Improved Method of Structure-Based Virtual Screening via Interaction-Energy-Based Learning

Application of Machine Learning Techniques to Predict Binding Affinity for Drug Targets: A Study of Cyclin-Dependent Kinase 2

BACKGROUND

The elucidation of the structure of cyclin-dependent kinase 2 (CDK2) made it possible to develop targeted scoring functions for virtual screening aimed to identify new inhibitors for this enzyme. CDK2 is a protein target for the development of drugs intended to modulate cellcycle progression and control. Such drugs have potential anticancer activities.

OBJECTIVE

Our goal here is to review recent applications of machine learning methods to predict ligand- binding affinity for protein targets. To assess the predictive performance of classical scoring functions and targeted scoring functions, we focused our analysis on CDK2 structures.

METHODS

We have experimental structural data for hundreds of binary complexes of CDK2 with different ligands, many of them with inhibition constant information. We investigate here computational methods to calculate the binding affinity of CDK2 through classical scoring functions and machine- learning models.

RESULTS

Analysis of the predictive performance of classical scoring functions available in docking programs such as Molegro Virtual Docker, AutoDock4, and Autodock Vina indicated that these methods failed to predict binding affinity with significant correlation with experimental data. Targeted scoring functions developed through supervised machine learning techniques showed a significant correlation with experimental data.

CONCLUSION

Here, we described the application of supervised machine learning techniques to generate a scoring function to predict binding affinity. Machine learning models showed superior predictive performance when compared with classical scoring functions. Analysis of the computational models obtained through machine learning could capture essential structural features responsible for binding affinity against CDK2.

Accuracy or novelty: what can we gain from target-specific machine-learning-based scoring functions in virtual screening?

Machine-learning (ML)-based scoring functions (MLSFs) have gradually emerged as a promising alternative for protein-ligand binding affinity prediction and structure-based virtual screening. However, clouds of doubts have still been raised against the benefits of this novel type of scoring functions (SFs). In this study, to benchmark the performance of target-specific MLSFs on a relatively unbiased dataset, the MLSFs trained from three representative protein-ligand interaction representations were assessed on the LIT-PCBA dataset, and the classical Glide SP SF and three types of ligand-based quantitative structure-activity relationship (QSAR) models were also utilized for comparison. Two major aspects in virtual screening campaigns, including prediction accuracy and hit novelty, were systematically explored. The calculation results illustrate that the tested target-specific MLSFs yielded generally superior performance over the classical Glide SP SF, but they could hardly outperform the 2D fingerprint-based QSAR models. Although substantial improvements could be achieved by integrating multiple types of protein-ligand interaction features, the MLSFs were still not sufficient to exceed MACCS-based QSAR models. In terms of the correlations between the hit ranks or the structures of the top-ranked hits, the MLSFs developed by different featurization strategies would have the ability to identify quite different hits. Nevertheless, it seems that target-specific MLSFs do not have the intrinsic attributes of a traditional SF and may not be a substitute for classical SFs. In contrast, MLSFs can be regarded as a new derivative of ligand-based QSAR models. It is expected that our study may provide valuable guidance for the assessment and further development of target-specific MLSFs.

The latest automated docking technologies for novel drug discovery

INTRODUCTION

Molecular docking has been consolidated as one of the most important methods in the molecular modeling field. It has been recognized as a prominent tool in the study of protein-ligand complexes, to describe intermolecular interactions, to accurately predict poses of multiple ligands, to discover novel promising bioactive compounds. Molecular docking methods have evolved in terms of their accuracy and reliability; but there are pending issues to solve for improving the connection between the docking results and the experimental evidence.

AREAS COVERED

In this article, the author reviews very recent innovative molecular docking applications with special emphasis on reverse docking, treatment of protein flexibility, the use of experimental data to guide the selection of docking poses, the application of Quantum mechanics(QM) in docking, and covalent docking.

EXPERT OPINION

There are several issues being worked on in recent years that will lead to important breakthroughs in molecular docking methods in the near future These developments are related to more efficient exploration of large datasets and receptor conformations, advances in electronic description, and the use of structural information for guiding the selection of results.

