Protein-ligand Binding Site Prediction Research Articles

Comparative evaluation of methods for the prediction of protein-ligand binding sites.

The accurate identification of protein-ligand binding sites is of critical importance in understanding and modulating protein function. Accordingly, ligand binding site prediction has remained a research focus for over three decades with over 50 methods developed and a change of paradigm from geometry-based to machine learning. In this work, we collate 13 ligand binding site predictors, spanning 30years, focusing on the latest machine learning-based methods such as VN-EGNN, IF-SitePred, GrASP, PUResNet, and DeepPocket and compare them to the established P2Rank, PRANK and fpocket and earlier methods like PocketFinder, Ligsite and Surfnet. We benchmark the methods against the human subset of our new curated reference dataset, LIGYSIS. LIGYSIS is a comprehensive protein-ligand complex dataset comprising 30,000 proteins with bound ligands which aggregates biologically relevant unique protein-ligand interfaces across biological units of multiple structures from the same protein. LIGYSIS is an improvement for testing methods over earlier datasets like sc-PDB, PDBbind, binding MOAD, COACH420 and HOLO4K which either include 1:1 protein-ligand complexes or consider asymmetric units. Re-scoring of fpocket predictions by PRANK and DeepPocket display the highest recall (60%) whilst IF-SitePred presents the lowest recall (39%). We demonstrate the detrimental effect that redundant prediction of binding sites has on performance as well as the beneficial impact of stronger pocket scoring schemes, with improvements up to 14% in recall (IF-SitePred) and 30% in precision (Surfnet). Finally, we propose top-N+2 recall as the universal benchmark metric for ligand binding site prediction and urge authors to share not only the source code of their methods, but also of their benchmark.Scientific contributionsThis study conducts the largest benchmark of ligand binding site prediction methods to date, comparing 13 original methods and 15 variants using 10 informative metrics. The LIGYSIS dataset is introduced, which aggregates biologically relevant protein-ligand interfaces across multiple structures of the same protein. The study highlights the detrimental effect of redundant binding site prediction and demonstrates significant improvement in recall and precision through stronger scoring schemes. Finally, top-N+2 recall is proposed as a universal benchmark metric for ligand binding site prediction, with a recommendation for open-source sharing of both methods and benchmarks.

GeoNet enables the accurate prediction of protein-ligand binding sites through interpretable geometric deep learning.

The identification of protein binding residues is essential for understanding their functions invivo. However, it remains a computational challenge to accurately identify binding sites due to the lack of known residue binding patterns. Local residue spatial distribution and its interactive biophysical environment both determine binding patterns. Previous methods could not capture both information simultaneously, resulting in unsatisfactory performance. Here, we present GeoNet, an interpretable geometric deep learning model for predicting DNA, RNA, and protein binding sites by learning the latent residue binding patterns. GeoNet achieves this by introducing a coordinate-free geometric representation to characterize local residue distributions and generating an eigenspace to depict local interactive biophysical environments. Evaluation shows that GeoNet is superior compared to other leading predictors and it shows a strong interpretability of learned representations. We present three test cases, where interaction interfaces were successfully identified with GeoNet.

Prediction of protein-ligand binding sites modulating activity of MAST protein kinases

Aim. Identification of the protein-ligand binding sites, that may be the target of compounds, affecting individual human protein kinases of the MAST family (MAST1, 2, 3, 4 and MASTL / GWL). Methods. Literature and database search. Comparison of protein and ligand structures. Protein structure modeling, structural superimposition, etc. Results. The structural alignment demonstrates significant similarity of catalytic domains in MAST1, 2, 3, 4 and MASTL (GWL). It justifies transferring of reference ligands from PDB structures to human MASTs, discovering potential sites of ligand binding. 13 sites of ligand-binding were specified based on refrence ligands, transferred from RCSB Protein Data Bank structures, and differences in sites amino acid composition of MAST family members were discovered. Сonclusions. Based on the differences in the amino acid composition of the studied pockets in MAST1, 2, 3, 4 and MASTL (GWL), the sites B, C, D, E, F, were selected for further study and virtual screening for new selective inhibitors of individual members of MAST protein kinase family.

