Evaluation of AlphaFold-Multimer prediction on multi-chain protein complexes.

MOTIVATION: Despite near-experimental accuracy on single-chain predictions, there is still scope for improvement among multimeric predictions. Methods like AlphaFold-Multimer and FoldDock can accurately model dimers. However, how well these methods fare on larger complexes is still unclear. Further, evaluation methods of the quality of multimeric complexes are not well established. RESULTS: We analysed the performance of AlphaFold-Multimer on a homology-reduced dataset of homo- and heteromeric protein complexes. We highlight the differences between the pairwise and multi-interface evaluation of chains within a multimer. We describe why certain complexes perform well on one metric (e.g. TM-score) but poorly on another (e.g. DockQ). We propose a new score, Predicted DockQ version 2 (pDockQ2), to estimate the quality of each interface in a multimer. Finally, we modelled protein complexes (from CORUM) and identified two highly confident structures that do not have sequence homology to any existing structures. AVAILABILITY AND IMPLEMENTATION: All scripts, models, and data used to perform the analysis in this study are freely available at https://gitlab.com/ElofssonLab/afm-benchmark.

Towards a structurally resolved human protein interaction network.

Cellular functions are governed by molecular machines that assemble through protein-protein interactions. Their atomic details are critical to studying their molecular mechanisms. However, fewer than 5% of hundreds of thousands of human protein interactions have been structurally characterized. Here we test the potential and limitations of recent progress in deep-learning methods using AlphaFold2 to predict structures for 65,484 human protein interactions. We show that experiments can orthogonally confirm higher-confidence models. We identify 3,137 high-confidence models, of which 1,371 have no homology to a known structure. We identify interface residues harboring disease mutations, suggesting potential mechanisms for pathogenic variants. Groups of interface phosphorylation sites show patterns of co-regulation across conditions, suggestive of coordinated tuning of multiple protein interactions as signaling responses. Finally, we provide examples of how the predicted binary complexes can be used to build larger assemblies helping to expand our understanding of human cell biology.

A structural biology community assessment of AlphaFold2 applications.

Most proteins fold into 3D structures that determine how they function and orchestrate the biological processes of the cell. Recent developments in computational methods for protein structure predictions have reached the accuracy of experimentally determined models. Although this has been independently verified, the implementation of these methods across structural-biology applications remains to be tested. Here, we evaluate the use of AlphaFold2 (AF2) predictions in the study of characteristic structural elements; the impact of missense variants; function and ligand binding site predictions; modeling of interactions; and modeling of experimental structural data. For 11 proteomes, an average of 25% additional residues can be confidently modeled when compared with homology modeling, identifying structural features rarely seen in the Protein Data Bank. AF2-based predictions of protein disorder and complexes surpass dedicated tools, and AF2 models can be used across diverse applications equally well compared with experimentally determined structures, when the confidence metrics are critically considered. In summary, we find that these advances are likely to have a transformative impact in structural biology and broader life-science research.

Size of the protein-protein energy funnel in crowded environment.

Association of proteins to a significant extent is determined by their geometric complementarity. Large-scale recognition factors, which directly relate to the funnel-like intermolecular energy landscape, provide important insights into the basic rules of protein recognition. Previously, we showed that simple energy functions and coarse-grained models reveal major characteristics of the energy landscape. As new computational approaches increasingly address structural modeling of a whole cell at the molecular level, it becomes important to account for the crowded environment inside the cell. The crowded environment drastically changes protein recognition properties, and thus significantly alters the underlying energy landscape. In this study, we addressed the effect of crowding on the protein binding funnel, focusing on the size of the funnel. As crowders occupy the funnel volume, they make it less accessible to the ligands. Thus, the funnel size, which can be defined by ligand occupancy, is generally reduced with the increase of the crowders concentration. This study quantifies this reduction for different concentration of crowders and correlates this dependence with the structural details of the interacting proteins. The results provide a better understanding of the rules of protein association in the crowded environment.

