Recent Developments in Ultralarge and Structure-Based Virtual Screening Approaches

The freedom space - a new set of commercially available molecules for hit discovery

The advent of high-performance virtual screening techniques nowadays allows drug designers to explore ultra-large sets of candidate compounds in search of molecules predicted to have desired properties. However, the success of such an endeavor heavily relies on the pertinence (drug-likeness and, foremost, chemical feasibility) of these candidates, or otherwise, virtual screening will return valueless "hits", by the garbage in/garbage out principle. The huge popularity of the judiciously enumerated Enamine REAL Space is clear proof of the strength of this Big Data trend in drug discovery. Here we describe a new dataset of make-on-demand compounds called the Freedom space. It follows the principles of Enamine REAL Space and contains highly feasible molecules (synthesis success rate over 75 percent). However, the scaffold and chemography analysis revealed significant differences to both the REAL and biologically annotated compounds from the ChEMBL database. The Freedom Space is a significant extension of the REAL Space and can be utilized for a more comprehensive exploration of the synthetically feasible chemical space in hit finding and hit-to-lead campaigns.

Recent strategies in target identification of natural products: Exploring applications in chronic inflammation and beyond

Natural products are a treasure trove for drug discovery, especially in the areas of infection, inflammation and cancer, due to their diverse bioactivities and complex, and varied structures. Chronic inflammation is closely related to many diseases, including complex diseases such as cancer and neurodegeneration. Improving target identification for natural products contributes to elucidating their mechanism of action and clinical progress. It also facilitates the discovery of novel druggable targets and the elimination of undesirable ones, thereby significantly enhancing the productivity of drug discovery and development. Moreover, the rise of polypharmacological strategies, considered promising for the treatment of complex diseases, will further increase the demand for target deconvolution. This review underscores strategies for identifying natural product targets (NPs) in the context of chronic inflammation over the past 5 years. These strategies encompass computational methodologies for early target discovery and the anticipation of compound binding sites, proteomics-driven approaches for target delineation and experimental biology techniques for target validation and comprehensive mechanistic exploration.

High-throughput screening identification of apigenin that reverses the colistin resistance of mcr-1-positive pathogens

The plasmid-mediated gene mcr-1 that makes bacteria resistant to the antibiotic colistin is spreading quickly, which means that colistin is no longer working well to treat Gram-negative bacterial infections. Herein, we utilized a computer-aided high-throughput screening drugs method to identify the natural product apigenin, a potential mcr-protein inhibitor, which effectively enhanced the antimicrobial activity of colistin. Several assays, including a checkerboard minimum inhibitory concentration assay, a time-kill assay, the combined disk test, molecular simulation dynamics, and animal infection models assay, were conducted to verify whether apigenin enhanced the ability of colistin to fight Gram-negative bacterial infections. The results showed that apigenin improved the antimicrobial activity of colistin against multidrug-resistant Enterobacteriaceae infection. Moreover, apigenin not only did not increase the toxic effect of colistin but also had the ability to effectively inhibit the frequency of bacterial resistance mutations to colistin. Studies clearly elucidated that apigenin could interfere with the thermal stability of the protein by binding to the mcr-1 protein. Additionally, the combination of apigenin and colistin could exert multiple effects, including disrupting bacterial membranes, the generation of bacterial nitric oxide and reactive oxygen species, as well as inhibiting bacterial adenosine triphosphate production. Furthermore, the addition of apigenin was able to significantly inhibit colistin-stimulated high expression levels of the bacterial mcr-1 gene. Finally, apigenin exhibited a characteristic anti-inflammatory effect while enhancing the antimicrobial activity of colistin against mcr-1-positive Escherichia coli (E. coli) infected animals. In conclusion, as a potential lead compound, apigenin is promising in combination with colistin in the future treatment of mcr-1-positive E. coli infections.IMPORTANCEThis study found that apigenin was able to inhibit the activity of the mcr-1 protein using a high-throughput virtual screening method. Apigenin effectively enhanced the antimicrobial activity of colistin against multidrug-resistant Enterobacteriaceae, including mcr-1-positive strains, in vitro and in vivo. This study will provide new options and strategies for the future treatment of multidrug-resistant pathogen infections.

