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

New machine learning and physics-based scoring functions for drug discovery

Scoring functions are essential for modern in silico drug discovery. However, the accurate prediction of binding affinity by scoring functions remains a challenging task. The performance of scoring functions is very heterogeneous across different target classes. Scoring functions based on precise physics-based descriptors better representing protein–ligand recognition process are strongly needed. We developed a set of new empirical scoring functions, named DockTScore, by explicitly accounting for physics-based terms combined with machine learning. Target-specific scoring functions were developed for two important drug targets, proteases and protein–protein interactions, representing an original class of molecules for drug discovery. Multiple linear regression (MLR), support vector machine and random forest algorithms were employed to derive general and target-specific scoring functions involving optimized MMFF94S force-field terms, solvation and lipophilic interactions terms, and an improved term accounting for ligand torsional entropy contribution to ligand binding. DockTScore scoring functions demonstrated to be competitive with the current best-evaluated scoring functions in terms of binding energy prediction and ranking on four DUD-E datasets and will be useful for in silico drug design for diverse proteins as well as for specific targets such as proteases and protein–protein interactions. Currently, the MLR DockTScore is available at www.dockthor.lncc.br.

Computational design of enzymes for biotechnological applications

Enzymes are the natural catalysts that execute biochemical reactions upholding life. Their natural effectiveness has been fine-tuned as a result of millions of years of natural evolution. Such catalytic effectiveness has prompted the use of biocatalysts from multiple sources on different applications, including the industrial production of goods (food and beverages, detergents, textile, and pharmaceutics), environmental protection, and biomedical applications. Natural enzymes often need to be improved by protein engineering to optimize their function in non-native environments. Recent technological advances have greatly facilitated this process by providing the experimental approaches of directed evolution or by enabling computer-assisted applications. Directed evolution mimics the natural selection process in a highly accelerated fashion at the expense of arduous laboratory work and economic resources. Theoretical methods provide predictions and represent an attractive complement to such experiments by waiving their inherent costs. Computational techniques can be used to engineer enzymatic reactivity, substrate specificity and ligand binding, access pathways and ligand transport, and global properties like protein stability, solubility, and flexibility. Theoretical approaches can also identify hotspots on the protein sequence for mutagenesis and predict suitable alternatives for selected positions with expected outcomes. This review covers the latest advances in computational methods for enzyme engineering and presents many successful case studies.

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

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

DockingApp RF: A State-of-the-Art Novel Scoring Function for Molecular Docking in a User-Friendly Interface to AutoDock Vina

Motivation: Bringing a new drug to the market is expensive and time-consuming. To cut the costs and time, computer-aided drug design (CADD) approaches have been increasingly included in the drug discovery pipeline. However, despite traditional docking tools show a good conformational space sampling ability, they are still unable to produce accurate binding affinity predictions. This work presents a novel scoring function for molecular docking seamlessly integrated into DockingApp, a user-friendly graphical interface for AutoDock Vina. The proposed function is based on a random forest model and a selection of specific features to overcome the existing limits of Vina’s original scoring mechanism. A novel version of DockingApp, named DockingApp RF, has been developed to host the proposed scoring function and to automatize the rescoring procedure of the output of AutoDock Vina, even to nonexpert users. Results: By coupling intermolecular interaction, solvent accessible surface area features and Vina’s energy terms, DockingApp RF’s new scoring function is able to improve the binding affinity prediction of AutoDock Vina. Furthermore, comparison tests carried out on the CASF-2013 and CASF-2016 datasets demonstrate that DockingApp RF’s performance is comparable to other state-of-the-art machine-learning- and deep-learning-based scoring functions. The new scoring function thus represents a significant advancement in terms of the reliability and effectiveness of docking compared to AutoDock Vina’s scoring function. At the same time, the characteristics that made DockingApp appealing to a wide range of users are retained in this new version and have been complemented with additional features.

Isobenzofuran-1(3H)-ones as new tyrosinase inhibitors: Biological activity and interaction studies by molecular docking and NMR

Tyrosinase is a multifunctional, glycosylated and copper-containing oxidase enzyme that can be found in animals, plants, and fungi. It is involved in several biological processes such as melanin biosynthesis. In this work, a series of isobenzofuran-1(3H)-ones was evaluated as tyrosinase inhibitors. It was found that compounds phthalaldehydic acid (1), 3-(2,6-dihydroxy-4-isopropylphenyl)isobenzofuran-1(3H)-one (7), and 2-(3-oxo-1,3-dihydroisobenzofuran-1-yl)-1,3-phenylene diacetate (9) were the most potent compounds inhibiting tyrosinase activity in a concentration dependent manner. Ligand-enzyme NMR studies and docking investigations allowed to map the atoms of the ligands involved in the interaction with the copper atoms present in the active site of the tyrosinase. This behaviour is similar to kojic acid, a well know tyrosinase inhibitor and used as positive control in the biological assays. The findings herein described pave the way for future rational design of new tyrosinase inhibitors.

