Cheminformatics meets molecular mechanics: a combined application of knowledge-based pose scoring and physical force field-based hit scoring functions improves the accuracy of structure-based virtual screening

Poor performance of scoring functions is a well-known bottleneck in structure-based virtual screening (VS), which is most frequently manifested in the scoring functions' inability to discriminate between true ligands vs known nonbinders (therefore designated as binding decoys). This deficiency leads to a large number of false positive hits resulting from VS. We have hypothesized that filtering out or penalizing docking poses recognized as non-native (i.e., pose decoys) should improve the performance of VS in terms of improved identification of true binders. Using several concepts from the field of cheminformatics, we have developed a novel approach to identifying pose decoys from an ensemble of poses generated by computational docking procedures. We demonstrate that the use of target-specific pose (scoring) filter in combination with a physical force field-based scoring function (MedusaScore) leads to significant improvement of hit rates in VS studies for 12 of the 13 benchmark sets from the clustered version of the Database of Useful Decoys (DUD). This new hybrid scoring function outperforms several conventional structure-based scoring functions, including XSCORE::HMSCORE, ChemScore, PLP, and Chemgauss3, in 6 out of 13 data sets at early stage of VS (up 1% decoys of the screening database). We compare our hybrid method with several novel VS methods that were recently reported to have good performances on the same DUD data sets. We find that the retrieved ligands using our method are chemically more diverse in comparison with two ligand-based methods (FieldScreen and FLAP::LBX). We also compare our method with FLAP::RBLB, a high-performance VS method that also utilizes both the receptor and the cognate ligand structures. Interestingly, we find that the top ligands retrieved using our method are highly complementary to those retrieved using FLAP::RBLB, hinting effective directions for best VS applications. We suggest that this integrative VS approach combining cheminformatics and molecular mechanics methodologies may be applied to a broad variety of protein targets to improve the outcome of structure-based drug discovery studies.     

Machine learning optimization of cross docking accuracy

Performance of small molecule automated docking programs has conceptually been divided into docking -, scoring -, ranking - and screening power, which focuses on the crystal pose prediction, affinity prediction, ligand ranking and database screening capabilities of the docking program, respectively. Benchmarks show that different docking programs can excel in individual benchmarks which suggests that the scoring function employed by the programs can be optimized for a particular task. Here the scoring function of Smina is re-optimized towards enhancing the docking power using a supervised machine learning approach and a manually curated database of ligands and cross docking receptor pairs. The optimization method does not need associated binding data for the receptor-ligand examples used in the data set and works with small train sets. The re-optimization of the weights for the scoring function results in a similar docking performance with regard to docking power towards a cross docking test set. A ligand decoy based benchmark indicates a better discrimination between poses with high and low RMSD. The reported parameters for Smina are compatible with Autodock Vina and represent ready-to-use alternative parameters for researchers who aim at pose prediction rather than affinity prediction.     

GalaxyDock BP2 score: a hybrid scoring function for accurate protein–ligand docking

Protein–ligand docking is a useful tool for providing atomic-level understanding of protein functions in nature and design principles for artificial ligands or proteins with desired properties. The ability to identify the true binding pose of a ligand to a target protein among numerous possible candidate poses is an essential requirement for successful protein–ligand docking. Many previously developed docking scoring functions were trained to reproduce experimental binding affinities and were also used for scoring binding poses. However, in this study, we developed a new docking scoring function, called GalaxyDock BP2 Score, by directly training the scoring power of binding poses. This function is a hybrid of physics-based, empirical, and knowledge-based score terms that are balanced to strengthen the advantages of each component. The performance of the new scoring function exhibits significant improvement over existing scoring functions in decoy pose discrimination tests. In addition, when the score is used with the GalaxyDock2 protein–ligand docking program, it outperformed other state-of-the-art docking programs in docking tests on the Astex diverse set, the Cross2009 benchmark set, and the Astex non-native set. GalaxyDock BP2 Score and GalaxyDock2 with this score are freely available at http://galaxy.seoklab.org/softwares/galaxydock.html.     

Are predefined decoy sets of ligand poses able to quantify scoring function accuracy?

