D3R grand challenge 4: blind prediction of protein–ligand poses,affinity rankings,and relative binding free energies

Journal of Computer-Aided Molecular Design - The Drug Design Data Resource (D3R) aims to identify best practice methods for computer aided drug design through blinded ligand pose prediction and...     

Large scale free energy calculations for blind predictions of protein–ligand binding: the D3R Grand Challenge 2015

We describe binding free energy calculations in the D3R Grand Challenge 2015 for blind prediction of the binding affinities of 180 ligands to Hsp90. The present D3R challenge was built around experimental datasets involving Heat shock protein (Hsp) 90, an ATP-dependent molecular chaperone which is an important anticancer drug target. The Hsp90 ATP binding site is known to be a challenging target for accurate calculations of ligand binding affinities because of the ligand-dependent conformational changes in the binding site, the presence of ordered waters and the broad chemical diversity of ligands that can bind at this site. Our primary focus here is to distinguish binders from nonbinders. Large scale absolute binding free energy calculations that cover over 3000 protein–ligand complexes were performed using the BEDAM method starting from docked structures generated by Glide docking. Although the ligand dataset in this study resembles an intermediate to late stage lead optimization project while the BEDAM method is mainly developed for early stage virtual screening of hit molecules, the BEDAM binding free energy scoring has resulted in a moderate enrichment of ligand screening against this challenging drug target. Results show that, using a statistical mechanics based free energy method like BEDAM starting from docked poses offers better enrichment than classical docking scoring functions and rescoring methods like Prime MM-GBSA for the Hsp90 data set in this blind challenge. Importantly, among the three methods tested here, only the mean value of the BEDAM binding free energy scores is able to separate the large group of binders from the small group of nonbinders with a gap of 2.4 kcal/mol. None of the three methods that we have tested provided accurate ranking of the affinities of the 147 active compounds. We discuss the possible sources of errors in the binding free energy calculations. The study suggests that BEDAM can be used strategically to discriminate binders from nonbinders in virtual screening and to more accurately predict the ligand binding modes prior to the more computationally expensive FEP calculations of binding affinity.     

Performance of HADDOCK and a simple contact-based protein–ligand binding affinity predictor in the D3R Grand Challenge 2

We present the performance of HADDOCK, our information-driven docking software, in the second edition of the D3R Grand Challenge. In this blind experiment, participants were requested to predict the structures and binding affinities of complexes between the Farnesoid X nuclear receptor and 102 different ligands. The models obtained in Stage1 with HADDOCK and ligand-specific protocol show an average ligand RMSD of 5.1 Å from the crystal structure. Only 6/35 targets were within 2.5 Å RMSD from the reference, which prompted us to investigate the limiting factors and revise our protocol for Stage2. The choice of the receptor conformation appeared to have the strongest influence on the results. Our Stage2 models were of higher quality (13 out of 35 were within 2.5 Å), with an average RMSD of 4.1 Å. The docking protocol was applied to all 102 ligands to generate poses for binding affinity prediction. We developed a modified version of our contact-based binding affinity predictor PRODIGY, using the number of interatomic contacts classified by their type and the intermolecular electrostatic energy. This simple structure-based binding affinity predictor shows a Kendall’s Tau correlation of 0.37 in ranking the ligands (7th best out of 77 methods, 5th/25 groups). Those results were obtained from the average prediction over the top10 poses, irrespective of their similarity/correctness, underscoring the robustness of our simple predictor. This results in an enrichment factor of 2.5 compared to a random predictor for ranking ligands within the top 25%, making it a promising approach to identify lead compounds in virtual screening.     

Ranking docking poses by graph matching of protein–ligand interactions: lessons learned from the D3R Grand Challenge 2

A novel docking challenge has been set by the Drug Design Data Resource (D3R) in order to predict the pose and affinity ranking of a set of Farnesoid X receptor (FXR) agonists, prior to the public release of their bound X-ray structures and potencies. In a first phase, 36 agonists were docked to 26 Protein Data Bank (PDB) structures of the FXR receptor, and next rescored using the in-house developed GRIM method. GRIM aligns protein–ligand interaction patterns of docked poses to those of available PDB templates for the target protein, and rescore poses by a graph matching method. In agreement with results obtained during the previous 2015 docking challenge, we clearly show that GRIM rescoring improves the overall quality of top-ranked poses by prioritizing interaction patterns already visited in the PDB. Importantly, this challenge enables us to refine the applicability domain of the method by better defining the conditions of its success. We notably show that rescoring apolar ligands in hydrophobic pockets leads to frequent GRIM failures. In the second phase, 102 FXR agonists were ranked by decreasing affinity according to the Gibbs free energy of the corresponding GRIM-selected poses, computed by the HYDE scoring function. Interestingly, this fast and simple rescoring scheme provided the third most accurate ranking method among 57 contributions. Although the obtained ranking is still unsuitable for hit to lead optimization, the GRIM–HYDE scoring scheme is accurate and fast enough to post-process virtual screening data.     