Dockground resource for protein recognition studies.

Structural information of protein-protein interactions is essential for characterization of life processes at the molecular level. While a small fraction of known protein interactions has experimentally determined structures, computational modeling of protein complexes (protein docking) has to fill the gap. The Dockground resource (http://dockground.compbio.ku.edu) provides a collection of datasets for the development and testing of protein docking techniques. Currently, Dockground contains datasets for the bound and the unbound (experimentally determined and simulated) protein structures, model-model complexes, docking decoys of experimentally determined and modeled proteins, and templates for comparative docking. The Dockground bound proteins dataset is a core set, from which other Dockground datasets are generated. It is devised as a relational PostgreSQL database containing information on experimentally determined protein-protein complexes. This report on the Dockground resource describes current status of the datasets, new automated update procedures and further development of the core datasets. We also present a new Dockground interactive web interface, which allows search by various parameters, such as release date, multimeric state, complex type, structure resolution, and so on, visualization of the search results with a number of customizable parameters, as well as downloadable datasets with predefined levels of sequence and structure redundancy.

Docking-based long timescale simulation of cell-size protein systems at atomic resolution.

Computational methodologies are increasingly addressing modeling of the whole cell at the molecular level. Proteins and their interactions are the key component of cellular processes. Techniques for modeling protein interactions, thus far, have included protein docking and molecular simulation. The latter approaches account for the dynamics of the interactions but are relatively slow, if carried out at all-atom resolution, or are significantly coarse grained. Protein docking algorithms are far more efficient in sampling spatial coordinates. However, they do not account for the kinetics of the association (i.e., they do not involve the time coordinate). Our proof-of-concept study bridges the two modeling approaches, developing an approach that can reach unprecedented simulation timescales at all-atom resolution. The global intermolecular energy landscape of a large system of proteins was mapped by the pairwise fast Fourier transform docking and sampled in space and time by Monte Carlo simulations. The simulation protocol was parametrized on existing data and validated on a number of observations from experiments and molecular dynamics simulations. The simulation protocol performed consistently across very different systems of proteins at different protein concentrations. It recapitulated data on the previously observed protein diffusion rates and aggregation. The speed of calculation allows reaching second-long trajectories of protein systems that approach the size of the cells, at atomic resolution.

Predicting the structure of large protein complexes using AlphaFold and Monte Carlo tree search.

AlphaFold can predict the structure of single- and multiple-chain proteins with very high accuracy. However, the accuracy decreases with the number of chains, and the available GPU memory limits the size of protein complexes which can be predicted. Here we show that one can predict the structure of large complexes starting from predictions of subcomponents. We assemble 91 out of 175 complexes with 10-30 chains from predicted subcomponents using Monte Carlo tree search, with a median TM-score of 0.51. There are 30 highly accurate complexes (TM-score ≥0.8, 33% of complete assemblies). We create a scoring function, mpDockQ, that can distinguish if assemblies are complete and predict their accuracy. We find that complexes containing symmetry are accurately assembled, while asymmetrical complexes remain challenging. The method is freely available and accesible as a Colab notebook https://colab.research.google.com/github/patrickbryant1/MoLPC/blob/master/MoLPC.ipynb .

GWYRE: A Resource for Mapping Variants onto Experimental and Modeled Structures of Human Protein Complexes.

Rapid progress in structural modeling of proteins and their interactions is powered by advances in knowledge-based methodologies along with better understanding of physical principles of protein structure and function. The pool of structural data for modeling of proteins and protein-protein complexes is constantly increasing due to the rapid growth of protein interaction databases and Protein Data Bank. The GWYRE (Genome Wide PhYRE) project capitalizes on these developments by advancing and applying new powerful modeling methodologies to structural modeling of protein-protein interactions and genetic variation. The methods integrate knowledge-based tertiary structure prediction using Phyre2 and quaternary structure prediction using template-based docking by a full-structure alignment protocol to generate models for binary complexes. The predictions are incorporated in a comprehensive public resource for structural characterization of the human interactome and the location of human genetic variants. The GWYRE resource facilitates better understanding of principles of protein interaction and structure/function relationships. The resource is available at http://www.gwyre.org.

