Automated discovery of noncovalent inhibitors of SARS-CoV-2 main protease by consensus Deep Docking of 40 billion small molecules

In silico screening of LRRK2 WDR domain inhibitors using deep docking and free energy simulations

The Critical Assessment of Computational Hit-Finding Experiments (CACHE) Challenge series is focused on identifying small molecule inhibitors of protein targets using computational methods. Each challenge contains two phases, hit-finding and follow-up optimization, each of which is followed by experimental validation of the computational predictions. For the CACHE Challenge #1, the Leucine-Rich Repeat Kinase 2 (LRRK2) WD40 Repeat (WDR) domain was selected as the target for in silico hit-finding and optimization. Mutations in LRRK2 are the most common genetic cause of the familial form of Parkinson's disease. The LRRK2 WDR domain is an understudied drug target with no known molecular inhibitors. Herein we detail the first phase of our winning submission to the CACHE Challenge #1. We developed a framework for the high-throughput structure-based virtual screening of a chemically diverse small molecule space. Hit identification was performed using the large-scale Deep Docking (DD) protocol followed by absolute binding free energy (ABFE) simulations. ABFEs were computed using an automated molecular dynamics (MD)-based thermodynamic integration (TI) approach. 4.1 billion ligands from Enamine REAL were screened with DD followed by ABFEs computed by MD TI for 793 ligands. 76 ligands were prioritized for experimental validation, with 59 compounds successfully synthesized and 5 compounds identified as hits, yielding a 8.5% hit rate. Our results demonstrate the efficacy of the combined DD and ABFE approaches for hit identification for a target with no previously known hits. This approach is widely applicable for the efficient screening of ultra-large chemical libraries as well as rigorous protein-ligand binding affinity estimation leveraging modern computational resources.

Structure-based virtual screening of vast chemical space as a starting point for drug discovery

Structure-based virtual screening aims to find molecules forming favorable interactions with a biological macromolecule using computational models of complexes. The recent surge of commercially available chemical space provides the opportunity to search for ligands of therapeutic targets among billions of compounds. This review offers a compact overview of structure-based virtual screens of vast chemical spaces, highlighting successful applications in early drug discovery for therapeutically important targets such as G protein-coupled receptors and viral enzymes. Emphasis is placed on strategies to explore ultra-large chemical libraries and synergies with emerging machine learning techniques. The current opportunities and future challenges of virtual screening are discussed, indicating that this approach will play an important role in the next-generation drug discovery pipeline.

Emerging structure-based computational methods to screen the exploding accessible chemical space

Structure-based virtual screening can be a valuable approach to computationally select hit candidates based on their predicted interaction with a protein of interest. The recent explosion in the size of chemical libraries increases the chances of hitting high-quality compounds during virtual screening exercises but also poses new challenges as the number of chemically accessible molecules grows faster than the computing power necessary to screen them. We review here two novel approaches rapidly gaining in popularity to address this problem: machine learning-accelerated and synthon-based library screening. We summarize the results from seminal proof-of-concept studies, highlight the latest developments, and discuss limitations and future directions.

SchNetPack Hyperparameter Optimization for a More Reliable Top Docking Scores Prediction

Options to improve the extrapolation power of the neural network designed using the SchNetPack package with respect to top docking scores prediction are presented. It is shown that hyperparameter tuning of the atomistic model representation (in the schnetpack.representation) improves the prediction of the top scoring compounds, which have characteristically a low incidence in randomized data sets for training of machine learning models. The prediction robustness is evaluated according to the mean square error (MSE) and the entropy of the average loss landscape decrease. Admittedly, the improvement of the top scoring compounds' prediction accuracy comes with the penalty of worsening the overall prediction power. It is revealed that the most impactful hyperparameter is the cutoff (5 Å is reported as the optimal choice). Other parameters (e.g., number of radial basis functions, number of interaction layers of the neural network, feature vector size or its batch size) are found to not affect the prediction robustness of the top scoring compounds in any comparable way relative to the cutoff. The MSE of the best docking score prediction (below -13 kcal/mol) improves from ca. 3.5 to 0.9 kcal/mol, while the prediction of less potent compounds (-13 to -11 kcal/mol) shows a lesser improvement, i.e., a decrease of MSE from 1.6 to 1.3 kcal/mol. Additionally, oversampling and undersampling of the training set with respect to the top scoring compounds' abundance is presented. The results indicate that the cutoff choice performs better than over- or undersampling of the training set, with undersampling performing better than oversampling.

