Amino acid network and its scoring application in protein–protein docking

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.

iScore: a novel graph kernel-based function for scoring protein-protein docking models

MOTIVATION

Protein complexes play critical roles in many aspects of biological functions. Three-dimensional (3D) structures of protein complexes are critical for gaining insights into structural bases of interactions and their roles in the biomolecular pathways that orchestrate key cellular processes. Because of the expense and effort associated with experimental determinations of 3D protein complex structures, computational docking has evolved as a valuable tool to predict 3D structures of biomolecular complexes. Despite recent progress, reliably distinguishing near-native docking conformations from a large number of candidate conformations, the so-called scoring problem, remains a major challenge.

RESULTS

Here we present iScore, a novel approach to scoring docked conformations that combines HADDOCK energy terms with a score obtained using a graph representation of the protein-protein interfaces and a measure of evolutionary conservation. It achieves a scoring performance competitive with, or superior to, that of state-of-the-art scoring functions on two independent datasets: (i) Docking software-specific models and (ii) the CAPRI score set generated by a wide variety of docking approaches (i.e. docking software-non-specific). iScore ranks among the top scoring approaches on the CAPRI score set (13 targets) when compared with the 37 scoring groups in CAPRI. The results demonstrate the utility of combining evolutionary, topological and energetic information for scoring docked conformations. This work represents the first successful demonstration of graph kernels to protein interfaces for effective discrimination of near-native and non-native conformations of protein complexes.

AVAILABILITY AND IMPLEMENTATION

The iScore code is freely available from Github: https://github.com/DeepRank/iScore (DOI: 10.5281/zenodo.2630567). And the docking models used are available from SBGrid: https://data.sbgrid.org/dataset/684).

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Finding correct protein-protein docking models using ProQDock

Motivation: Protein–protein interactions are a key in virtually all biological processes. For a detailed understanding of the biological processes, the structure of the protein complex is essential. Given the current experimental techniques for structure determination, the vast majority of all protein complexes will never be solved by experimental techniques. In lack of experimental data, computational docking methods can be used to predict the structure of the protein complex. A common strategy is to generate many alternative docking solutions (atomic models) and then use a scoring function to select the best. The success of the computational docking technique is, to a large degree, dependent on the ability of the scoring function to accurately rank and score the many alternative docking models.

Results: Here, we present ProQDock, a scoring function that predicts the absolute quality of docking model measured by a novel protein docking quality score (DockQ). ProQDock uses support vector machines trained to predict the quality of protein docking models using features that can be calculated from the docking model itself. By combining different types of features describing both the protein–protein interface and the overall physical chemistry, it was possible to improve the correlation with DockQ from 0.25 for the best individual feature (electrostatic complementarity) to 0.49 for the final version of ProQDock. ProQDock performed better than the state-of-the-art methods ZRANK and ZRANK2 in terms of correlations, ranking and finding correct models on an independent test set. Finally, we also demonstrate that it is possible to combine ProQDock with ZRANK and ZRANK2 to improve performance even further.

Availability and implementation:http://bioinfo.ifm.liu.se/ProQDock

Contact:bjornw@ifm.liu.se

Supplementary information:Supplementary data are available at Bioinformatics online.

A combinatorial scoring function for protein-RNA docking

Protein-RNA docking is still an open question. One of the main challenges is to develop an effective scoring function that can discriminate near-native structures from the incorrect ones. To solve the problem, we have constructed a knowledge-based residue-nucleotide pairwise potential with secondary structure information considered for nonribosomal protein-RNA docking. Here we developed a weighted combined scoring function RpveScore that consists of the pairwise potential and six physics-based energy terms. The weights were optimized using the multiple linear regression method by fitting the scoring function to L_rmsd for the bound docking decoys from Benchmark II. The scoring functions were tested on 35 unbound docking cases. The results show that the scoring function RpveScore including all terms performs best. Also RpveScore was compared with the statistical mechanics-based method derived potential ITScore-PR, and the united atom-based statistical potentials QUASI-RNP and DARS-RNP. The success rate of RpveScore is 71.6% for the top 1000 structures and the number of cases where a near-native structure is ranked in top 30 is 25 out of 35 cases. For 32 systems (91.4%), RpveScore can find the binding mode in top 5 that has no lower than 50% native interface residues on protein and nucleotides on RNA. Additionally, it was found that the long-range electrostatic attractive energy plays an important role in distinguishing near-native structures from the incorrect ones. This work can be helpful for the development of protein-RNA docking methods and for the understanding of protein-RNA interactions. RpveScore program is available to the public at http://life.bjut.edu.cn/kxyj/kycg/2017116/14845362285362368_1.html Proteins 2017; 85:741-752. © 2016 Wiley Periodicals, Inc.