Merging Ligand-Based and Structure-Based Methods in Drug Discovery: An Overview of Combined Virtual Screening Approaches

Virtual screening (VS) is an outstanding cornerstone in the drug discovery pipeline. A variety of computational approaches, which are generally classified as ligand-based (LB) and structure-based (SB) techniques, exploit key structural and physicochemical properties of ligands and targets to enable the screening of virtual libraries in the search of active compounds. Though LB and SB methods have found widespread application in the discovery of novel drug-like candidates, their complementary natures have stimulated continued efforts toward the development of hybrid strategies that combine LB and SB techniques, integrating them in a holistic computational framework that exploits the available information of both ligand and target to enhance the success of drug discovery projects. In this review, we analyze the main strategies and concepts that have emerged in the last years for defining hybrid LB + SB computational schemes in VS studies. Particularly, attention is focused on the combination of molecular similarity and docking, illustrating them with selected applications taken from the literature.

Selecting machine-learning scoring functions for structure-based virtual screening

Interest in docking technologies has grown parallel to the ever increasing number and diversity of 3D models for macromolecular therapeutic targets. Structure-Based Virtual Screening (SBVS) aims at leveraging these experimental structures to discover the necessary starting points for the drug discovery process. It is now established that Machine Learning (ML) can strongly enhance the predictive accuracy of scoring functions for SBVS by exploiting large datasets from targets, molecules and their associations. However, with greater choice, the question of which ML-based scoring function is the most suitable for prospective use on a given target has gained importance. Here we analyse two approaches to select an existing scoring function for the target along with a third approach consisting in generating a scoring function tailored to the target. These analyses required discussing the limitations of popular SBVS benchmarks, the alternatives to benchmark scoring functions for SBVS and how to generate them or use them using freely-available software.

CRDS: Consensus Reverse Docking System for target fishing

MOTIVATION

Identification of putative drug targets is a critical step for explaining the mechanism of drug action against multiple targets, finding new therapeutic indications for existing drugs and unveiling the adverse drug reactions. One important approach is to use the molecular docking. However, its widespread utilization has been hindered by the lack of easy-to-use public servers. Therefore, it is vital to develop a streamlined computational tool for target prediction by molecular docking on a large scale.

RESULTS

We present a fully automated web tool named Consensus Reverse Docking System (CRDS), which predicts potential interaction sites for a given drug. To improve hit rates, we developed a strategy of consensus scoring. CRDS carries out reverse docking against 5254 candidate protein structures using three different scoring functions (GoldScore, Vina and LeDock from GOLD version 5.7.1, AutoDock Vina version 1.1.2 and LeDock version 1.0, respectively), and those scores are combined into a single score named Consensus Docking Score (CDS). The web server provides the list of top 50 predicted interaction sites, docking conformations, 10 most significant pathways and the distribution of consensus scores.

AVAILABILITY AND IMPLEMENTATION

The web server is available at http://pbil.kaist.ac.kr/CRDS.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

In vitro Acetylcholinesterase inhibitory activity of polyphenolic compounds identified from Matricaria recutita

Acetylcholinesterase (AChE) is a key enzyme enhancing the cognitive disorder, leading to Alzheimer’s disease, and AChE inhibition is a crucial therapeutic mechanism against it. Matricaria recutita (MR) is widely used as a herbal medicine due to its phytotherapeutic properties. For this reason, MR flower was evaluated to identify polyphenolic compounds (PC), and then each PC is examined for AChE inhibitory activity. The ultra-performance liquid chromatography-electrospray tandem mass spectrometry UPLC-ESI-MS/MS was used to detect PC, and molecular docking was performed to insight potential inhibitory activity of PC against AChE. A series of 13 PC compounds were identified in the fractions of MR plant. Docking studies revealed that the inhibitory free energy and the position of the docked compounds in the active site are favored for the active compounds complex formed between AChE and the identified PC compounds. The accurate analysis of the docking result demonstrates that Kaempferol-3-O-rutinoside (KR) and Luteolin-8-C-glucoside (orientin) (LG) are the most significant inhibitory compounds against AChE. It can be concluded that MR is a significant source of PC compounds, and KR and LG are the most promising compounds that have high-affinity binding to AChE, based on docking outcome. Further experiments are recommended to explore in vivo enzyme compound interaction and toxicity models to establish the maximum suggested dose.