A Point Cloud Graph Neural Network for Protein-Ligand Binding Site Prediction.

Predicting protein-ligand binding sites is an integral part of structural biology and drug design. A comprehensive understanding of these binding sites is essential for advancing drug innovation, elucidating mechanisms of biological function, and exploring the nature of disease. However, accurately identifying protein-ligand binding sites remains a challenging task. To address this, we propose PGpocket, a geometric deep learning-based framework to improve protein-ligand binding site prediction. Initially, the protein surface is converted into a point cloud, and then the geometric and chemical properties of each point are calculated. Subsequently, the point cloud graph is constructed based on the inter-point distances, and the point cloud graph neural network (GNN) is applied to extract and analyze the protein surface information to predict potential binding sites. PGpocket is trained on the scPDB dataset, and its performance is verified on two independent test sets, Coach420 and HOLO4K. The results show that PGpocket achieves a 58% success rate on the Coach420 dataset and a 56% success rate on the HOLO4K dataset. These results surpass competing algorithms, demonstrating PGpocket's advancement and practicality for protein-ligand binding site prediction.

Protein ligand binding site prediction using graph transformer neural network.

Ligand binding site prediction is a crucial initial step in structure-based drug discovery. Although several methods have been proposed previously, including those using geometry based and machine learning techniques, their accuracy is considered to be still insufficient. In this study, we introduce an approach that leverages a graph transformer neural network to rank the results of a geometry-based pocket detection method. We also created a larger training dataset compared to the conventionally used sc-PDB and investigated the correlation between the dataset size and prediction performance. Our findings indicate that utilizing a graph transformer-based method alongside a larger training dataset could enhance the performance of ligand binding site prediction.

Learnt representations of proteins can be used for accurate prediction of small molecule binding sites on experimentally determined and predicted protein structures

Protein-ligand binding site prediction is a useful tool for understanding the functional behaviour and potential drug-target interactions of a novel protein of interest. However, most binding site prediction methods are tested by providing crystallised ligand-bound (holo) structures as input. This testing regime is insufficient to understand the performance on novel protein targets where experimental structures are not available. An alternative option is to provide computationally predicted protein structures, but this is not commonly tested. However, due to the training data used, computationally-predicted protein structures tend to be extremely accurate, and are often biased toward a holo conformation. In this study we describe and benchmark IF-SitePred, a protein-ligand binding site prediction method which is based on the labelling of ESM-IF1 protein language model embeddings combined with point cloud annotation and clustering. We show that not only is IF-SitePred competitive with state-of-the-art methods when predicting binding sites on experimental structures, but it performs better on proxies for novel proteins where low accuracy has been simulated by molecular dynamics. Finally, IF-SitePred outperforms other methods if ensembles of predicted protein structures are generated.

PUResNet: prediction of protein-ligand binding sites using deep residual neural network

BackgroundPredicting protein-ligand binding sites is a fundamental step in understanding the functional characteristics of proteins, which plays a vital role in elucidating different biological functions and is a crucial step in drug discovery. A protein exhibits its true nature after binding to its interacting molecule known as a ligand that binds only in the favorable binding site of the protein structure. Different computational methods exploiting the features of proteins have been developed to identify the binding sites in the protein structure, but none seems to provide promising results, and therefore, further investigation is required.ResultsIn this study, we present a deep learning model PUResNet and a novel data cleaning process based on structural similarity for predicting protein-ligand binding sites. From the whole scPDB (an annotated database of druggable binding sites extracted from the Protein DataBank) database, 5020 protein structures were selected to address this problem, which were used to train PUResNet. With this, we achieved better and justifiable performance than the existing methods while evaluating two independent sets using distance, volume and proportion metrics.

