Empirical Scoring Functions for Structure-Based Virtual Screening: Applications, Critical Aspects, and Challenges

Addressing docking pose selection with structure-based deep learning: Recent advances, challenges and opportunities

Molecular docking is a widely used technique in drug discovery to predict the binding mode of a given ligand to its target. However, the identification of the near-native binding pose in docking experiments still represents a challenging task as the scoring functions currently employed by docking programs are parametrized to predict the binding affinity, and, therefore, they often fail to correctly identify the ligand native binding conformation. Selecting the correct binding mode is crucial to obtaining meaningful results and to conveniently optimizing new hit compounds. Deep learning (DL) algorithms have been an area of a growing interest in this sense for their capability to extract the relevant information directly from the protein-ligand structure. Our review aims to present the recent advances regarding the development of DL-based pose selection approaches, discussing limitations and possible future directions. Moreover, a comparison between the performances of some classical scoring functions and DL-based methods concerning their ability to select the correct binding mode is reported. In this regard, two novel DL-based pose selectors developed by us are presented.

Exploring Binding Pockets in the Conformational States of the SARS-CoV-2 Spike Trimers for the Screening of Allosteric Inhibitors Using Molecular Simulations and Ensemble-Based Ligand Docking

Understanding mechanisms of allosteric regulation remains elusive for the SARS-CoV-2 spike protein, despite the increasing interest and effort in discovering allosteric inhibitors of the viral activity and interactions with the host receptor ACE2. The challenges of discovering allosteric modulators of the SARS-CoV-2 spike proteins are associated with the diversity of cryptic allosteric sites and complex molecular mechanisms that can be employed by allosteric ligands, including the alteration of the conformational equilibrium of spike protein and preferential stabilization of specific functional states. In the current study, we combine conformational dynamics analysis of distinct forms of the full-length spike protein trimers and machine-learning-based binding pocket detection with the ensemble-based ligand docking and binding free energy analysis to characterize the potential allosteric binding sites and determine structural and energetic determinants of allosteric inhibition for a series of experimentally validated allosteric molecules. The results demonstrate a good agreement between computational and experimental binding affinities, providing support to the predicted binding modes and suggesting key interactions formed by the allosteric ligands to elicit the experimentally observed inhibition. We establish structural and energetic determinants of allosteric binding for the experimentally known allosteric molecules, indicating a potential mechanism of allosteric modulation by targeting the hinges of the inter-protomer movements and blocking conformational changes between the closed and open spike trimer forms. The results of this study demonstrate that combining ensemble-based ligand docking with conformational states of spike protein and rigorous binding energy analysis enables robust characterization of the ligand binding modes, the identification of allosteric binding hotspots, and the prediction of binding affinities for validated allosteric modulators, which is consistent with the experimental data. This study suggested that the conformational adaptability of the protein allosteric sites and the diversity of ligand bound conformations are both in play to enable efficient targeting of allosteric binding sites and interfere with the conformational changes.

Dynamic Profiling and Binding Affinity Prediction of NBTI Antibacterials against DNA Gyrase Enzyme by Multidimensional Machine Learning and Molecular Dynamics Simulations

Bacterial type II topoisomerases are well-characterized and clinically important targets for antibacterial chemotherapy. Novel bacterial topoisomerase inhibitors (NBTIs) are a newly disclosed class of antibacterials. Prediction of their binding affinity to these enzymes would be beneficial for de novo design/optimization of new NBTIs. Utilizing in vitro NBTI experimental data, we constructed two comprehensive multidimensional DNA gyrase surrogate models for Staphylococcus aureus (q2 = 0.791) and Escherichia coli (q2 = 0.806). Both models accurately predicted the IC50s of 26 NBTIs from our recent studies. To investigate the NBTI's dynamic profile and binding to both targets, 10 selected NBTIs underwent molecular dynamics (MD) simulations. The analysis of MD production trajectories confirmed key hydrogen-bonding and hydrophobic contacts that NBTIs establish in both enzymes. Moreover, the binding free energies of selected NBTIs were computed by the linear interaction energy (LIE) method employing an in-house derived set of fitting parameters (α = 0.16, β = 0.029, γ = 0.0, and intercept = -1.72), which are successfully applicable to DNA gyrase of Gram-positive/Gram-negative pathogens. Both methods offer accurate predictions of the binding free energies of NBTIs against S. aureus and E. coli DNA gyrase. We are confident that this integrated modeling approach could be valuable in the de novo design and optimization of efficient NBTIs for combating resistant bacterial pathogens.

A review on natural sweeteners, sweet taste modulators and bitter masking compounds: structure-activity strategies for the discovery of novel taste molecules

Growing demand for the tasty and healthy food has driven the development of low-calorie sweeteners, sweet taste modulators, and bitter masking compounds originated from natural sources. With the discovery of human taste receptors, increasing numbers of sweet taste modulators have been identified through human taste response and molecular docking techniques. However, the discovery of novel taste-active molecules in nature can be accelerated by using advanced spectrometry technologies based on structure-activity relationships (SARs). SARs explain why structurally similar compounds can elicit similar taste qualities. Given the characterization of structural information from reported data, strategies employing SAR techniques to find structurally similar compounds become an innovative approach to expand knowledge of sweeteners. This review aims to summarize the structural patterns of known natural non-nutritive sweeteners, sweet taste enhancers, and bitter masking compounds. Innovative SAR-based approaches to explore sweetener derivatives are also discussed. Most sweet-tasting flavonoids belong to either the flavanonols or the dihydrochalcones and known bitter masking molecules are flavanones. Based on SAR findings that structural similarities are related to the sensory properties, innovative methodologies described in this paper can be applied to screen and discover the derivatives of taste-active compounds or potential taste modulators.

Unravelling the potential of Triflusal as an anti-TB repurposed drug by targeting replication protein DciA

The increasing prevalence of drug-resistant Tuberculosis (TB) is imposing extreme difficulties in controlling the TB infection rate globally, making treatment critically challenging. To combat the prevailing situation, it is crucial to explore new anti-TB drugs with a novel mechanism of action and high efficacy. The Mycobacterium tuberculosis (M.tb)DciA is an essential protein involved in bacterial replication and regulates its growth. DciA interacts with DNA and provides critical help in binding other replication machinery proteins to the DNA. Moreover, the lack of any structural homology of M.tb DciA with human proteins makes it an appropriate target for drug development. In this study, FDA-approved drugs were virtually screened against M.tb DciA to identify potential inhibitors. Four drugs namely Lanreotide, Risedronate, Triflusal, and Zoledronic acid showed higher molecular docking scores. Further, molecular dynamics simulations analysis of DciA-drugs complexes reported stable interaction, more compactness, and reduced atomic motion. The anti-TB activity of drugs was further evaluated under in vitro and ex vivo conditions where Triflusal was observed to have the best possible activity with the MIC of 25 μg/ml. Our findings present novel DciA inhibitors and anti-TB activity of Triflusal. Further investigations on the use of Triflusal may lead to the discovery of a new anti-TB drug.

Computational resources and chemoinformatics for translational health research

The integration of computational resources and chemoinformatics has revolutionized translational health research. It has offered a powerful set of tools for accelerating drug discovery. This chapter overviews the computational resources and chemoinformatics methods used in translational health research. The resources and methods can be used to analyze large datasets, identify potential drug candidates, predict drug-target interactions, and optimize treatment regimens. These resources have the potential to transform the drug discovery process and foster personalized medicine research. We discuss insights into their various applications in translational health and emphasize the need for addressing challenges, promoting collaboration, and advancing the field to fully realize the potential of these tools in transforming healthcare.