Machine learning combines atomistic simulations to predict SARS-CoV-2 Mpro inhibitors from natural compounds

To date, the COVID-19 pandemic has still been infectious around the world, continuously causing social and economic damage on a global scale. One of the most important therapeutic targets for the treatment of COVID-19 is the main protease (Mpro) of SARS-CoV-2. In this study, we combined machine-learning (ML) model with atomistic simulations to computationally search for highly promising SARS-CoV-2 Mpro inhibitors from the representative natural compounds of the National Cancer Institute (NCI) Database. First, the trained ML model was used to scan the library quickly and reliably for possible Mpro inhibitors. The ML output was then confirmed using atomistic simulations integrating molecular docking and molecular dynamic simulations with the linear interaction energy scheme. The results turned out to show that there was evidently good agreement between ML and atomistic simulations. Ten substances were proposed to be able to inhibit SARS-CoV-2 Mpro. Seven of them have high-nanomolar affinity and are very potential inhibitors. The strategy has been proven to be reliable and appropriate for fast prediction of SARS-CoV-2 Mpro inhibitors, benefiting for new emerging SARS-CoV-2 variants in the future accordingly.

Protein Structure-Based Organic Chemistry-Driven Ligand Design from Ultralarge Chemical Spaces

Ultralarge chemical spaces describing several billion compounds are revolutionizing hit identification in early drug discovery. Because of their size, such chemical spaces cannot be fully enumerated and require ad-hoc computational tools to navigate them and pick potentially interesting hits. We here propose a structure-based approach to ultralarge chemical space screening in which commercial chemical reagents are first docked to the target of interest and then directly connected according to organic chemistry and topological rules, to enumerate drug-like compounds under three-dimensional constraints of the target. When applied to bespoke chemical spaces of different sizes and chemical complexity targeting two receptors of pharmaceutical interest (estrogen β receptor, dopamine D3 receptor), the computational method was able to quickly enumerate hits that were either known ligands (or very close analogs) of targeted receptors as well as chemically novel candidates that could be experimentally confirmed by in vitro binding assays. The proposed approach is generic, can be applied to any docking algorithm, and requires few computational resources to prioritize easily synthesizable hits from billion-sized chemical spaces.

Compromise in Docking Power of Liganded Crystal Structures of Mpro SARS-CoV-2 Surpasses 90% Success Rate

Herein, we present the capacity of three different molecular docking programs (AutoDock, AutoDock Vina, and PLANTS) to identify and reproduce the binding modes of ligands present in 247 covalent and 169 noncovalent complex crystal structures of the severe acute respiratory syndrome coronavirus 2 main protease (Mpro). The compromise in docking power is evaluated with respect to their ability to generate poses similar to the crystal structure binding mode (heavy atoms' root-mean-square deviation < 2 Å) and their ability to recognize the native binding mode with an included compensation for the scoring function error. Noncovalently bound inhibitors are best modeled by AutoDock Vina (90.6% success rate in the active site), while the most relevant results for covalently bound inhibitors are produced by PLANTS (93.0%). AutoDock shows acceptable performance for both types of ligands, 81.1 and 76.4% for noncovalent and covalent complexes, respectively. All three programs manifest worse performance when reproducing surface-bound ligands. Comparison with other works illustrates the importance of crystal structure processing (12% of noncovalent and 26% of covalent ligands had to be manually corrected), proper sampling protocol settings, and inclusion of root-mean-square deviation (RMSD)/scoring function error compensations in crystal structure pose identification. Results are analyzed with respect to a clustering scheme of the noncovalently bound ligands and the chemical reaction type of the covalent ligand bound to the Cys145 residue. A comparison of screening power based on the docking scores of noncovalent ligands from the crystal structures with a "Directory of Useful Decoys, Enhanced" set of known decoys (6562 compounds) and ZINC15 in vivo subset (60,394 compounds) is provided. Ligand and protein input files are provided for future benchmarking purposes.