Identification of 6-(piperazin-1-yl)-1,3,5-triazine as a chemical scaffold with broad anti-schistosomal activities

Background: Schistosomiasis, caused by infection with blood fluke schistosomes, is a neglected tropical disease of considerable importance in resource-poor communities throughout the developing world. In the absence of an immunoprophylactic vaccine and due to over-reliance on a single chemotherapy (praziquantel), schistosomiasis control is at risk should drug insensitive schistosomes develop. In this context, application of in silico virtual screening on validated schistosome targets has proven successful in the identification of novel small molecules with anti-schistosomal activity.   Methods: Focusing on the Schistosoma mansoni histone methylation machinery, we herein have used RNA interference (RNAi), ELISA-mediated detection of H3K4 methylation, homology modelling and in silico virtual screening to identify a small collection of small molecules for anti-schistosomal testing. A combination of low to high-throughput whole organism assays were subsequently used to assess these compounds' activities on miracidia to sporocyst transformation, schistosomula phenotype/motility metrics and adult worm motility/oviposition readouts. Results: RNAi-mediated knockdown of smp_138030/smmll-1 (encoding a histone methyltransferase, HMT) in adult worms (~60%) reduced parasite motility and egg production. Moreover, in silico docking of compounds into Smp_138030/SmMLL-1's homology model highlighted competitive substrate pocket inhibitors, some of which demonstrated significant activity on miracidia, schistosomula and adult worm lifecycle stages together with variable effects on HepG2 cells. Particularly, the effect of compounds containing a 6-(piperazin-1-yl)-1,3,5-triazine core on adult schistosomes recapitulated the results of the smp_138030/smmll-1 RNAi screens. Conclusions: The biological data and the structure-activity relationship presented in this study define the 6-(piperazin-1-yl)-1,3,5-triazine core as a promising starting point in ongoing efforts to develop new urgently needed schistosomicides.

Comparison of Binding Site of Remdesivir and Its Metabolites with NSP12-NSP7-NSP8, and NSP3 of SARS CoV-2 Virus and Alternative Potential Drugs for COVID-19 Treatment

Remdesivir was approved by the U.S.A. Food and Drug administration for emergency use to interfere with the replication of SARS CoV-2 virus (the agent that causes COVID-19) in adults and children hospitalized with severe disease. The crystal structure of the metabolite of remdesivir (Monophosphate of GS-441524) and NSP12-NSP8-NSP7 of SARS CoV-2 virus was recently reported. The crystal structures of ADP-Ribose or AMP and NSP3 of SARS CoV-2 virus were also released, recently. This study compared their binding sites and suggests the crystal structure of NSP3 of SARS CoV-2 virus as an alternative binding site of AMP or ADP-ribose to treat COVID-19. We virtually screened 682 FDA-approved compounds, and the top 10 compounds were selected by analysis of docking scores, (G-score, D-score, and Chemscore) and visual analysis using a structure-based docking approach of NSP3 of SARS CoV-2 virus. All immunization approaches are based on the SARS-CoV-2 virus spike protein. A recent study reported that the D614G mutation in the SARS-CoV-2 virus spike protein reduces S1 shedding and increases infectivity of SARS COV-2 virus. Therefore, if there is a severe change in the spike protein of a modified Coronavirus, all developed vaccines can lose their efficacy, necessitating the need for an alternative treatment method. The top 10 compounds (FDA-approved) in this study are selected based on NSP 3 binding site, and therefore are a potential viable treatment because they will show potential activity for all mutations in the SARS-CoV-2 virus spike protein.

GlycoTorch Vina: Docking Designed and Tested for Glycosaminoglycans

Glycosaminoglycans (GAGs) are a family of anionic carbohydrates that play an essential role in the physiology and pathology of all eukaryotic life forms. Experimental determination of GAG-protein complexes is challenging due to their difficult isolation from biological sources, natural heterogeneity, and conformational flexibility-including possible ring puckering of sulfated iduronic acid from ¹C₄ to ²S_O conformation. To overcome these challenges, we present GlycoTorch Vina (GTV), a molecular docking tool based on the carbohydrate docking program VinaCarb (VC). Our program is unique in that it contains parameters to model ²S_O sugars while also supporting glycosidic linkages specific to GAGs. We discuss how crystallographic models of carbohydrates can be biased by the choice of refinement software and structural dictionaries. To overcome these variations, we carefully curated 12 of the best available GAG and GAG-like crystal structures (ranging from tetra- to octasaccharides or longer) obtained from the PDB-REDO server and refined using the same protocol. Both GTV and VC produced pose predictions with a mean root-mean-square deviation (RMSD) of 3.1 Å from the native crystal structure-a statistically significant improvement when compared to AutoDock Vina (4.5 Å) and the commercial software Glide (5.9 Å). Examples of how real-space correlation coefficients can be used to better assess the accuracy of docking pose predictions are given. Comparisons between statistical distributions of empirical "salt bridge" interactions, relevant to GAGs, were compared to density functional theory (DFT) studies of model salt bridges, and water-mediated salt bridges; however, there was generally a poor agreement between these data. Water bridges appear to play an important, yet poorly understood, role in the structures of GAG-protein complexes. To aid in the rapid prototyping of future pose scoring functions, we include a module that allows users to include their own torsional and nonbonded parameters.