Molecular docking as a popular tool in drug design, an in silico travel

New molecular modeling approaches, driven by rapidly improving computational platforms, have allowed many success stories for the use of computer-assisted drug design in the discovery of new mechanism-or structure-based drugs. In this overview, we highlight three aspects of the use of molecular docking. First, we discuss the combination of molecular and quantum mechanics to investigate an unusual enzymatic mechanism of a flavoprotein. Second, we present recent advances in anti-infectious agents' synthesis driven by structural insights. At the end, we focus on larger biological complexes made by protein-protein interactions and discuss their relevance in drug design. This review provides information on how these large systems, even in the presence of the solvent, can be investigated with the outlook of drug discovery.

Predicted binding site information improves model ranking in protein docking using experimental and computer-generated target structures

Background

Protein-protein interactions (PPIs) mediate the vast majority of biological processes, therefore, significant efforts have been directed to investigate PPIs to fully comprehend cellular functions. Predicting complex structures is critical to reveal molecular mechanisms by which proteins operate. Despite recent advances in the development of new methods to model macromolecular assemblies, most current methodologies are designed to work with experimentally determined protein structures. However, because only computer-generated models are available for a large number of proteins in a given genome, computational tools should tolerate structural inaccuracies in order to perform the genome-wide modeling of PPIs.

Results

To address this problem, we developed eRank^PPI, an algorithm for the identification of near-native conformations generated by protein docking using experimental structures as well as protein models. The scoring function implemented in eRank^PPI employs multiple features including interface probability estimates calculated by eFindSite^PPI and a novel contact-based symmetry score. In comparative benchmarks using representative datasets of homo- and hetero-complexes, we show that eRank^PPI consistently outperforms state-of-the-art algorithms improving the success rate by ~10 %.

Conclusions

eRank^PPI was designed to bridge the gap between the volume of sequence data, the evidence of binary interactions, and the atomic details of pharmacologically relevant protein complexes. Tolerating structure imperfections in computer-generated models opens up a possibility to conduct the exhaustive structure-based reconstruction of PPI networks across proteomes. The methods and datasets used in this study are available at www.brylinski.org/erankppi.

NPPD: A Protein-Protein Docking Scoring Function Based on Dyadic Differences in Networks of Hydrophobic and Hydrophilic Amino Acid Residues

Protein-protein docking (PPD) predictions usually rely on the use of a scoring function to rank docking models generated by exhaustive sampling. To rank good models higher than bad ones, a large number of scoring functions have been developed and evaluated, but the methods used for the computation of PPD predictions remain largely unsatisfactory. Here, we report a network-based PPD scoring function, the NPPD, in which the network consists of two types of network nodes, one for hydrophobic and the other for hydrophilic amino acid residues, and the nodes are connected when the residues they represent are within a certain contact distance. We showed that network parameters that compute dyadic interactions and those that compute heterophilic interactions of the amino acid networks thus constructed allowed NPPD to perform well in a benchmark evaluation of 115 PPD scoring functions, most of which, unlike NPPD, are based on some sort of protein-protein interaction energy. We also showed that NPPD was highly complementary to these energy-based scoring functions, suggesting that the combined use of conventional scoring functions and NPPD might significantly improve the accuracy of current PPD predictions.

