Binding Affinity Of Protein-ligand Complex Research Articles

Machine Learning Predicts 1-[(4-Fluorophenyl) Methyl] Indole-2,3- Dione as Drug Lead for Peptide Deformylase in Plasmodium falciparum

Malaria continues to be a serious illness for world health. Deadly parasites that cause malaria infect female Anopheles mosquitoes and bite humans are the disease's vector. Since Plasmodium falciparum is the deadliest of the five Plasmodium species and research indicates that medicines for malaria are increasingly revealing drug-resistance mechanisms, it is imperative that new and effective medications be developed. This project aims to identify and produce a novel therapeutic lead against a P. falciparum target that has been validated. Target2Scan, a programmed tool, was employed in this investigation to find potential therapeutic targets for P. falciparum peptide deformylase. After the tool received the target signature, it ran a BLAST methodology to find targets that resembled peptide deformylase. To ascertain the binding affinities of protein-ligand complexes, molecular docking was performed using PyRx and CBDock. Of the 12,561 compounds produced, 11,304 were used as the training set and 1,256 as the test set. Six ligands were produced by machine learning as potential therapeutic leads, and using molecular docking, 1-[(4-fluorophenyl) methyl] indole-2,3-dione showed the greatest biding effect on peptide deformylase when compared to 5-chloro-1-(2-phenylethyl) indole-2,3-dione. The higher binding affinity of 1-[(4-fluorophenyl) methyl] indole-2,3-dione over 5-chloro-1-(2-phenylethyl) indole-2,3-dione and other ligands on peptide deformylase suggests that it has the ability to suppress P. falciparum pepide deformylase activity.

GraphLambda: Fusion Graph Neural Networks for Binding Affinity Prediction.

Predicting the binding affinity of protein-ligand complexes is crucial for computer-aided drug discovery (CADD) and the identification of potential drug candidates. The deep learning-based scoring functions have emerged as promising predictors of binding constants. Building on recent advancements in graph neural networks, we present graphLambda for protein-ligand binding affinity prediction, which utilizes graph convolutional, attention, and isomorphism blocks to enhance the predictive capabilities. The graphLambda model exhibits superior performance across CASF16 and CSAR HiQ NRC benchmarks and demonstrates robustness with respect to different types of train-validation set partitions. The development of graphLambda underscores the potential of graph neural networks in advancing binding affinity prediction models, contributing to more effective CADD methodologies.

Exploring protein-ligand binding affinity prediction with electron density-based geometric deep learning.

Rational structure-based drug design relies on accurate predictions of protein-ligand binding affinity from structural molecular information. Although deep learning-based methods for predicting binding affinity have shown promise in computational drug design, certain approaches have faced criticism for their potential to inadequately capture the fundamental physical interactions between ligands and their macromolecular targets or for being susceptible to dataset biases. Herein, we propose to include bond-critical points based on the electron density of a protein-ligand complex as a fundamental physical representation of protein-ligand interactions. Employing a geometric deep learning model, we explore the usefulness of these bond-critical points to predict absolute binding affinities of protein-ligand complexes, benchmark model performance against existing methods, and provide a critical analysis of this new approach. The models achieved root-mean-squared errors of 1.4-1.8 log units on the PDBbind dataset, and 1.0-1.7 log units on the PDE10A dataset, not indicating significant advantages over benchmark methods, and thus rendering the utility of electron density for deep learning models context-dependent. The relationship between intermolecular electron density and corresponding binding affinity was analyzed, and Pearson correlation coefficients r > 0.7 were obtained for several macromolecular targets.

Repurposing Antipsychotic Agents Against Targets Of Angiogenesis Pathways For Cancer Therapy: An In-Silico Approach.