Identification and characterization of domain-specific inhibitors of DENV NS3 and NS5 proteins by in silico screening methods

The dengue virus (DENV) infects approximately 400 million people annually worldwide causing significant morbidity and mortality. Despite advances in understanding the virus life cycle and infectivity, no specific treatment for this disease exists due to the lack of therapeutic drugs. In addition, vaccines available currently are ineffective with severe side effects. Therefore, there is an urgent need for developing therapeutics suitable for effective management of DENV infection. In this study, we adopted a drug repurposing strategy to identify new therapeutic use of existing FDA approved drug molecules to target DENV2 non-structural proteins NS3 and NS5 using computational approaches. We used Drugbank database molecules for virtual screening and multiple docking analysis against a total of four domains, the NS3 protease and helicase domains and NS5 MTase and RdRp domains. Subsequently, MD simulations and MM-PBSA analysis were performed to validate the intrinsic atomic interactions and the binding affinities. Furthermore, the internal dynamics in all four protein domains, in presence of drug molecule binding were assessed using essential dynamics and free energy landscape analyses, which were further coupled with conformational dynamics-based clustering studies and cross-correlation analysis to map the regions that exhibit these structural variations. Our comprehensive analysis identified tolcapone, cefprozil, delavirdine and indinavir as potential inhibitors of NS5 MTase, NS5 RdRp, NS3 protease and NS3 helicase functions, respectively. These high-confidence candidate molecules will be useful for developing effective anti-DENV therapy to combat dengue infection.Communicated by Ramaswamy H. Sarma.

Considerations Around Structure-Based Drug Discovery for KRAS Using DOCK

Molecular docking is a popular computational tool in drug discovery. Leveraging structural information, docking software predicts binding poses of small molecules to cavities on the surfaces of proteins. Virtual screening for ligand discovery is a useful application of docking software. In this chapter, using the enigmatic KRAS protein as an example system, we endeavor to teach the reader about best practices for performing molecular docking with UCSF DOCK. We discuss methods for virtual screening and docking molecules on KRAS. We present the following six points to optimize our docking setup for prosecuting a virtual screen: protein structure choice, pocket selection, optimization of the scoring function, modification of sampling spheres and sampling procedures, choosing an appropriate portion of chemical space to dock, and the choice of which top scoring molecules to pick for purchase.

Recent Deep Learning Applications to Structure-Based Drug Design

Identification and optimization of small molecules that bind to and modulate protein function is a crucial step in the early stages of drug development. For decades, this process has benefitted greatly from the use of computational models that can provide insights into molecular binding affinity and optimization. Over the past several years, various types of deep learning models have shown great potential in improving and enhancing the performance of traditional computational methods. In this chapter, we provide an overview of recent deep learning-based developments with applications in drug discovery. We classify these methods into four subcategories dependent on the task each method is aiming to solve. For each subcategory, we provide the general framework of the approach and discuss individual methods.

A Review on Molecular Docking As an Interpretative Tool for Molecular Targets in Disease Management

One of the most often utilized methods for drug discovery is molecular docking. With docking, one may discover new therapeutically relevant molecules by targeting the molecule and predicting the target-ligand interactions as well as different conformation of ligand at various positions. The prediction signifies the effectiveness of the molecule or the developed molecule having different affinity with target. Drug discovery plays an important role in the development of a new drug molecule of different moiety attached to it, which leads us in the management of several diseases. In silico approach led us to identification of numerous diseases caused by virus, fungi, bacteria, protozoa, and other microorganisms that affect human health. By means of computational approach, we can categorize disease symptoms and use the drugs available for such types of warning signs. After the docking process, molecular dynamics computational technique helps in the simulation of the physical movement of atoms and molecules for a fixed period of time, giving a view of the dynamic evaluation of the system. This review is an attempt to illustrate the role of molecular docking in drug development.

In Silico Screening of Natural Flavonoids against 3-Chymotrypsin-like Protease of SARS-CoV-2 Using Machine Learning and Molecular Modeling

The "Long-COVID syndrome" has posed significant challenges due to a lack of validated therapeutic options. We developed a novel multi-step virtual screening strategy to reliably identify inhibitors against 3-chymotrypsin-like protease of SARS-CoV-2 from abundant flavonoids, which represents a promising source of antiviral and immune-boosting nutrients. We identified 57 interacting residues as contributors to the protein-ligand binding pocket. Their energy interaction profiles constituted the input features for Machine Learning (ML) models. The consensus of 25 classifiers trained using various ML algorithms attained 93.9% accuracy and a 6.4% false-positive-rate. The consensus of 10 regression models for binding energy prediction also achieved a low root-mean-square error of 1.18 kcal/mol. We screened out 120 flavonoid hits first and retained 50 drug-like hits after predefined ADMET filtering to ensure bioavailability and safety profiles. Furthermore, molecular dynamics simulations prioritized nine bioactive flavonoids as promising anti-SARS-CoV-2 agents exhibiting both high structural stability (root-mean-square deviation < 5 Å for 218 ns) and low MM/PBSA binding free energy (<-6 kcal/mol). Among them, KB-2 (PubChem-CID, 14630497) and 9-O-Methylglyceofuran (PubChem-CID, 44257401) displayed excellent binding affinity and desirable pharmacokinetic capabilities. These compounds have great potential to serve as oral nutraceuticals with therapeutic and prophylactic properties as care strategies for patients with long-COVID syndrome.

In the quest for histone deacetylase inhibitors: current trends in the application of multilayered computational methods

Histone deacetylase (HDAC) inhibitors have gained attention over the past three decades because of their potential in the treatment of different diseases including various forms of cancers, neurodegenerative disorders, autoimmune, inflammatory diseases, and other metabolic disorders. To date, 5 HDAC inhibitor drugs are marketed for the treatment of hematological malignancies and several drug-candidate HDAC inhibitors are at different stages of clinical trials. However, due to the toxic side effects of these drugs resulting from the lack of target selectivity, active studies are ongoing to design and develop either class-selective or isoform-selective inhibitors. Computational methods have aided the discovery of HDAC inhibitors with the desired potency and/or selectivity. These methods include ligand-based approaches such as scaffold hopping, pharmacophore modeling, three-dimensional quantitative structure-activity relationships (3D-QSAR); and structure-based virtual screening (molecular docking). The current trends involve the application of the combination of these methods and incorporating molecular dynamics simulations coupled with Poisson-Boltzmann/molecular mechanics generalized Born surface area (MM-PBSA/MM-GBSA) to improve the prediction of ligand binding affinity. This review aimed at understanding the current trends in applying these multilayered strategies and their contribution to the design/identification of HDAC inhibitors.

Ensemble-based virtual screening of African natural products to target human thymidylate synthase

Human thymidylate synthase (hTS) is a validated drug target for chemotherapy. A virtual screening experiment was used to prioritize a list of compounds from African Natural Products Databases docked against the orthosteric binding pocket of hTS. Consensus scores of binding affinities from ensemble-based virtual screening, hydrated docking and MM-PBSA calculations ranked compounds NEA4433 and NEA4434 as the best candidates owing to binding affinity scores in the picomolar order, their excellent ADMET profiles and the good stability of the protein-ligand complexes formed. The current study demonstrates the role of water in small molecule binding to hTS in mediating protein-ligand interactions. Similarly, the robust ensemble docking (relaxed scheme complex) ranked NEA4433 and NEA4434 as the best candidates. Furthermore, the best candidates prioritized were shown to strongly interact with the same residues that interacted with hTS substrate and cofactor.