Identification of key interactions between SARS-CoV-2 main protease and inhibitor drug candidates

The number of cases of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection (COVID-19) has reached over 114,000. SARS-CoV-2 caused a pandemic in Wuhan, China, in December 2019 and is rapidly spreading globally. It has been reported that peptide-like anti-HIV-1 drugs are effective against SARS-CoV Main protease (Mpro). Due to the close phylogenetic relationship between SARS-CoV and SARS-CoV-2, their main proteases share many structural and functional features. Thus, these drugs are also regarded as potential drug candidates targeting SARS-CoV-2 Mpro. However, the mechanism of action of SARS-CoV-2 Mpro at the atomic-level is unknown. In the present study, we revealed key interactions between SARS-CoV-2 Mpro and three drug candidates by performing pharmacophore modeling and 1 μs molecular dynamics (MD) simulations. His41, Gly143, and Glu166 formed interactions with the functional groups that were common among peptide-like inhibitors in all MD simulations. These interactions are important targets for potential drugs against SARS-CoV-2 Mpro.

The impact of compound library size on the performance of scoring functions for structure-based virtual screening

Larger training datasets have been shown to improve the accuracy of machine learning (ML)-based scoring functions (SFs) for structure-based virtual screening (SBVS). In addition, massive test sets for SBVS, known as ultra-large compound libraries, have been demonstrated to enable the fast discovery of selective drug leads with low-nanomolar potency. This proof-of-concept was carried out on two targets using a single docking tool along with its SF. It is thus unclear whether this high level of performance would generalise to other targets, docking tools and SFs. We found that screening a larger compound library results in more potent actives being identified in all six additional targets using a different docking tool along with its classical SF. Furthermore, we established that a way to improve the potency of the retrieved molecules further is to rank them with more accurate ML-based SFs (we found this to be true in four of the six targets; the difference was not significant in the remaining two targets). A 3-fold increase in average hit rate across targets was also achieved by the ML-based SFs. Lastly, we observed that classical and ML-based SFs often find different actives, which supports using both types of SFs on those targets.

Improving structure-based virtual screening performance via learning from scoring function components

Scoring functions (SFs) based on complex machine learning (ML) algorithms have gradually emerged as a promising alternative to overcome the weaknesses of classical SFs. However, extensive efforts have been devoted to the development of SFs based on new protein-ligand interaction representations and advanced alternative ML algorithms instead of the energy components obtained by the decomposition of existing SFs. Here, we propose a new method named energy auxiliary terms learning (EATL), in which the scoring components are extracted and used as the input for the development of three levels of ML SFs including EATL SFs, docking-EATL SFs and comprehensive SFs with ascending VS performance. The EATL approach not only outperforms classical SFs for the absolute performance (ROC) and initial enrichment (BEDROC) but also yields comparable performance compared with other advanced ML-based methods on the diverse subset of Directory of Useful Decoys: Enhanced (DUD-E). The test on the relatively unbiased actives as decoys (AD) dataset also proved the effectiveness of EATL. Furthermore, the idea of learning from SF components to yield improved screening power can also be extended to other docking programs and SFs available.

Improving Docking-Based Virtual Screening Ability by Integrating Multiple Energy Auxiliary Terms from Molecular Docking Scoring

Virtual Screening (VS) based on molecular docking is an efficient method used for retrieving novel hit compounds in drug discovery. However, the accuracy of the current docking scoring function (SF) is usually insufficient. In this study, in order to improve the screening power of SF, a novel approach named EAT-Score was proposed by directly utilizing the energy auxiliary terms (EAT) provided by molecular docking scoring through eXtreme Gradient Boosting (XGBoost). Here, EAT specifically refers to the output of the Molecular Operating Environment (MOE) scoring, including the energy scores of five different classical SFs and the Protein-Ligand Interaction Fingerprint (PLIF) terms. The performance of EAT-Score to discriminate actives from decoys was strictly validated on the DUD-E diverse subset by using different performance metrics. The results showed that EAT-Score performed much better than classical SFs in VS, with its AUC values exhibiting an improvement of around 0.3. Meanwhile, EAT-Score could achieve comparable even better prediction performance compared with other state-of-the-art VS methods, such as some machine learning (ML)-based SFs and classical SFs implemented in docking programs, in terms of AUC, LogAUC, or BEDROC. Furthermore, the EAT-Score model can capture important binding pattern information from protein-ligand complexes by Shapley additive explanations (SHAP) analysis, which may be very helpful in interpreting the ligand binding mechanism for a certain target and thereby guiding drug design.