Due to the large number of different docking programs and scoring functions available, researchers are faced with the problem of selecting the most suitable one when starting a structure-based drug discovery project. To guide the decision process, several studies comparing different docking and scoring approaches have been published. In the context of comparing scoring function performance, it is common practice to use a predefined, computer-generated set of ligand poses (decoys) and to reevaluate their score using the set of scoring functions to be compared. But are predefined decoy sets able to unambiguously evaluate and rank different scoring functions with respect to pose prediction performance? This question arose when the pose prediction performance of our piecewise linear potential derived scoring functions (Korb et al. in J Chem Inf Model 49:84–96, 2009) was assessed on a standard decoy set (Cheng et al. in J Chem Inf Model 49:1079–1093, 2009). While they showed excellent pose identification performance when they were used for rescoring of the predefined decoy conformations, a pronounced degradation in performance could be observed when they were directly applied in docking calculations using the same test set. This implies that on a discrete set of ligand poses only the rescoring performance can be evaluated. For comparing the pose prediction performance in a more rigorous manner, the search space of each scoring function has to be sampled extensively as done in the docking calculations performed here. We were able to identify relative strengths and weaknesses of three scoring functions (ChemPLP, GoldScore, and Astex Statistical Potential) by analyzing the performance for subsets of the complexes grouped by different properties of the active site. However, reasons for the overall poor performance of all three functions on this test set compared to other test sets of similar size could not be identified.     

Structure-based virtual screening with supervised consensus scoring: evaluation of pose prediction and enrichment factors

Since the evaluation of ligand conformations is a crucial aspect of structure-based virtual screening, scoring functions play significant roles in it. However, it is known that a scoring function does not always work well for all target proteins. When one cannot know which scoring function works best against a target protein a priori, there is no standard scoring method to know it even if 3D structure of a target protein-ligand complex is available. Therefore, development of the method to achieve high enrichments from given scoring functions and 3D structure of protein-ligand complex is a crucial and challenging task. To address this problem, we applied SCS (supervised consensus scoring), which employs a rough linear correlation between the binding free energy and the root-mean-square deviation (rmsd) of a native ligand conformations and incorporates protein-ligand binding process with docked ligand conformations using supervised learning, to virtual screening. We evaluated both the docking poses and enrichments of SCS and five scoring functions (F-Score, G-Score, D-Score, ChemScore, and PMF) for three different target proteins: thymidine kinase (TK), thrombin (thrombin), and peroxisome proliferator-activated receptor gamma (PPARgamma). Our enrichment studies show that SCS is competitive or superior to a best single scoring function at the top ranks of screened database. We found that the enrichments of SCS could be limited by a best scoring function, because SCS is obtained on the basis of the five individual scoring functions. Therefore, it is concluded that SCS works very successfully from our results. Moreover, from docking pose analysis, we revealed the connection between enrichment and average centroid distance of top-scored docking poses. Since SCS requires only one 3D structure of protein-ligand complex, SCS will be useful for identifying new ligands.     

The ensemble performance index: an improved measure for assessing ensemble pose prediction performance

We present a theoretical study on the performance of ensemble docking methodologies considering multiple protein structures. We perform a theoretical analysis of pose prediction experiments which is completely unbiased, as we make no assumptions about specific scoring functions, search paradigms, protein structures, or ligand data sets. We introduce a novel interpretable measure, the ensemble performance index (EPI), for the assessment of scoring performance in ensemble docking, which will be applied to simulated and real data sets.     

Pose prediction and virtual screening performance of GOLD scoring functions in a standardized test

The performance of all four GOLD scoring functions has been evaluated for pose prediction and virtual screening under the standardized conditions of the comparative docking and scoring experiment reported in this Edition. Excellent pose prediction and good virtual screening performance was demonstrated using unmodified protein models and default parameter settings. The best performing scoring function for both pose prediction and virtual screening was demonstrated to be the recently introduced scoring function ChemPLP. We conclude that existing docking programs already perform close to optimally in the cognate pose prediction experiments currently carried out and that more stringent pose prediction tests should be used in the future. These should employ cross-docking sets. Evaluation of virtual screening performance remains problematic and much remains to be done to improve the usefulness of publically available active and decoy sets for virtual screening. Finally we suggest that, for certain target/scoring function combinations, good enrichment may sometimes be a consequence of 2D property recognition rather than a modelling of the correct 3D interactions.     

Optimizing fragment and scaffold docking by use of molecular interaction fingerprints

Protein-ligand interaction fingerprints have been used to postprocess docking poses of three ligand data sets: a set of 40 low-molecular-weight compounds from the Protein Data Bank, a collection of 40 scaffolds from pharmaceutically relevant protein ligands, and a database of 19 scaffolds extracted from true cdk2 inhibitors seeded in 2230 scaffold decoys. Four popular docking tools (FlexX, Glide, Gold, and Surflex) were used to generate poses for ligands of the three data sets. In all cases, scoring by the similarity of interaction fingerprints to a given reference was statistically superior to conventional scoring functions in posing low-molecular-weight fragments, predicting protein-bound scaffold coordinates according to the known binding mode of related ligands, and screening a scaffold library to enrich a hit list in true cdk2-targeted scaffolds.     