Integrating QSAR modelling and deep learning in drug discovery: the emergence of deep QSAR

Quantitative structure-activity relationship (QSAR) modelling, an approach that was introduced 60 years ago, is widely used in computer-aided drug design. In recent years, progress in artificial intelligence techniques, such as deep learning, the rapid growth of databases of molecules for virtual screening and dramatic improvements in computational power have supported the emergence of a new field of QSAR applications that we term 'deep QSAR'. Marking a decade from the pioneering applications of deep QSAR to tasks involved in small-molecule drug discovery, we herein describe key advances in the field, including deep generative and reinforcement learning approaches in molecular design, deep learning models for synthetic planning and the application of deep QSAR models in structure-based virtual screening. We also reflect on the emergence of quantum computing, which promises to further accelerate deep QSAR applications and the need for open-source and democratized resources to support computer-aided drug design.

Docking and other computing tools in drug design against SARS-CoV-2

The use of computer simulation methods has become an indispensable component in identifying drugs against the SARS-CoV-2 coronavirus. There is a huge body of literature on application of molecular modelling to predict inhibitors against target proteins of SARS-CoV-2. To keep our review clear and readable, we limited ourselves primarily to works that use computational methods to find inhibitors and test the predicted compounds experimentally either in target protein assays or in cell culture with live SARS-CoV-2. Some works containing results of experimental discovery of corresponding inhibitors without using computer modelling are included as examples of a success. Also, some computational works without experimental confirmations are also included if they attract our attention either by simulation methods or by databases used. This review collects studies that use various molecular modelling methods: docking, molecular dynamics, quantum mechanics, machine learning, and others. Most of these studies are based on docking, and other methods are used mainly for post-processing to select the best compounds among those found through docking. Simulation methods are presented concisely, information is also provided on databases of organic compounds that can be useful for virtual screening, and the review itself is structured in accordance with coronavirus target proteins.

On the origins of SARS-CoV-2 main protease inhibitors

In order to address the world-wide health challenge caused by the COVID-19 pandemic, the 3CL protease/SARS-CoV-2 main protease (SARS-CoV-2-Mpro) coded by its nsp5 gene became one of the biochemical targets for the design of antiviral drugs. In less than 3 years of research, 4 inhibitors of SARS-CoV-2-Mpro have actually been authorized for COVID-19 treatment (nirmatrelvir, ensitrelvir, leritrelvir and simnotrelvir) and more such as EDP-235, FB-2001 and STI-1558/Olgotrelvir or five undisclosed compounds (CDI-988, ASC11, ALG-097558, QLS1128 and H-10517) are undergoing clinical trials. This review is an attempt to picture this quite unprecedented medicinal chemistry feat and provide insights on how these cysteine protease inhibitors were discovered. Since many series of covalent SARS-CoV-2-Mpro inhibitors owe some of their origins to previous work on other proteases, we first provided a description of various inhibitors of cysteine-bearing human caspase-1 or cathepsin K, as well as inhibitors of serine proteases such as human dipeptidyl peptidase-4 or the hepatitis C protein complex NS3/4A. This is then followed by a description of the results of the approaches adopted (repurposing, structure-based and high throughput screening) to discover coronavirus main protease inhibitors.