D3R grand challenge 2015: Evaluation of protein–ligand pose and affinity predictions

The Drug Design Data Resource (D3R) ran Grand Challenge 2015 between September 2015 and February 2016. Two targets served as the framework to test community docking and scoring methods: (1) HSP90, donated by AbbVie and the Community Structure Activity Resource (CSAR), and (2) MAP4K4, donated by Genentech. The challenges for both target datasets were conducted in two stages, with the first stage testing pose predictions and the capacity to rank compounds by affinity with minimal structural data; and the second stage testing methods for ranking compounds with knowledge of at least a subset of the ligand–protein poses. An additional sub-challenge provided small groups of chemically similar HSP90 compounds amenable to alchemical calculations of relative binding free energy. Unlike previous blinded Challenges, we did not provide cognate receptors or receptors prepared with hydrogens and likewise did not require a specified crystal structure to be used for pose or affinity prediction in Stage 1. Given the freedom to select from over 200 crystal structures of HSP90 in the PDB, participants employed workflows that tested not only core docking and scoring technologies, but also methods for addressing water-mediated ligand–protein interactions, binding pocket flexibility, and the optimal selection of protein structures for use in docking calculations. Nearly 40 participating groups submitted over 350 prediction sets for Grand Challenge 2015. This overview describes the datasets and the organization of the challenge components, summarizes the results across all submitted predictions, and considers broad conclusions that may be drawn from this collaborative community endeavor.     

A functional feature analysis on diverse protein–protein interactions: application for the prediction of binding affinity

Protein–protein interactions (PPIs) play crucial roles in diverse cellular processes. There are different types of PPIs based on the composition, affinity and whether the association is permanent or transient. Analyzing the diversity of PPIs at the atomic level is crucial for uncovering the key features governing the interactions involved in PPI. A systematic physico-chemical and conformational studies were implemented on interfaces involved in different PPIs, including crystal packing, weak transient heterodimers, weak transient homodimers, strong transient heterodimers and homodimers. The comparative analysis shows that the interfaces tend to be larger, less planar, and more tightly packed with the increase of the interaction strength. Meanwhile the strong interactions undergo greater conformational changes than the weak ones involving main chains as well as side chains. Finally, using 18 features derived from our analysis, we developed a support vector regression model to predict the binding affinity with a promising result, which further demonstrate the reliability of our studies. We believe this study will provide great help in more thorough understanding the mechanism of diverse PPIs.     

Biomacromolecular quantitative structure–activity relationship (BioQSAR): a proof-of-concept study on the modeling, prediction and interpretation of protein–protein binding affinity

Quantitative structure–activity relationship (QSAR), a regression modeling methodology that establishes statistical correlation between structure feature and apparent behavior for a series of congeneric molecules quantitatively, has been widely used to evaluate the activity, toxicity and property of various small-molecule compounds such as drugs, toxicants and surfactants. However, it is surprising to see that such useful technique has only very limited applications to biomacromolecules, albeit the solved 3D atom-resolution structures of proteins, nucleic acids and their complexes have accumulated rapidly in past decades. Here, we present a proof-of-concept paradigm for the modeling, prediction and interpretation of the binding affinity of 144 sequence-nonredundant, structure-available and affinity-known protein complexes (Kastritis et al. Protein Sci 20:482–491, 2011) using a biomacromolecular QSAR (BioQSAR) scheme. We demonstrate that the modeling performance and predictive power of BioQSAR are comparable to or even better than that of traditional knowledge-based strategies, mechanism-type methods and empirical scoring algorithms, while BioQSAR possesses certain additional features compared to the traditional methods, such as adaptability, interpretability, deep-validation and high-efficiency. The BioQSAR scheme could be readily modified to infer the biological behavior and functions of other biomacromolecules, if their X-ray crystal structures, NMR conformation assemblies or computationally modeled structures are available.     

The importance of protonation and tautomerization in relative binding affinity prediction: a comparison of AMBER TI and Schrödinger FEP

In drug discovery, protonation states and tautomerization are easily overlooked. Through a Merck–Rutgers collaboration, this paper re-examined the initial settings and preparations for the Thermodynamic Integration (TI) calculation in AMBER Free-Energy Workflows, demonstrating the value of careful consideration of ligand protonation and tautomer state. Finally, promising results comparing AMBER TI and Schrödinger FEP+ are shown that should encourage others to explore the value of TI in routine Structure-based Drug Design.     

