Predicting protein complex geometries with a neural network

A major challenge of the protein docking problem is to define scoring functions that can distinguish near‐native protein complex geometries from a large number of non‐native geometries (decoys) generated with noncomplexed protein structures (unbound docking). In this study, we have constructed a neural network that employs the information from atom‐pair distance distributions of a large number of decoys to predict protein complex geometries. We found that docking prediction can be significantly improved using two different types of polar hydrogen atoms. To train the neural network, 2000 near‐native decoys of even distance distribution were used for each of the 185 considered protein complexes. The neural network normalizes the information from different protein complexes using an additional protein complex identity input neuron for each complex. The parameters of the neural network were determined such that they mimic a scoring funnel in the neighborhood of the native complex structure. The neural network approach avoids the reference state problem, which occurs in deriving knowledge‐based energy functions for scoring. We show that a distance‐dependent atom pair potential performs much better than a simple atom‐pair contact potential. We have compared the performance of our scoring function with other empirical and knowledge‐based scoring functions such as ZDOCK 3.0, ZRANK, ITScore‐PP, EMPIRE, and RosettaDock. In spite of the simplicity of the method and its functional form, our neural network‐based scoring function achieves a reasonable performance in rigid‐body unbound docking of proteins. Proteins 2010. © 2009 Wiley‐Liss, Inc.     

Native fold and docking pose discrimination by the same residue‐based scoring function

Structure prediction and quality assessment are crucial steps in modeling native protein conformations. Statistical potentials are widely used in related algorithms, with different parametrizations typically developed for different contexts such as folding protein monomers or docking protein complexes. Here, we describe BACH‐SixthSense, a single residue‐based statistical potential that can be successfully employed in both contexts. BACH‐SixthSense shares the same approach as BACH, a knowledge‐based potential originally developed to score monomeric protein structures. A term that penalizes steric clashes as well as the distinction between polar and apolar sidechain‐sidechain contacts are crucial novel features of BACH‐SixthSense. The performance of BACH‐SixthSense in discriminating correctly the native structure among a competing set of decoys is significantly higher than other state‐of‐the‐art scoring functions, that were specifically trained for a single context, for both monomeric proteins (QMEAN, Rosetta, RF_CB_SRS_OD, benchmarked on CASP targets) and protein dimers (IRAD, Rosetta, PIE*PISA, HADDOCK, FireDock, benchmarked on 14 CAPRI targets). The performance of BACH‐SixthSense in recognizing near‐native docking poses within CAPRI decoy sets is good as well. Proteins 2015; 83:621–630. © 2015 Wiley Periodicals, Inc.     

Protein–protein structure prediction by scoring molecular dynamics trajectories of putative poses

The prediction of protein–protein interactions and their structural configuration remains a largely unsolved problem. Most of the algorithms aimed at finding the native conformation of a protein complex starting from the structure of its monomers are based on searching the structure corresponding to the global minimum of a suitable scoring function. However, protein complexes are often highly flexible, with mobile side chains and transient contacts due to thermal fluctuations. Flexibility can be neglected if one aims at finding quickly the approximate structure of the native complex, but may play a role in structure refinement, and in discriminating solutions characterized by similar scores. We here benchmark the capability of some state‐of‐the‐art scoring functions (BACH‐SixthSense, PIE/PISA and Rosetta) in discriminating finite‐temperature ensembles of structures corresponding to the native state and to non‐native configurations. We produce the ensembles by running thousands of molecular dynamics simulations in explicit solvent starting from poses generated by rigid docking and optimized in vacuum. We find that while Rosetta outperformed the other two scoring functions in scoring the structures in vacuum, BACH‐SixthSense and PIE/PISA perform better in distinguishing near‐native ensembles of structures generated by molecular dynamics in explicit solvent. Proteins 2016; 84:1312–1320. © 2016 Wiley Periodicals, Inc.     

iATTRACT: Simultaneous global and local interface optimization for protein–protein docking refinement

Protein‐protein interactions are abundant in the cell but to date structural data for a large number of complexes is lacking. Computational docking methods can complement experiments by providing structural models of complexes based on structures of the individual partners. A major caveat for docking success is accounting for protein flexibility. Especially, interface residues undergo significant conformational changes upon binding. This limits the performance of docking methods that keep partner structures rigid or allow limited flexibility. A new docking refinement approach, iATTRACT, has been developed which combines simultaneous full interface flexibility and rigid body optimizations during docking energy minimization. It employs an atomistic molecular mechanics force field for intermolecular interface interactions and a structure‐based force field for intramolecular contributions. The approach was systematically evaluated on a large protein‐protein docking benchmark, starting from an enriched decoy set of rigidly docked protein–protein complexes deviating by up to 15 Å from the native structure at the interface. Large improvements in sampling and slight but significant improvements in scoring/discrimination of near native docking solutions were observed. Complexes with initial deviations at the interface of up to 5.5 Å were refined to significantly better agreement with the native structure. Improvements in the fraction of native contacts were especially favorable, yielding increases of up to 70%. Proteins 2015; 83:248–258. © 2014 Wiley Periodicals, Inc.     

