a template-based method (SPRING) with a template-free method (ZDOCK). Cross-validated using the protein-protein docking benchmark version 5.0, our method (ZING) achieved a success rate of 68.2%, outperforming SPRING and ZDOCK, with success rates of 52.1% and 35.9% respectively, when the top 10 predictions were considered per test case. In conclusion, a statistics-based method that evaluates and integrates predictions from template-based and template-free methods is more successful than either method independently.

AVAILABILITY AND IMPLEMENTATION

ZING is available for download as a Github repository (https://github.com/weng-lab/ZING.git).

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

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.

The CASP13-CAPRI targets as case studies to illustrate a novel scoring pipeline integrating CONSRANK with clustering and interface analyses

Background

Properly scoring protein-protein docking models to single out the correct ones is an open challenge, also object of assessment in CAPRI (Critical Assessment of PRedicted Interactions), a community-wide blind docking experiment. We introduced in the field CONSRANK (CONSensus RANKing), the first pure consensus method. Also available as a web server, CONSRANK ranks docking models in an ensemble based on their ability to match the most frequent inter-residue contacts in it. We have been blindly testing CONSRANK in all the latest CAPRI rounds, where we showed it to perform competitively with the state-of-the-art energy and knowledge-based scoring functions. More recently, we developed Clust-CONSRANK, an algorithm introducing a contact-based clustering of the models as a preliminary step of the CONSRANK scoring process.

In the latest CASP13-CAPRI joint experiment, we participated as scorers with a novel pipeline, combining both our scoring tools, CONSRANK and Clust-CONSRANK, with our interface analysis tool COCOMAPS. Selection of the 10 models for submission was guided by the strength of the emerging consensus, and their final ranking was assisted by results of the interface analysis.

Results

As a result of the above approach, we were by far the first scorer in the CASP13-CAPRI top-1 ranking, having high/medium quality models ranked at the top-1 position for the majority of targets (11 out of the total 19). We were also the first scorer in the top-10 ranking, on a par with another group, and the second scorer in the top-5 ranking. Further, we topped the ranking relative to the prediction of binding interfaces, among all the scorers and predictors. Using the CASP13-CAPRI targets as case studies, we illustrate here in detail the approach we adopted.

Conclusions

Introducing some flexibility in the final model selection and ranking, as well as differentiating the adopted scoring approach depending on the targets were the key assets for our highly successful performance, as compared to previous CAPRI rounds. The approach we propose is entirely based on methods made available to the community and could thus be reproduced by any user.

Novel sampling strategies and a coarse-grained score function for docking homomers, flexible heteromers, and oligosaccharides using Rosetta in CAPRI rounds 37-45

Critical Assessment of PRediction of Interactions (CAPRI) rounds 37 through 45 introduced larger complexes, new macromolecules, and multistage assemblies. For these rounds, we used and expanded docking methods in Rosetta to model 23 target complexes. We successfully predicted 14 target complexes and recognized and refined near-native models generated by other groups for two further targets. Notably, for targets T110 and T136, we achieved the closest prediction of any CAPRI participant. We created several innovative approaches during these rounds. Since round 39 (target 122), we have used the new RosettaDock 4.0, which has a revamped coarse-grained energy function and the ability to perform conformer selection during docking with hundreds of pregenerated protein backbones. Ten of the complexes had some degree of symmetry in their interactions, so we tested Rosetta SymDock, realized its shortcomings, and developed the next-generation symmetric docking protocol, SymDock2, which includes docking of multiple backbones and induced-fit refinement. Since the last CAPRI assessment, we also developed methods for modeling and designing carbohydrates in Rosetta, and we used them to successfully model oligosaccharide-protein complexes in round 41. Although the results were broadly encouraging, they also highlighted the pressing need to invest in (a) flexible docking algorithms with the ability to model loop and linker motions and in (b) new sampling and scoring methods for oligosaccharide-protein interactions.

Performance and Its Limits in Rigid Body Protein-Protein Docking

The development of fast Fourier transform (FFT) algorithms enabled the sampling of billions of complex conformations and thus revolutionized protein-protein docking. FFT-based methods are now widely available and have been used in hundreds of thousands of docking calculations. Although the methods perform "soft" docking, which allows for some overlap of component proteins, the rigid body assumption clearly introduces limitations on accuracy and reliability. In addition, the method can work only with energy expressions represented by sums of correlation functions. In this paper we use a well-established protein-protein docking benchmark set to evaluate the results of these limitations by focusing on the performance of the docking server ClusPro, which implements one of the best rigid body methods. Furthermore, we explore the theoretical limits of accuracy when using established energy terms for scoring, provide comparison with flexible docking algorithms, and review the historical performance of servers in the CAPRI docking experiment.