Perspectives on current approaches to virtual screening in drug discovery

INTRODUCTION

For the past two decades, virtual screening (VS) has been an efficient hit finding approach for drug discovery. Today, billions of commercially accessible compounds are routinely screened, and many successful examples of VS have been reported. VS methods continue to evolve, including machine learning and physics-based methods.

AREAS COVERED

The authors examine recent examples of VS in drug discovery and discuss prospective hit finding results from the critical assessment of computational hit-finding experiments (CACHE) challenge. The authors also highlight the cost considerations and open-source options for conducting VS and examine chemical space coverage and library selections for VS.

EXPERT OPINION

The advancement of sophisticated VS approaches, including the use of machine learning techniques and increased computer resources as well as the ease of access to synthetically available chemical spaces, and commercial and open-source VS platforms allow for interrogating ultra-large libraries (ULL) of billions of molecules. An impressive number of prospective ULL VS campaigns have generated potent and structurally novel hits across many target classes. Nonetheless, many successful contemporary VS approaches still use considerably smaller focused libraries. This apparent dichotomy illustrates that VS is best conducted in a fit-for-purpose way choosing an appropriate chemical space. Better methods need to be developed to tackle more challenging targets.

Identifying Artifacts from Large Library Docking

While large library docking has discovered potent ligands for multiple targets, as the libraries have grown the hit lists can become dominated by rare artifacts that cheat our scoring functions. Here, we investigate rescoring top-ranked docked molecules with orthogonal methods to identify these artifacts, exploring implicit solvent models and absolute binding free energy perturbation as cross-filters. In retrospective studies, this approach deprioritized high-ranking nonbinders for nine targets while leaving true ligands relatively unaffected. We tested the method prospectively against hits from docking against AmpC β-lactamase. We prioritized 128 high-ranking molecules for synthesis and testing, a mixture of 39 molecules flagged as likely cheaters and 89 that were plausible inhibitors. None of the predicted cheating compounds inhibited AmpC detectably, while 57% of the 89 plausible compounds did so. As our libraries continue to grow, deprioritizing docking artifacts by rescoring with orthogonal methods may find wide use.

Caught between a ROCK and a hard place: current challenges in structure-based drug design

The discipline of structure-based drug design (SBDD) is several decades old and it is tempting to think that the proliferation of experimental structures for many drug targets might make computer-aided drug design (CADD) straightforward. However, this is far from true. In this review, we illustrate some of the challenges that CADD scientists face every day in their work, even now. We use Rho-associated protein kinase (ROCK), and public domain structures and data, as an example to illustrate some of the challenges we have experienced during our project targeting this protein. We hope that this will help to prevent unrealistic expectations of what CADD can accomplish and to educate non-CADD scientists regarding the challenges still facing their CADD colleagues.

Identifying Artifacts from Large Library Docking

While large library docking has discovered potent ligands for multiple targets, as the libraries have grown, the very top of the hit-lists can become populated with artifacts that cheat our scoring functions. Though these cheating molecules are rare, they become ever-more dominant with library growth. Here, we investigate rescoring top-ranked molecules from docking screens with orthogonal methods to identify these artifacts, exploring implicit solvent models and absolute binding free energy perturbation (AB-FEP) as cross-filters. In retrospective studies, this approach deprioritized high-ranking non-binders for nine targets while leaving true ligands relatively unaffected. We tested the method prospectively against results from large library docking AmpC β-lactamase. From the very top of the docking hit lists, we prioritized 128 molecules for synthesis and experimental testing, a mixture of 39 molecules that rescoring flagged as likely cheaters and another 89 that were plausible true actives. None of the 39 predicted cheating compounds inhibited AmpC up to 200 μ M in enzyme assays, while 57% of the 89 plausible true actives did do so, with 19 of them inhibiting the enzyme with apparentK i values better than 50 μ M . As our libraries continue to grow, a strategy of catching docking artifacts by rescoring with orthogonal methods may find wide use in the field.