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.     

Intuitive,but not simple: Including explicit water molecules in protein–protein docking simulations improves model quality

Characterizing the nature of interaction between proteins that have not been experimentally cocrystallized requires a computational docking approach that can successfully predict the spatial conformation adopted in the complex. In this work, the Hydropathic INTeractions (HINT) force field model was used for scoring docked models in a data set of 30 high‐resolution crystallographically characterized “dry” protein–protein complexes and was shown to reliably identify native‐like models. However, most current protein–protein docking algorithms fail to explicitly account for water molecules involved in bridging interactions that mediate and stabilize the association of the protein partners, so we used HINT to illuminate the physical and chemical properties of bridging waters and account for their energetic stabilizing contributions. The HINT water Relevance metric identified the “truly” bridging waters at the 30 protein–protein interfaces and we utilized them in “solvated” docking by manually inserting them into the input files for the rigid body ZDOCK program. By accounting for these interfacial waters, a statistically significant improvement of ～24% in the average hit‐count within the top‐10 predictions the protein–protein dataset was seen, compared to standard “dry” docking. The results also show scoring improvement, with medium and high accuracy models ranking much better than incorrect ones. These improvements can be attributed to the physical presence of water molecules that alter surface properties and better represent native shape and hydropathic complementarity between interacting partners, with concomitantly more accurate native‐like structure predictions. Proteins 2014; 82:916–932. © 2013 Wiley Periodicals, Inc.     

CyClus: A fast,comprehensive cylindrical interface approximation clustering/reranking method for rigid‐body protein–protein docking decoys

We propose a fast clustering and reranking method, CyClus, for protein–protein docking decoys. This method enables comprehensive clustering of whole decoys generated by rigid‐body docking using cylindrical approximation of the protein–proteininterface and hierarchical clustering procedures. We demonstrate the clustering and reranking of 54,000 decoy structures generated by ZDOCK for each complex within a few minutes. After parameter tuning for the test set in ZDOCK benchmark 2.0 with the ZDOCK and ZRANK scoring functions, blind tests for the incremental data in ZDOCK benchmark 3.0 and 4.0 were conducted. CyClus successfully generated smaller subsets of decoys containing near‐native decoys. For example, the number of decoys required to create subsets containing near‐native decoys with 80% probability was reduced from 22% to 50% of the number required in the original ZDOCK. Although specific ZDOCK and ZRANK results were demonstrated, the CyClus algorithm was designed to be more general and can be applied to a wide range of decoys and scoring functions by adjusting just two parameters, p and T. CyClus results were also compared to those from ClusPro. Proteins 2013; © 2012 Wiley Periodicals, Inc.     

DockRank: Ranking docked conformations using partner‐specific sequence homology‐based protein interface prediction

Selecting near‐native conformations from the immense number of conformations generated by docking programs remains a major challenge in molecular docking. We introduce DockRank, a novel approach to scoring docked conformations based on the degree to which the interface residues of the docked conformation match a set of predicted interface residues. DockRank uses interface residues predicted by partner‐specific sequence homology‐based protein–protein interface predictor (PS‐HomPPI), which predicts the interface residues of a query protein with a specific interaction partner. We compared the performance of DockRank with several state‐of‐the‐art docking scoring functions using Success Rate (the percentage of cases that have at least one near‐native conformation among the top m conformations) and Hit Rate (the percentage of near‐native conformations that are included among the top m conformations). In cases where it is possible to obtain partner‐specific (PS) interface predictions from PS‐HomPPI, DockRank consistently outperforms both (i) ZRank and IRAD, two state‐of‐the‐art energy‐based scoring functions (improving Success Rate by up to 4‐fold); and (ii) Variants of DockRank that use predicted interface residues obtained from several protein interface predictors that do not take into account the binding partner in making interface predictions (improving success rate by up to 39‐fold). The latter result underscores the importance of using partner‐specific interface residues in scoring docked conformations. We show that DockRank, when used to re‐rank the conformations returned by ClusPro, improves upon the original ClusPro rankings in terms of both Success Rate and Hit Rate. DockRank is available as a server at http://einstein.cs.iastate.edu/DockRank/ . Proteins 2014; 82:250–267. © 2013 Wiley Periodicals, Inc.     

H‐bond network optimization in protein–protein complexes: Are all‐atom force field scores enough?