Optimizing the signal-to-noise ratio of scoring functions for protein--ligand docking

Empirical scoring functions provide estimates of the free energy of protein-ligand binding in situations when atomic-scale simulations are intractable, for example, in virtual high-throughput screening. Currently, such scoring functions are often inaccurate, and further improvements are complicated by the lack of reliable training data, the complex interplay between scoring functions and docking algorithms, and an inconsistent statistical treatment of positive and negative training data. In comparison to various other performance measures of scoring functions, "analysis of variance" provides a well-behaved objective function for optimization, which focuses on the signal-to-noise ratio of ligand-decoy discrimination. In combination with a large database of ligands and decoys, an in situ optimization of scoring function parameters was able to generate improved, target-specific scoring functions for three different proteins of pharmaceutical interest: cyclin-dependent kinase 2, the estrogen receptor, and cyclooxygenase-2. Statistical analysis of the improvements observed in "receiver-operating characteristic" curves showed that the optimized scoring functions achieved a significantly (between p < 0.0001 and p < 0.05) higher enrichment of true ligands. A scaffold dependence of the resulting binding modes was observed, which is discussed in conjunction with the rigid receptor hypothesis commonly made in protein-ligand docking. In summary, the approach described here represents a well-adapted statistical method for setting up scoring functions.     

Ligand-biased ensemble receptor docking (LigBEnD): a hybrid ligand/receptor structure-based approach

Ligand docking to flexible protein molecules can be efficiently carried out through ensemble docking to multiple protein conformations, either from experimental X-ray structures or from in silico simulations. The success of ensemble docking often requires the careful selection of complementary protein conformations, through docking and scoring of known co-crystallized ligands. False positives, in which a ligand in a wrong pose achieves a better docking score than that of native pose, arise as additional protein conformations are added. In the current study, we developed a new ligand-biased ensemble receptor docking method and composite scoring function which combine the use of ligand-based atomic property field (APF) method with receptor structure-based docking. This method helps us to correctly dock 30 out of 36 ligands presented by the D3R docking challenge. For the six mis-docked ligands, the cognate receptor structures prove to be too different from the 40 available experimental Pocketome conformations used for docking and could be identified only by receptor sampling beyond experimentally explored conformational subspace.     

Supervised consensus scoring for docking and virtual screening

Docking programs are widely used to discover novel ligands efficiently and can predict protein-ligand complex structures with reasonable accuracy and speed. However, there is an emerging demand for better performance from the scoring methods. Consensus scoring (CS) methods improve the performance by compensating for the deficiencies of each scoring function. However, conventional CS and existing scoring functions have the same problems, such as a lack of protein flexibility, inadequate treatment of salvation, and the simplistic nature of the energy function used. Although there are many problems in current scoring functions, we focus our attention on the incorporation of unbound ligand conformations. To address this problem, we propose supervised consensus scoring (SCS), which takes into account protein-ligand binding process using unbound ligand conformations with supervised learning. An evaluation of docking accuracy for 100 diverse protein-ligand complexes shows that SCS outperforms both CS and 11 scoring functions (PLP, F-Score, LigScore, DrugScore, LUDI, X-Score, AutoDock, PMF, G-Score, ChemScore, and D-score). The success rates of SCS range from 89% to 91% in the range of rmsd < 2 A, while those of CS range from 80% to 85%, and those of the scoring functions range from 26% to 76%. Moreover, we also introduce a method for judging whether a compound is active or inactive with the appropriate criterion for virtual screening. SCS performs quite well in docking accuracy and is presumably useful for screening large-scale compound databases before predicting binding affinity.     