Artificial intelligence in small molecule drug discovery from 2018 to 2023: Does it really work?

Utilizing artificial intelligence (AI) in drug design represents an advanced approach for identifying targets and developing new drugs. Integrating AI techniques significantly reduces the workload involved in drug development and enhances the efficiency of early-stage drug discovery. This review aims to present a comprehensive overview of the utilization of AI methods in the field of small drug design, with a specific focus on four key areas: protein structure prediction, molecular virtual screening, molecular design, and absorption, distribution, metabolism, excretion, and toxicity (ADMET) prediction. Additionally, the role and limitations of AI in drug development are explored, and the impact of AI on decision-making processes is studied. It is important to note that while AI can bring numerous benefits to the early stage of drug development, the direction and quality of decision-making should still be emphasized, as AI should be considered as a tool rather than a decisive factor.

In-vitro and in-silico studies of annelated 1,4,7,8-tetrahydroazocine ester derivatives as nanomolar selective inhibitors of human butyrylcholinesterase

Based on previous finding showing 2,3,6,11-tetrahydro-1H-azocino[4,5-b]indole as suitable scaffold of novel inhibitors of acetylcholinesterase (AChE), a main target of drugs for the treatment of Alzheimer's disease and related dementias, herein we investigated diverse newly and previously synthesized β-enamino esters (and ketones) derivatives of 1,4,7,8-tetrahydroazocines (and some azonines) fused with benzene, 1H-indole, 4H-chromen-4-one and pyrimidin-4(3H)-one. Twenty derivatives of diversely annelated eight-to-nine-membered azaheterocyclic ring, prepared through domino reaction of the respective tetrahydropyridine and azepine with activated alkynes, were assayed for the inhibitory activity against AChE and butyrylcholinesterase (BChE). As a major outcome, compound 7c, an alkylamino derivative of tetrahydropyrimido[4,5-d]azocine, was found to be a highly potent BChE-selective inhibitor, which showed a noncompetitive/mixed-type inhibition mechanism against human BChE with single digit nanomolar inhibition constant (Ki = 7.8 ± 0.2 nM). The four-order magnitude BChE-selectivity of 7c clearly reflects the effect of lipophilicity upon binding to the BChE binding cavity. The ChEs' inhibition data, interpreted by chemoinformatic tools and an in-depth in-silico study (molecular docking combined with molecular dynamics calculations), not only highlighted key structural factors enhancing inhibition potency and selectivity toward BChE, but also shed light on subtle differences distinguishing the binding sites of equine BChE from the recombinant human BChE. Compound 7c inhibited P-glycoprotein with IC50 of 0.27 μM, which may support its ability to permeate blood-brain barrier, and proved to be no cytotoxic in human liver cancer cell line (HepG2) at the BChE bioactive concentrations. Overall, the biological profile allows us to envision 7c as a promising template to improve design and development of BChE-selective ligands of pharmaceutical interest, including inhibitors and fluorogenic probes.

Anatomy of Potency Predictions Focusing on Structural Analogues with Increasing Potency Differences Including Activity Cliffs

Potency predictions are popular in compound design and optimization but are complicated by intrinsic limitations. Moreover, even for nonlinear methods, activity cliffs (ACs, formed by structural analogues with large potency differences) represent challenging test cases for compound potency predictions. We have devised a new test system for potency predictions, including AC compounds, that is based on partitioned matched molecular pairs (MMP) and makes it possible to monitor prediction accuracy at the level of analogue pairs with increasing potency differences. The results of systematic predictions using different machine learning and control methods on MMP-based data sets revealed increasing prediction errors when potency differences between corresponding training and test compounds increased, including large prediction errors for AC compounds. At the global level, these prediction errors were not apparent due to the statistical dominance of analogue pairs with small potency differences. Test compounds from such pairs were accurately predicted and determined the observed global prediction accuracy. Shapley value analysis, an explainable artificial intelligence approach, was applied to identify structural features determining potency predictions using different methods. The analysis revealed that numerical predictions of different regression models were determined by features that were shared by MMP partner compounds or absent in these compounds, with opposing effects. These findings provided another rationale for accurate predictions of similar potency values for structural analogues and failures in predicting the potency of AC compounds.

Pangenomic and immunoinformatics based analysis of Nipah virus revealed CD4+ and CD8+ T-Cell epitopes as potential vaccine candidates

Introduction: Nipah (NiV) is the zoonotic deadly bat-borne virus that causes neurological and respiratory infections which ultimately lead to death. There are 706 infected cases reported up till now especially in Asia, out of which 409 patients died. There is no vaccine and effective treatment available for NiV infections and we have to timely design such strategies as world could not bear another pandemic situation. Methods: In this study, we screened viral proteins of NiV strains based on pangenomics analysis, antigenicity, molecular weight, and sub-cellular localization. The immunoproteomics based approach was used to predict T-cell epitopes of MHC class-I and II as potential vaccine candidates. These epitopes are capable to activate CD4+, CD8+, and T-cell dependent B-lymphocytes. Results: The two surface proteins including fusion glycoprotein (F) and attachment glycoprotein (G) are antigenic with molecular weights of 60 kDa and 67 kDa respectively. Three epitopes of F protein (VNYNSEGIA, PNFILVRNT, and IKMIPNVSN) were ranked and selected based on the binding affinity with MHC class-I, and 3 epitopes (VILNKRYYS, ILVRNTLIS, and VKLQETAEK) with MHC-II molecules. Similarly, for G protein, 3 epitopes each for MHC-I (GKYDKVMPY, ILKPKLISY, and KNKIWCISL) and MHC-II (LRNIEKGKY, FLIDRINWI, and FLLKNKIWC) with substantial binding energies were predicted. Based on the physicochemical properties, all these epitopes are non-toxic, hydrophilic, and stable. Conclusion: Our vaccinomics and system-level investigation could help to trigger the host immune system to prevent NiV infection.

Applying molecular docking to pesticides

Pesticide creation is related to the development of sustainable agricultural and ecological safety, and molecular docking technology can effectively help in pesticide innovation. This paper introduces the basic theory behind molecular docking, pesticide databases, and docking software. It also summarizes the application of molecular docking in the pesticide field, including the virtual screening of lead compounds, detection of pesticides and their metabolites in the environment, reverse screening of pesticide targets, and the study of resistance mechanisms. Finally, problems with the use of molecular docking technology in pesticide creation are discussed, and prospects for the future use of molecular docking technology in new pesticide development are discussed. © 2023 Society of Chemical Industry.

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 .

A generalized protein-ligand scoring framework with balanced scoring, docking, ranking and screening powers

Applying machine learning algorithms to protein-ligand scoring functions has aroused widespread attention in recent years due to the high predictive accuracy and affordable computational cost. Nevertheless, most machine learning-based scoring functions are only applicable to a specific task, e.g., binding affinity prediction, binding pose prediction or virtual screening, suggesting that the development of a scoring function with balanced performance in all critical tasks remains a grand challenge. To this end, we propose a novel parameterization strategy by introducing an adjustable binding affinity term that represents the correlation between the predicted outcomes and experimental data into the training of mixture density network. The resulting residue-atom distance likelihood potential not only retains the superior docking and screening power over all the other state-of-the-art approaches, but also achieves a remarkable improvement in scoring and ranking performance. We emphatically explore the impacts of several key elements on prediction accuracy as well as the task preference, and demonstrate that the performance of scoring/ranking and docking/screening tasks of a certain model could be well balanced through an appropriate manner. Overall, our study highlights the potential utility of our innovative parameterization strategy as well as the resulting scoring framework in future structure-based drug design.