Structural prediction of protein-protein complexes given the structures of the two interacting compounds in their unbound state is a key problem in biophysics. In addition to the problem of sampling of near-native orientations, one of the modeling main difficulties is to discriminate true from false positives. Here, we present a hierarchical protocol for docking refinement able to discriminate near native poses from a group of docking candidates. The main idea is to combine an efficient sampling of the full system hydrogen bond network and side chains, together with an all-atom force field and a surface generalized born implicit solvent. We tested our method on a set of twenty two complexes containing a near-native solution within the top 100 docking poses, obtaining a near native solution as the top pose in 70% of the cases. We show that all atom force fields optimized H-bond networks do improve significantly state of the art scoring functions.     

PIE—Efficient filters and coarse grained potentials for unbound protein–protein docking

Identifying correct binding modes in a large set of models is an important step in protein–protein docking. We identified protein docking filter based on overlap area that significantly reduces the number of candidate structures that require detailed examination. We also developed potentials based on residue contacts and overlap areas using a comprehensive learning set of 640 two‐chain protein complexes with mathematical programming. Our potential showed substantially better recognition capacity compared to other publicly accessible protein docking potentials in discriminating between native and nonnative binding modes on a large test set of 84 complexes independent of our training set. We were able to rank a near‐native model on the top in 43 cases and within top 10 in 51 cases. We also report an atomic potential that ranks a near‐native model on the top in 46 cases and within top 10 in 58 cases. Our filter+potential is well suited for selecting a small set of models to be refined to atomic resolution. Proteins 2010. © 2009 Wiley‐Liss, Inc.     

Detecting the native ligand orientation by interfacial rigidity: SiteInterlock

Understanding the physical attributes of protein‐ligand interfaces, the source of most biological activity, is a fundamental problem in biophysics. Knowing the characteristic features of interfaces also enables the design of molecules with potent and selective interactions. Prediction of native protein‐ligand interactions has traditionally focused on the development of physics‐based potential energy functions, empirical scoring functions that are fit to binding data, and knowledge‐based potentials that assess the likelihood of pairwise interactions. Here we explore a new approach, testing the hypothesis that protein‐ligand binding results in computationally detectable rigidification of the protein‐ligand interface. Our SiteInterlock approach uses rigidity theory to efficiently measure the relative interfacial rigidity of a series of small‐molecule ligand orientations and conformations for a number of protein complexes. In the majority of cases, SiteInterlock detects a near‐native binding mode as being the most rigid, with particularly robust performance relative to other methods when the ligand‐free conformation of the protein is provided. The interfacial rigidification of both the protein and ligand prove to be important characteristics of the native binding mode. This measure of rigidity is also sensitive to the spatial coupling of interactions and bond‐rotational degrees of freedom in the interface. While the predictive performance of SiteInterlock is competitive with the best of the five other scoring functions tested, its measure of rigidity encompasses cooperative rather than just additive binding interactions, providing novel information for detecting native‐like complexes. SiteInterlock shows special strength in enhancing the prediction of native complexes by ruling out inaccurate poses. Proteins 2016; 84:1888–1901. © 2016 Wiley Periodicals, Inc.     

Score_set: A CAPRI benchmark for scoring protein complexes

Critical Assessment of PRedicted Interactions (CAPRI) has proven to be a catalyst for the development of docking algorithms. An essential step in docking is the scoring of predicted binding modes in order to identify stable complexes. In 2005, CAPRI introduced the scoring experiment, where upon completion of a prediction round, a larger set of models predicted by different groups and comprising both correct and incorrect binding modes, is made available to all participants for testing new scoring functions independently from docking calculations. Here we present an expanded benchmark data set for testing scoring functions, which comprises the consolidated ensemble of predicted complexes made available in the CAPRI scoring experiment since its inception. This consolidated scoring benchmark contains predicted complexes for 15 published CAPRI targets. These targets were subjected to 23 CAPRI assessments, due to existence of multiple binding modes for some targets. The benchmark contains more than 19,000 protein complexes. About 10% of the complexes represent docking predictions of acceptable quality or better, the remainder represent incorrect solutions (decoys). The benchmark set contains models predicted by 47 different predictor groups including web servers, which use different docking and scoring procedures, and is arguably as diverse as one may expect, representing the state of the art in protein docking. The data set is publicly available at the following URL: http://cb.iri.univ‐lille1.fr/Users/lensink/Score_set . Proteins 2014; 82:3163–3169. © 2014 Wiley Periodicals, Inc.     

Multi-LZerD: multiple protein docking for asymmetric complexes

The tertiary structures of protein complexes provide a crucial insight about the molecular mechanisms that regulate their functions and assembly. However, solving protein complex structures by experimental methods is often more difficult than single protein structures. Here, we have developed a novel computational multiple protein docking algorithm, Multi‐LZerD, that builds models of multimeric complexes by effectively reusing pairwise docking predictions of component proteins. A genetic algorithm is applied to explore the conformational space followed by a structure refinement procedure. Benchmark on eleven hetero‐multimeric complexes resulted in near‐native conformations for all but one of them (a root mean square deviation smaller than 2.5Å). We also show that our method copes with unbound docking cases well, outperforming the methodology that can be directly compared with our approach. Multi‐LZerD was able to predict near‐native structures for multimeric complexes of various topologies.Proteins 2012; © 2012 Wiley Periodicals, Inc.     