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

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

Ligand Entropy Is Hard but Should Not Be Ignored

Good binding poses and affinities predicted by docking can be calculated accurately if proper care is taken. Accounting for the entropic penalty to the binding energy due to restriction of conformational freedom in flexible ligands on binding is computationally difficult but very important for obtaining reliable ranking of ligand binding affinities to specific protein targets.

Automated Design of Macrocycles for Therapeutic Applications: From Small Molecules to Peptides and Proteins

Macrocycles and cyclic peptides are increasingly attractive therapeutic modalities as they often have improved affinity, are able to bind to extended protein surfaces, and otherwise have favorable properties. Macrocyclization of a known binder may stabilize its bioactive conformation and improve its metabolic stability, cell permeability, and in certain cases oral bioavailability. Herein, we present implementation and application of an approach that automatically generates, evaluates, and proposes cyclizations utilizing a library of well-established chemical reactions and reagents. Using the three-dimensional (3D) conformation of the linear molecule in complex with a target protein as the starting point, this approach identifies attachment points, generates linkers, evaluates their geometric compatibility, and ranks the resulting molecules with respect to their predicted conformational stability and interactions with the target protein. As we show here with prospective and retrospective case studies, this procedure can be applied for the macrocyclization of small molecules and peptides and even PROteolysis TArgeting Chimeras (PROTACs) and proteins.

Synthesis, In Silico and In Vitro Evaluation of Some Flavone Derivatives for Acetylcholinesterase and BACE-1 Inhibitory Activity

Acetylcholinesterase (AChE) and β-secretase (BACE-1) have become attractive therapeutic targets for Alzheimer’s disease (AD). Flavones are flavonoid derivatives with various bioactive effects, including AChE and BACE-1 inhibition. In the present work, a series of 14 flavone derivatives was synthesized in relatively high yields (35–85%). Six of the synthetic flavones (B4, B5, B6, B8, D6 and D7) had completely new structures. The AChE and BACE-1 inhibitory activities were tested, giving pIC₅₀ 3.47–4.59 (AChE) and 4.15–5.80 (BACE-1). Three compounds (B3, D5 and D6) exhibited the highest biological effects on both AChE and BACE-1. A molecular docking investigation was conducted to explain the experimental results. These molecules could be employed for further studies to discover new structures with dual action on both AChE and BACE-1 that could serve as novel therapies for AD.

Fast Rescoring Protocols to Improve the Performance of Structure-Based Virtual Screening Performed on Protein-Protein Interfaces

Protein-protein interactions (PPIs) are attractive targets for drug design because of their essential role in numerous cellular processes and disease pathways. However, in general, PPIs display exposed binding pockets at the interface, and as such, have been largely unexploited for therapeutic interventions with low-molecular weight compounds. Here, we used docking and various rescoring strategies in an attempt to recover PPI inhibitors from a set of active and inactive molecules for 11 targets collected in ChEMBL and PubChem. Our focus is on the screening power of the various developed protocols and on using fast approaches so as to be able to apply such a strategy to the screening of ultralarge libraries in the future. First, we docked compounds into each target using the fast "pscreen" mode of the structure-based virtual screening (VS) package Surflex. Subsequently, the docking poses were postprocessed to derive a set of 3D topological descriptors: (i) shape similarity and (ii) interaction fingerprint similarity with a co-crystallized inhibitor, (iii) solvent-accessible surface area, and (iv) extent of deviation from the geometric center of a reference inhibitor. The derivatized descriptors, together with descriptor-scaled scoring functions, were utilized to investigate possible impacts on VS performance metrics. Moreover, four standalone scoring functions, RF-Score-VS (machine-learning), DLIGAND2 (knowledge-based), Vinardo (empirical), and X-SCORE (empirical), were employed to rescore the PPI compounds. Collectively, the results indicate that the topological scoring algorithms could be valuable both at a global level, with up to 79% increase in areas under the receiver operating characteristic curve for some targets, and in early stages, with up to a 4-fold increase in enrichment factors at 1% of the screened collections. Outstandingly, DLIGAND2 emerged as the best scoring function on this data set, outperforming all rescoring techniques in terms of VS metrics. The described methodology could help in the rational design of small-molecule PPI inhibitors and has direct applications in many therapeutic areas, including cancer, CNS, and infectious diseases such as COVID-19.

Identification of 6-(piperazin-1-yl)-1,3,5-triazine as a chemical scaffold with broad anti-schistosomal activities