Simultaneous prediction of binding free energy and specificity for PDZ domain–peptide interactions

Interactions between protein domains and linear peptides underlie many biological processes. Among these interactions, the recognition of C-terminal peptides by PDZ domains is one of the most ubiquitous. In this work, we present a mathematical model for PDZ domain–peptide interactions capable of predicting both affinity and specificity of binding based on X-ray crystal structures and comparative modeling with Rosetta. We developed our mathematical model using a large phage display dataset describing binding specificity for a wild type PDZ domain and 91 single mutants, as well as binding affinity data for a wild type PDZ domain binding to 28 different peptides. Structural refinement was carried out through several Rosetta protocols, the most accurate of which included flexible peptide docking and several iterations of side chain repacking and backbone minimization. Our findings emphasize the importance of backbone flexibility and the energetic contributions of side chain-side chain hydrogen bonds in accurately predicting interactions. We also determined that predicting PDZ domain–peptide interactions became increasingly challenging as the length of the peptide increased in the N-terminal direction. In the training dataset, predicted binding energies correlated with those derived through calorimetry and specificity switches introduced through single mutations at interface positions were recapitulated. In independent tests, our best performing protocol was capable of predicting dissociation constants well within one order of magnitude of the experimental values and specificity profiles at the level of accuracy of previous studies. To our knowledge, this approach represents the first integrated protocol for predicting both affinity and specificity for PDZ domain–peptide interactions.     

A new method for estimating the relative binding free energy,derived from a free energy variational principle for the Pim-1-kinase–ligand and FKBP–ligand systems

Journal of Computer-Aided Molecular Design - In this study, a new method is proposed for calculating the relative binding free energy between a ligand and a protein, derived from a free energy...     

Resolving the problem of trapped water in binding cavities: prediction of host–guest binding free energies in the SAMPL5 challenge by funnel metadynamics

The funnel metadynamics method enables rigorous calculation of the potential of mean force along an arbitrary binding path and thereby evaluation of the absolute binding free energy. A problem of such physical paths is that the mechanism characterizing the binding process is not always obvious. In particular, it might involve reorganization of the solvent in the binding site, which is not easily captured with a few geometrically defined collective variables that can be used for biasing. In this paper, we propose and test a simple method to resolve this trapped-water problem by dividing the process into an artificial host-desolvation step and an actual binding step. We show that, under certain circumstances, the contribution from the desolvation step can be calculated without introducing further statistical errors. We apply the method to the problem of predicting host–guest binding free energies in the SAMPL5 blind challenge, using two octa-acid hosts and six guest molecules. For one of the hosts, well-converged results are obtained and the prediction of relative binding free energies is the best among all the SAMPL5 submissions. For the other host, which has a narrower binding pocket, the statistical uncertainties are slightly higher; longer simulations would therefore be needed to obtain conclusive results.     

The configurational dependence of binding free energies: A Poisson–Boltzmann study of Neuraminidase inhibitors

The linear finite difference Poisson-Boltzmann (FDPB) equation is applied to the calculation of the electrostatic binding free energies of a group of inhibitors to the Neuraminidase enzyme. An ensemble of enzyme-inhibitor complex conformations was generated using Monte Carlo simulations and the electrostatic binding free energies of subtly different configurations of the enzyme-inhibitor complexes were calculated. It was seen that the binding free energies calculated using FDPB depend strongly on the configuration of the complex taken from the ensemble. This configurational dependence was investigated in detail in the electrostatic hydration free energies of the inhibitors. Differences in hydration energies of up to 7 kcal mol^–1 were obtained for root mean square (RMS) structural deviations of only 0.5 Å. To verify the result, the grid size and parameter dependence of the calculated hydration free energies were systematically investigated. This showed that the absolute hydration free energies calculated using the FDPB equation were very sensitive to the values of key parameters, but that the configurational dependence of the free energies was independent of the parameters chosen. Thus just as molecular mechanics energies are very sensitive to configuration, and single-structure values are not typically used to score binding free energies, single FDPB energies should be treated with the same caution.     

Individually double minimum-distance definition of protein–RNA binding residues and application to structure-based prediction

Identifying protein–RNA binding residues is essential for understanding the mechanism of protein–RNA interactions. So far, rigid distance thresholds are commonly used to define protein–RNA binding residues. However, after investigating 182 non-redundant protein–RNA complexes, we find that it would be unsuitable for a certain amount of complexes since the distances between proteins and RNAs vary widely. In this work, a novel definition method was proposed based on a flexible distance cutoff. This method can fully consider the individual differences among complexes by setting a variable tolerance limit of protein–RNA interactions, i.e. the double minimum-distance by which different distance thresholds are achieved for different complexes. In order to validate our method, a comprehensive comparison between our flexible method and traditional rigid methods was implemented in terms of interface structure, amino acid composition, interface area and interaction force, etc. The results indicate that this method is more reasonable because it incorporates the specificity of different complexes by extracting the important residues lost by rigid distance methods and discarding some redundant residues. Finally, to further test our double minimum-distance definition strategy, we developed a classifier to predict those binding sites derived from our new method by using structural features and a random forest machine learning algorithm. The model achieved a satisfactory prediction performance and the accuracy on independent data sets reaches to 85.0%. To the best of our knowledge, it is the first prediction model to define positive and negative samples using a flexible cutoff. So the comparison analysis and modeling results have demonstrated that our method would be a very promising strategy for more precisely defining protein–RNA binding sites.     