HIt Discovery using docking ENriched by GEnerative Modeling (HIDDEN GEM): A novel computational workflow for accelerated virtual screening of ultra-large chemical libraries

Recent rapid expansion of make-on-demand, purchasable, chemical libraries comprising dozens of billions or even trillions of molecules has challenged the efficient application of traditional structure-based virtual screening methods that rely on molecular docking. We present a novel computational methodology termed HIDDEN GEM (HIt Discovery using Docking ENriched by GEnerative Modeling) that greatly accelerates virtual screening. This workflow uniquely integrates machine learning, generative chemistry, massive chemical similarity searching and molecular docking of small, selected libraries in the beginning and the end of the workflow. For each target, HIDDEN GEM nominates a small number of top-scoring virtual hits prioritized from ultra-large chemical libraries. We have benchmarked HIDDEN GEM by conducting virtual screening campaigns for 16 diverse protein targets using Enamine REAL Space library comprising 37 billion molecules. We show that HIDDEN GEM yields the highest enrichment factors as compared to state of the art accelerated virtual screening methods, while requiring the least computational resources. HIDDEN GEM can be executed with any docking software and employed by users with limited computational resources.

Medicinal chemistry strategies towards the development of non-covalent SARS-CoV-2 Mpro inhibitors

The main protease (Mpro) of SARS-CoV-2 is an attractive target in anti-COVID-19 therapy for its high conservation and major role in the virus life cycle. The covalent Mpro inhibitor nirmatrelvir (in combination with ritonavir, a pharmacokinetic enhancer) and the non-covalent inhibitor ensitrelvir have shown efficacy in clinical trials and have been approved for therapeutic use. Effective antiviral drugs are needed to fight the pandemic, while non-covalent Mpro inhibitors could be promising alternatives due to their high selectivity and favorable druggability. Numerous non-covalent Mpro inhibitors with desirable properties have been developed based on available crystal structures of Mpro. In this article, we describe medicinal chemistry strategies applied for the discovery and optimization of non-covalent Mpro inhibitors, followed by a general overview and critical analysis of the available information. Prospective viewpoints and insights into current strategies for the development of non-covalent Mpro inhibitors are also discussed.

Molecular Dynamics and Other HPC Simulations for Drug Discovery

High performance computing (HPC) is taking an increasingly important place in drug discovery. It makes possible the simulation of complex biochemical systems with high precision in a short time, thanks to the use of sophisticated algorithms. It promotes the advancement of knowledge in fields that are inaccessible or difficult to access through experimentation and it contributes to accelerating the discovery of drugs for unmet medical needs while reducing costs. Herein, we report how computational performance has evolved over the past years, and then we detail three domains where HPC is essential. Molecular dynamics (MD) is commonly used to explore the flexibility of proteins, thus generating a better understanding of different possible approaches to modulate their activity. Modeling and simulation of biopolymer complexes enables the study of protein-protein interactions (PPI) in healthy and disease states, thus helping the identification of targets of pharmacological interest. Virtual screening (VS) also benefits from HPC to predict in a short time, among millions or billions of virtual chemical compounds, the best potential ligands that will be tested in relevant assays to start a rational drug design process.

The prediction of main protease SARS-CoV-2 inhibition based on models of enzyme-inhibitor complexes

A set of linear regression equations predicting the IC50 values for SARS-CoV-2 main protease inhibitors was analyzed. For 180 competitive inhibitors, we have simulated the molecular dynamics of enzyme-inhibitor complexes with known structures or modeled using molecular docking. In the docking procedure, the selection of final poses was restricted by similarity to known structural analogs. The values of the energy contributions obtained by means of calculation of the free energy change of the enzyme-inhibitor complex performed by two variants of the MMPBSA (MMGBSA) method and a number of physicochemical characteristics of the inhibitors were used as independent variables. During the learning process, indicator variables were used for inhibitor subsets obtained from various literature sources to compensate the existing systematic deviations from the target value. A leave one out and leave 20% out cross validation procedures were used to evaluate the prediction quality. For the total logarithmic range width of 3.71, the mean error in predicting the lg(IC50) value was 0.45 log units. The stability of the prediction depending on the variability of the complex in molecular dynamics was investigated.