Antipsychotics interfere with virtually all hallmarks of cancer, including angiogenesis. Vascular endothelial growth factor receptors (VEGFRs) and platelet-derived growth receptors (PDGFRs) play crucial roles in angiogenesis and represent targets of many anti-cancer agents. We assessed and compared the binding effects of antipsychotics and receptor tyrosine kinase inhibitors (RTKIs) on VEGFR2 and PDGFRα. FDA-approved antipsychotics and RTKIs were retrieved from DrugBank. VEGFR2 and PDGFRα structures were obtained from Protein Data Bank and loaded on Biovia Discovery Studio software to remove nonstandard molecules. Molecular docking was carried out using PyRx and CB-Dock to determine the binding affinities of protein-ligand complexes. Risperidone exerted the highest binding effect on PDGFRα (-11.0 Kcal/mol) as compared to other antipsychotic drugs and RTKIs. Risperidone also demonstrated a stronger binding effect on VEGFR2 (-9.6 Kcal/mol) than the RTKIs, pazopanib (-8.7 Kcal/mol), axitinib (-9.3 Kcal/mol), vandetanib (-8.3 Kcal/mol), lenvatinib ( -7.6 Kcal/mol) and sunitinib (-8.3 Kcal/mol). Sorafenib (an RTKI), however, exhibited the highest VEGFR2 binding affinity of 11.7 Kcal/mol. Risperidone's superior binding affinity with PDGFRα when compared to all reference RTKIs and antipsychotic drugs, as well as its stronger binding effect on VEGFR2 over the RTKIs, sunitinib, pazopanib, axitinib, vandetanib, and lenvatinib, imply that it could be repurposed to inhibit angiogenic pathways and subjected to pre-clinical and clinical trials for cancer therapy.

Toward Simple, Predictive Understanding of Protein-Ligand Interactions: Electronic Structure Calculations on Torpedo Californica Acetylcholinesterase Join Forces with the Chemist\u2019s Intuition

Contemporary efforts for empirically-unbiased modeling of protein-ligand interactions entail a painful tradeoff – as reliable information on both noncovalent binding factors and the dynamic behavior of a protein-ligand complex is often beyond practical limits. We demonstrate that information drawn exclusively from static molecular structures can be used for reproducing and predicting experimentally-measured binding affinities for protein-ligand complexes. In particular, inhibition constants (Ki) were calculated for seven different competitive inhibitors of Torpedo californica acetylcholinesterase using a multiple-linear-regression-based model. The latter, incorporating five independent variables – drawn from QM cluster, DLPNO-CCSD(T) calculations and LED analyses on the seven complexes, each containing active amino-acid residues found within interacting distance (3.5 Å) from the corresponding ligand – is shown to recover 99.9% of the sum of squares for measured Ki values, while having no statistically-significant residual errors. Despite being fitted to a small number of data points, leave-one-out cross-validation statistics suggest that it possesses surprising predictive value (Q2LOO=0.78, or 0.91 upon removal of a single outlier). This thus challenges ligand-invariant definitions of active sites, such as implied in the lock-key binding theory, as well as in alternatives highlighting shape-complementarity without taking electronic effects into account. Broader implications of the current work are discussed in dedicated appendices.

RosENet: Improving Binding Affinity Prediction by Leveraging Molecular Mechanics Energies with an Ensemble of 3D Convolutional Neural Networks.

The worldwide increase and proliferation of drug resistant microbes, coupled with the lag in new drug development, represents a major threat to human health. In order to reduce the time and cost for exploring the chemical search space, drug discovery increasingly relies on computational biology approaches. One key step in these approaches is the need for the rapid and accurate prediction of the binding affinity for potential leads. Here, we present RosENet (Rosetta Energy Neural Networks), an ensemble of three-dimensional (3D) Convolutional Neural Networks (CNNs), which combines voxelized molecular mechanics energies and molecular descriptors for predicting the absolute binding affinity of protein-ligand complexes. By leveraging the physicochemical properties captured by the molecular force field, our ensemble model achieved a Root Mean Square Error (RMSE) of 1.24 on the PDBBind v2016 core set. We also explored some limitations and the robustness of the PDBBind data set and our approach on nearly 500 structures, including structures determined by Nuclear Magnetic Resonance and virtual screening experiments. Our study demonstrated that molecular mechanics energies can be voxelized and used to help improve the predictive power of the CNNs. In the future, our framework can be extended to features extracted from other biophysical and biochemical models, such as molecular dynamics simulations.

Taba: A Tool to Analyze the Binding Affinity

Evaluation of ligand-binding affinity using the atomic coordinates of a protein-ligand complex is a challenge from the computational point of view. The availability of crystallographic structures of complexes with binding affinity data opens the possibility to create machine-learning models targeted to a specific protein system. Here, we describe a new methodology that combines a mass-spring system approach with supervised machine-learning techniques to predict the binding affinity of protein-ligand complexes. The combination of these techniques allows exploring the scoring function space, generating a model targeted to a protein system of interest. The new model shows superior predictive performance when compared with classical scoring functions implemented in the programs Molegro Virtual Docker, AutoDock4, and AutoDock Vina. We implemented this methodology in a new program named Taba. Taba is implemented in Python and available to download under the GNU license at https://github.com/azevedolab/taba. © 2019 Wiley Periodicals, Inc.

