Combination of scoring functions improves discrimination in protein-protein docking

Two structure-based potentials are used for both filtering (i.e., selecting a subset of conformations generated by rigid-body docking), and rescoring and ranking the selected conformations. ACP (atomic contact potential) is an atom-level extension of the Miyazawa-Jernigan potential parameterized on protein structures, whereas RPScore (residue pair potential score) is a residue-level potential, based on interactions in protein-protein complexes. These potentials are combined with other energy terms and applied to 13 sets of protein decoys, as well as to the results of docking 10 pairs of unbound proteins. For both potentials, the ability to discriminate between near-native and non-native docked structures is substantially improved by refining the structures and by adding a van der Waals energy term. It is observed that ACP and RPScore complement each other in a number of ways (e.g., although RPScore yields more hits than ACP, mainly as a result of its better performance for charged complexes, ACP usually ranks the near-native complexes better). As a general solution to the protein-docking problem, we have found that the best discrimination strategies combine either an RPScore filter with an ACP-based scoring function, or an ACP-based filter with an RPScore-based scoring function. Thus, ACP and RPScore capture complementary structural information, and combining them in a multistage postprocessing protocol provides substantially better discrimination than the use of the same potential for both filtering and ranking the docked conformations.     

Energy-based graph convolutional networks for scoring protein docking models

Structural information about protein-protein interactions, often missing at the interactome scale, is important for mechanistic understanding of cells and rational discovery of therapeutics. Protein docking provides a computational alternative for such information. However, ranking near-native docked models high among a large number of candidates, often known as the scoring problem, remains a critical challenge. Moreover, estimating model quality, also known as the quality assessment problem, is rarely addressed in protein docking. In this study, the two challenging problems in protein docking are regarded as relative and absolute scoring, respectively, and addressed in one physics-inspired deep learning framework. We represent protein and complex structures as intra- and inter-molecular residue contact graphs with atom-resolution node and edge features. And we propose a novel graph convolutional kernel that aggregates interacting nodes’ features through edges so that generalized interaction energies can be learned directly from 3D data. The resulting energy-based graph convolutional networks (EGCN) with multihead attention are trained to predict intra- and inter-molecular energies, binding affinities, and quality measures (interface RMSD) for encounter complexes. Compared to a state-of-the-art scoring function for model ranking, EGCN significantly improves ranking for a critical assessment of predicted interactions (CAPRI) test set involving homology docking; and is comparable or slightly better for Score_set, a CAPRI benchmark set generated by diverse community-wide docking protocols not known to training data. For Score_set quality assessment, EGCN shows about 27% improvement to our previous efforts. Directly learning from 3D structure data in graph representation, EGCN represents the first successful development of graph convolutional networks for protein docking.     

Residue conservation information for generating near-native structures in protein-protein docking

MOTIVATION: Protein-protein docking algorithms typically generate large numbers of possible complex structures with only a few of them resembling the native structure. Recently (Duan et al., Protein Sci, 14:316-218, 2005), it was observed that the surface density of conserved residue positions is high at the interface regions of interacting protein surfaces, except for antibody-antigen complexes, where a lesser number of conserved positions than average is observed at the interface regions. Using this observation, we identified putative interacting regions on the surface of interacting partners and significantly improved docking results by assigning top ranks to near-native complex structures. In this paper, we combine the residue conservation information with a widely used shape complementarity algorithm to generate candidate complex structures with a higher percentage of near-native structures (hits). What is new in this work is that the conservation information is used early in the generation stage and not only in the ranking stage of the docking algorithm. This results in a significantly larger number of generated hits and an improved predictive ability in identifying the native structure of protein-protein complexes. RESULTS: We report on results from 48 well-characterized protein complexes, which have enough residue conservation information from the same 59 benchmark complexes used in our previous work. We compute conservation indices of residue positions on the surfaces of interacting proteins using available homologous sequences from UNIPROT and calculate the solvent accessible surface area. We combine this information with shape-complementarity scores to generate candidate protein-protein complex structures. When compared with pure shape-complementarity algorithms, performed by FTDock, our method results in significantly more hits, with the improvement being over 100% in many instances. We demonstrate that residue conservation information is useful not only in refinement and scoring of docking solutions, but also helpful in enrichment of near-native-structures during the generation of candidate geometries of complex structures.     