Validation studies of the site-directed docking program LibDock

The performance of the site-features docking algorithm LibDock has been evaluated across eight GlaxoSmithKline targets as a follow-up to a broad validation study of docking and scoring software (Warren, G. L.; Andrews, W. C.; Capelli, A.; Clarke, B.; Lalonde, J.; Lambert, M. H.; Lindvall, M.; Nevins, N.; Semus, S. F.; Senger, S.; Tedesco, G.; Walls, I. D.; Woolven, J. M.; Peishoff, C. E.; Head, M. S. J. Med. Chem. 2006, 49, 5912-5931). Docking experiments were performed to assess both the accuracy in reproducing the binding mode of the ligand and the retrieval of active compounds in a virtual screening protocol using both the DJD (Diller, D. J.; Merz, K. M., Jr. Proteins 2001, 43, 113-124) and LigScore2 (Krammer, A. K.; Kirchoff, P. D.; Jiang, X.; Venkatachalam, C. M.; Waldman, M. J. Mol. Graphics Modell. 2005, 23, 395-407) scoring functions. This study was conducted using DJD scoring, and poses were rescored using all available scoring functions in the Accelrys LigandFit module, including LigScore2. For six out of eight targets at least 30% of the ligands were docked within a root-mean-square difference (RMSD) of 2.0 A for the crystallographic poses when the LigScore2 scoring function was used. LibDock retrieved at least 20% of active compounds in the top 10% of screened ligands for four of the eight targets in the virtual screening protocol. In both studies the LigScore2 scoring function enhanced the retrieval of crystallographic poses or active compounds in comparison with the results obtained using the DJD scoring function. The results for LibDock accuracy and ligand retrieval in virtual screening are compared to 10 other docking and scoring programs. These studies demonstrate the utility of the LigScore2 scoring function and that LibDock as a feature directed docking method performs as well as docking programs that use genetic/growing and Monte Carlo driven algorithms.     

Surflex-Dock: Docking benchmarks and real-world application

Benchmarks for molecular docking have historically focused on re-docking the cognate ligand of a well-determined protein-ligand complex to measure geometric pose prediction accuracy, and measurement of virtual screening performance has been focused on increasingly large and diverse sets of target protein structures, cognate ligands, and various types of decoy sets. Here, pose prediction is reported on the Astex Diverse set of 85 protein ligand complexes, and virtual screening performance is reported on the DUD set of 40 protein targets. In both cases, prepared structures of targets and ligands were provided by symposium organizers. The re-prepared data sets yielded results not significantly different than previous reports of Surflex-Dock on the two benchmarks. Minor changes to protein coordinates resulting from complex pre-optimization had large effects on observed performance, highlighting the limitations of cognate ligand re-docking for pose prediction assessment. Docking protocols developed for cross-docking, which address protein flexibility and produce discrete families of predicted poses, produced substantially better performance for pose prediction. Performance on virtual screening performance was shown to benefit by employing and combining multiple screening methods: docking, 2D molecular similarity, and 3D molecular similarity. In addition, use of multiple protein conformations significantly improved screening enrichment.     

Improving binding mode and binding affinity predictions of docking by ligand-based search of protein conformations: evaluation in D3R grand challenge 2015

The growing number of protein–ligand complex structures, particularly the structures of proteins co-bound with different ligands, in the Protein Data Bank helps us tackle two major challenges in molecular docking studies: the protein flexibility and the scoring function. Here, we introduced a systematic strategy by using the information embedded in the known protein–ligand complex structures to improve both binding mode and binding affinity predictions. Specifically, a ligand similarity calculation method was employed to search a receptor structure with a bound ligand sharing high similarity with the query ligand for the docking use. The strategy was applied to the two datasets (HSP90 and MAP4K4) in recent D3R Grand Challenge 2015. In addition, for the HSP90 dataset, a system-specific scoring function (ITScore2_hsp90) was generated by recalibrating our statistical potential-based scoring function (ITScore2) using the known protein–ligand complex structures and the statistical mechanics-based iterative method. For the HSP90 dataset, better performances were achieved for both binding mode and binding affinity predictions comparing with the original ITScore2 and with ensemble docking. For the MAP4K4 dataset, although there were only eight known protein–ligand complex structures, our docking strategy achieved a comparable performance with ensemble docking. Our method for receptor conformational selection and iterative method for the development of system-specific statistical potential-based scoring functions can be easily applied to other protein targets that have a number of protein–ligand complex structures available to improve predictions on binding.     

CRDOCK: An Ultrafast Multipurpose Protein-Ligand Docking Tool

An ultrafast docking and virtual screening program, CRDOCK, is presented that contains (1) a search engine that can use a variety of sampling methods and an initial energy evaluation function, (2) several energy minimization algorithms for fine tuning the binding poses, and (3) different scoring functions. This modularity ensures the easy configuration of custom-made protocols that can be optimized depending on the problem in hand. CRDOCK employs a precomputed library of ligand conformations that are initially generated from one-dimensional SMILES strings. Testing CRDOCK on two widely used benchmarks, the ASTEX diverse set and the Directory of Useful Decoys, yielded a success rate of ～75% in pose prediction and an average AUC of 0.66. A typical ligand can be docked, on average, in just ～13 s. Extension to a representative group of pharmacologically relevant G protein-coupled receptors that have been recently cocrystallized with some selective ligands allowed us to demonstrate the utility of this tool and also highlight some current limitations. CRDOCK is now included within VSDMIP, our integrated platform for drug discovery.     