Descriptor Data Bank (DDB): A Cloud Platform for Multiperspective Modeling of Protein-Ligand Interactions.

Protein-ligand (PL) interactions play a key role in many life processes such as molecular recognition, molecular binding, signal transmission, and cell metabolism. Examples of interaction forces include hydrogen bonding, hydrophobic effects, steric clashes, electrostatic contacts, and van der Waals attractions. Currently, a large number of hypotheses and perspectives to model these interaction forces are scattered throughout the literature and largely forgotten. Instead, had they been assembled and utilized collectively, they would have substantially improved the accuracy of predicting binding affinity of protein-ligand complexes. In this work, we present Descriptor Data Bank (DDB), a data-driven platform on the cloud for facilitating multiperspective modeling of PL interactions. DDB is an open-access hub for depositing, hosting, executing, and sharing descriptor extraction tools and data for a large number of interaction modeling hypotheses. The platform also implements a machine-learning (ML) toolbox for automatic descriptor filtering and analysis and scoring function (SF) fitting and prediction. The descriptor filtering module is used to filter out irrelevant and/or noisy descriptors and to produce a compact subset from all available features. We seed DDB with 16 diverse descriptor extraction tools developed in-house and collected from the literature. The tools altogether generate over 2700 descriptors that characterize (i) proteins, (ii) ligands, and (iii) protein-ligand complexes. The in-house descriptors we extract are protein-specific which are based on pairwise primary and tertiary alignment of protein structures followed by clustering and trilateration. We built and used DDB's ML library to fit SFs to the in-house descriptors and those collected from the literature. We then evaluated them on several data sets that were constructed to reflect real-world drug screening scenarios. We found that multiperspective SFs that were constructed using a large number of diverse DDB descriptors capturing various PL interactions in different ways outperformed their single-perspective counterparts in all evaluation scenarios, with an average improvement of more than 15%. We also found that our proposed protein-specific descriptors improve the accuracy of SFs.

Dynamic undocking and the quasi-bound state as tools for drug discovery.

There is a pressing need for new technologies that improve the efficacy and efficiency of drug discovery. Structure-based methods have contributed towards this goal but they focus on predicting the binding affinity of protein-ligand complexes, which is notoriously difficult. We adopt an alternative approach that evaluates structural, rather than thermodynamic, stability. As bioactive molecules present a static binding mode, we devised dynamic undocking (DUck), a fast computational method to calculate the work necessary to reach a quasi-bound state at which the ligand has just broken the most important native contact with the receptor. This non-equilibrium property is surprisingly effective in virtual screening because true ligands form more-resilient interactions than decoys. Notably, DUck is orthogonal to docking and other 'thermodynamic' methods. We demonstrate the potential of the docking-undocking combination in a fragment screening against the molecular chaperone and oncology target Hsp90, for which we obtain novel chemotypes and a hit rate that approaches 40%.

A Self-Adaptive Steered Molecular Dynamics Method Based on Minimization of Stretching Force Reveals the Binding Affinity of Protein-Ligand Complexes.

Binding affinity prediction of protein–ligand complexes has attracted widespread interest. In this study, a self-adaptive steered molecular dynamics (SMD) method is proposed to reveal the binding affinity of protein–ligand complexes. The SMD method is executed through adjusting pulling direction to find an optimum trajectory of ligand dissociation, which is realized by minimizing the stretching force automatically. The SMD method is then used to simulate the dissociations of 19 common protein–ligand complexes which are derived from two homology families, and the binding free energy values are gained through experimental techniques. Results show that the proposed SMD method follows a different dissociation pathway with lower a rupture force and energy barrier when compared with the conventional SMD method, and further analysis indicates the rupture forces of the complexes in the same protein family correlate well with their binding free energy, which reveals the possibility of using the proposed SMD method to identify the active ligand.

BgN-Score and BsN-Score: bagging and boosting based ensemble neural networks scoring functions for accurate binding affinity prediction of protein-ligand complexes.