SS-GNN: A Simple-Structured Graph Neural Network for Affinity Prediction

Efficient and effective drug-target binding affinity (DTBA) prediction is a challenging task due to the limited computational resources in practical applications and is a crucial basis for drug screening. Inspired by the good representation ability of graph neural networks (GNNs), we propose a simple-structured GNN model named SS-GNN to accurately predict DTBA. By constructing a single undirected graph based on a distance threshold to represent protein-ligand interactions, the scale of the graph data is greatly reduced. Moreover, ignoring covalent bonds in the protein further reduces the computational cost of the model. The graph neural network-multilayer perceptron (GNN-MLP) module takes the latent feature extraction of atoms and edges in the graph as two mutually independent processes. We also develop an edge-based atom-pair feature aggregation method to represent complex interactions and a graph pooling-based method to predict the binding affinity of the complex. We achieve state-of-the-art prediction performance using a simple model (with only 0.6 M parameters) without introducing complicated geometric feature descriptions. SS-GNN achieves Pearson's R_p = 0.853 on the PDBbind v2016 core set, outperforming state-of-the-art GNN-based methods by 5.2%. Moreover, the simplified model structure and concise data processing procedure improve the prediction efficiency of the model. For a typical protein-ligand complex, affinity prediction takes only 0.2 ms. All codes are freely accessible at https://github.com/xianyuco/SS-GNN.

A Review on Artificial Intelligence Approaches and Rational Approaches in Drug Discovery

Artificial intelligence (AI) speeds up the drug development process and reduces its time, as well as the cost which is of enormous importance in outbreaks such as COVID-19. It uses a set of machine learning algorithms that collects the available data from resources, categorises, processes and develops novel learning methodologies. Virtual screening is a successful application of AI, which is used in screening huge drug-like databases and filtering to a small number of compounds. The brain's thinking of AI is its neural networking which uses techniques such as Convoluted Neural Network (CNN), Recursive Neural Network (RNN) or Generative Adversial Neural Network (GANN). The application ranges from small molecule drug discovery to the development of vaccines. In the present review article, we discussed various techniques of drug design, structure and ligand-based, pharmacokinetics and toxicity prediction using AI. The rapid phase of discovery is the need of the hour and AI is a targeted approach to achieve this.

Updates on drug designing approach through computational strategies: a review

The drug discovery and development (DDD) process in pursuit of novel drug candidates is a challenging procedure requiring lots of time and resources. Therefore, computer-aided drug design (CADD) methodologies are used extensively to promote proficiency in drug development in a systematic and time-effective manner. The point in reference is SARS-CoV-2 which has emerged as a global pandemic. In the absence of any confirmed drug moiety to treat the infection, the science fraternity adopted hit and trial methods to come up with a lead drug compound. This article is an overview of the virtual methodologies, which assist in finding novel hits and help in the progression of drug development in a short period with a specific medicinal solution.

Targeting EGFR, RSK1, RAF1, PARP2 and LIN28B for several cancer type therapies with newly synthesized pyrazole derivatives via a computational study

Cancer remains the leading cause of death in the world despite the significant advancements made in anticancer drug discovery. This study is aimed to computationally evaluate the efficacy of 63 in-house synthesized pyrazole derivatives targeted to bind with prominent cancer targets namely EGFR, RSK1, RAF1, PARP2 and LIN28B known to be expressed, respectively, in lung, colon, skin, ovarian and pancreatic cancer cells. Initially, we perform the molecular docking investigations for all pyrazole compounds with a comparison to known standard drugs for each target. Docking studies have revealed that some pyrazole compounds possess better binding affinity scores than standard drug compounds. Thereafter, a long-range of 1 μs molecular dynamic (MD) simulation study for top ranked docked compounds with all respective proteins was carried out to assess the interaction stability in a dynamic environment. The results suggested that the top ranked complexes showed a stable interaction profile for a longer period of time. The outcome of this study suggests that pyrazole compounds, M33, M36, M76 and M77, are promising molecular candidates that can modulate the studied target proteins significantly in comparison to their known inhibitor based on their selective binding interactions profile. Furthermore, ADME-T profile has been explored to check for the drug-likeness and pharmacokinetics profiles and found that all proposed compounds exhibited acceptable values for being a potential drug-like candidate with non-toxic characteristics. Overall, extensive computational investigations indicate that the four proposed pyrazole inhibitors/modulators studied against each respective target protein will be helpful for future cancer therapeutic developments.Communicated by Ramaswamy H. Sarma.

Algorithm selection for protein-ligand docking: strategies and analysis on ACE

The present study investigates the use of algorithm selection for automatically choosing an algorithm for any given protein-ligand docking task. In drug discovery and design process, conceptualizing protein-ligand binding is a major problem. Targeting this problem through computational methods is beneficial in order to substantially reduce the resource and time requirements for the overall drug development process. One way of addressing protein-ligand docking is to model it as a search and optimization problem. There have been a variety of algorithmic solutions in this respect. However, there is no ultimate algorithm that can efficiently tackle this problem, both in terms of protein-ligand docking quality and speed. This argument motivates devising new algorithms, tailored to the particular protein-ligand docking scenarios. To this end, this paper reports a machine learning-based approach for improved and robust docking performance. The proposed set-up is fully automated, operating without any expert opinion or involvement both on the problem and algorithm aspects. As a case study, an empirical analysis was performed on a well-known protein, Human Angiotensin-Converting Enzyme (ACE), with 1428 ligands. For general applicability, AutoDock 4.2 was used as the docking platform. The candidate algorithms are also taken from AutoDock 4.2. Twenty-eight distinctly configured Lamarckian-Genetic Algorithm (LGA) are chosen to build an algorithm set. ALORS which is a recommender system-based algorithm selection system was preferred for automating the selection from those LGA variants on a per-instance basis. For realizing this selection automation, molecular descriptors and substructure fingerprints were employed as the features characterizing each target protein-ligand docking instance. The computational results revealed that algorithm selection outperforms all those candidate algorithms. Further assessment is reported on the algorithms space, discussing the contributions of LGA's parameters. As it pertains to protein-ligand docking, the contributions of the aforementioned features are examined, which shed light on the critical features affecting the docking performance.

Designing highly potent compounds using a chemical language model

Compound potency prediction is a major task in medicinal chemistry and drug design. Inspired by the concept of activity cliffs (which encode large differences in potency between similar active compounds), we have devised a new methodology for predicting potent compounds from weakly potent input molecules. Therefore, a chemical language model was implemented consisting of a conditional transformer architecture for compound design guided by observed potency differences. The model was evaluated using a newly generated compound test system enabling a rigorous assessment of its performance. It was shown to predict known potent compounds from different activity classes not encountered during training. Moreover, the model was capable of creating highly potent compounds that were structurally distinct from input molecules. It also produced many novel candidate compounds not included in test sets. Taken together, the findings confirmed the ability of the new methodology to generate structurally diverse highly potent compounds.

