GraphDelta: MPNN Scoring Function for the Affinity Prediction of Protein-Ligand Complexes.
Ontology highlight
ABSTRACT:
SUBMITTER: Karlov DS
PROVIDER: S-EPMC7081425 | biostudies-literature | 2020 Mar
REPOSITORIES: biostudies-literature
Publications
graphDelta: MPNN Scoring Function for the Affinity Prediction of Protein-Ligand Complexes.
Karlov Dmitry S DS Sosnin Sergey S Fedorov Maxim V MV Popov Petr P
ACS omega 20200309 10
In this work, we present graph-convolutional neural networks for the prediction of binding constants of protein-ligand complexes. We derived the model using multi task learning, where the target variables are the dissociation constant (<i>K</i> <sub>d</sub>), inhibition constant (<i>K</i> <sub>i</sub>), and half maximal inhibitory concentration (IC<sub>50</sub>). Being rigorously trained on the PDBbind dataset, the model achieves the Pearson correlation coefficient of 0.87 and the RMSE value of ...[more]
Similar Datasets
Project description:Computational methods for predicting protein-ligand binding free energy continue to be popular as a potential cost-cutting method in the drug discovery process. However, accurate predictions are often difficult to make as estimates must be made for certain electronic and entropic terms in conventional force field based scoring functions. Mixed quantum mechanics/molecular mechanics (QM/MM) methods allow electronic effects for a small region of the protein to be calculated, treating the remaining atoms as a fixed charge background for the active site. Such a semi-empirical QM/MM scoring function has been implemented in AMBER using DivCon and tested on a set of 23 metalloprotein-ligand complexes, where QM/MM methods provide a particular advantage in the modeling of the metal ion. The binding affinity of this set of proteins can be calculated with an R(2) of 0.64 and a standard deviation of 1.88 kcal/mol without fitting and 0.71 and a standard deviation of 1.69 kcal/mol with fitted weighting of the individual scoring terms. In this study we explore using various methods to calculate terms in the binding free energy equation, including entropy estimates and minimization standards. From these studies we found that using the rotational bond estimate to ligand entropy results in a reasonable R(2) of 0.63 without fitting. We also found that using the ESCF energy of the proteins without minimization resulted in an R(2) of 0.57, when using the rotatable bond entropy estimate.
| S-EPMC3017370 | biostudies-literature
Project description:BackgroundComputer-aided drug design provides an effective method of identifying lead compounds. However, success rates are significantly bottlenecked by the lack of accurate and reliable scoring functions needed to evaluate binding affinities of protein-ligand complexes. Therefore, many scoring functions based on machine learning or deep learning have been developed to improve prediction accuracies in recent years. In this work, we proposed a novel featurization method, generating a new scoring function model based on 3D convolutional neural network.ResultsThis work showed the results from testing four architectures and three featurization methods, and outlined the development of a novel deep 3D convolutional neural network scoring function model. This model simplified feature engineering, and in combination with Grad-CAM made the intermediate layers of the neural network more interpretable. This model was evaluated and compared with other scoring functions on multiple independent datasets. The Pearson correlation coefficients between the predicted binding affinities by our model and the experimental data achieved 0.7928, 0.7946, 0.6758, and 0.6474 on CASF-2016 dataset, CASF-2013 dataset, CSAR_HiQ_NRC_set, and Astex_diverse_set, respectively. Overall, our model performed accurately and stably enough in the scoring power to predict the binding affinity of a protein-ligand complex.ConclusionsThese results indicate our model is an excellent scoring function, and performs well in scoring power for accurately and stably predicting the protein-ligand affinity. Our model will contribute towards improving the success rate of virtual screening, thus will accelerate the development of potential drugs or novel biologically active lead compounds.
| S-EPMC9178885 | biostudies-literature
Project description:As high-throughput biochemical screens are both expensive and labor intensive, researchers in academia and industry are turning increasingly to virtual-screening methodologies. Virtual screening relies on scoring functions to quickly assess ligand potency. Although useful for in silico ligand identification, these scoring functions generally give many false positives and negatives; indeed, a properly trained human being can often assess ligand potency by visual inspection with greater accuracy. Given the success of the human mind at protein-ligand complex characterization, we present here a scoring function based on a neural network, a computational model that attempts to simulate, albeit inadequately, the microscopic organization of the brain. Computer-aided drug design depends on fast and accurate scoring functions to aid in the identification of small-molecule ligands. The scoring function presented here, used either on its own or in conjunction with other more traditional functions, could prove useful in future drug-discovery efforts.