Background: Schistosomiasis, caused by infection with blood fluke schistosomes, is a neglected tropical disease of considerable importance in resource-poor communities throughout the developing world. In the absence of an immunoprophylactic vaccine and due to over-reliance on a single chemotherapy (praziquantel), schistosomiasis control is at risk should drug insensitive schistosomes develop. In this context, application of in silico virtual screening on validated schistosome targets has proven successful in the identification of novel small molecules with anti-schistosomal activity.   Methods: Focusing on the Schistosoma mansoni histone methylation machinery, we herein have used RNA interference (RNAi), ELISA-mediated detection of H3K4 methylation, homology modelling and in silico virtual screening to identify a small collection of small molecules for anti-schistosomal testing. A combination of low to high-throughput whole organism assays were subsequently used to assess these compounds' activities on miracidia to sporocyst transformation, schistosomula phenotype/motility metrics and adult worm motility/oviposition readouts. Results: RNAi-mediated knockdown of smp_138030/smmll-1 (encoding a histone methyltransferase, HMT) in adult worms (~60%) reduced parasite motility and egg production. Moreover, in silico docking of compounds into Smp_138030/SmMLL-1's homology model highlighted competitive substrate pocket inhibitors, some of which demonstrated significant activity on miracidia, schistosomula and adult worm lifecycle stages together with variable effects on HepG2 cells. Particularly, the effect of compounds containing a 6-(piperazin-1-yl)-1,3,5-triazine core on adult schistosomes recapitulated the results of the smp_138030/smmll-1 RNAi screens. Conclusions: The biological data and the structure-activity relationship presented in this study define the 6-(piperazin-1-yl)-1,3,5-triazine core as a promising starting point in ongoing efforts to develop new urgently needed schistosomicides.

Design, Synthesis and Biological Evaluation of Novel Triazole N-acylhydrazone Hybrids for Alzheimer's Disease

Alzheimer's disease (AD) is a multifactorial neurodegenerative disorder that involves different pathogenic mechanisms. In this regard, the goal of this study was the design and synthesis of new compounds with multifunctional pharmacological activity by molecular hybridization of structural fragments of curcumin and resveratrol connected by an N-acyl-hydrazone function linked to a 1,4-disubstituted triazole system. Among these hybrid compounds, derivative 3e showed the ability to inhibit acetylcholinesterase activity, the intracellular formation of reactive oxygen species as well as the neurotoxicity elicited by Aβ42 oligomers in neuronal SH-SY5Y cells. In parallel, compound 3e showed a good profile of safety and ADME parameters. Taken together, these results suggest that 3e could be considered a lead compound for the further development of AD therapeutics.

Identification of Potential Inhibitors for Targets Involved in Dengue Fever

Lethality due to dengue infection is a global threat. Nearly 400 million people are affected every year, which approximately costs 500 million dollars for surveillance and vector control itself. Many investigations on the structure-function relationship of proteins expressed by the dengue virus are being made for more than a decade and had come up with many reports on small molecule drug discovery. In this review, we present a detailed note on viral proteins and their functions as well as the inhibitors discovered/designed so far using experimental and computational methods. Further, the phytoconstituents from medicinal plants, specifically the extract of the papaya leaves, neem and bael, which combat dengue infection via dengue protease, helicase, methyl transferase and polymerase are summarized.

Beware of the generic machine learning-based scoring functions in structure-based virtual screening

Machine learning-based scoring functions (MLSFs) have attracted extensive attention recently and are expected to be potential rescoring tools for structure-based virtual screening (SBVS). However, a major concern nowadays is whether MLSFs trained for generic uses rather than a given target can consistently be applicable for VS. In this study, a systematic assessment was carried out to re-evaluate the effectiveness of 14 reported MLSFs in VS. Overall, most of these MLSFs could hardly achieve satisfactory results for any dataset, and they could even not outperform the baseline of classical SFs such as Glide SP. An exception was observed for RFscore-VS trained on the Directory of Useful Decoys-Enhanced dataset, which showed its superiority for most targets. However, in most cases, it clearly illustrated rather limited performance on the targets that were dissimilar to the proteins in the corresponding training sets. We also used the top three docking poses rather than the top one for rescoring and retrained the models with the updated versions of the training set, but only minor improvements were observed. Taken together, generic MLSFs may have poor generalization capabilities to be applicable for the real VS campaigns. Therefore, it should be quite cautious to use this type of methods for VS.

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

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

High-Throughput Docking Using Quantum Mechanical Scoring

Today high-throughput docking is one of the most commonly used computational tools in drug lead discovery. While there has been an impressive methodological improvement in docking accuracy, docking scoring still remains an open challenge. Most docking programs are rooted in classical molecular mechanics. However, to better characterize protein-ligand interactions, the use of a more accurate quantum mechanical (QM) description would be necessary. In this work, we introduce a QM-based docking scoring function for high-throughput docking and evaluate it on 10 protein systems belonging to diverse protein families, and with different binding site characteristics. Outstanding results were obtained, with our QM scoring function displaying much higher enrichment (screening power) than a traditional docking method. It is acknowledged that developments in quantum mechanics theory, algorithms and computer hardware throughout the upcoming years will allow semi-empirical (or low-cost) quantum mechanical methods to slowly replace force-field calculations. It is thus urgently needed to develop and validate novel quantum mechanical-based scoring functions for high-throughput docking toward more accurate methods for the identification and optimization of modulators of pharmaceutically relevant targets.