ChemFlow_py: a flexible toolkit for docking and rescoring

The design of accurate virtual screening tools is an open challenge in drug discovery. Several structure-based methods have been developed at different levels of approximation. Among them, molecular docking is an established technique with high efficiency, but typically low accuracy. Moreover, docking performances are known to be target-dependent, which makes the choice of the docking program and corresponding scoring function critical when approaching a new protein target. To compare the performances of different docking protocols, we developed ChemFlow_py, an automated tool to perform docking and rescoring. Using four protein systems extracted from DUD-E with 100 known active compounds and 3000 decoys per target, we compared the performances of several rescoring strategies including consensus scoring. We found that the average docking results can be improved by consensus ranking, which emphasizes the relevance of consensus scoring when little or no chemical information is available for a given target. ChemFlow_py is a free toolkit to optimize the performances of virtual high-throughput screening (vHTS). The software is publicly available at https://github.com/IFMlab/ChemFlow_py .

An interaction-based drug discovery screen explains known SARS-CoV-2 inhibitors and predicts new compound scaffolds

The recent outbreak of the COVID-19 pandemic caused by severe acute respiratory syndrome-Coronavirus-2 (SARS-CoV-2) has shown the necessity for fast and broad drug discovery methods to enable us to react quickly to novel and highly infectious diseases. A well-known SARS-CoV-2 target is the viral main 3-chymotrypsin-like cysteine protease (M^pro), known to control coronavirus replication, which is essential for the viral life cycle. Here, we applied an interaction-based drug repositioning algorithm on all protein-compound complexes available in the protein database (PDB) to identify M^pro inhibitors and potential novel compound scaffolds against SARS-CoV-2. The screen revealed a heterogeneous set of 692 potential M^pro inhibitors containing known ones such as Dasatinib, Amodiaquine, and Flavin mononucleotide, as well as so far untested chemical scaffolds. In a follow-up evaluation, we used publicly available data published almost two years after the screen to validate our results. In total, we are able to validate 17% of the top 100 predictions with publicly available data and can furthermore show that predicted compounds do cover scaffolds that are yet not associated with M^pro. Finally, we detected a potentially important binding pattern consisting of 3 hydrogen bonds with hydrogen donors of an oxyanion hole within the active side of M^pro. Overall, these results give hope that we will be better prepared for future pandemics and that drug development will become more efficient in the upcoming years.

Large-Scale Virtual Screening for the Discovery of SARS-CoV-2 Papain-like Protease (PLpro) Non-covalent Inhibitors

The rapid global spread of the SARS-CoV-2 virus facilitated the development of novel direct-acting antiviral agents (DAAs). The papain-like protease (PLpro) has been proposed as one of the major SARS-CoV-2 targets for DAAs due to its dual role in processing viral proteins and facilitating the host's immune suppression. This dual role makes identifying small molecules that can effectively neutralize SARS-CoV-2 PLpro activity a high-priority task. However, PLpro drug discovery faces a significant challenge due to the high mobility and induced-fit effects in the protease's active site. Herein, we virtually screened the ZINC20 database with Deep Docking (DD) to identify prospective noncovalent PLpro binders and combined ultra-large consensus docking with two pharmacophore (ph4)-filtering strategies. The analysis of active compounds revealed their somewhat-limited diversity, likely attributed to the induced-fit nature of PLpro's active site in the crystal structures, and therefore, the use of rigid docking protocols poses inherited limitations. The top hits were assessed against recombinant viral proteins and live viruses, demonstrating desirable inhibitory activities. The best compound VPC-300195 (IC₅₀: 15 μM) ranks among the top noncovalent PLpro inhibitors discovered through in silico methodologies. In the search for novel SARS-CoV-2 PLpro-specific chemotypes, the identified inhibitors could serve as diverse templates for the development of effective noncovalent PLpro inhibitors.