Complex-type-dependent scoring functions in protein-protein docking

A major challenge in the field of protein-protein docking is to discriminate between the many wrong and few near-native conformations, i.e. scoring. Here, we introduce combinatorial complex-type-dependent scoring functions for different types of protein-protein complexes, protease/inhibitor, antibody/antigen, enzyme/inhibitor and others. The scoring functions incorporate both physical and knowledge-based potentials, i.e. atomic contact energy (ACE), the residue pair potential (RP), electrostatic and van der Waals' interactions. For different type complexes, the weights of the scoring functions were optimized by the multiple linear regression method, in which only top 300 structures with ligand root mean square deviation (L_RMSD) less than 20 A from the bound (co-crystallized) docking of 57 complexes were used to construct a training set. We employed the bound docking studies to examine the quality of the scoring function, and also extend to the unbound (separately crystallized) docking studies and extra 8 protein-protein complexes. In bound docking of the 57 cases, the first hits of protease/inhibitor cases are all ranked in the top 5. For the cases of antibody/antigen, enzyme/inhibitor and others, there are 17/19, 5/6 and 13/15 cases with the first hits ranked in the top 10, respectively. In unbound docking studies, the first hits of 9/17 protease/inhibitor, 6/19 antibody/antigen, 1/6 enzyme/inhibitor and 6/15 others' complexes are ranked in the top 10. Additionally, for the extra 8 cases, the first hits of the two protease/inhibitor cases are ranked in the top for the bound and unbound test. For the two enzyme/inhibitor cases, the first hits are ranked 1st for bound test, and the 119th and 17th for the unbound test. For the others, the ranks of the first hits are the 1st for the bound test and the 12th for the 1WQ1 unbound test. To some extent, the results validated our divide-and-conquer strategy in the docking study, which might hopefully shed light on the prediction of protein-protein interactions.     

Scoring a diverse set of high-quality docked conformations: a metascore based on electrostatic and desolvation interactions

Predicting protein-protein interactions involves sampling and scoring docked conformations. Barring some large structural rearrangement, rapidly sampling the space of docked conformations is now a real possibility, and the limiting step for the successful prediction of protein interactions is the scoring function used to reduce the space of conformations from billions to a few, and eventually one high affinity complex. An atomic level free-energy scoring function that estimates in units of kcal/mol both electrostatic and desolvation interactions (plus van der Waals if appropriate) of protein-protein docked conformations is used to rerank the blind predictions (860 in total) submitted for six targets to the community-wide Critical Assessment of PRediction of Interactions (CAPRI; http://capri.ebi.ac.uk). We found that native-like models often have varying intermolecular contacts and atom clashes, making unlikely that one can construct a universal function that would rank all these models as native-like. Nevertheless, our scoring function is able to consistently identify the native-like complexes as those with the lowest free energy for the individual models of 16 (out of 17) human predictors for five of the targets, while at the same time the modelers failed to do so in more than half of the cases. The scoring of high-quality models developed by a wide variety of methods and force fields confirms that electrostatic and desolvation forces are the dominant interactions determining the bound structure. The CAPRI experiment has shown that modelers can predict valuable models of protein-protein complexes, and improvements in scoring functions should soon solve the docking problem for complexes whose backbones do not change much upon binding. A scoring server and programs are available at http://structure.pitt.edu.     

Identification of near-native structures by clustering protein docking conformations

Most state-of-the-art protein-protein docking algorithms use the Fast Fourier Transform (FFT) technique to sample the six-dimensional translational and rotational space. Scoring functions including shape complementarity, electrostatics, and desolvation are usually exploited in ranking the docking conformations. While these rigid-body docking methods provide good performance in bound docking, using unbound structures as input frequently leads to a high number of false positive hits. For the purpose of better selecting correct docking conformations, we structurally cluster the docking decoys generated by four widely-used FFT-based protein-protein docking methods. In all cases, the selection based on cluster size outperforms the ranking based on the inherent scoring function. If we cluster decoys from different servers together, only marginal improvement is obtained in comparison with clustering decoys from the best individual server. A collection of multiple decoy sets of comparable quality will be the key to improve the clustering result from meta-docking servers.     