Virtual screening web servers: designing chemical probes and drug candidates in the cyberspace

The interplay between life sciences and advancing technology drives a continuous cycle of chemical data growth; these data are most often stored in open or partially open databases. In parallel, many different types of algorithms are being developed to manipulate these chemical objects and associated bioactivity data. Virtual screening methods are among the most popular computational approaches in pharmaceutical research. Today, user-friendly web-based tools are available to help scientists perform virtual screening experiments. This article provides an overview of internet resources enabling and supporting chemical biology and early drug discovery with a main emphasis on web servers dedicated to virtual ligand screening and small-molecule docking. This survey first introduces some key concepts and then presents recent and easily accessible virtual screening and related target-fishing tools as well as briefly discusses case studies enabled by some of these web services. Notwithstanding further improvements, already available web-based tools not only contribute to the design of bioactive molecules and assist drug repositioning but also help to generate new ideas and explore different hypotheses in a timely fashion while contributing to teaching in the field of drug development.

Predicting or Pretending: Artificial Intelligence for Protein-Ligand Interactions Lack of Sufficiently Large and Unbiased Datasets

Predicting protein-ligand interactions using artificial intelligence (AI) models has attracted great interest in recent years. However, data-driven AI models unequivocally suffer from a lack of sufficiently large and unbiased datasets. Here, we systematically investigated the data biases on the PDBbind and DUD-E datasets. We examined the model performance of atomic convolutional neural network (ACNN) on the PDBbind core set and achieved a Pearson R² of 0.73 between experimental and predicted binding affinities. Strikingly, the ACNN models did not require learning the essential protein-ligand interactions in complex structures and achieved similar performance even on datasets containing only ligand structures or only protein structures, while data splitting based on similarity clustering (protein sequence or ligand scaffold) significantly reduced the model performance. We also identified the property and topology biases in the DUD-E dataset which led to the artificially increased enrichment performance of virtual screening. The property bias in DUD-E was reduced by enforcing the more stringent ligand property matching rules, while the topology bias still exists due to the use of molecular fingerprint similarity as a decoy selection criterion. Therefore, we believe that sufficiently large and unbiased datasets are desirable for training robust AI models to accurately predict protein-ligand interactions.

Highly Flexible Ligand Docking: Benchmarking of the DockThor Program on the LEADS-PEP Protein-Peptide Data Set

Protein-peptide interactions play a crucial role in many cellular and biological functions, which justify the increasing interest in the development of peptide-based drugs. However, predicting experimental binding modes and affinities in protein-peptide docking remains a great challenge for most docking programs due to some particularities of this class of ligands, such as the high degree of flexibility. In this paper, we present the performance of the DockThor program on the LEADS-PEP data set, a benchmarking set composed of 53 diverse protein-peptide complexes with peptides ranging from 3 to 12 residues and with up to 51 rotatable bonds. The DockThor performance for pose prediction on redocking studies was compared with some state-of-the-art docking programs that were also evaluated on the LEADS-PEP data set, AutoDock, AutoDock Vina, Surflex, GOLD, Glide, rDock, and DINC, as well as with the task-specific docking protocol HPepDock. Our results indicate that DockThor could dock 40% of the cases with an overall backbone RMSD below 2.5 Å when the top-scored docking pose was considered, exhibiting similar results to Glide and outperforming other protein-ligand docking programs, whereas rDock and HPepDock achieved superior results. Assessing the docking poses closest to the crystal structure (i.e., best-RMSD pose), DockThor achieved a success rate of 60% in pose prediction. Due to the great overall performance of handling peptidic compounds, the DockThor program can be considered as suitable for docking highly flexible and challenging ligands, with up to 40 rotatable bonds. DockThor is freely available as a virtual screening Web server at https://www.dockthor.lncc.br/ .

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

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

The role of human in the loop: lessons from D3R challenge 4

The rapid development of new machine learning techniques led to significant progress in the area of computer-aided drug design. However, despite the enormous predictive power of new methods, they lack explainability and are often used as black boxes. The most important decisions in drug discovery are still made by human experts who rely on intuitions and simplified representation of the field. We used D3R Grand Challenge 4 to model contributions of human experts during the prediction of the structure of protein-ligand complexes, and prediction of binding affinities for series of ligands in the context of absence or abundance of experimental data. We demonstrated that human decisions have a series of biases: a tendency to focus on easily identifiable protein-ligand interactions such as hydrogen bonds, and neglect for a more distributed and complex electrostatic interactions and solvation effects. While these biases still allow human experts to compete with blind algorithms in some areas, the underutilization of the information leads to significantly worse performance in data-rich tasks such as binding affinity prediction.

Molecular Docking Using Quantum Mechanical-Based Methods

Computational methods are a powerful and consolidated tool in the early stage of the drug lead discovery process. Among these techniques, high-throughput molecular docking has proved to be extremely useful in identifying novel bioactive compounds within large chemical libraries. In the docking procedure, the predominant binding mode of each small molecule within a target binding site is assessed, and a docking score reflective of the likelihood of binding is assigned to them. These methods also shed light on how a given hit could be modified in order to improve protein-ligand interactions and are thus able to guide lead optimization. The possibility of reducing time and cost compared to experimental approaches made this technology highly appealing. Due to methodological developments and the increase of computational power, the application of quantum mechanical methods to study macromolecular systems has gained substantial attention in the last decade. A quantum mechanical description of the interactions involved in molecular association of biomolecules may lead to better accuracy compared to molecular mechanics, since there are many physical phenomena that cannot be correctly described within a classical framework, such as covalent bond formation, polarization effects, charge transfer, bond rearrangements, halogen bonding, and others, that require electrons to be explicitly accounted for. Considering the fact that quantum mechanics-based approaches in biomolecular simulation constitute an active and important field of research, we highlight in this work the recent developments of quantum mechanical-based molecular docking and high-throughput docking.