BackgroundAccurately predicting the binding affinities of large sets of protein-ligand complexes is a key challenge in computational biomolecular science, with applications in drug discovery, chemical biology, and structural biology. Since a scoring function (SF) is used to score, rank, and identify drug leads, the fidelity with which it predicts the affinity of a ligand candidate for a protein's binding site has a significant bearing on the accuracy of virtual screening. Despite intense efforts in developing conventional SFs, which are either force-field based, knowledge-based, or empirical, their limited predictive power has been a major roadblock toward cost-effective drug discovery. Therefore, in this work, we present novel SFs employing a large ensemble of neural networks (NN) in conjunction with a diverse set of physicochemical and geometrical features characterizing protein-ligand complexes to predict binding affinity.ResultsWe assess the scoring accuracies of two new ensemble NN SFs based on bagging (BgN-Score) and boosting (BsN-Score), as well as those of conventional SFs in the context of the 2007 PDBbind benchmark that encompasses a diverse set of high-quality protein families. We find that BgN-Score and BsN-Score have more than 25% better Pearson's correlation coefficient (0.804 and 0.816 vs. 0.644) between predicted and measured binding affinities compared to that achieved by a state-of-the-art conventional SF. In addition, these ensemble NN SFs are also at least 19% more accurate (0.804 and 0.816 vs. 0.675) than SFs based on a single neural network that has been traditionally used in drug discovery applications. We further find that ensemble models based on NNs surpass SFs based on the decision-tree ensemble technique Random Forests.ConclusionsEnsemble neural networks SFs, BgN-Score and BsN-Score, are the most accurate in predicting binding affinity of protein-ligand complexes among the considered SFs. Moreover, their accuracies are even higher when they are used to predict binding affinities of protein-ligand complexes that are related to their training sets.

Four-body atomic potential for modeling protein-ligand binding affinity: application to enzyme-inhibitor binding energy prediction

BackgroundModels that are capable of reliably predicting binding affinities for protein-ligand complexes play an important role the field of structure-guided drug design.MethodsHere, we begin by applying the computational geometry technique of Delaunay tessellation to each set of atomic coordinates for over 1400 diverse macromolecular structures, for the purpose of deriving a four-body statistical potential that serves as a topological scoring function. Next, we identify a second, independent set of three hundred protein-ligand complexes, having both high-resolution structures and known dissociation constants. Two-thirds of these complexes are randomly selected to train a predictive model of binding affinity as follows: two tessellations are generated in each case, one for the entire complex and another strictly for the isolated protein without its bound ligand, and a topological score is computed for each tessellation with the four-body potential. Predicted protein-ligand binding affinity is then based on an empirically derived linear function of the difference between both topological scores, one that appropriately scales the value of this difference.ResultsA comparison between experimental and calculated binding affinity values over the two hundred complexes reveals a Pearson's correlation coefficient of r = 0.79 with a standard error of SE = 1.98 kcal/mol. To validate the method, we similarly generated two tessellations for each of the remaining protein-ligand complexes, computed their topological scores and the difference between the two scores for each complex, and applied the previously derived linear transformation of this topological score difference to predict binding affinities. For these one hundred complexes, we again observe a correlation of r = 0.79 (SE = 1.93 kcal/mol) between known and calculated binding affinities. Applying our model to an independent test set of high-resolution structures for three hundred diverse enzyme-inhibitor complexes, each with an experimentally known inhibition constant, also yields a correlation of r = 0.79 (SE = 2.39 kcal/mol) between experimental and calculated binding energies.ConclusionsLastly, we generate predictions with our model on a diverse test set of one hundred protein-ligand complexes previously used to benchmark 15 related methods, and our correlation of r = 0.66 between the calculated and experimental binding energies for this dataset exceeds those of the other approaches. Compared with these related prediction methods, our approach stands out based on salient features that include the reliability of our model, combined with the rapidity of the generated predictions, which are less than one second for an average sized complex.

The First Total Synthesis Of Morusin And Himanimide D As Arachidonate 5-lipoxygenase Inhibitor In Automated Docking

Our research group has exhibited a long-standing interest in the synthesis and bioassay study of a number of unique natural products containing flavonoids, camphorataimides, and benzofurans. In previous works, we have shown that tumor suppressor protein p53 and p38 MAPK (mitogen activated protein kinase) play a prominent role in the caffaic acid phenethyl ester (CAPE) induced-apoptosis of C6 glioma cells. In addition, studies on the constituents of the Chinese crude drug “Sang-bai-pi” (Morus root bark) have been recorded in books of traditional Chinese herbal medicines, which are used as an antiphlogistic, a diuretic, an expectorant, and anti-hepatitis B activity. Herein, we present the first total synthesis of morusin and himanimide D, and then show the development of the COX/LOX inhibitors by an automated docking method. Morusin, which can be isolated from Chinese herbal medicine, is achieved in which the longest linear sequence is only 13 steps in 12% overall yield from commercially available phloroglucinol. In addition, to probe accessibility of the active sites of proteins, particular COXs/LOXs, the binding affinity of protein-ligand complexes were examined by an automated docking method. Consequently, the rationally optimized LEE-BNOHDM was identified as a potent inhibitor of the arachidonate 5-lipoxygenase.