Advances in the discovery of new chemotypes through ultra-large library docking

INTRODUCTION

The size and complexity of virtual screening libraries in drug discovery have skyrocketed in recent years, reaching up to multiple billions of accessible compounds. However, virtual screening of such ultra-large libraries poses several challenges associated with preparing the libraries, sampling, and pre-selection of suitable compounds. The utilization of artificial intelligence (AI)-assisted screening approaches, such as deep learning, poses a promising countermeasure to deal with this rapidly expanding chemical space. For example, various AI-driven methods were recently successfully used to identify novel small molecule inhibitors of the SARS-CoV-2 main protease (M^pro).

AREAS COVERED

This review focuses on presenting various kinds of virtual screening methods suitable for dealing with ultra-large libraries. Challenges associated with these computational methodologies are discussed, and recent advances are highlighted in the example of the discovery of novel M^pro inhibitors targeting the SARS-CoV-2 virus.

EXPERT OPINION

With the rapid expansion of the virtual chemical space, the methodologies for docking and screening such quantities of molecules need to keep pace. Employment of AI-driven screening compounds has already been shown to be effective in a range from a few thousand to multiple billion compounds, furthered by de novo generation of drug-like molecules without human interference.

Role of SARS-CoV-2 Spike-Protein-Induced Activation of Microglia and Mast Cells in the Pathogenesis of Neuro-COVID

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) causes coronavirus disease 2019 (COVID-19). About 45% of COVID-19 patients experience several symptoms a few months after the initial infection and develop post-acute sequelae of SARS-CoV-2 (PASC), referred to as "Long-COVID," characterized by persistent physical and mental fatigue. However, the exact pathogenetic mechanisms affecting the brain are still not well-understood. There is increasing evidence of neurovascular inflammation in the brain. However, the precise role of the neuroinflammatory response that contributes to the disease severity of COVID-19 and long COVID pathogenesis is not clearly understood. Here, we review the reports that the SARS-CoV-2 spike protein can cause blood-brain barrier (BBB) dysfunction and damage neurons either directly, or via activation of brain mast cells and microglia and the release of various neuroinflammatory molecules. Moreover, we provide recent evidence that the novel flavanol eriodictyol is particularly suited for development as an effective treatment alone or together with oleuropein and sulforaphane (ViralProtek®), all of which have potent anti-viral and anti-inflammatory actions.

Surely you are joking, Mr Docking!

In the wake of recent COVID-19 pandemics scientists around the world rushed to deliver numerous CADD (Computer-Aided Drug Discovery) methods and tools that could be reliably used to discover novel drug candidates against the SARS-CoV-2 virus. With that, there emerged a trend of a significant democratization of CADD that contributed to the rapid development of various COVID-19 drug candidates currently undergoing different stages of validation. On the other hand, this democratization also inadvertently led to the surge rapidly performed molecular docking studies to nominate multiple scores of novel drug candidates supported by computational arguments only. Albeit driven by best intentions, most of such studies also did not follow best practices in the field that require experience and expertise learned through multiple rigorously designed benchmarking studies and rigorous experimental validation. In this Viewpoint we reflect on recent disbalance between small number of rigorous and comprehensive studies and the proliferation of purely computational studies enabled by the ease of docking software availability. We further elaborate on the hyped oversale of CADD methods' ability to rapidly yield viable drug candidates and reiterate the critical importance of rigor and adherence to the best practices of CADD in view of recent emergence of AI and Big Data in the field.

Development of Optimal Virtual Screening Strategies to Identify Novel Toll-Like Receptor Ligands Using the DockBox Suite

Toll-like receptors (TLRs) represent attractive targets for developing modulators for the treatment of many pathologies, including inflammation, cancer, and autoimmune diseases. Here, we describe a protocol based on the DockBox package that enables to set up and perform structure-based virtual screening in order to increase the chance of identifying novel TLR ligands from chemical libraries.