Integration of association and computational methods reveals functional variants of LEPR gene for abdominal fat content in chickens

Leptin receptor (LEPR) plays a vital role in obesity in humans and animals. The objective of this study is to assess LEPR functional variants for chicken adipose deposition by integration of association and in-silico analysis using a unique chicken population, the Northeast Agricultural University broiler lines divergently selected for abdominal fat content (NEAUHLF). Five online bioinformatics tools were used to predict the functionality of the single nucleotide polymorphisms (SNPs) in coding region. Further, the possible structure–function relationship of high confidence SNPs was determined by bioinformatics analyses, including the conservation and stability analysis based on amino acid residues, prediction of protein ligand-binding sites, and the superposition of protein tertiary structure. Meanwhile, we analyzed the association between abdominal fat traits and 20 polymorphisms of chicken LEPR gene. The integrated results showed that rs731962924 (N867I) and rs13684622 (C1002R) could lead to striking changes in the structure and function of proteins, of which rs13684622 (C1002R) was significantly associated with abdominal fat weight (AFW, P=0.0413) and abdominal fat percentage (AFP, P=0.0260) in chickens. Therefore, we are of the opinion that rs13684622 (C1002R) may be an essential functional SNP affecting chicken abdominal fat deposition, and potentially applied to improvement of broiler abdominal fat in molecular marker-assisted selection (MAS) program. Additionally, the coupling of association with computer electronic predictive analysis provides a new avenue to identify important molecular markers for breeders.

Addressing data imbalance problems in ligand-binding site prediction using a variational autoencoder and a convolutional neural network.

Since 2015, a fast growing number of deep learning-based methods have been proposed for protein-ligand binding site prediction and many have achieved promising performance. These methods, however, neglect the imbalanced nature of binding site prediction problems. Traditional data-based approaches for handling data imbalance employ linear interpolation of minority class samples. Such approaches may not be fully exploited by deep neural networks on downstream tasks. We present a novel technique for balancing input classes by developing a deep neural network-based variational autoencoder (VAE) that aims to learn important attributes of the minority classes concerning nonlinear combinations. After learning, the trained VAE was used to generate new minority class samples that were later added to the original data to create a balanced dataset. Finally, a convolutional neural network was used for classification, for which we assumed that the nonlinearity could be fully integrated. As a case study, we applied our method to the identification of FAD- and FMN-binding sites of electron transport proteins. Compared with the best classifiers that use traditional machine learning algorithms, our models obtained a great improvement on sensitivity while maintaining similar or higher levels of accuracy and specificity. We also demonstrate that our method is better than other data imbalance handling techniques, such as SMOTE, ADASYN, and class weight adjustment. Additionally, our models also outperform existing predictors in predicting the same binding types. Our method is general and can be applied to other data types for prediction problems with moderate-to-heavy data imbalances.

Predicting Protein-Ligand Binding Site for Drug Design Using Context Relevant Self Organizing Maps (CRSOM)

Research on binding sites has been done to find suitable ligands to treat a particular disease. The binding site is a pocket on the surface of the protein, which acts as a place to attach a ligand. In bioinformatics, searching for binding sites is applied to drug design problems. Currently, computer-aided drug design has been developed. In this study, the prediction of protein-ligand binding sites formulated as a binary classification, which is distinguish the location that has potential to binding the ligand and the location that has no potential to binding the ligand. The dataset that will be used in this research is taken from the RCSB Protein Data Bank of 14 proteins data. The classification method used in this research is Context Relevant Self Organizing Maps (CRSOM), where the CRSOM method gives higher accuracy results compared to Backpropagation and Deep Learning. Context Relevant Self Organizing Maps (CRSOM) is chosen as a supervised learning classification algorithm that has an optimal internal representation, where data belonging different classes are separated with wider margin, while data belonging to the same class are clustered closely to each other. Thus, CRSOM is able to visualize high-dimensional protein data into binding site and non-binding site classes significantly. The results of the study obtained an average training accuracy of 99,60%, testing accuracy of 96.26%, and the average test time of 28.63 seconds, the result is better than the predecessor.