CBSF: A New Empirical Scoring Function for Docking Parameterized by Weights of Neural Network

A new CBSF empirical scoring function for the estimation of binding energies between proteins and small molecules is proposed in this report. The final score is obtained as a sum of three energy terms calculated using descriptors based on a simple counting of the interacting protein-ligand atomic pairs. All the required weighting coefficients for this method were derived from a pretrained neural network. The proposed method demonstrates a high accuracy and reproduces binding energies of protein-ligand complexes from the CASF-2016 test set with a standard deviation of 2.063 kcal/mol (1.511 log units) and an average error of 1.682 kcal/mol (1.232 log units). Thus, CBSF has a significant potential for the development of rapid and accurate estimates of the protein-ligand interaction energies.

Synthesis of new lophine-carbohydrate hybrids as cholinesterase inhibitors: cytotoxicity evaluation and molecular modeling

In this study, we synthesized nine novel hybrids derived from d-xylose, d-ribose, and d-galactose sugars connected by a methylene chain with lophine. The compounds were synthesized by a four-component reaction to afford the substituted imidazole moiety, followed by the displacement reaction between sugar derivatives with an appropriate N-alkylamino-lophine. All the compounds were found to be the potent and selective inhibitors of BuChE activity in mouse serum, with compound 9a (a d-galactose derivative) being the most potent inhibitor (IC50 = 0.17 μM). According to the molecular modeling results, all the compounds indicated that the lophine moiety existed at the bottom of the BuChE cavity and formed a T-stacking interaction with Trp231, a residue accessible exclusively in the BuChE cavity. Noteworthily, only one compound exhibited activity against AChE (8b; IC50 = 2.75 μM). Moreover, the in silico ADME predictions indicated that all the hybrids formulated in this study were drug-likely, orally available, and able to reach the CNS. Further, in vitro studies demonstrated that the two most potent compounds against BuChE (8b and 9a) had no cytotoxic effects in the Vero (kidney), HepG2 (hepatic), and C6 (astroglial) cell lines.

Incorporating Explicit Water Molecules and Ligand Conformation Stability in Machine-Learning Scoring Functions

Structure-based drug design is critically dependent on accuracy of molecular docking scoring functions, and there is of significant interest to advance scoring functions with machine learning approaches. In this work, by judiciously expanding the training set, exploring new features related to explicit mediating water molecules as well as ligand conformation stability, and applying extreme gradient boosting (XGBoost) with Δ-Vina parametrization, we have improved robustness and applicability of machine-learning scoring functions. The new scoring function ΔvinaXGB can not only perform consistently among the top compared to classical scoring functions for the CASF-2016 benchmark but also achieves significantly better prediction accuracy in different types of structures that mimic real docking applications.

Comparison Study of Computational Prediction Tools for Drug-Target Binding Affinities

The drug development is generally arduous, costly, and success rates are low. Thus, the identification of drug-target interactions (DTIs) has become a crucial step in early stages of drug discovery. Consequently, developing computational approaches capable of identifying potential DTIs with minimum error rate are increasingly being pursued. These computational approaches aim to narrow down the search space for novel DTIs and shed light on drug functioning context. Most methods developed to date use binary classification to predict if the interaction between a drug and its target exists or not. However, it is more informative but also more challenging to predict the strength of the binding between a drug and its target. If that strength is not sufficiently strong, such DTI may not be useful. Therefore, the methods developed to predict drug-target binding affinities (DTBA) are of great value. In this study, we provide a comprehensive overview of the existing methods that predict DTBA. We focus on the methods developed using artificial intelligence (AI), machine learning (ML), and deep learning (DL) approaches, as well as related benchmark datasets and databases. Furthermore, guidance and recommendations are provided that cover the gaps and directions of the upcoming work in this research area. To the best of our knowledge, this is the first comprehensive comparison analysis of tools focused on DTBA with reference to AI/ML/DL.

Nonparametric chemical descriptors for the calculation of ligand-biopolymer affinities with machine-learning scoring functions

The computational prediction of ligand-biopolymer affinities is a crucial endeavor in modern drug discovery and one that still poses major challenges. The choice of the appropriate computational method often reveals itself as a trade-off between accuracy and speed, with mathematical devices referred to as scoring functions being the fastest. Among the many shortcomings of scoring functions there is the lack of universal applicability to every molecular system. This is so largely due to their reliance on atom type perception and/or parametrization. This article proposes the use of nonparametric Model of Effective Radii of Atoms descriptors that can be readily computed for the entire Periodic Table and demonstrate that, in combination with machine learning algorithms, they can yield competitive performances and chemically meaningful insights.