Improving Protein-Ligand Docking Results with High-Throughput Molecular Dynamics Simulations

Structure-based virtual screening relies on classical scoring functions that often fail to reliably discriminate binders from nonbinders. In this work, we present a high-throughput protein-ligand complex molecular dynamics (MD) simulation that uses the output from AutoDock Vina to improve docking results in distinguishing active from decoy ligands in a directory of useful decoy-enhanced (DUD-E) dataset. MD trajectories are processed by evaluating ligand-binding stability using root-mean-square deviations. We select 56 protein targets (of 7 different protein classes) and 560 ligands (280 actives, 280 decoys) and show 22% improvement in ROC AUC (area under the curve, receiver operating characteristics curve), from an initial value of 0.68 (AutoDock Vina) to a final value of 0.83. The MD simulation demonstrates a robust performance across all seven different protein classes. In addition, some predicted ligand-binding modes are moderately refined during MD simulations. These results systematically validate the reliability of a physics-based approach to evaluate protein-ligand binding interactions.

How Sure Can We Be about ML Methods-Based Evaluation of Compound Activity: Incorporation of Information about Prediction Uncertainty Using Deep Learning Techniques

A great variety of computational approaches support drug design processes, helping in selection of new potentially active compounds, and optimization of their physicochemical and ADMET properties. Machine learning is a group of methods that are able to evaluate in relatively short time enormous amounts of data. However, the quality of machine-learning-based prediction depends on the data supplied for model training. In this study, we used deep neural networks for the task of compound activity prediction and developed dropout-based approaches for estimating prediction uncertainty. Several types of analyses were performed: the relationships between the prediction error, similarity to the training set, prediction uncertainty, number and standard deviation of activity values were examined. It was tested whether incorporation of information about prediction uncertainty influences compounds ranking based on predicted activity and prediction uncertainty was used to search for the potential errors in the ChEMBL database. The obtained outcome indicates that incorporation of information about uncertainty of compound activity prediction can be of great help during virtual screening experiments.

Improved method of structure-based virtual screening based on ensemble learning

Virtual screening has become a successful alternative and complementary technique to experimental high-throughput screening technologies for drug design. Since the scoring function of docking software cannot predict binding affinity accurately, how to improve the hit rate remains a common issue in structure-based virtual screening. This paper proposed a target-specific virtual screening method based on ensemble learning named ENS-VS. In this method, protein-ligand interaction energy terms and structure vectors of the ligands were used as a combination descriptor. Support vector machine, decision tree and Fisher linear discriminant classifiers were integrated into ENS-VS for predicting the activity of the compounds. The results showed that the enrichment factor (EF) 1% of ENS-VS was 6 times higher than that of Autodock vina. Compared with the newest virtual screening method SIEVE-Score, the mean EF 1% and AUC of ENS-VS (mean EF 1% = 52.77, AUC = 0.982) were statistically significantly higher than those of SIEVE-Score (mean EF 1% = 42.64, AUC = 0.912) on DUD-E datasets; and the mean EF 1% and AUC of ENS-VS (mean EF 1% = 29.73, AUC = 0.793) were also higher than those of SIEVE-Score (mean EF 1% = 25.56, AUC = 0.765) on eight DEKOIS datasets. ENS-VS also showed significant improvements compared with other similar research. The source code is available at https://github.com/eddyblue/ENS-VS.

Can machine learning consistently improve the scoring power of classical scoring functions? Insights into the role of machine learning in scoring functions