Potential and limitations of ensemble docking

A major problem in structure-based virtual screening applications is the appropriate selection of a single or even multiple protein structures to be used in the virtual screening process. A priori it is unknown which protein structure(s) will perform best in a virtual screening experiment. We investigated the performance of ensemble docking, as a function of ensemble size, for eight targets of pharmaceutical interest. Starting from single protein structure docking results, for each ensemble size up to 500,000 combinations of protein structures were generated, and, for each ensemble, pose prediction and virtual screening results were derived. Comparison of single to multiple protein structure results suggests improvements when looking at the performance of the worst and the average over all single protein structures to the performance of the worst and average over all protein ensembles of size two or greater, respectively. We identified several key factors affecting ensemble docking performance, including the sampling accuracy of the docking algorithm, the choice of the scoring function, and the similarity of database ligands to the cocrystallized ligands of ligand-bound protein structures in an ensemble. Due to these factors, the prospective selection of optimum ensembles is a challenging task, shown by a reassessment of published ensemble selection protocols.     

Maximum common binding modes (MCBM): consensus docking scoring using multiple ligand information and interaction fingerprints

Improving the scoring functions for small molecule-protein docking is a highly challenging task in current computational drug design. Here we present a novel consensus scoring concept for the prediction of binding modes for multiple known active ligands. Similar ligands are generally believed to bind to their receptor in a similar fashion. The presumption of our approach was that the true binding modes of similar ligands should be more similar to each other compared to false positive binding modes. The number of conserved (consensus) interactions between similar ligands was used as a docking score. Patterns of interactions were modeled using ligand receptor interaction fingerprints. Our approach was evaluated for four different data sets of known cocrystal structures (CDK-2, dihydrofolate reductase, HIV-1 protease, and thrombin). Docking poses were generated with FlexX and rescored by our approach. For comparison the CScore scoring functions from Sybyl were used, and consensus scores were calculated thereof. Our approach performed better than individual scoring functions and was comparable to consensus scoring. Analysis of the distribution of docking poses by self-organizing maps (SOM) and interaction fingerprints confirmed that clusters of docking poses composed of multiple ligands were preferentially observed near the native binding mode. Being conceptually unrelated to commonly used docking scoring functions our approach provides a powerful method to complement and improve computational docking experiments.     

Improving molecular docking through eHiTS’ tunable scoring function

We present three complementary approaches for score-tuning that improve docking performance in pose prediction, virtual screening and binding affinity assessment. The methodology utilizes experimental data to customize the scoring function for the system of interest considering the specific docking scenario. The tuning approach, which has been implemented as an automated utility in eHiTS, is introduced as a solution to one of the conundrums of the molecular docking paradigm, namely, the lack of a universally well performing scoring function. The accuracy of scoring functions has been shown to be generally system-dependent, and particularly lacking for binding energy and bio-activity predictions. In the proposed approach, pose and energy predictions are enhanced by adjusting the relative weights of the eHiTS energy terms to improve score-RMSD or score-affinity correlations. In a virtual screening context ligand-based similarity is used to rescale the docking score such that better enrichment factors are achieved. We discuss the algorithmic details of the methods, and demonstrate the effects of score tuning on a variety of targets, including CDK2, BACE1 and neuraminidase, as well as on the popular benchmarks—the Directory of Useful Decoys and the PDBBind database.     

Validation of an empirical RNA-ligand scoring function for fast flexible docking using RiboDock®

We report the design and validation of a fast empirical function for scoring RNA-ligand interactions, and describe its implementation within RiboDock, a virtual screening system for automated flexible docking. Building on well-known protein-ligand scoring function foundations, features were added to describe the interactions of common RNA-binding functional groups that were not handled adequately by conventional terms, to disfavour non-complementary polar contacts, and to control non-specific charged interactions. The results of validation experiments against known structures of RNA-ligand complexes compare favourably with previously reported methods. Binding modes were well predicted in most cases and good discrimination was achieved between native and non-native ligands for each binding site, and between native and non-native binding sites for each ligand. Further evidence of the ability of the method to identify true RNA binders is provided by compound selection ('enrichment factor') experiments based around a series of HIV-1 TAR RNA-binding ligands. Significant enrichment in true binders was achieved amongst high scoring docking hits, even when selection was from a library of structurally related, positively charged molecules. Coupled with a semi-automated cavity detection algorithm for identification of putative ligand binding sites, also described here, the method is suitable for the screening of very large databases of molecules against RNA and RNA-protein interfaces, such as those presented by the bacterial ribosome.