Exploring the computational methods for protein-ligand binding site prediction

Proteins participate in various essential processes in vivo via interactions with other molecules. Identifying the residues participating in these interactions not only provides biological insights for protein function studies but also has great significance for drug discoveries. Therefore, predicting protein–ligand binding sites has long been under intense research in the fields of bioinformatics and computer aided drug discovery. In this review, we first introduce the research background of predicting protein–ligand binding sites and then classify the methods into four categories, namely, 3D structure-based, template similarity-based, traditional machine learning-based and deep learning-based methods. We describe representative algorithms in each category and elaborate on machine learning and deep learning-based prediction methods in more detail. Finally, we discuss the trends and challenges of the current research such as molecular dynamics simulation based cryptic binding sites prediction, and highlight prospective directions for the near future.

Boosting Granular Support Vector Machines for the Accurate Prediction of Protein-Nucleotide Binding Sites.

The accurate identification of protein-ligand binding sites helps elucidate protein function and facilitate the design of new drugs. Machine-learning-based methods have been widely used for the prediction of protein-ligand binding sites. Nevertheless, the severe class imbalance phenomenon, where the number of nonbinding (majority) residues is far greater than that of binding (minority) residues, has a negative impact on the performance of such machine-learning-based predictors. In this study, we aim to relieve the negative impact of class imbalance by Boosting Multiple Granular Support Vector Machines (BGSVM). In BGSVM, each base SVM is trained on a granular training subset consisting of all minority samples and some reasonably selected majority samples. The efficacy of BGSVM for dealing with class imbalance was validated by benchmarking it with several typical imbalance learning algorithms. We further implemented a protein-nucleotide binding site predictor, called BGSVM-NUC, with the BGSVM algorithm. Rigorous cross-validation and independent validation tests for five types of proteinnucleotide interactions demonstrated that the proposed BGSVM-NUC achieves promising prediction performance and outperforms several popular sequence-based protein-nucleotide binding site predictors. The BGSVM-NUC web server is freely available at http://csbio.njust.edu.cn/bioinf/BGSVM-NUC/ for academic use.

SXGBsite: Prediction of Protein-Ligand Binding Sites Using Sequence Information and Extreme Gradient Boosting.

The prediction of protein–ligand binding sites is important in drug discovery and drug design. Protein–ligand binding site prediction computational methods are inexpensive and fast compared with experimental methods. This paper proposes a new computational method, SXGBsite, which includes the synthetic minority over-sampling technique (SMOTE) and the Extreme Gradient Boosting (XGBoost). SXGBsite uses the position-specific scoring matrix discrete cosine transform (PSSM-DCT) and predicted solvent accessibility (PSA) to extract features containing sequence information. A new balanced dataset was generated by SMOTE to improve classifier performance, and a prediction model was constructed using XGBoost. The parallel computing and regularization techniques enabled high-quality and fast predictions and mitigated overfitting caused by SMOTE. An evaluation using 12 different types of ligand binding site independent test sets showed that SXGBsite performs similarly to the existing methods on eight of the independent test sets with a faster computation time. SXGBsite may be applied as a complement to biological experiments.

G-LoSA for Prediction of Protein-Ligand Binding Sites and Structures.

Recent advances in high-throughput structure determination and computational protein structure prediction have significantly enriched the universe of protein structure. However, there is still a large gap between the number of available protein structures and that of proteins with annotated function in high accuracy. Computational structure-based protein function prediction has emerged to reduce this knowledge gap. The identification of a ligand binding site and its structure is critical to the determination of a protein's molecular function. We present a computational methodology for predicting small molecule ligand binding site and ligand structure using G-LoSA, our protein local structure alignment and similarity measurement tool. All the computational procedures described here can be easily implemented using G-LoSA Toolkit, a package of standalone software programs and preprocessed PDB structure libraries. G-LoSA and G-LoSA Toolkit are freely available to academic users at http://compbio.lehigh.edu/GLoSA . We also illustrate a case study to show the potential of our template-based approach harnessing G-LoSA for protein function prediction.