| S-EPMC2964041 | biostudies-literature
Project description:Use of knowledge based scoring function (KBSF) for virtual screening and molecular docking has become an established method for drug discovery. Lack of a precise and reliable free energy function that describes several interactions including water-mediated atomic interaction between amino-acid residues and ligand makes distance based statistical measure as the only alternative. Till now all the distance based scoring functions in KBSF arena use atom singularity concept, which neglects the environmental effect of the atom under consideration. We have developed a novel knowledge-based statistical energy function for protein-ligand complexes which takes atomic environment in to account hence functional group as a singular entity. The proposed knowledge based scoring function is fast, simple to construct, easy to use and moreover it tackle the existing problem of handling molecular orientation in active site pocket. We have designed and used Functional group based Ligand retrieval (FBLR) system which can identify and detect the orientation of functional groups in ligand. This decoy searching was used to build the above KBSF to quantify the activity and affinity of high resolution protein-ligand complexes. We have proposed the probable use of these decoys in molecular build-up as a de-novo drug designing approach. We have also discussed the possible use of the said KSBF in pharmacophore fragment detection and pseudo center based fragment alignment procedure.
| S-EPMC2646862 | biostudies-other
Project description:Over the years, various computational methodologies have been developed to understand and quantify receptor-ligand interactions. Protein-ligand interactions can also be explained in the form of a network and its properties. The ligand binding at the protein-active site is stabilized by formation of new interactions like hydrogen bond, hydrophobic and ionic. These non-covalent interactions when considered as links cause non-isomorphic sub-graphs in the residue interaction network. This study aims to investigate the relationship between these induced sub-graphs and ligand activity. Graphlet signature-based analysis of networks has been applied in various biological problems; the focus of this work is to analyse protein-ligand interactions in terms of neighbourhood connectivity and to develop a method in which the information from residue interaction networks, i.e. graphlet signatures, can be applied to quantify ligand affinity. A scoring method was developed, which depicts the variability in signatures adopted by different amino acids during inhibitor binding, and was termed as GSUS (graphlet signature uniqueness score). The score is specific for every individual inhibitor. Two well-known drug targets, COX-2 and CA-II and their inhibitors, were considered to assess the method. Residue interaction networks of COX-2 and CA-II with their respective inhibitors were used. Only hydrogen bond network was considered to calculate GSUS and quantify protein-ligand interaction in terms of graphlet signatures. The correlation of the GSUS with pIC50 was consistent in both proteins and better in comparison to the Autodock results. The GSUS scoring method was better in activity prediction of molecules with similar structure and diverse activity and vice versa. This study can be a major platform in developing approaches that can be used alone or together with existing methods to predict ligand affinity from protein-ligand complexes.
| S-EPMC4448774 | biostudies-literature
Project description:Almost all critical functions in cells rely on specific protein-protein interactions. Understanding these is therefore crucial in the investigation of biological systems. Despite all past efforts, we still lack a thorough understanding of the energetics of association of proteins. Here, we introduce a new and simple approach to predict binding affinity based on functional and structural features of the biological system, namely the network of interfacial contacts. We assess its performance against a protein-protein binding affinity benchmark and show that both experimental methods used for affinity measurements and conformational changes have a strong impact on prediction accuracy. Using a subset of complexes with reliable experimental binding affinities and combining our contacts and contact-types-based model with recent observations on the role of the non-interacting surface in protein-protein interactions, we reach a high prediction accuracy for such a diverse dataset outperforming all other tested methods.
| S-EPMC4523921 | biostudies-literature
Project description:Accurate prediction of the binding affinities of small-molecule ligands to their biological targets is fundamental for structure-based drug design but remains a very challenging task. In this paper, we have performed computational studies to predict the binding models of 31 small-molecule Smac (the second mitochondria-derived activator of caspase) mimetics to their target, the XIAP (X-linked inhibitor of apoptosis) protein, and their binding affinities. Our results showed that computational docking was able to reliably predict the binding models, as confirmed by experimentally determined crystal structures of some Smac mimetics complexed with XIAP. However, all the computational methods we have tested, including an empirical scoring function, two knowledge-based scoring functions, and MM-GBSA (molecular mechanics and generalized Born surface area), yield poor to modest prediction for binding affinities. The linear correlation coefficient (r(2)) value between the predicted affinities and the experimentally determined affinities was found to be between 0.21 and 0.36. Inclusion of ensemble protein-ligand conformations obtained from molecular dynamic simulations did not significantly improve the prediction. However, major improvement was achieved when the free-energy change for ligands between their free- and bound-states, or "ligand-reorganization free energy", was included in the MM-GBSA calculation, and the r(2) value increased from 0.36 to 0.66. The prediction was validated using 10 additional Smac mimetics designed and evaluated by an independent group. This study demonstrates that ligand reorganization free energy plays an important role in the overall binding free energy between Smac mimetics and XIAP. This term should be evaluated for other ligand-protein systems and included in the development of new scoring functions. To our best knowledge, this is the first computational study to demonstrate the importance of ligand reorganization free energy for the prediction of protein-ligand binding free energy.