Characterizing the ligand-binding affinity toward SARS-CoV-2 Mpro via physics- and knowledge-based approaches

Computational approaches, including physics- and knowledge-based methods, have commonly been used to determine the ligand-binding affinity toward SARS-CoV-2 main protease (Mpro or 3CLpro). Strong binding ligands can thus be suggested as potential inhibitors for blocking the biological activity of the protease. In this context, this paper aims to provide a short review of computational approaches that have recently been applied in the search for inhibitor candidates of Mpro. In particular, molecular docking and molecular dynamics (MD) simulations are usually combined to predict the binding affinity of thousands of compounds. Quantitative structure-activity relationship (QSAR) is the least computationally demanding and therefore can be used for large chemical collections of ligands. However, its accuracy may not be high. Moreover, the quantum mechanics/molecular mechanics (QM/MM) method is most commonly used for covalently binding inhibitors, which also play an important role in inhibiting the activity of SARS-CoV-2. Furthermore, machine learning (ML) models can significantly increase the searching space of ligands with high accuracy for binding affinity prediction. Physical insights into the binding process can then be confirmed via physics-based calculations. Integration of ML models into computational chemistry provides many more benefits and can lead to new therapies sooner.

[The prediction of SARS-CoV-2 main protease inhibition with filtering by position of ligand]

The paper analyzes a set of equations that adequately predict the IC50 value for SARS-CoV-2 main protease inhibitors. The training set was obtained using filtering by criteria independent of prediction of target value. It included 76 compounds, and the test set included nine compounds. We used the values of energy contributions obtained in the calculation of the change of the free energy of complex by MMGBSA method and a number of characteristics of the physical and chemical properties of the inhibitors as independent variables. It is sufficient to use only seven independent variables without loss of prediction quality (Q² = 0.79; R²prediction = 0.89). The maximum error in this case does not exceed 0.92 lg(IC50) units with a full range of observed values from 1.26 to 4.95.

Deep learning-based molecular dynamics simulation for structure-based drug design against SARS-CoV-2

Coronavirus disease 2019 (COVID-19), caused by severe acute respiratory syndrome coronavirus type 2 (SARS-CoV-2), has led to a global pandemic. Deep learning (DL) technology and molecular dynamics (MD) simulation are two mainstream computational approaches to investigate the geometric, chemical and structural features of protein and guide the relevant drug design. Despite a large amount of research papers focusing on drug design for SARS-COV-2 using DL architectures, it remains unclear how the binding energy of the protein-protein/ligand complex dynamically evolves which is also vital for drug development. In addition, traditional deep neural networks usually have obvious deficiencies in predicting the interaction sites as protein conformation changes. In this review, we introduce the latest progresses of the DL and DL-based MD simulation approaches in structure-based drug design (SBDD) for SARS-CoV-2 which could address the problems of protein structure and binding prediction, drug virtual screening, molecular docking and complex evolution. Furthermore, the current challenges and future directions of DL-based MD simulation for SBDD are also discussed.

Ligand Binding Prediction Using Protein Structure Graphs and Residual Graph Attention Networks

Computational prediction of ligand–target interactions is a crucial part of modern drug discovery as it helps to bypass high costs and labor demands of in vitro and in vivo screening. As the wealth of bioactivity data accumulates, it provides opportunities for the development of deep learning (DL) models with increasing predictive powers. Conventionally, such models were either limited to the use of very simplified representations of proteins or ineffective voxelization of their 3D structures. Herein, we present the development of the PSG-BAR (Protein Structure Graph-Binding Affinity Regression) approach that utilizes 3D structural information of the proteins along with 2D graph representations of ligands. The method also introduces attention scores to selectively weight protein regions that are most important for ligand binding. Results: The developed approach demonstrates the state-of-the-art performance on several binding affinity benchmarking datasets. The attention-based pooling of protein graphs enables identification of surface residues as critical residues for protein–ligand binding. Finally, we validate our model predictions against an experimental assay on a viral main protease (Mpro)—the hallmark target of SARS-CoV-2 coronavirus.