DOCKGROUND membrane protein-protein set.

Membrane proteins are significantly underrepresented in Protein Data Bank despite their essential role in cellular mechanisms and the major progress in experimental protein structure determination. Thus, computational approaches are especially valuable in the case of membrane proteins and their assemblies. The main focus in developing structure prediction techniques has been on soluble proteins, in part due to much greater availability of the structural data. Currently, structure prediction of protein complexes (protein docking) is a well-developed field of study. However, the generic protein docking approaches are not optimal for the membrane proteins because of the differences in physicochemical environment and the spatial constraints imposed by the membranes. Thus, docking of the membrane proteins requires specialized computational methods. Development and benchmarking of the membrane protein docking approaches has to be based on high-quality sets of membrane protein complexes. In this study we present a new dataset of 456 non-redundant alpha helical binary interfaces. The set is significantly larger and more representative than the previously developed sets. In the future, it will become the basis for the development of docking and scoring benchmarks, similar to the ones for soluble proteins in the Dockground resource http://dockground.compbio.ku.edu.

Scoring of protein-protein docking models utilizing predicted interface residues.

Scoring docking solutions is a difficult task, and many methods have been developed for this purpose. In docking, only a handful of the hundreds of thousands of models generated by docking algorithms are acceptable, causing difficulties when developing scoring functions. Today's best scoring functions can significantly increase the number of top-ranked models but still fail for most targets. Here, we examine the possibility of utilizing predicted interface residues to score docking models generated during the scan stage of a docking algorithm. Many methods have been developed to infer the regions of a protein surface that interact with another protein, but most have not been benchmarked using docking algorithms. This study systematically tests different interface prediction methods for scoring >300.000 low-resolution rigid-body template free docking decoys. Overall we find that contact-based interface prediction by BIPSPI is the best method to score docking solutions, with >12% of first ranked docking models being acceptable. Additional experiments indicated precision as a high-importance metric when estimating interface prediction quality, focusing on docking constraints production. Finally, we discussed several limitations for adopting interface predictions as constraints in a docking protocol.

Dockground scoring benchmarks for protein docking.

Protein docking protocols typically involve global docking scan, followed by re-ranking of the scan predictions by more accurate scoring functions that are either computationally too expensive or algorithmically impossible to include in the global scan. Development and validation of scoring methodologies are often performed on scoring benchmark sets (docking decoys) which offer concise and nonredundant representation of the global docking scan output for a large and diverse set of protein-protein complexes. Two such protein-protein scoring benchmarks were built for the Dockground resource, which contains various datasets for the development and testing of protein docking methodologies. One set was generated based on the Dockground unbound docking benchmark 4, and the other based on protein models from the Dockground model-model benchmark 2. The docking decoys were designed to reflect the reality of the real-case docking applications (e.g., correct docking predictions defined as near-native rather than native structures), and to minimize applicability of approaches not directly related to the development of scoring functions (reducing clustering of predictions in the binding funnel and disparity in structural quality of the near-native and nonnative matches). The sets were further characterized by the source organism and the function of the protein-protein complexes. The sets, freely available to the research community on the Dockground webpage, present a unique, user-friendly resource for the developing and testing of protein-protein scoring approaches.

Limits and potential of combined folding and docking.