Allosteric covalent inhibition of TOE1 as potential unexplored anti-cancer target: structure-based virtual screening and covalent molecular dynamics analysis

Cancer remains a formidable challenge in therapeutic development owing to its complex molecular mechanisms and resistance to conventional treatments. Recent evidence suggests that TOE1 may play a role in cancer progression, making it an attractive target for therapeutic interventions, nevertheless, very limited research in literature has explored the potential of TOE1 inhibitors as anti-cancer. Herein, by exploring a library of 13,900 cysteine-targeted covalent inhibitors via a comprehensive virtual screening process, we sought to identify potential compounds that could be developed into effective cancer therapies against TOE1. The compounds were first screened based on their binding affinity, followed by their compliance with drug-like properties, and finally, by their effective covalent modeling to a reactive cysteine (Cys80). A total of 66 compounds, 28 compounds, and 3 compounds were found to have higher binding affinities, optimum drug-likeness, and higher covalent docking scores, respectively, than the reference compound. The top three screened compounds, 0462, 2204, and 7034, demonstrated favorable interaction profiles, covalent binding dynamics, free binding energetics, and per-residue energy contributions as compared to the reference compound. Notably, compound 0462 contributed to the highest free binding energy and significantly enhanced the stability and rigidity of TOE1, while restricting residue flexibility. This study provides an account of the molecular mechanics underpinning the covalent inhibition of TOE1, while providing a compelling case for further investigation and translation of the screened TOE1 inhibitors, particularly compound 0462, as novel therapeutics against cancer.

SchNetPack Hyperparameter Optimization for a More Reliable Top Docking Scores Prediction

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

DynamicBind: predicting ligand-specific protein-ligand complex structure with a deep equivariant generative model

While significant advances have been made in predicting static protein structures, the inherent dynamics of proteins, modulated by ligands, are crucial for understanding protein function and facilitating drug discovery. Traditional docking methods, frequently used in studying protein-ligand interactions, typically treat proteins as rigid. While molecular dynamics simulations can propose appropriate protein conformations, they're computationally demanding due to rare transitions between biologically relevant equilibrium states. In this study, we present DynamicBind, a deep learning method that employs equivariant geometric diffusion networks to construct a smooth energy landscape, promoting efficient transitions between different equilibrium states. DynamicBind accurately recovers ligand-specific conformations from unbound protein structures without the need for holo-structures or extensive sampling. Remarkably, it demonstrates state-of-the-art performance in docking and virtual screening benchmarks. Our experiments reveal that DynamicBind can accommodate a wide range of large protein conformational changes and identify cryptic pockets in unseen protein targets. As a result, DynamicBind shows potential in accelerating the development of small molecules for previously undruggable targets and expanding the horizons of computational drug discovery.

MedGAN: optimized generative adversarial network with graph convolutional networks for novel molecule design

Generative Artificial Intelligence can be an important asset in the drug discovery process to meet the demand for novel medicines. This work outlines the optimization and fine-tuning steps of MedGAN, a deep learning model based on Wasserstein Generative Adversarial Networks and Graph Convolutional Networks, developed to generate new quinoline-scaffold molecules from complex molecular graphs, including hyperparameter adjustments and evaluations of drug-likeness attributes such as pharmacokinetics, toxicity, and synthetic accessibility. The best model was capable of generating 25% valid molecules, 62% fully connected, from which 92% were quinolines, 93% were novel, and 95% unique, preserving chirality, atom charge, and favorable drug-like properties while generating 4831 novel quinolines. These results provide valuable insights into how activation functions, optimizers, learning rates, neuron units, molecule size and constitution, and scaffold structure affect the performance of generative models and their potential to create new molecular structures, enhancing deep learning applications in computational drug design.

Discovery of a novel cardiac-specific myosin modulator using artificial intelligence-based virtual screening

Direct modulation of cardiac myosin function has emerged as a therapeutic target for both heart disease and heart failure. However, the development of myosin-based therapeutics has been hampered by the lack of targeted in vitro screening assays. In this study we use Artificial Intelligence-based virtual high throughput screening (vHTS) to identify novel small molecule effectors of human β-cardiac myosin. We test the top scoring compounds from vHTS in biochemical counter-screens and identify a novel chemical scaffold called 'F10' as a cardiac-specific low-micromolar myosin inhibitor. Biochemical and biophysical characterization in both isolated proteins and muscle fibers show that F10 stabilizes both the biochemical (i.e. super-relaxed state) and structural (i.e. interacting heads motif) OFF state of cardiac myosin, and reduces force and left ventricular pressure development in isolated myofilaments and Langendorff-perfused hearts, respectively. F10 is a tunable scaffold for the further development of a novel class of myosin modulators.