Development of a protein-ligand-binding site prediction method based on interaction energy and sequence conservation.

We present a new method for predicting protein–ligand-binding sites based on protein three-dimensional structure and amino acid conservation. This method involves calculation of the van der Waals interaction energy between a protein and many probes placed on the protein surface and subsequent clustering of the probes with low interaction energies to identify the most energetically favorable locus. In addition, it uses amino acid conservation among homologous proteins. Ligand-binding sites were predicted by combining the interaction energy and the amino acid conservation score. The performance of our prediction method was evaluated using a non-redundant dataset of 348 ligand-bound and ligand-unbound protein structure pairs, constructed by filtering entries in a ligand-binding site structure database, LigASite. Ligand-bound structure prediction (bound prediction) indicated that 74.0 % of predicted ligand-binding sites overlapped with real ligand-binding sites by over 25 % of their volume. Ligand-unbound structure prediction (unbound prediction) indicated that 73.9 % of predicted ligand-binding residues overlapped with real ligand-binding residues. The amino acid conservation score improved the average prediction accuracy by 17.0 and 17.6 points for the bound and unbound predictions, respectively. These results demonstrate the effectiveness of the combined use of the interaction energy and amino acid conservation in the ligand-binding site prediction.Electronic supplementary materialThe online version of this article (doi:10.1007/s10969-016-9204-2) contains supplementary material, which is available to authorized users.

In silico Identification and Characterization of Protein-Ligand Binding Sites.

Protein-ligand binding site prediction methods aim to predict, from amino acid sequence, protein-ligand interactions, putative ligands, and ligand binding site residues using either sequence information, structural information, or a combination of both. In silico characterization of protein-ligand interactions has become extremely important to help determine a protein's functionality, as in vivo-based functional elucidation is unable to keep pace with the current growth of sequence databases. Additionally, in vitro biochemical functional elucidation is time-consuming, costly, and may not be feasible for large-scale analysis, such as drug discovery. Thus, in silico prediction of protein-ligand interactions must be utilized to aid in functional elucidation. Here, we briefly discuss protein function prediction, prediction of protein-ligand interactions, the Critical Assessment of Techniques for Protein Structure Prediction (CASP) and the Continuous Automated EvaluatiOn (CAMEO) competitions, along with their role in shaping the field. We also discuss, in detail, our cutting-edge web-server method, FunFOLD for the structurally informed prediction of protein-ligand interactions. Furthermore, we provide a step-by-step guide on using the FunFOLD web server and FunFOLD3 downloadable application, along with some real world examples, where the FunFOLD methods have been used to aid functional elucidation.

Proteins and Their Interacting Partners: An Introduction to Protein-Ligand Binding Site Prediction Methods.

Elucidating the biological and biochemical roles of proteins, and subsequently determining their interacting partners, can be difficult and time consuming using in vitro and/or in vivo methods, and consequently the majority of newly sequenced proteins will have unknown structures and functions. However, in silico methods for predicting protein–ligand binding sites and protein biochemical functions offer an alternative practical solution. The characterisation of protein–ligand binding sites is essential for investigating new functional roles, which can impact the major biological research spheres of health, food, and energy security. In this review we discuss the role in silico methods play in 3D modelling of protein–ligand binding sites, along with their role in predicting biochemical functionality. In addition, we describe in detail some of the key alternative in silico prediction approaches that are available, as well as discussing the Critical Assessment of Techniques for Protein Structure Prediction (CASP) and the Continuous Automated Model EvaluatiOn (CAMEO) projects, and their impact on developments in the field. Furthermore, we discuss the importance of protein function prediction methods for tackling 21st century problems.