Structures of the SARS-CoV-2 spike glycoprotein and applications for novel drug development

COVID-19 caused by SARS-CoV-2 has raised a health crisis worldwide. The high morbidity and mortality associated with COVID-19 and the lack of effective drugs or vaccines for SARS-CoV-2 emphasize the urgent need for standard treatment and prophylaxis of COVID-19. The receptor-binding domain (RBD) of the glycosylated spike protein (S protein) is capable of binding to human angiotensin-converting enzyme 2 (hACE2) and initiating membrane fusion and virus entry. Hence, it is rational to inhibit the RBD activity of the S protein by blocking the RBD interaction with hACE2, which makes the glycosylated S protein a potential target for designing and developing antiviral agents. In this study, the molecular features of the S protein of SARS-CoV-2 are highlighted, such as the structures, functions, and interactions of the S protein and ACE2. Additionally, computational tools developed for the treatment of COVID-19 are provided, for example, algorithms, databases, and relevant programs. Finally, recent advances in the novel development of antivirals against the S protein are summarized, including screening of natural products, drug repurposing and rational design. This study is expected to provide novel insights for the efficient discovery of promising drug candidates against the S protein and contribute to the development of broad-spectrum anti-coronavirus drugs to fight against SARS-CoV-2.

Targeting SARS-CoV-2 Papain-Like Protease in the Post-Vaccine Era

While vaccines remain at the forefront of global healthcare responses, pioneering therapeutics against SARS-CoV-2 are expected to fill the gaps for waning immunity. Rapid development and approval of orally available direct-acting antivirals targeting crucial SARS-CoV-2 proteins marked the beginning of the era of small-molecule drugs for COVID-19. In that regard, the papain-like protease (PLpro) can be considered a major SARS-CoV-2 therapeutic target due to its dual biological role in suppressing host innate immune responses and in ensuring viral replication. Here, we summarize the challenges of targeting PLpro and innovative early-stage PLpro-specific small molecules. We propose that state-of-the-art computer-aided drug design (CADD) methodologies will play a critical role in the discovery of PLpro compounds as a novel class of COVID-19 drugs.

Maximizing the integration of virtual and experimental screening in hit discovery

INTRODUCTION

Experimental and virtual screening contributes to the discovery of more than 50% of clinical candidates. Considering the similar concept and goals, early-phase drug discovery would benefit from the effective integration of these approaches.

AREAS COVERED

After reviewing the recent trends in both experimental and virtual screening, the authors discuss different integration strategies from parallel, focused, sequential, and iterative screening. Strategic considerations are demonstrated in a number of real-life case studies.

EXPERT OPINION

Experimental and virtual screening are complementary approaches that should be integrated in lead discovery settings. Virtual screening can access extremely large synthetically feasible chemical space that can be effectively searched on GPU clusters or cloud architectures. Experimental screening provides reliable datasets by quantitative HTS applications, and DNA-encoded libraries (DEL) have enlarged the chemical space covered by these technologies. These developments, together with the use of artificial intelligence methods, represent new options for their efficient integration. The case studies discussed here demonstrate the benefits of complementary strategies, such as focused and iterative screening.

Drugsniffer: An Open Source Workflow for Virtually Screening Billions of Molecules for Binding Affinity to Protein Targets

The SARS-CoV2 pandemic has highlighted the importance of efficient and effective methods for identification of therapeutic drugs, and in particular has laid bare the need for methods that allow exploration of the full diversity of synthesizable small molecules. While classical high-throughput screening methods may consider up to millions of molecules, virtual screening methods hold the promise of enabling appraisal of billions of candidate molecules, thus expanding the search space while concurrently reducing costs and speeding discovery. Here, we describe a new screening pipeline, called drugsniffer, that is capable of rapidly exploring drug candidates from a library of billions of molecules, and is designed to support distributed computation on cluster and cloud resources. As an example of performance, our pipeline required ∼40,000 total compute hours to screen for potential drugs targeting three SARS-CoV2 proteins among a library of ∼3.7 billion candidate molecules.