| S-EPMC2773700 | biostudies-literature
Project description:We introduce a statistical method for evaluating atomic level 3D interaction patterns of protein-ligand contacts. Such patterns can be used for fast separation of likely ligand and ligand binding site combinations out of all those that are geometrically possible. The practical purpose of this probabilistic method is for molecular docking and scoring, as an essential part of a scoring function. Probabilities of interaction patterns are calculated conditional on structural x-ray data and predefined chemical classification of molecular fragment types. Spatial coordinates of atoms are modeled using a Bayesian statistical framework with parametric 3D probability densities. The parameters are given distributions a priori, which provides the possibility to update the densities of model parameters with new structural data and use the parameter estimates to create a contact hierarchy. The contact preferences can be defined for any spatial area around a specified type of fragment. We compared calculated contact point hierarchies with the number of contact atoms found near the contact point in a reference set of x-ray data, and found that these were in general in a close agreement. Additionally, using substrate binding site in cathechol-O-methyltransferase and 27 small potential binder molecules, it was demonstrated that these probabilities together with auxiliary parameters separate well ligands from decoys (true positive rate 0.75, false positive rate 0). A particularly useful feature of the proposed Bayesian framework is that it also characterizes predictive uncertainty in terms of probabilities, which have an intuitive interpretation from the applied perspective.
| S-EPMC3498326 | biostudies-literature
Project description:Predicting the binding affinities of large sets of diverse molecules against a range of macromolecular targets is an extremely challenging task. The scoring functions that attempt such computational prediction are essential for exploiting and analyzing the outputs of docking, which is in turn an important tool in problems such as structure-based drug design. Classical scoring functions assume a predetermined theory-inspired functional form for the relationship between the variables that describe an experimentally determined or modeled structure of a protein-ligand complex and its binding affinity. The inherent problem of this approach is in the difficulty of explicitly modeling the various contributions of intermolecular interactions to binding affinity. New scoring functions based on machine-learning regression models, which are able to exploit effectively much larger amounts of experimental data and circumvent the need for a predetermined functional form, have already been shown to outperform a broad range of state-of-the-art scoring functions in a widely used benchmark. Here, we investigate the impact of the chemical description of the complex on the predictive power of the resulting scoring function using a systematic battery of numerical experiments. The latter resulted in the most accurate scoring function to date on the benchmark. Strikingly, we also found that a more precise chemical description of the protein-ligand complex does not generally lead to a more accurate prediction of binding affinity. We discuss four factors that may contribute to this result: modeling assumptions, codependence of representation and regression, data restricted to the bound state, and conformational heterogeneity in data.
| S-EPMC3966527 | biostudies-literature
Project description:BACKGROUND: A good scoring function is essential for molecular docking computations. In conventional scoring functions, energy terms modeling pairwise interactions are cumulatively summed, and the best docking solution is selected. Here, we propose to transform protein-ligand interactions into three-dimensional geometric networks, from which recurring network substructures, or network motifs, are selected and used to provide probability-ranked interaction templates with which to score docking solutions. RESULTS: A novel scoring function for protein-ligand docking, MotifScore, was developed. It is non-energy-based, and docking is, instead, scored by counting the occurrences of motifs of protein-ligand interaction networks constructed using structures of protein-ligand complexes. MotifScore has been tested on a benchmark set established by others to assess its ability to identify near-native complex conformations among a set of decoys. In this benchmark test, 84% of the highest-scored docking conformations had root-mean-square deviations (rmsds) below 2.0 A from the native conformation, which is comparable with the best of several energy-based docking scoring functions. Many of the top motifs, which comprise a multitude of chemical groups that interact simultaneously and make a highly significant contribution to MotifScore, capture recurrent interacting patterns beyond pairwise interactions. CONCLUSIONS: While providing quite good docking scores, MotifScore is quite different from conventional energy-based functions. MotifScore thus represents a new, network-based approach for exploring problems associated with molecular docking.
| S-EPMC3098071 | biostudies-literature