SFCscore: Scoring functions for affinity prediction of protein–ligand complexes

Empirical scoring functions to calculate binding affinities of protein-ligand complexes have been calibrated based on experimental structure and affinity data collected from public and industrial sources. Public data were taken from the AffinDB database, whereas access to industrial data was gained through the Scoring Function Consortium (SFC), a collaborative effort with various pharmaceutical companies and the Cambridge Crystallographic Data Center. More than 850 complexes were obtained by the data collection procedure and subsequently used to setup different training sets for the parameterization of new scoring functions. Over 60 different descriptors were evaluated for all complexes, including terms accounting for interactions with and among aromatic ring systems as well as many surface-dependent terms. After exploratory correlation and regression analyses, stepwise variable selection procedures and systematic searches, the most suitable descriptors were chosen as variables to calibrate regression functions by means of multiple linear regression or partial least squares analysis. Eight different functions are presented herein. Cross-validated r(2) (Q(2)) values of up to 0.72 and standard errors (s(PRESS)) generally below 1.15 pK(i) units suggest highly predictive functions. Extensive unbiased validation was carried out by testing the functions on large data sets from the PDBbind database as used by Wang et al. (J Chem Inf Comput Sci 2004;44:2114-2125) in a comparative analysis of other scoring functions. Superior performance of the SFCscore functions is observed in many cases, but the results also illustrate the need for further improvements.

DrugScore meets CoMFA: adaptation of fields for molecular comparison (AFMoC) or how to tailor knowledge-based pair-potentials to a particular protein.

The development of a new tailor-made scoring function to predict binding affinities of protein-ligand complexes is described. Knowledge-based pair-potentials are specifically adapted to a particular protein by considering additional ligand-based information. The formalism applied to derive the new function is similar to the well-known CoMFA approach, however, the fields used in the approach originate from the protein environment (and not from the aligned ligands as in CoMFA, thus, a "reverse" CoMFA (= AFMoC) named Adaptation of Fields for Molecular Comparison is performed). A regular-spaced grid is placed into the binding site and knowledge-based pair-potentials between protein atoms and ligand atom probes are mapped onto the grid intersections resulting in "potential fields". By multiplying distance-dependent atom-type properties of actual ligands docked into the binding site with the neighboring grid values, "interaction fields" are produced from the original "potential fields". In a PLS analysis, these atom-type specific interaction fields are correlated to the actual binding affinities of the embedded ligands, resulting in individual weighting factors for each field value. As in CoMFA, the results of the analysis can be interpreted in graphical terms by contribution maps, and binding affinities of novel ligands are predicted by applying the derived 3D QSAR equation. The scope of the new method is demonstrated using thermolysin and glycogen phosphorylase b as test examples. Impressive improvements of the predictive power for affinity prediction can be achieved compared to the application of the original knowledge-based potentials by considering a sample set of only 15 known training ligands. Thus, with growing information about the drug target studied, the new method allows one to move gradually from generally valid to protein-specifically adapted pair-potentials, depending on the amount of training information available and its degree of structural diversity. In addition, convincing predictive power is also achieved for ligand poses generated by automatic docking tools.

From knowledge-based potentials to combinatorial lead design in silico.

Computational methods are becoming increasingly used in the drug discovery process. In this Account, we review a novel computational method for lead discovery. This method, called CombiSMoG for "combinatorial small molecule growth", is based on two components: a fast and accurate knowledge-based scoring function used to predict binding affinities of protein-ligand complexes, and a Monte Carlo combinatorial growth algorithm that generates large numbers of low-free-energy ligands in the binding site of a protein. We illustrate the advantages of the method by describing its application in the design of picomolar inhibitors for human carbonic anhydrase.

Fast and accurate predictions of relative binding energies

We report on the development of a fast, empirical method for estimating the binding affinity of protein-ligand complexes. The method is of comparable accuracy to existing empirical methods, but uses fewer parameters. We also report on experiments, using a combined quantum mechanical/molecular mechanical (QM/MM) approach, applied to a dataset of thermolysin inhibitors, with improved performance.