Current computational methods for predicting protein interactions of natural products

Natural products (NPs) are an indispensable source of drugs and they have a better coverage of the pharmacological space than synthetic compounds, owing to their high structural diversity. The prediction of their interaction profiles with druggable protein targets remains a major challenge in modern drug discovery. Experimental (off-)target predictions of NPs are cost- and time-consuming, whereas computational methods, on the other hand, are much faster and cheaper. As a result, computational predictions are preferentially used in the first instance for NP profiling, prior to experimental validations. This review covers recent advances in computational approaches which have been developed to aid the annotation of unknown drug-target interactions (DTIs), by focusing on three broad classes, namely: ligand-based, target-based, and target-ligand-based (hybrid) approaches. Computational DTI prediction methods have the potential to significantly advance the discovery and development of novel selective drugs exhibiting minimal side effects. We highlight some inherent caveats of these methods which must be overcome to enable them to realize their full potential, and a future outlook is given.

Key Topics in Molecular Docking for Drug Design

Molecular docking has been widely employed as a fast and inexpensive technique in the past decades, both in academic and industrial settings. Although this discipline has now had enough time to consolidate, many aspects remain challenging and there is still not a straightforward and accurate route to readily pinpoint true ligands among a set of molecules, nor to identify with precision the correct ligand conformation within the binding pocket of a given target molecule. Nevertheless, new approaches continue to be developed and the volume of published works grows at a rapid pace. In this review, we present an overview of the method and attempt to summarise recent developments regarding four main aspects of molecular docking approaches: (i) the available benchmarking sets, highlighting their advantages and caveats, (ii) the advances in consensus methods, (iii) recent algorithms and applications using fragment-based approaches, and (iv) the use of machine learning algorithms in molecular docking. These recent developments incrementally contribute to an increase in accuracy and are expected, given time, and together with advances in computing power and hardware capability, to eventually accomplish the full potential of this area.

Molecular Docking: Shifting Paradigms in Drug Discovery

Molecular docking is an established in silico structure-based method widely used in drug discovery. Docking enables the identification of novel compounds of therapeutic interest, predicting ligand-target interactions at a molecular level, or delineating structure-activity relationships (SAR), without knowing a priori the chemical structure of other target modulators. Although it was originally developed to help understanding the mechanisms of molecular recognition between small and large molecules, uses and applications of docking in drug discovery have heavily changed over the last years. In this review, we describe how molecular docking was firstly applied to assist in drug discovery tasks. Then, we illustrate newer and emergent uses and applications of docking, including prediction of adverse effects, polypharmacology, drug repurposing, and target fishing and profiling, discussing also future applications and further potential of this technique when combined with emergent techniques, such as artificial intelligence.

Functional characterization of the translation initiation factor eIF4E of Echinococcus granulosus

The eukaryotic initiation factor 4E (eIF4E) specifically recognizes the 5' mRNA cap, a rate-limiting step in the translation initiation process. Although the 7-methylguanosine cap (MMGcap) is the most common 5' cap structure in eukaryotes, the trans-splicing process that occurs in several organism groups, including nematodes and flatworms, leads to the addition of a trimethylguanosine cap (TMGcap) to some RNA transcripts. In some helminths, eIF4E can have a dual capacity to bind both MMGcap and TMGcap. In the present work, we evaluated the distribution of eIF4E protein sequences in platyhelminths and we showed that only one gene coding for eIF4E is present in most parasitic flatworms. Based on this result, we cloned the Echinococcus granulosus cDNA sequence encoding eIF4E in Escherichia coli, expressed the recombinant eIF4E as a fusion protein to GST, and tested its ability to capture mRNAs through the 5' cap using pull-down assay and qPCR. Our results indicate that the recombinant eIF4E was able to bind preferentially 5'-capped mRNAs compared with rRNAs from total RNA preparations of E. granulosus. By qPCR, we observed an enrichment in MMG-capped mRNA compared with TMG-capped mRNAs among Eg-eIF4E-GST pull-down RNAs. Eg-eIF4E structural model using the Schistosoma mansoni eIF4E as template showed to be well preserved with only a few differences between chemically similar amino acid residues at the binding sites. These data showed that E. granulosus eIF4E can be used as a potential tool to study full-length 5'-capped mRNA, besides being a potential drug target against parasitic flatworms.

Local Interaction Density (LID), a Fast and Efficient Tool to Prioritize Docking Poses

Ligand docking at a protein site can be improved by prioritizing poses by similarity to validated binding modes found in the crystal structures of ligand/protein complexes. The interactions formed in the predicted model are searched in each of the reference 3D structures, taken individually. We propose to merge the information provided by all references, creating a single representation of all known binding modes. The method is called LID, an acronym for Local Interaction Density. LID was benchmarked in a pose prediction exercise on 19 proteins and 1382 ligands using PLANTS as docking software. It was also tested in a virtual screening challenge on eight proteins, with a dataset of 140,000 compounds from DUD-E and PubChem. LID significantly improved the performance of the docking program in both pose prediction and virtual screening. The gain is comparable to that obtained with a rescoring approach based on the individual comparison of reference binding modes (the GRIM method). Importantly, LID is effective with a small number of references. LID calculation time is negligible compared to the docking time.