The construction of an amino acid network for understanding protein structure and function

Amino acid networks (AANs) are undirected networks consisting of amino acid residues and their interactions in three-dimensional protein structures. The analysis of AANs provides novel insight into protein science, and several common amino acid network properties have revealed diverse classes of proteins. In this review, we first summarize methods for the construction and characterization of AANs. We then compare software tools for the construction and analysis of AANs. Finally, we review the application of AANs for understanding protein structure and function, including the identification of functional residues, the prediction of protein folding, analyzing protein stability and protein-protein interactions, and for understanding communication within and between proteins.

The scoring of poses in protein-protein docking: current capabilities and future directions

BACKGROUND

Protein-protein docking, which aims to predict the structure of a protein-protein complex from its unbound components, remains an unresolved challenge in structural bioinformatics. An important step is the ranking of docked poses using a scoring function, for which many methods have been developed. There is a need to explore the differences and commonalities of these methods with each other, as well as with functions developed in the fields of molecular dynamics and homology modelling.

RESULTS

We present an evaluation of 115 scoring functions on an unbound docking decoy benchmark covering 118 complexes for which a near-native solution can be found, yielding top 10 success rates of up to 58%. Hierarchical clustering is performed, so as to group together functions which identify near-natives in similar subsets of complexes. Three set theoretic approaches are used to identify pairs of scoring functions capable of correctly scoring different complexes. This shows that functions in different clusters capture different aspects of binding and are likely to work together synergistically.

CONCLUSIONS

All functions designed specifically for docking perform well, indicating that functions are transferable between sampling methods. We also identify promising methods from the field of homology modelling. Further, differential success rates by docking difficulty and solution quality suggest a need for flexibility-dependent scoring. Investigating pairs of scoring functions, the set theoretic measures identify known scoring strategies as well as a number of novel approaches, indicating promising augmentations of traditional scoring methods. Such augmentation and parameter combination strategies are discussed in the context of the learning-to-rank paradigm.

A modified amino acid network model contains similar and dissimilar weight

For a more detailed description of the interaction between residues, this paper proposes an amino acid network model, which contains two types of weight—similar weight and dissimilar weight. The weight of the link is based on a self-consistent statistical contact potential between different types of amino acids. In this model, we can get a more reasonable representation of the distance between residues. Furthermore, with the network parameter, average shortest path length, we can get a more accurate reflection of the molecular size. This amino acid network is a “small-world” network, and the network parameter is sensitive to the conformation change of protein. For some disease-related proteins, the highly central residues of the amino acid network are highly correlated with the hot spots. In the compound with the related drug, these residues either interacted directly with the drug or with the residue which is in contact with the drug.

Network models reveal stability and structural rearrangement of signal recognition particle

The signal recognition particle (SRP) and its receptors (SR) mediate the cotranslational targeting of the membrane and secretory proteins in all cells. In Escherichia coli, SRP is composed of the Ffh protein and the 4.5S SRP RNA. Ffh is a multidomain protein comprising a methionine-rich (M) domain, a helical N domain, and a Ras-like guanine triphosphatase (GTPase) (G) domain. The N and G domains are commonly referred to as one structural unit, the NG domain. In this article, the complex structure of SRP and SR is investigated with the Gaussian network model (GNM) and anisotropic network model (ANM). GNM provides the information of structure stability. It is found that the intermolecular interactions between SRP and SR can obviously decrease the fluctuation of NG domains. Nevertheless, the large structural rearrangement will take place during the cotranslational protein targeting cycle. Hence, the moving directions of fluctuation regions are further ascertained by using cross-correlation analysis and the ANM. The NG domain of Ffh undergoes a clockwise rotation around the GM linker and the M domain of Ffh shows an opposite direction to the NG domain. These functional movements will facilitate the SRP structure to transform into the free form and the sequence-bound form. These simple coarse-grained analyses can be used as a general and quick method for the mechanism studies of protein assembly and supramolecular systems.