Refinement of unbound protein docking studies using biological knowledge

In this work we present two methods for the reranking of protein-protein docking studies. One scoring method searches the InterDom database for domains that are available in the proteins to be docked and evaluates the interaction of these domains in other complexes of known structure. The second one analyzes the interface of each proposed conformation with regard to the conservation of Phe, Met, and Trp and their polar neighbor residues. The special relevance of these residues is based on a publication by Ma et al. (Proc Natl Acad Sci USA 2003;100:5772-5777), who compared the conservation of all residues in the interface region to the conservation on the rest of the protein's surface. The scoring functions were tested on 30 unbound docking test cases. The evaluation of the methods is based on the ability to rerank the output of a Fast Fourier Transformation (FFT) docking. Both were able to improve the ranking of the docking output. The best improvement was achieved for enzyme-inhibitor examples. Especially the domain-based scoring function was successful and able to place a near-native solution on one of the first six ranks for 13 of 17 (76%) enzyme-inhibitor complexes [in 53% (nine complexes) even on the first rank]. The method evaluating residue conservation allowed us to increase the number of good solutions within the first 100 ranks out of approximately 9000 in 82% of the 17 enzyme-inhibitor test cases, and for seven (41%) out of 17 enzyme-inhibitor complexes, a near native solution was placed within the first seven ranks.     

A collaborative filtering approach for protein-protein docking scoring functions

A protein-protein docking procedure traditionally consists in two successive tasks: a search algorithm generates a large number of candidate conformations mimicking the complex existing in vivo between two proteins, and a scoring function is used to rank them in order to extract a native-like one. We have already shown that using Voronoi constructions and a well chosen set of parameters, an accurate scoring function could be designed and optimized. However to be able to perform large-scale in silico exploration of the interactome, a near-native solution has to be found in the ten best-ranked solutions. This cannot yet be guaranteed by any of the existing scoring functions. In this work, we introduce a new procedure for conformation ranking. We previously developed a set of scoring functions where learning was performed using a genetic algorithm. These functions were used to assign a rank to each possible conformation. We now have a refined rank using different classifiers (decision trees, rules and support vector machines) in a collaborative filtering scheme. The scoring function newly obtained is evaluated using 10 fold cross-validation, and compared to the functions obtained using either genetic algorithms or collaborative filtering taken separately. This new approach was successfully applied to the CAPRI scoring ensembles. We show that for 10 targets out of 12, we are able to find a near-native conformation in the 10 best ranked solutions. Moreover, for 6 of them, the near-native conformation selected is of high accuracy. Finally, we show that this function dramatically enriches the 100 best-ranking conformations in near-native structures.     

pyDock: electrostatics and desolvation for effective scoring of rigid-body protein-protein docking

The accurate scoring of rigid-body docking orientations represents one of the major difficulties in protein-protein docking prediction. Other challenges are the development of faster and more efficient sampling methods and the introduction of receptor and ligand flexibility during simulations. Overall, good discrimination of near-native docking poses from the very early stages of rigid-body protein docking is essential step before applying more costly interface refinement to the correct docking solutions. Here we explore a simple approach to scoring of rigid-body docking poses, which has been implemented in a program called pyDock. The scheme is based on Coulombic electrostatics with distance dependent dielectric constant, and implicit desolvation energy with atomic solvation parameters previously adjusted for rigid-body protein-protein docking. This scoring function is not highly dependent on specific geometry of the docking poses and therefore can be used in rigid-body docking sets generated by a variety of methods. We have tested the procedure in a large benchmark set of 80 unbound docking cases. The method is able to detect a near-native solution from 12,000 docking poses and place it within the 100 lowest-energy docking solutions in 56% of the cases, in a completely unrestricted manner and without any other additional information. More specifically, a near-native solution will lie within the top 20 solutions in 37% of the cases. The simplicity of the approach allows for a better understanding of the physical principles behind protein-protein association, and provides a fast tool for the evaluation of large sets of rigid-body docking poses in search of the near-native orientation.     