Past, Present, and Future Perspectives on Computer-Aided Drug Design Methodologies

The application of computational approaches in drug discovery has been consolidated in the last decades. These families of techniques are usually grouped under the common name of "computer-aided drug design" (CADD), and they now constitute one of the pillars in the pharmaceutical discovery pipelines in many academic and industrial environments. Their implementation has been demonstrated to tremendously improve the speed of the early discovery steps, allowing for the proficient and rational choice of proper compounds for a desired therapeutic need among the extreme vastness of the drug-like chemical space. Moreover, the application of CADD approaches allows the rationalization of biochemical and interactive processes of pharmaceutical interest at the molecular level. Because of this, computational tools are now extensively used also in the field of rational 3D design and optimization of chemical entities starting from the structural information of the targets, which can be experimentally resolved or can also be obtained with other computer-based techniques. In this work, we revised the state-of-the-art computer-aided drug design methods, focusing on their application in different scenarios of pharmaceutical and biological interest, not only highlighting their great potential and their benefits, but also discussing their actual limitations and eventual weaknesses. This work can be considered a brief overview of computational methods for drug discovery.

Large-Scale Predictions of Compound Potency with Original and Modified Activity Classes Reveal General Prediction Characteristics and Intrinsic Limitations of Conventional Benchmarking Calculations

Predicting compound potency is a major task in computational medicinal chemistry, for which machine learning is often applied. This study systematically predicted compound potency values for 367 target-based compound activity classes from medicinal chemistry using a preferred machine learning approach and simple control methods. The predictions produced unexpectedly similar results for different classes and comparably high accuracy for machine learning and simple control models. Based on these findings, the influence of different data set modifications on relative prediction accuracies was explored, including potency range balancing, removal of nearest neighbors, and analog series-based compound partitioning. The predictions were surprisingly resistant to these modifications, leading to only small error margin increases. These findings also show that conventional benchmark settings are unsuitable for directly comparing potency prediction methods.

Designing of 2,3-dihydrobenzofuran derivatives as inhibitors of PDE1B using pharmacophore screening, ensemble docking and molecular dynamics approach

In recent years, the PDE1B enzyme has become a desirable drug target for the treatment of psychological and neurological disorders, particularly schizophrenia disorder, due to the expression of PDE1B in brain regions involved in volitional behaviour, learning and memory. Although several inhibitors of PDE1 have been identified using different methods, none of these inhibitors has reached the market yet. Thus, searching for novel PDE1B inhibitors is considered a major scientific challenge. In this study, pharmacophore-based screening, ensemble docking and molecular dynamics simulations have been performed to identify a lead inhibitor of PDE1B with a new chemical scaffold. Five PDE1B crystal structures have been utilised in the docking study to improve the possibility of identifying an active compound compared to the use of a single crystal structure. Finally, the structure-activity- relationship was studied, and the structure of the lead molecule was modified to design novel inhibitors with a high affinity for PDE1B. As a result, two novel compounds have been designed that exhibited a higher affinity to PDE1B compared to the lead compound and the other designed compounds.

Biochemical analysis, photosynthetic gene (psbA) down–regulation, and in silico receptor prediction in weeds in response to exogenous application of phenolic acids and their analogs

Chemical herbicides are the primary weed management tool, although several incidences of herbicide resistance have emerged, causing serious threat to agricultural sustainability. Plant derived phenolic acids with herbicidal potential provide organic and eco-friendly substitute to such harmful chemicals. In present study, phytotoxicity of two phenolic compounds, ferulic acid (FA) and gallic acid (GA), was evaluated in vitro and in vivo against three prevalent herbicide-resistant weed species (Sinapis arvensis, Lolium multiflorum and Parthenium hysterophorus). FA and GA not only suppressed the weed germination (80 to 60% respectively), but also negatively affected biochemical and photosynthetic pathway of weeds. In addition to significantly lowering the total protein and chlorophyll contents of the targeted weed species, the application of FA and GA treatments increased levels of antioxidant enzymes and lipid peroxidation. Photosynthetic gene (psbA) expression was downregulated (10 to 30 folds) post 48 h of phenolic application. In silico analysis for receptor identification of FA and GA in psbA protein (D1) showed histidine (his-198) and threonine (thr-286) as novel receptors of FA and GA. These two receptors differ from the D1 amino acid receptors which have previously been identified (serine-264 and histidine-215) in response to PSII inhibitor herbicides. Based on its toxicity responses, structural analogs of FA were also designed. Four out of twelve analogs (0.25 mM) significantly inhibited weed germination (30 to 40%) while enhancing their oxidative stress. These results are unique which provide fundamental evidence of phytotoxicity of FA and GA and their analogs to develop cutting-edge plant based bio-herbicides formulation in future.

Computational and artificial intelligence-based methods for antibody development

Due to their high target specificity and binding affinity, therapeutic antibodies are currently the largest class of biotherapeutics. The traditional largely empirical antibody development process is, while mature and robust, cumbersome and has significant limitations. Substantial recent advances in computational and artificial intelligence (AI) technologies are now starting to overcome many of these limitations and are increasingly integrated into development pipelines. Here, we provide an overview of AI methods relevant for antibody development, including databases, computational predictors of antibody properties and structure, and computational antibody design methods with an emphasis on machine learning (ML) models, and the design of complementarity-determining region (CDR) loops, antibody structural components critical for binding.

Predicting Potent Compounds Using a Conditional Variational Autoencoder Based upon a New Structure-Potency Fingerprint

Prediction of the potency of bioactive compounds generally relies on linear or nonlinear quantitative structure-activity relationship (QSAR) models. Nonlinear models are generated using machine learning methods. We introduce a novel approach for potency prediction that depends on a newly designed molecular fingerprint (FP) representation. This structure-potency fingerprint (SPFP) combines different modules accounting for the structural features of active compounds and their potency values in a single bit string, hence unifying structure and potency representation. This encoding enables the derivation of a conditional variational autoencoder (CVAE) using SPFPs of training compounds and apply the model to predict the SPFP potency module of test compounds using only their structure module as input. The SPFP-CVAE approach correctly predicts the potency values of compounds belonging to different activity classes with an accuracy comparable to support vector regression (SVR), representing the state-of-the-art in the field. In addition, highly potent compounds are predicted with very similar accuracy as SVR and deep neural networks.

Molecular dynamics, MMGBSA, and docking studies of natural products conjugated to tumor-targeted peptide for targeting BRAF V600E and MERTK receptors

Recent studies have revealed that MERTK and BRAF V600E receptors have been found to be over-expressed in several types of cancers including melanoma, making these receptors targets for drug design. In this study, we have designed novel peptide conjugates with the natural products vanillic acid, thiazole-2-carboxylic acid, cinnamic acid, theanine, and protocatechuic acid. Each of these compounds was conjugated with the tumor targeting peptide sequence TAASGVRSMH, known to bind to NG2 and target tumor neovasculature. We examined their binding affinities and stability with MERTK and BRAF V600E receptors using molecular docking and molecular dynamics studies. Compared to the neat compounds, the peptide conjugates displayed higher binding affinity toward both receptors. In the case of MERTK, the most stable complexes were formed with di-theaninate-peptide, vanillate-peptide, and thiazole-2-amido peptide conjugates and binding occurred in the hinge region. Additionally, it was discovered that the peptide alone also had high binding ability and stability with the MERTK receptor. In the case of BRAF V600E, the peptide conjugates of protocatechuate, vanillate and thiazole-2-amido peptide conjugates showed the formation of the most stable complexes and binding occurred in the ATP binding cleft. Further analysis revealed that the number of hydrogen bonds and hydrophobic interactions played a critical role in enhanced stability of the complexes. Docking studies also revealed that binding affinities for NG2 were similar to MERTK and higher for BRAF V600E. MMGBSA studies of the trajectories revealed that the protocatechuate-peptide conjugate showed the highest binding energy with BRAF V600E while the peptide-TAASGVRSMH showed the highest binding energy with MERTK. ADME studies revealed that each of the compounds showed medium to high permeability toward MDCK cells and were not hERG blockers. Furthermore, the conjugates were not CYP inhibitors or substrates, but they were found to be Pgp substrates. Our results indicated that the protocatechuate-TAASGVRSMH, thiazole-2-amido-TAASGVRSMH, and vanillate-TAASGVRSMH conjugates may be furthered developed for in vitro and in vivo studies as novel tumor targeting compounds for tumor cells over-expressing BRAF V600E, while di-theaninate-amido-TAASGVRSMH and thiazole-2-amido-TAASGVRSMH conjugates may be developed for targeting MERTK receptors. These studies provide insight into the molecular interactions of natural product-peptide conjugates and their potential for binding to and targeting MERTK and BRAF V600E receptors in developing new therapeutics for targeting cancer.