Improving protein-ligand binding site prediction accuracy by classification of inner pocket points using local features.

BackgroundProtein-ligand binding site prediction from a 3D protein structure plays a pivotal role in rational drug design and can be helpful in drug side-effects prediction or elucidation of protein function. Embedded within the binding site detection problem is the problem of pocket ranking – how to score and sort candidate pockets so that the best scored predictions correspond to true ligand binding sites. Although there exist multiple pocket detection algorithms, they mostly employ a fairly simple ranking function leading to sub-optimal prediction results.ResultsWe have developed a new pocket scoring approach (named PRANK) that prioritizes putative pockets according to their probability to bind a ligand. The method first carefully selects pocket points and labels them by physico-chemical characteristics of their local neighborhood. Random Forests classifier is subsequently applied to assign a ligandability score to each of the selected pocket point. The ligandability scores are finally merged into the resulting pocket score to be used for prioritization of the putative pockets. With the used of multiple datasets the experimental results demonstrate that the application of our method as a post-processing step greatly increases the quality of the prediction of Fpocket and ConCavity, two state of the art protein-ligand binding site prediction algorithms.ConclusionsThe positive experimental results show that our method can be used to improve the success rate, validity and applicability of existing protein-ligand binding site prediction tools. The method was implemented as a stand-alone program that currently contains support for Fpocket and Concavity out of the box, but is easily extendible to support other tools. PRANK is made freely available at http://siret.ms.mff.cuni.cz/prank.Electronic supplementary materialThe online version of this article (doi:10.1186/s13321-015-0059-5) contains supplementary material, which is available to authorized users.

Prediction of Protein-Ligand Binding Sites for Cisplatin and Transplatin based on Hydrogen Bonds

Platinum compounds are very important to treatment of various malignant tumors. However, prediction of platinum-binding sites is very hard to be made. Nevertheless, hydrolysis of leaving groups bounded to platinum compounds plays an important role in delivering platinum to a target molecule. Herein, a study in silico provides an understanding of the molecular surface in atomic level of three-dimensional structure of cisplatin and transplatin and their binding-sites in order to offer some insights in drug designing. The goal of this work was to implement a new approach based on geometric and physicochemical parameters to find platinum-binding sites using parallel computing algorithms for graphics processing units (GPUs). These algorithms were tested and validated by analysing platinum-binding sites in five known proteins. The results indicated that these binding sites were predicted with significant success. In our analysis HexServer and PatchDock server did not find putative binding-sites for cisplatin and transplatin as we found for the five chosen proteins. Herein, we have shown that the present method have had a better prediction of platinum-binding site than HexServer and PatchDock methods.

Amino Acids in Nine Ligand-Prefer Ramachandran Regions.

Several secondary structures, such as π-helix and left-handed helix, have been frequently identified at protein ligand-binding sites. A secondary structure is considered to be constrained to a specific region of dihedral angles. However, a comprehensive analysis of the correlation between main chain dihedral angles and ligand-binding sites has not been performed. We undertook an extensive analysis of the relationship between dihedral angles in proteins and their distance to ligand-binding sites, frequency of occurrence, molecular potential energy, amino acid composition, van der Waals contacts, and hydrogen bonds with ligands. The results showed that the values of dihedral angles have a strong preference for ligand-binding sites at certain regions in the Ramachandran plot. We discovered that amino acids preceding the ligand-prefer ϕ/ψ box residues are exposed more to solvents, whereas amino acids following ligand-prefer ϕ/ψ box residues form more hydrogen bonds and van der Waals contacts with ligands. Our method exhibited a similar performance compared with the program Ligsite-csc for both ligand-bound structures and ligand-free structures when just one ligand-binding site was predicted. These results should be useful for the prediction of protein ligand-binding sites and for analysing the relationship between structure and function.