Optimal design of protein docking potentials: efficiency and limitations

Protein-protein docking is a challenging computational problem in functional genomics, particularly when one or both proteins undergo conformational change(s) upon binding. The major challenge is to define scoring function soft enough to tolerate these changes and specific enough to distinguish between near-native and "misdocked" conformations. Using a linear programming technique, we derived protein docking potentials (PDPs) that comply with this requirement. We considered a set of 63 nonredundant complexes to this aim, and generated 400,000 putative docked complexes (decoys) based on shape complementarity criterion for each complex. The PDPs were required to yield for the native (correctly docked) structure a potential energy lower than those of all the nonnative (misdocked) structures. The energy constraints applied to all complexes led to ca. 25 million inequalities, the simultaneous solution of which yielded an optimal set of PDPs that discriminated the correctly docked (up to 4.0 A root-mean-square deviation from known complex structure) structure among the 85 top-ranking (0.02%) decoys in 59/63 examined bound-bound cases. The high performance of the potentials was further verified in jackknife tests and by ranking putative docked conformation submitted to CAPRI. In addition to their utility in identifying correctly folded complexes, the PDPs reveal biologically meaningful features that distinguish docking potentials from folding potentials.     

Macromolecular docking restrained by a small angle X-ray scattering profile

While many structures of single protein components are becoming available, structural characterization of their complexes remains challenging. Methods for modeling assembly structures from individual components frequently suffer from large errors, due to protein flexibility and inaccurate scoring functions. However, when additional information is available, it may be possible to reduce the errors and compute near-native complex structures. One such type of information is a small angle X-ray scattering (SAXS) profile that can be collected in a high-throughput fashion from a small amount of sample in solution. Here, we present an efficient method for protein–protein docking with a SAXS profile (FoXSDock): generation of complex models by rigid global docking with PatchDock, filtering of the models based on the SAXS profile, clustering of the models, and refining the interface by flexible docking with FireDock. FoXSDock is benchmarked on 124 protein complexes with simulated SAXS profiles, as well as on 6 complexes with experimentally determined SAXS profiles. When induced fit is less than 1.5 Å interface C_α RMSD and the fraction residues of missing from the component structures is less than 3%, FoXSDock can find a model close to the native structure within the top 10 predictions in 77% of the cases; in comparison, docking alone succeeds in only 34% of the cases. Thus, the integrative approach significantly improves on molecular docking alone. The improvement arises from an increased resolution of rigid docking sampling and more accurate scoring.     

Protein docking using surface matching and supervised machine learning

Computational prediction of protein complex structures through docking offers a means to gain a mechanistic understanding of protein interactions that mediate biological processes. This is particularly important as the number of experimentally determined structures of isolated proteins exceeds the number of structures of complexes. A comprehensive docking procedure is described in which efficient sampling of conformations is achieved by matching surface normal vectors, fast filtering for shape complementarity, clustering by RMSD, and scoring the docked conformations using a supervised machine learning approach. Contacting residue pair frequencies, residue propensities, evolutionary conservation, and shape complementarity score for each docking conformation are used as input data to a Random Forest classifier. The performance of the Random Forest approach for selecting correctly docked conformations was assessed by cross-validation using a nonredundant benchmark set of X-ray structures for 93 heterodimer and 733 homodimer complexes. The single highest rank docking solution was the correct (near-native) structure for slightly more than one third of the complexes. Furthermore, the fraction of highly ranked correct structures was significantly higher than the overall fraction of correct structures, for almost all complexes. A detailed analysis of the difficult to predict complexes revealed that the majority of the homodimer cases were explained by incorrect oligomeric state annotation. Evolutionary conservation and shape complementarity score as well as both underrepresented and overrepresented residue types and residue pairs were found to make the largest contributions to the overall prediction accuracy. Finally, the method was also applied to docking unbound subunit structures from a previously published benchmark set.     