Targeting human thymidylate synthase: Ensemble-based virtual screening for drug repositioning and the role of water

A drug repositioning computational approach was carried to search inhibitors for human thymidylate synthase. An ensemble-based virtual screening of FDA-approved drugs showed the drugs Imatinib, Lumacaftor and Naldemedine to be likely candidates for repurposing. The role of water in the drug-receptor interactions was revealed by the application of an extended AutoDock scoring function that included the water forcefield. The binding affinity scores when hydrated ligands were docked were improved in the drugs considered. Further binding free energy calculations based on the Molecular Mechanics Poisson-Boltzmann Surface Area method revealed that Imatinib, Lumacaftor and Naldemedine scored -130.7 ± 28.1, -210.6 ± 29.9 and -238.0 ± 25.4 kJ/mol, respectively, showing good binding affinity for the candidates considered. Overall, the analysis of the molecular dynamics trajectory of the receptor-drug complexes revealed stable structures for Imatinib, Lumacaftor and Naldemedine, for the entire simulation time.

In vitro and in silico evaluation of antiretrovirals against SARS-CoV-2: A drug repurposing approach

Background

Drug repurposing is a valuable strategy for rapidly developing drugs for treating COVID-19. This study aimed to evaluate the antiviral effect of six antiretrovirals against SARS-CoV-2 in vitro and in silico.

Methods

The cytotoxicity of lamivudine, emtricitabine, tenofovir, abacavir, efavirenz and raltegravir on Vero E6 was evaluated by MTT assay. The antiviral activity of each of these compounds was evaluated via a pre-post treatment strategy. The reduction in the viral titer was assessed by plaque assay. In addition, the affinities of the antiretroviral interaction with viral targets RdRp (RNA-dependent RNA polymerase), ExoN-NSP10 (exoribonuclease and its cofactor, the non-structural protein 10) complex and 3CLpro (3-chymotrypsin-like cysteine protease) were evaluated by molecular docking.

Results

Lamivudine exhibited antiviral activity against SARS-CoV-2 at 200 µM (58.3%) and 100 µM (66.7%), while emtricitabine showed anti-SARS-CoV-2 activity at 100 µM (59.6%), 50 µM (43.4%) and 25 µM (33.3%). Raltegravir inhibited SARS-CoV-2 at 25, 12.5 and 6.3 µM (43.3%, 39.9% and 38.2%, respectively). The interaction between the antiretrovirals and SARS-CoV-2 RdRp, ExoN-NSP10 and 3CLpro yielded favorable binding energies (from -4.9 kcal/mol to -7.7 kcal/mol) using bioinformatics methods.

Conclusion

Lamivudine, emtricitabine and raltegravir showed in vitro antiviral effects against the D614G strain of SARS-CoV-2. Raltegravir was the compound with the greatest in vitro antiviral potential at low concentrations, and it showed the highest binding affinities with crucial SARS-CoV-2 proteins during the viral replication cycle. However, further studies on the therapeutic utility of raltegravir in patients with COVID-19 are required.

Benefits of hybrid QM/MM over traditional classical mechanics in pharmaceutical systems

Hybrid quantum mechanics/molecular mechanics (QM/MM) is one of the most reliable approaches for accurately modeling and studying the complex pharmaceutical discovery system. Classical mechanics has significantly accelerated the drug discovery process in the past decade. However, the current challenge is the large pool of false positives, which require extensive validation. Hybrid QM/MM is an effective solution for accurately studying ligand binding, structural mechanisms, free energy evaluation, and spectroscopic characterization. This article highlights the methodological details relevant to cost-effective hybrid QM/MM methods. This approach, combined with traditional pharmacoinformatics methods, could be a reliable strategy to balance the cost and accuracy of the calculations.

Venetoclax: a promising repurposed drug against SARS-CoV-2 main protease

Global health care emergency caused by a new coronavirus (severe acute respiratory syndrome coronavirus 2 or SARS-CoV-2) demands urgent need to repurpose the approved pharmaceutical drugs. Main protease, M^pro of SARS-CoV-2 draws significant attention as a drug target. Herein, we have screened FDA approved organosulfur drugs (till 2016) and our laboratory synthesized organosulfur and organoselenium compounds (L1-L306) against M^pro-apo using docking followed by classical MD simulations. Additionally, a series of compounds (L307-L364) were chosen from previous experimental studies, which were reported to exhibit inhibitory potentials towards M^pro. We found several organosulfur drugs, particularly Venetoclax (FDA approved organosulfur drug for Leukemia) to be a high-affinity binders to the M^pro of SARS-CoV-2. The results reveal that organosulfur compounds including Venetoclax preferentially bind (non-covalently) to the non-catalytic pocket of the protein located in the dimer interface. We found that the ligand binding is primarily favoured by ligand-protein van der Waals interaction and penalized by desolvation effect. Interestingly, Venetoclax binding alters the local flexibility of M^pro and exerts pronounced effect in the C-terminal as well as two loop regions (Loop-A and Loop-B) that play important roles in catalysis. These findings highlighted the importance of drug repurposing and explored the non-catalytic pockets of M^pro in combating COVID-19 infection in addition to the importance of catalytic binding pocket of the protein.Communicated by Ramaswamy H. Sarma.

Pharmacophore model-aided virtual screening combined with comparative molecular docking and molecular dynamics for identification of marine natural products as SARS-CoV-2 papain-like protease inhibitors

Targeting SARS-CoV-2 papain-like protease using inhibitors is a suitable approach for inhibition of virus replication and dysregulation of host anti-viral immunity. Engaging all five binding sites far from the catalytic site of PLpro is essential for developing a potent inhibitor. We developed and validated a structure-based pharmacophore model with 9 features of a potent PLpro inhibitor. The pharmacophore model-aided virtual screening of the comprehensive marine natural product database predicted 66 initial hits. This hit library was downsized by filtration through a molecular weight filter of ≤ 500 g/mol. The 50 resultant hits were screened by comparative molecular docking using AutoDock and AutoDock Vina. Comparative molecular docking enables benchmarking docking and relieves the disparities in the search and scoring functions of docking engines. Both docking engines retrieved 3 same compounds at different positions in the top 1 % rank, hence consensus scoring was applied, through which CMNPD28766, aspergillipeptide F emerged as the best PLpro inhibitor. Aspergillipeptide F topped the 50-hit library with a pharmacophore-fit score of 75.916. Favorable binding interactions were predicted between aspergillipeptide F and PLpro similar to the native ligand XR8-24. Aspergillipeptide F was able to engage all the 5 binding sites including the newly discovered BL2 groove, site V. Molecular dynamics for quantification of Cα-atom movements of PLpro after ligand binding indicated that it exhibits highly correlated domain movements contributing to the low free energy of binding and a stable conformation. Thus, aspergillipeptide F is a promising candidate for pharmaceutical and clinical development as a potent SARS-CoV-2 PLpro inhibitor.