A Structure-Based Drug Discovery Paradigm

Structure-based drug design is becoming an essential tool for faster and more cost-efficient lead discovery relative to the traditional method. Genomic, proteomic, and structural studies have provided hundreds of new targets and opportunities for future drug discovery. This situation poses a major problem: the necessity to handle the “big data” generated by combinatorial chemistry. Artificial intelligence (AI) and deep learning play a pivotal role in the analysis and systemization of larger data sets by statistical machine learning methods. Advanced AI-based sophisticated machine learning tools have a significant impact on the drug discovery process including medicinal chemistry. In this review, we focus on the currently available methods and algorithms for structure-based drug design including virtual screening and de novo drug design, with a special emphasis on AI- and deep-learning-based methods used for drug discovery.

Biguanide is a modifiable pharmacophore for recruitment of endogenous Zn2+ to inhibit cysteinyl cathepsins: review and implications

Excessive activities of cysteinyl cathepsins (CysCts) contribute to the progress of many diseases; however, therapeutic inhibition has been problematic. Zn²⁺ is a natural inhibitor of proteases with CysHis dyads or CysHis(Xaa) triads. Biguanide forms bidentate metal complexes through the two imino nitrogens. Here, it is discussed that phenformin (phenylethyl biguanide) is a model for recruitment of endogenous Zn²⁺ to inhibit CysHis/CysHis(X) peptidolysis. Phenformin is a Zn²⁺-interactive, anti-proteolytic agent in bioassay of living tissue. Benzoyl-L-arginine amide (BAA) is a classical substrate of papain-like proteases; the amide bond is scissile. In this review, the structures of BAA and the phenformin-Zn²⁺ complex were compared in silico. Their chemistry and dimensions are discussed in light of the active sites of papain-like proteases. The phenyl moieties of both structures bind to the "S2" substrate-binding site that is typical of many proteases. When the phenyl moiety of BAA binds to S2, then the scissile amide bond is directed to the position of the thiolate-imidazolium ion pair, and is then hydrolyzed. However, when the phenyl moiety of phenformin binds to S2, then the coordinated Zn²⁺ is directed to the identical position; and catalysis is inhibited. Phenformin stabilizes a "Zn²⁺ sandwich" between the drug and protease active site. Hundreds of biguanide derivatives have been synthesized at the 1 and 5 nitrogen positions; many more are conceivable. Various substituent moieties can register with various arrays of substrate-binding sites so as to align coordinated Zn²⁺ with catalytic partners of diverse proteases. Biguanide is identified here as a modifiable pharmacophore for synthesis of therapeutic CysCt inhibitors with a wide range of potencies and specificities. Phenformin-Zn²⁺ Complex.

Quantification of noncovalent interactions – promises and problems

Quantification of noncovalent interactions is the key for the understanding of binding mechanisms, of biological systems, for the design of drugs, their delivery and for the design of receptors for separations, sensors, actuators, or smart materials.

Advances and challenges in drug design against tuberculosis: application of in silico approaches

INTRODUCTION

Tuberculosis (TB) caused by Mycobacterium tuberculosis (Mtb) remains the deadliest infectious disease in the world with one-third of the world's population thought to be infected. Over the years, TB mortality rate has been largely reduced; however, this progress has been threatened by the increasing appearance of multidrug-resistant Mtb. Considerable recent efforts have been undertaken to develop new generation antituberculosis drugs. Many of these attempts have relied on in silico approaches, which have emerged recently as powerful tools complementary to biochemical attempts. Areas covered: The authors review the status of pharmaceutical drug development against TB with a special emphasis on computational work. They focus on those studies that have been validated by in vitro and/or in vivo experiments, and thus, that can be considered as successful. The major goals of this review are to present target protein systems, to highlight how in silico efforts compliment experiments, and to aid future drug design endeavors. Expert opinion: Despite having access to all of the gene and protein sequences of Mtb, the search for new optimal treatments against this deadly pathogen are still ongoing. Together with the geometric growth of protein structural and sequence databases, computational methods have become a powerful technique accelerating the successful identification of new ligands.

Structure-based Methods for Binding Mode and Binding Affinity Prediction for Peptide-MHC Complexes

Understanding the mechanisms involved in the activation of an immune response is essential to many fields in human health, including vaccine development and personalized cancer immunotherapy. A central step in the activation of the adaptive immune response is the recognition, by T-cell lymphocytes, of peptides displayed by a special type of receptor known as Major Histocompatibility Complex (MHC). Considering the key role of MHC receptors in T-cell activation, the computational prediction of peptide binding to MHC has been an important goal for many immunological applications. Sequence- based methods have become the gold standard for peptide-MHC binding affinity prediction, but structure-based methods are expected to provide more general predictions (i.e., predictions applicable to all types of MHC receptors). In addition, structural modeling of peptide-MHC complexes has the potential to uncover yet unknown drivers of T-cell activation, thus allowing for the development of better and safer therapies. In this review, we discuss the use of computational methods for the structural modeling of peptide-MHC complexes (i.e., binding mode prediction) and for the structure-based prediction of binding affinity.