ClusPro: an automated docking and discrimination method for the prediction of protein complexes

MOTIVATION: Predicting protein interactions is one of the most challenging problems in functional genomics. Given two proteins known to interact, current docking methods evaluate billions of docked conformations by simple scoring functions, and in addition to near-native structures yield many false positives, i.e. structures with good surface complementarity but far from the native. RESULTS: We have developed a fast algorithm for filtering docked conformations with good surface complementarity, and ranking them based on their clustering properties. The free energy filters select complexes with lowest desolvation and electrostatic energies. Clustering is then used to smooth the local minima and to select the ones with the broadest energy wells-a property associated with the free energy at the binding site. The robustness of the method was tested on sets of 2000 docked conformations generated for 48 pairs of interacting proteins. In 31 of these cases, the top 10 predictions include at least one near-native complex, with an average RMSD of 5 A from the native structure. The docking and discrimination method also provides good results for a number of complexes that were used as targets in the Critical Assessment of PRedictions of Interactions experiment. AVAILABILITY: The fully automated docking and discrimination server ClusPro can be found at http://structure.bu.edu     

DOCKGROUND protein-protein docking decoy set

A protein-protein docking decoy set is built for the Dockground unbound benchmark set. The GRAMM-X docking scan was used to generate 100 non-native and at least one near-native match per complex for 61 complexes. The set is a publicly available resource for the development of scoring functions and knowledge-based potentials for protein docking methodologies. AVAILABILITY: The decoys are freely available for download at http://dockground.bioinformatics.ku.edu/UNBOUND/decoy/decoy.php     

Consensus scoring for enriching near-native structures from protein-protein docking decoys

The identification of near native protein-protein complexes among a set of decoys remains highly challenging. A strategy for improving the success rate of near native detection is to enrich near native docking decoys in a small number of top ranked decoys. Recently, we found that a combination of three scoring functions (energy, conservation, and interface propensity) can predict the location of binding interface regions with reasonable accuracy. Here, these three scoring functions are modified and combined into a consensus scoring function called ENDES for enriching near native docking decoys. We found that all individual scores result in enrichment for the majority of 28 targets in ZDOCK2.3 decoy set and the 22 targets in Benchmark 2.0. Among the three scores, the interface propensity score yields the highest enrichment in both sets of protein complexes. When these scores are combined into the ENDES consensus score, a significant increase in enrichment of near-native structures is found. For example, when 2000 dock decoys are reduced to 200 decoys by ENDES, the fraction of near-native structures in docking decoys increases by a factor of about six in average. ENDES was implemented into a computer program that is available for download at http://sparks.informatics.iupui.edu.     

A protein-specifically adapted scoring function for the reranking of docking solutions

In this work, we developed a protein-specifically adapted scoring function and applied it to the reranking of protein-protein docking solutions generated with a conventional docking program. The approach was validated using experimentally determined structures of the bacterial HPr-protein in complex with four structurally nonhomologous binding partners as an example. A sufficiently large data basis for the generation of protein-specifically adapted pair potentials was generated by modeling all orthologous complexes for each type of interaction resulting in a total of 224 complexes. The parameters for potential generation were systematically varied and resulted in a total of 66,132 different scoring functions that were tested for their ability of successful reranking of 1000 docking solutions generated from modeled structures of the unbound binding partners. Parameters that proved critical for the generation of good scoring functions were the distance cutoff used for the generation of the pair potential, and an additional cutoff that allows a proper weighting of conserved and nonconserved contacts in the interface. Compared to the original scoring function, application of this novel type of scoring functions resulted in a significant accumulation of acceptable docking solutions within the first 10 ranks. Depending on the type of complex investigated one to five acceptable complex geometries are found among the 10 highest-ranked solutions and for three of the four systems tested, an acceptable solution was placed on the first rank.