Assessing How Residual Errors of Scoring Functions Correlate to Ligand Structural Features

Scoring functions (SFs) are ubiquitous tools for early stage drug discovery. However, their accuracy currently remains quite moderate. Despite a number of successful target-specific SFs appearing recently, up until now, no ideas on how to systematically improve the general scope of SFs have been formulated. In this work, we hypothesized that the specific features of ligands, corresponding to interactions well appreciated by medicinal chemists (e.g., hydrogen bonds, hydrophobic and aromatic interactions), might be responsible, in part, for the remaining SF errors. The latter provides direction to efforts aimed at the rational and systematic improvement of SF accuracy. In this proof-of-concept work, we took a CASF-2016 coreset of 285 ligands as a basis for comparison and calculated the values of scores for a representative panel of SFs (including AutoDock 4.2, AutoDock Vina, X-Score, NNScore2.0, ΔVina RF20, and DSX). The residual error of linear correlation of each SF value, with the experimental values of affinity and activity, was then analyzed in terms of its correlation with the presence of the fragments responsible for certain medicinal chemistry defined interactions. We showed that, despite the fact that SFs generally perform reasonably, there is room for improvement in terms of better parameterization of interactions involving certain fragments in ligands. Thus, this approach opens a potential way for the systematic improvement of SFs without their significant complication. However, the straightforward application of the proposed approach is limited by the scarcity of reliable available data for ligand-receptor complexes, which is a common problem in the field.

DyScore: A Boosting Scoring Method with Dynamic Properties for Identifying True Binders and Nonbinders in Structure-Based Drug Discovery

The accurate prediction of protein-ligand binding affinity is critical for the success of computer-aided drug discovery. However, the accuracy of current scoring functions is usually unsatisfactory due to their rough approximation or sometimes even omittance of many factors involved in protein-ligand binding. For instance, the intrinsic dynamics of the protein-ligand binding state is usually disregarded in scoring function because these rapid binding affinity prediction approaches are only based on a representative complex structure of the protein and ligand in the binding state. That is, the dynamic protein-ligand binding complex ensembles are simplified as a static snapshot in calculation. In this study, two novel features were proposed for characterizing the dynamic properties of protein-ligand binding based on the static structure of the complex, which is expected to be a valuable complement to the current scoring functions. The two features demonstrate the geometry-shape matching between a protein and a ligand as well as the dynamic stability of protein-ligand binding. We further combined these two novel features with several classical scoring functions to develop a binary classification model called DyScore that uses the Extreme Gradient Boosting algorithm to classify compound poses as binders or non-binders. We have found that DyScore achieves state-of-the-art performance in distinguishing active and decoy ligands on both enhanced DUD data set and external test sets with both proposed novel features showing significant contributions to the improved performance. Especially, DyScore exhibits superior performance on early recognition, a crucial requirement for success in virtual screening and de novo drug design. The standalone version of DyScore and Dyscore-MF are freely available to all at: https://github.com/YanjunLi-CS/dyscore.

Assessment of the Generalization Abilities of Machine-Learning Scoring Functions for Structure-Based Virtual Screening

In structure-based virtual screening (SBVS), it is critical that scoring functions capture protein-ligand atomic interactions. By focusing on the local domains of ligand binding pockets, a standardized pocket Pfam-based clustering (Pfam-cluster) approach was developed to assess the cross-target generalization ability of machine-learning scoring functions (MLSFs). Subsequently, 12 typical MLSFs were evaluated using random cross-validation (Random-CV), protein sequence similarity-based cross-validation (Seq-CV), and pocket Pfam-based cross-validation (Pfam-CV) methods. Surprisingly, all of the tested models showed decreased performances from Random-CV to Seq-CV to Pfam-CV experiments, not showing satisfactory generalization capacity. Our interpretable analysis suggested that the predictions on novel targets by MLSFs were dependent on buried solvent-accessible surface area (SASA)-related features of complex structures, with greater predicted binding affinities on complexes owning larger protein-ligand interfaces. By combining buried SASA-related features with target-specific patterns that were only shared among structurally similar compounds in the same cluster, the random forest (RF)-Score attained a good performance in the Random-CV test. Based on these findings, we strongly advise assessing the generalization ability of MLSFs with the Pfam-cluster approach and being cautious with the features learned by MLSFs.

Metabolomic Profiling, Antioxidant and Enzyme Inhibition Properties and Molecular Docking Analysis of Antarctic Lichens

The lichen species Lecania brialmontii, Pseudephebe pubescens, and Sphaerophorus globosus are part of the prominent lichenoflora of the Antarctic territory. In this work, we report the metabolomic identification of ethanolic extracts of these species, their antioxidant and cholinesterase enzyme inhibitory activity, and conduct a molecular docking analysis with typical compounds. Eighteen compounds were identified by UHPLC-ESI-QTOF-MS in L. brialmontii, 18 compounds in P. pubescens, and 14 compounds in S. globosus. The content of phenolic compounds was variable among the species, ranging from 0.279 to 2.821 mg AG/g, and all three species showed high inhibition potential on the cholinesterase enzymes. Molecular docking showed important interactions between AChE and BChE with the selected compounds. This study evidences the chemical fingerprint of three species of the order Lecanorales that support the continuation of the study of other biological activities and their potential for medical research.

A Hybrid Docking and Machine Learning Approach to Enhance the Performance of Virtual Screening Carried out on Protein-Protein Interfaces

The modulation of protein-protein interactions (PPIs) by small chemical compounds is challenging. PPIs play a critical role in most cellular processes and are involved in numerous disease pathways. As such, novel strategies that assist the design of PPI inhibitors are of major importance. We previously reported that the knowledge-based DLIGAND2 scoring tool was the best-rescoring function for improving receptor-based virtual screening (VS) performed with the Surflex docking engine applied to several PPI targets with experimentally known active and inactive compounds. Here, we extend our investigation by assessing the vs. potential of other types of scoring functions with an emphasis on docking-pose derived solvent accessible surface area (SASA) descriptors, with or without the use of machine learning (ML) classifiers. First, we explored rescoring strategies of Surflex-generated docking poses with five GOLD scoring functions (GoldScore, ChemScore, ASP, ChemPLP, ChemScore with Receptor Depth Scaling) and with consensus scoring. The top-ranked poses were post-processed to derive a set of protein and ligand SASA descriptors in the bound and unbound states, which were combined to derive descriptors of the docked protein-ligand complexes. Further, eight ML models (tree, bagged forest, random forest, Bayesian, support vector machine, logistic regression, neural network, and neural network with bagging) were trained using the derivatized SASA descriptors and validated on test sets. The results show that many SASA descriptors are better than Surflex and GOLD scoring functions in terms of overall performance and early recovery success on the used dataset. The ML models were superior to all scoring functions and rescoring approaches for most targets yielding up to a seven-fold increase in enrichment factors at 1% of the screened collections. In particular, the neural networks and random forest-based ML emerged as the best techniques for this PPI dataset, making them robust and attractive vs. tools for hit-finding efforts. The presented results suggest that exploring further docking-pose derived SASA descriptors could be valuable for structure-based virtual screening projects, and in the present case, to assist the rational design of small-molecule PPI inhibitors.