Sampling and scoring: A marriage made in heaven

Most structure prediction algorithms consist of initial sampling of the conformational space, followed by rescoring and possibly refinement of a number of selected structures. Here we focus on protein docking, and show that while decoupling sampling and scoring facilitates method development, integration of the two steps can lead to substantial improvements in docking results. Since decoupling is usually achieved by generating a decoy set containing both non‐native and near‐native docked structures, which can be then used for scoring function construction, we first review the roles and potential pitfalls of decoys in protein–protein docking, and show that some type of decoys are better than others for method development. We then describe three case studies showing that complete decoupling of scoring from sampling is not the best choice for solving realistic docking problems. Although some of the examples are based on our own experience, the results of the CAPRI docking and scoring experiments also show that performing both sampling and scoring generally yields better results than scoring the structures generated by all predictors. Next we investigate how the selection of training and decoy sets affects the performance of the scoring functions obtained. Finally, we discuss pathways to better alignment of the two steps, and show some algorithms that achieve a certain level of integration. Although we focus on protein–protein docking, our observations most likely also apply to other conformational search problems, including protein structure prediction and the docking of small molecules to proteins.Proteins 2013; 81:1874–1884. © 2013 Wiley Periodicals, Inc.     

Towards the prediction of protein interaction partners using physical docking

Deciphering the whole network of protein interactions for a given proteome (‘interactome’) is the goal of many experimental and computational efforts in Systems Biology. Separately the prediction of the structure of protein complexes by docking methods is a well‐established scientific area. To date, docking programs have not been used to predict interaction partners. We provide a proof of principle for such an approach. Using a set of protein complexes representing known interactors in their unbound form, we show that a standard docking program can distinguish the true interactors from a background of 922 non‐redundant potential interactors. We additionally show that true interactions can be distinguished from non‐likely interacting proteins within the same structural family. Our approach may be put in the context of the proposed ‘funnel‐energy model’; the docking algorithm may not find the native complex, but it distinguishes binding partners because of the higher probability of favourable models compared with a collection of non‐binders. The potential exists to develop this proof of principle into new approaches for predicting interaction partners and reconstructing biological networks.     

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.     

How different from random are docking predictions when ranked by scoring functions?

Docking algorithms predict the structure of protein–protein interactions. They sample the orientation of two unbound proteins to produce various predictions about their interactions, followed by a scoring step to rank the predictions. We present a statistical assessment of scoring functions used to rank near‐native orientations, applying our statistical analysis to a benchmark dataset of decoys of protein–protein complexes and assessing the statistical significance of the outcome in the Critical Assessment of PRedicted Interactions (CAPRI) scoring experiment. A P value was assigned that depended on the number of near‐native structures in the sampling. We studied the effect of filtering out redundant structures and tested the use of pair‐potentials derived using ZDock and ZRank. Our results show that for many targets, it is not possible to determine when a successful reranking performed by scoring functions results merely from random choice. This analysis reveals that changes should be made in the design of the CAPRI scoring experiment. We propose including the statistical assessment in this experiment either at the preprocessing or the evaluation step. Proteins 2010. © 2010 Wiley‐Liss, Inc.     

A generalized knowledge‐based discriminatory function for biomolecular interactions

Several novel and established knowledge‐based discriminatory function formulations and reference state derivations have been evaluated to identify parameter sets capable of distinguishing native and near‐native biomolecular interactions from incorrect ones. We developed the r·m·r function, a novel atomic level radial distribution function with mean reference state that averages over all pairwise atom types from a reduced atom type composition, using experimentally determined intermolecular complexes in the Cambridge Structural Database (CSD) and the Protein Data Bank (PDB) as the information sources. We demonstrate that r·m·r had the best discriminatory accuracy and power for protein‐small molecule and protein‐DNA interactions, regardless of whether the native complex was included or excluded, from the test set. The superior performance of the r·m·r discriminatory function compared with seventeen alternative functions evaluated on publicly available test sets for protein‐small molecule and protein‐DNA interactions indicated that the function was not over optimized through back testing on a single class of biomolecular interactions. The initial success of the reduced composition and superior performance with the CSD as the distribution set over the PDB implies that further improvements and generality of the function are possible by deriving probabilities from subsets of the CSD, using structures that consist of only the atom types to be considered for given biomolecular interactions. The method is available as a web server module at http://protinfo.compbio.washington.edu . Proteins 2009. © 2008 Wiley‐Liss, Inc.     

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.