Performance of human and server prediction in CAPRI rounds 38-45

CAPRI challenges offer a variety of blind tests for protein-protein interaction prediction. In CAPRI Rounds 38-45, we generated a set of putative binding modes for each target with an FFT-based docking algorithm, and then scored and ranked these binding modes with a proprietary scoring function, ITScorePP. We have also developed a novel web server, Rebipp. The algorithm utilizes information retrieval to identify relevant biological information to significantly reduce the search space for a particular protein. In parallel, we have also constructed a GPU-based docking server, MDockPP, for protein-protein complex structure prediction. Here, the performance of our protocol in CAPRI rounds 38-45 is reported, which include 16 docking and scoring targets. Among them, three targets contain multiple interfaces: Targets 124, 125, and 136 have 2, 4, and 3 interfaces, respectively. In the predictor experiments, we predicted correct binding modes for nine targets, including one high-accuracy interface, six medium-accuracy binding modes, and six acceptable-accuracy binding modes. For the docking server prediction experiments, we predicted correct binding modes for eight targets, including one high-accuracy, three medium-accuracy, and five acceptable-accuracy binding modes.

VoroMQA web server for assessing three-dimensional structures of proteins and protein complexes

The VoroMQA (Voronoi tessellation-based Model Quality Assessment) web server is dedicated to the estimation of protein structure quality, a common step in selecting realistic and most accurate computational models and in validating experimental structures. As an input, the VoroMQA web server accepts one or more protein structures in PDB format. Input structures may be either monomeric proteins or multimeric protein complexes. For every input structure, the server provides both global and local (per-residue) scores. Visualization of the local scores along the protein chain is enhanced by providing secondary structure assignment and information on solvent accessibility. A unique feature of the VoroMQA server is the ability to directly assess protein-protein interaction interfaces. If this type of assessment is requested, the web server provides interface quality scores, interface energy estimates, and local scores for residues involved in inter-chain interfaces. VoroMQA, the underlying method of the web server, was extensively tested in recent community-wide CASP and CAPRI experiments. During these experiments VoroMQA showed outstanding performance both in model selection and in estimation of accuracy of local structural regions. The VoroMQA web server is available at http://bioinformatics.ibt.lt/wtsam/voromqa.

ClusPro in rounds 38 to 45 of CAPRI: Toward combining template-based methods with free docking

Targets in the protein docking experiment CAPRI (Critical Assessment of Predicted Interactions) generally present new challenges and contribute to new developments in methodology. In rounds 38 to 45 of CAPRI, most targets could be effectively predicted using template-based methods. However, the server ClusPro required structures rather than sequences as input, and hence we had to generate and dock homology models. The available templates also provided distance restraints that were directly used as input to the server. We show here that such an approach has some advantages. Free docking with template-based restraints using ClusPro reproduced some interfaces suggested by weak or ambiguous templates while not reproducing others, resulting in correct server predicted models. More recently we developed the fully automated ClusPro TBM server that performs template-based modeling and thus can use sequences rather than structures of component proteins as input. The performance of the server, freely available for noncommercial use at https://tbm.cluspro.org, is demonstrated by predicting the protein-protein targets of rounds 38 to 45 of CAPRI.

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.

Challenges and opportunities of automated protein-protein docking: HDOCK server vs human predictions in CAPRI Rounds 38-46

Protein-protein docking plays an important role in the computational prediction of the complex structure between two proteins. For years, a variety of docking algorithms have been developed, as witnessed by the critical assessment of prediction interactions (CAPRI) experiments. However, despite their successes, many docking algorithms often require a series of manual operations like modeling structures from sequences, incorporating biological information, and selecting final models. The difficulties in these manual steps have significantly limited the applications of protein-protein docking, as most of the users in the community are nonexperts in docking. Therefore, automated docking like a web server, which can give a comparable performance to human docking protocol, is pressingly needed. As such, we have participated in the blind CAPRI experiments for Rounds 38-45 and CASP13-CAPRI challenge for Round 46 with both our HDOCK automated docking web server and human docking protocol. It was shown that our HDOCK server achieved an "acceptable" or higher CAPRI-rated model in the top 10 submitted predictions for 65.5% and 59.1% of the targets in the docking experiments of CAPRI and CASP13-CAPRI, respectively, which are comparable to 66.7% and 54.5% for human docking protocol. Similar trends can also be observed in the scoring experiments. These results validated our HDOCK server as an efficient automated docking protocol for nonexpert users. Challenges and opportunities of automated docking are also discussed.

Performance of ZDOCK and IRAD in CAPRI rounds 39-45

We report docking performance on the six targets of Critical Assessment of PRedicted Interactions (CAPRI) rounds 39-45 that involved heteromeric protein-protein interactions and had the solved structures released since the rounds were held. Our general strategy involved protein-protein docking using ZDOCK, reranking using IRAD, and structural refinement using Rosetta. In addition, we made extensive use of experimental data to guide our docking runs. All the experimental information at the amino-acid level proved correct. However, for two targets, we also used protein-complex structures as templates for modeling interfaces. These resulted in incorrect predictions, presumably due to the low sequence identity between the targets and templates. Albeit a small number of targets, the performance described here compared somewhat less favorably with our previous CAPRI reports, which may be due to the CAPRI targets being increasingly challenging.