Analysis of a novel class A β-lactamase OKP-B-6 of Klebsiella quasipneumoniae: structural characterisation and interaction with commercially available drugs

BACKGROUND

Gram-negative and Gram-positive bacteria produce beta-lactamase as factors to overcome beta-lactam antibiotics, causing their hydrolysis and impaired antimicrobial action. Class A beta-lactamase contains the chromosomal sulfhydryl reagent variable (SHV, point mutation variants of SHV-1), LEN (Klebsiella pneumoniae strain LEN-1), and other K. pneumoniae beta-lactamase (OKP) found mostly in Klebsiella’s phylogroups. The SHV known as extended-spectrum β-lactamase can inactivate most beta-lactam antibiotics. Class A also includes the worrisome plasmid-encoded Klebsiella pneumoniae carbapenemase (KPC-2), a carbapenemase that can inactivate most beta-lactam antibiotics, carbapenems, and some beta-lactamase inhibitors.

OBJECTIVES

So far, there is no 3D crystal structure for OKP-B, so our goal was to perform structural characterisation and molecular docking studies of this new enzyme.

METHODS

We applied a homology modelling method to build the OKP-B-6 structure, which was compared with SHV-1 and KPC-2 according to their electrostatic potentials at the active site. Using the DockThor-VS, we performed molecular docking of the SHV-1 inhibitors commercially available as sulbactam, tazobactam, and avibactam against the constructed model of OKP-B-6.

FINDINGS

From the point of view of enzyme inhibition, our results indicate that OKP-B-6 should be an extended-spectrum beta-lactamase (ESBL) susceptible to the same drugs as SHV-1.

MAIN CONCLUSIONS

This conclusion advantageously impacts the clinical control of the bacterial pathogens encoding OKP-B in their genome by using any effective, broad-spectrum, and multitarget inhibitor against SHV-containing bacteria.

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.

MDO: A Computational Protocol for Prediction of Flexible Enzyme-Ligand Binding Mode

AIM

Developing a method for use in computer aided drug design Background: Predicting the structure of enzyme-ligand binding mode is essential for understanding the properties, functions, and mechanisms of the bio-complex, but is rather difficult due to the enormous sampling space involved.

OBJECTIVE

Accurate prediction of enzyme-ligand binding mode conformation.

METHOD

A new computational protocol, MDO, is proposed for finding the structure of ligand binding pose. MDO consists of sampling enzyme sidechain conformations via molecular dynamics simulation of enzyme-ligand system and clustering of the enzyme configurations, sampling ligand binding poses via molecular docking and clustering of the ligand conformations, and the optimal ligand binding pose prediction via geometry optimization and ranking by the ONIOM method. MDO is tested on 15 enzyme-ligand complexes with known accurate structures.

RESULTS

The success rate of MDO predictions, with RMSD < 2 Å, is 67%, substantially higher than the 40% success rate of conventional methods. The MDO success rate can be increased to 83% if the ONIOM calculations are applied only for the starting poses with ligands inside the binding cavities.

CONCLUSION

The MDO protocol provides high quality enzyme-ligand binding mode prediction with reasonable computational cost. The MDO protocol is recommended for use in the structure-based drug design.

Designing drugs when there is low data availability: one-shot learning and other approaches to face the issues of a long-term concern

INTRODUCTION

Modern drug discovery generally is accessed by useful information from previous large databases or uncovering novel data. The lack of biological and/or chemical data tends to slow the development of scientific research and innovation. Here, approaches that may help provide solutions to generate or obtain enough relevant data or improve/accelerate existing methods within the last five years were reviewed.

AREAS COVERED

One-shot learning (OSL) approaches, structural modeling, molecular docking, scoring function space (SFS), molecular dynamics (MD), and quantum mechanics (QM) may be used to amplify the amount of available data to drug design and discovery campaigns, presenting methods, their perspectives, and discussions to be employed in the near future.

EXPERT OPINION

Recent works have successfully used these techniques to solve a range of issues in the face of data scarcity, including complex problems such as the challenging scenario of drug design aimed at intrinsically disordered proteins and the evaluation of potential adverse effects in a clinical scenario. These examples show that it is possible to improve and kickstart research from scarce available data to design and discover new potential drugs.

SCORCH: Improving structure-based virtual screening with machine learning classifiers, data augmentation, and uncertainty estimation

INTRODUCTION

The discovery of a new drug is a costly and lengthy endeavour. The computational prediction of which small molecules can bind to a protein target can accelerate this process if the predictions are fast and accurate enough. Recent machine-learning scoring functions re-evaluate the output of molecular docking to achieve more accurate predictions. However, previous scoring functions were trained on crystalised protein-ligand complexes and datasets of decoys. The limited availability of crystal structures and biases in the decoy datasets can lower the performance of scoring functions.

OBJECTIVES

To address key limitations of previous scoring functions and thus improve the predictive performance of structure-based virtual screening.

METHODS

A novel machine-learning scoring function was created, named SCORCH (Scoring COnsensus for RMSD-based Classification of Hits). To develop SCORCH, training data is augmented by considering multiple ligand poses and labelling poses based on their RMSD from the native pose. Decoy bias is addressed by generating property-matched decoys for each ligand and using the same methodology for preparing and docking decoys and ligands. A consensus of 3 different machine learning approaches is also used to improve performance.

RESULTS

We find that multi-pose augmentation in SCORCH improves its docking power and screening power on independent benchmark datasets. SCORCH outperforms an equivalent scoring function trained on single poses, with a 1% enrichment factor (EF) of 13.78 vs. 10.86 on 18 DEKOIS 2.0 targets and a mean native pose rank of 5.9 vs 30.4 on CSAR 2014. Additionally, SCORCH outperforms widely used scoring functions in virtual screening and pose prediction on independent benchmark datasets.

CONCLUSION

By rationally addressing key limitations of previous scoring functions, SCORCH improves the performance of virtual screening. SCORCH also provides an estimate of its uncertainty, which can help reduce the cost and time required for drug discovery.

Opportunities and Challenges for In Silico Drug Discovery at Delta Opioid Receptors

The delta opioid receptor is a Gi-protein-coupled receptor (GPCR) with a broad expression pattern both in the central nervous system and the body. The receptor has been investigated as a potential target for a multitude of significant diseases including migraine, alcohol use disorder, ischemia, and neurodegenerative diseases. Despite multiple attempts, delta opioid receptor-selective molecules have not been translated into the clinic. Yet, the therapeutic promise of the delta opioid receptor remains and thus there is a need to identify novel delta opioid receptor ligands to be optimized and selected for clinical trials. Here, we highlight recent developments involving the delta opioid receptor, the closely related mu and kappa opioid receptors, and in the broader area of the GPCR drug discovery research. We focus on the validity and utility of the available delta opioid receptor structures. We also discuss the increased ability to perform ultra-large-scale docking studies on GPCRs, the rise in high-resolution cryo-EM structures, and the increased prevalence of machine learning and artificial intelligence in drug discovery. Overall, we pose that there are multiple opportunities to enable in silico drug discovery at the delta opioid receptor to identify novel delta opioid modulators potentially with unique pharmacological properties, such as biased signaling.