How to accurately estimate protein-ligand binding affinity remains a key challenge in computer-aided drug design (CADD). In many cases, it has been shown that the binding affinities predicted by classical scoring functions (SFs) cannot correlate well with experimentally measured biological activities. In the past few years, machine learning (ML)-based SFs have gradually emerged as potential alternatives and outperformed classical SFs in a series of studies. In this study, to better recognize the potential of classical SFs, we have conducted a comparative assessment of 25 commonly used SFs. Accordingly, the scoring power was systematically estimated by using the state-of-the-art ML methods that replaced the original multiple linear regression method to refit individual energy terms. The results show that the newly-developed ML-based SFs consistently performed better than classical ones. In particular, gradient boosting decision tree (GBDT) and random forest (RF) achieved the best predictions in most cases. The newly-developed ML-based SFs were also tested on another benchmark modified from PDBbind v2007, and the impacts of structural and sequence similarities were evaluated. The results indicated that the superiority of the ML-based SFs could be fully guaranteed when sufficient similar targets were contained in the training set. Moreover, the effect of the combinations of features from multiple SFs was explored, and the results indicated that combining NNscore2.0 with one to four other classical SFs could yield the best scoring power. However, it was not applicable to derive a generic target-specific SF or SF combination.

A prospective compound screening contest identified broader inhibitors for Sirtuin 1

Potential inhibitors of a target biomolecule, NAD-dependent deacetylase Sirtuin 1, were identified by a contest-based approach, in which participants were asked to propose a prioritized list of 400 compounds from a designated compound library containing 2.5 million compounds using in silico methods and scoring. Our aim was to identify target enzyme inhibitors and to benchmark computer-aided drug discovery methods under the same experimental conditions. Collecting compound lists derived from various methods is advantageous for aggregating compounds with structurally diversified properties compared with the use of a single method. The inhibitory action on Sirtuin 1 of approximately half of the proposed compounds was experimentally accessed. Ultimately, seven structurally diverse compounds were identified.

Mimicking Strategy for Protein-Protein Interaction Inhibitor Discovery by Virtual Screening

As protein–protein interactions (PPIs) are highly involved in most cellular processes, the discovery of PPI inhibitors that mimic the structure of the natural protein partners is a promising strategy toward the discovery of PPI inhibitors. In this review, we discuss recent advances in the application of virtual screening for identifying mimics of protein partners. The classification and function of the mimicking protein partner inhibitor discovery by virtual screening are described. We anticipate that this review would be of interest to medicinal chemists and chemical biologists working in the field of protein–protein interaction inhibitors or probes.

Molecular Dynamics Simulation reveals the mechanism by which the Influenza Cap-dependent Endonuclease acquires resistance against Baloxavir marboxil

Baloxavir marboxil (BXM), an antiviral drug for influenza virus, inhibits RNA replication by binding to RNA replication cap-dependent endonuclease (CEN) of influenza A and B viruses. Although this drug was only approved by the FDA in October 2018, drug resistant viruses have already been detected from clinical trials owing to an I38 mutation of CEN. To investigate the reduction of drug sensitivity by the I38 mutant variants, we performed a molecular dynamics (MD) simulation on the CEN-BXM complex structure to analyze variations in the mode of interaction. Our simulation results suggest that the side chain methyl group of I38 in CEN engages in a CH-pi interaction with the aromatic ring of BXM. This interaction is abolished in various I38 mutant variants. Moreover, MD simulation on various mutation models and binding free energy prediction by MM/GBSA method suggest that the I38 mutation precludes any interaction with the aromatic ring of BXA and thereby reduces BXA sensitivity.

Target-Specific Prediction of Ligand Affinity with Structure-Based Interaction Fingerprints

Discovery and optimization of small molecule inhibitors as therapeutic drugs have immensely benefited from rational structure-based drug design. With recent advances in high-resolution structure determination, computational power, and machine learning methodology, it is becoming more tractable to elucidate the structural basis of drug potency. However, the applicability of machine learning models to drug design is limited by the interpretability of the resulting models in terms of feature importance. Here, we take advantage of the large number of available inhibitor-bound HIV-1 protease structures and associated potencies to evaluate inhibitor diversity and machine learning models to predict ligand affinity. First, using a hierarchical clustering approach, we grouped HIV-1 protease inhibitors and identified distinct core structures. Explicit features including protein-ligand interactions were extracted from high-resolution cocrystal structures as 3D-based fingerprints. We found that a gradient boosting machine learning model with this explicit feature attribution can predict binding affinity with high accuracy. Finally, Shapley values were derived to explain local feature importance. We found specific van der Waals (vdW) interactions of key protein residues are pivotal for the predicted potency. Protein-specific and interpretable prediction models can guide the optimization of many small molecule drugs for improved potency.