On the fly estimation of host–guest binding free energies using the movable type method: participation in the SAMPL5 blind challenge

We review our performance in the SAMPL5 challenge for predicting host–guest binding affinities using the movable type (MT) method. The challenge included three hosts, acyclic Cucurbit[2]uril and two octa-acids with and without methylation at the entrance to their binding cavities. Each host was associated with 6–10 guest molecules. The MT method extrapolates local energy landscapes around particular molecular states and estimates the free energy by Monte Carlo integration over these landscapes. Two blind submissions pairing MT with variants of the KECSA potential function yielded mean unsigned errors of 1.26 and 1.53 kcal/mol for the non-methylated octa-acid, 2.83 and 3.06 kcal/mol for the methylated octa-acid, and 2.77 and 3.36 kcal/mol for Cucurbit[2]uril host. While our results are in reasonable agreement with experiment, we focused on particular cases in which our estimates gave incorrect results, particularly with regard to association between the octa-acids and an adamantane derivative. Working on the hypothesis that differential solvation effects play a role in effecting computed binding affinities for the parent octa-acid and the methylated octa-acid and that the ligands bind inside the pockets (rather than on the surface) we devised a new solvent accessible surface area term to better quantify solvation energy contributions in MT based studies. To further explore this issue a, molecular dynamics potential of mean force (PMF) study indicates that, as found by our docking calculations, the stable binding mode for this ligand is inside (rather than surface bound) the octa-acid cavity whether the entrance is methylated or not. The PMF studies also obtained the correct order for the methylation-induced change in binding affinities and associated the difference, to a large extent to differential solvation effects. Overall, the SAMPL5 challenge yielded in improvements our solvation modeling and also demonstrated the need for thorough validation of input data integrity prior to any computational analysis.     

Assessing protein–ligand binding modes with computational tools: the case of PDE4B

In a first step in the discovery of novel potent inhibitor structures for the PDE4B family with limited side effects, we present a protocol to rank newly designed molecules through the estimation of their IC\(_{50}\) values. Our protocol is based on reproducing the linear relationship between the logarithm of experimental IC\(_{50}\) values [\(\log\)(IC\(_{50}\))] and their calculated binding free energies (\(\Delta G_\mathrm{binding}\)). From 13 known PDE4B inhibitors, we show here that (1) binding free energies obtained after a docking process by AutoDock are not accurate enough to reproduce this linear relationship; (2) MM-GB/SA post-processing of molecular dynamics (MD) trajectories of the top ranked AutoDock pose improves the linear relationship; (3) by taking into account all representative structures obtained by AutoDock and by averaging MM-GB/SA computations on a series of 40 independent MD trajectories, a linear relationship between \(\log\)(IC\(_{50}\)) and the lowest \(\Delta G_\mathrm{binding}\) is achieved with \(R^2=0.944\).     

Identification of a lacosamide binding protein using an affinity bait and chemical reporter strategy: 14-3-3 ζ

We have advanced a useful strategy to elucidate binding partners of ligands (drugs) with modest binding affinity. Key to this strategy is attaching to the ligand an affinity bait (AB) and a chemical reporter (CR) group, where the AB irreversibly attaches the ligand to the receptor upon binding and the CR group is employed for receptor detection and isolation. We have tested this AB&CR strategy using lacosamide ((R)-1), a low-molecular-weight antiepileptic drug. We demonstrate that using a (R)-lacosamide AB&CR agent ((R)-2) 14-3-3 ζ in rodent brain soluble lysates is preferentially adducted, adduction is stereospecific with respect to the AB&CR agent, and adduction depends upon the presence of endogenous levels of the small molecule metabolite xanthine. Substitution of lacosamide AB agent ((R)-5) for (R)-2 led to the identification of the 14-3-3 ζ adduction site (K120) by mass spectrometry. Competition experiments using increasing amounts of (R)-1 in the presence of (R)-2 demonstrated that (R)-1 binds at or near the (R)-2 modification site on 14-3-3 ζ. Structure-activity studies of xanthine derivatives provided information concerning the likely binding interaction between this metabolite and recombinant 14-3-3 ζ. Documentation of the 14-3-3 ζ-xanthine interaction was obtained with isothermal calorimetry using xanthine and the xanthine analogue 1,7-dimethylxanthine.