MOTIVATION: In the last decade, de novo protein structure prediction accuracy for individual proteins has improved significantly by utilising deep learning (DL) methods for harvesting the co-evolution information from large multiple sequence alignments (MSAs). The same approach can, in principle, also be used to extract information about evolutionary-based contacts across protein-protein interfaces. However, most earlier studies have not used the latest DL methods for inter-chain contact distance prediction. This article introduces a fold-and-dock method based on predicted residue-residue distances with trRosetta. RESULTS: The method can simultaneously predict the tertiary and quaternary structure of a protein pair, even when the structures of the monomers are not known. The straightforward application of this method to a standard dataset for protein-protein docking yielded limited success. However, using alternative methods for generating MSAs allowed us to dock accurately significantly more proteins. We also introduced a novel scoring function, PconsDock, that accurately separates 98% of correctly and incorrectly folded and docked proteins. The average performance of the method is comparable to the use of traditional, template-based or ab initio shape-complementarity-only docking methods. Moreover, the results of conventional and fold-and-dock approaches are complementary, and thus a combined docking pipeline could increase overall docking success significantly. This methodology contributed to the best model for one of the CASP14 oligomeric targets, H1065. AVAILABILITY AND IMPLEMENTATION: All scripts for predictions and analysis are available from https://github.com/ElofssonLab/bioinfo-toolbox/ and https://gitlab.com/ElofssonLab/benchmark5/. All models joined alignments, and evaluation results are available from the following figshare repository https://doi.org/10.6084/m9.figshare.14654886.v2. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

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.

Text mining for modeling of protein complexes enhanced by machine learning.

MOTIVATION: Procedures for structural modeling of protein-protein complexes (protein docking) produce a number of models which need to be further analyzed and scored. Scoring can be based on independently determined constraints on the structure of the complex, such as knowledge of amino acids essential for the protein interaction. Previously, we showed that text mining of residues in freely available PubMed abstracts of papers on studies of protein-protein interactions may generate such constraints. However, absence of post-processing of the spotted residues reduced usability of the constraints, as a significant number of the residues were not relevant for the binding of the specific proteins. RESULTS: We explored filtering of the irrelevant residues by two machine learning approaches, Deep Recursive Neural Network (DRNN) and Support Vector Machine (SVM) models with different training/testing schemes. The results showed that the DRNN model is superior to the SVM model when training is performed on the PMC-OA full-text articles and applied to classification (interface or non-interface) of the residues spotted in the PubMed abstracts. When both training and testing is performed on full-text articles or on abstracts, the performance of these models is similar. Thus, in such cases, there is no need to utilize computationally demanding DRNN approach, which is computationally expensive especially at the training stage. The reason is that SVM success is often determined by the similarity in data/text patterns in the training and the testing sets, whereas the sentence structures in the abstracts are, in general, different from those in the full text articles. AVAILABILITYAND IMPLEMENTATION: The code and the datasets generated in this study are available at https://gitlab.ku.edu/vakser-lab-public/text-mining/-/tree/2020-09-04. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

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.

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.

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.

Computational Feasibility of an Exhaustive Search of Side-Chain Conformations in Protein-Protein Docking.

Protein-protein docking procedures typically perform the global scan of the proteins relative positions, followed by the local refinement of the putative matches. Because of the size of the search space, the global scan is usually implemented as rigid-body search, using computationally inexpensive intermolecular energy approximations. An adequate refinement has to take into account structural flexibility. Since the refinement performs conformational search of the interacting proteins, it is extremely computationally challenging, given the enormous amount of the internal degrees of freedom. Different approaches limit the search space by restricting the search to the side chains, rotameric states, coarse-grained structure representation, principal normal modes, and so on. Still, even with the approximations, the refinement presents an extreme computational challenge due to the very large number of the remaining degrees of freedom. Given the complexity of the search space, the advantage of the exhaustive search is obvious. The obstacle to such search is computational feasibility. However, the growing computational power of modern computers, especially due to the increasing utilization of Graphics Processing Unit (GPU) with large amount of specialized computing cores, extends the ranges of applicability of the brute-force search methods. This proof-of-concept study demonstrates computational feasibility of an exhaustive search of side-chain conformations in protein pocking. The procedure, implemented on the GPU architecture, was used to generate the optimal conformations in a large representative set of protein-protein complexes. © 2018 Wiley Periodicals, Inc.