Scoring function based on weighted residue network

Molecular docking is an important method for the research of protein-protein interaction and recognition. A protein can be considered as a network when the residues are treated as its nodes. With the contact energy between residues as link weight, a weighted residue network is constructed in this paper. Two weighted parameters (strength and weighted average nearest neighbors' degree) are introduced into this model at the same time. The stability of a protein is characterized by its strength. The global topological properties of the protein-protein complex are reflected by the weighted average nearest neighbors' degree. Based on this weighted network model and these two parameters, a new docking scoring function is proposed in this paper. The scoring and ranking for 42 systems' bound and unbounded docking results are performed with this new scoring function. Comparing the results obtained from this new scoring function with that from the pair potentials scoring function, we found that this new scoring function has a similar performance to the pair potentials on some items, and this new scoring function can get a better success rate. The calculation of this new scoring function is easy, and the result of its scoring and ranking is acceptable. This work can help us better understand the mechanisms of protein-protein interactions and recognition.

Prediction of protein-binding areas by small-world residue networks and application to docking

BACKGROUND

Protein-protein interactions are involved in most cellular processes, and their detailed physico-chemical and structural characterization is needed in order to understand their function at the molecular level. In-silico docking tools can complement experimental techniques, providing three-dimensional structural models of such interactions at atomic resolution. In several recent studies, protein structures have been modeled as networks (or graphs), where the nodes represent residues and the connecting edges their interactions. From such networks, it is possible to calculate different topology-based values for each of the nodes, and to identify protein regions with high centrality scores, which are known to positively correlate with key functional residues, hot spots, and protein-protein interfaces.

RESULTS

Here we show that this correlation can be efficiently used for the scoring of rigid-body docking poses. When integrated into the pyDock energy-based docking method, the new combined scoring function significantly improved the results of the individual components as shown on a standard docking benchmark. This improvement was particularly remarkable for specific protein complexes, depending on the shape, size, type, or flexibility of the proteins involved.

CONCLUSIONS

The network-based representation of protein structures can be used to identify protein-protein binding regions and to efficiently score docking poses, complementing energy-based approaches.

Insights into protein-DNA interactions through structure network analysis

Protein–DNA interactions are crucial for many cellular processes. Now with the increased availability of structures of protein–DNA complexes, gaining deeper insights into the nature of protein–DNA interactions has become possible. Earlier, investigations have characterized the interface properties by considering pairwise interactions. However, the information communicated along the interfaces is rarely a pairwise phenomenon, and we feel that a global picture can be obtained by considering a protein–DNA complex as a network of noncovalently interacting systems. Furthermore, most of the earlier investigations have been carried out from the protein point of view (protein-centric), and the present network approach aims to combine both the protein-centric and the DNA-centric points of view. Part of the study involves the development of methodology to investigate protein–DNA graphs/networks with the development of key parameters. A network representation provides a holistic view of the interacting surface and has been reported here for the first time. The second part of the study involves the analyses of these graphs in terms of clusters of interacting residues and the identification of highly connected residues (hubs) along the protein–DNA interface. A predominance of deoxyribose–amino acid clusters in β-sheet proteins, distinction of the interface clusters in helix–turn–helix, and the zipper-type proteins would not have been possible by conventional pairwise interaction analysis. Additionally, we propose a potential classification scheme for a set of protein–DNA complexes on the basis of the protein–DNA interface clusters. This provides a general idea of how the proteins interact with the different components of DNA in different complexes. Thus, we believe that the present graph-based method provides a deeper insight into the analysis of the protein–DNA recognition mechanisms by throwing more light on the nature and the specificity of these interactions.

The interaction of proteins with DNA is crucial for several cellular processes. Some insights into the mode of interaction can be obtained from the analysis of the complexed structures. Conventional analyses are based on the identification of pairwise interactions. However, a collective representation of the network of interactions and the analyses of such networks provide valuable information, which is not easy to obtain from pairwise analyses. Although the protein structure networks have been described in the literature, this is the first time that a network representation of protein–DNA is described. Construction and analysis of such networks have given valuable information on protein–DNA interactions in terms of network parameters, such as clusters of interacting residues and hubs, which are highly connected residues. Furthermore, the results also represent both the protein- and the DNA-centric viewpoints, because the analysis is carried out on combined networks. The methodology developed here can lead to predictions, such as important residues responsible for stabilizing protein–DNA interactions, and will be of interest to experimentalists.