Ultra-large library docking for discovering new chemotypes

Identification of putative allosteric inhibitors of BCKDK via virtual screening and biological evaluation

Abnormal accumulation of branched-chain amino acids (BCAAs) can lead to metabolic diseases and cancers. Branched-chain α-keto acid dehydrogenase kinase (BCKDK) is a key negative regulator of BCAA catabolism, and targeting BCKDK provides a promising therapeutic approach for diseases caused by BCAA accumulation. Here, we screened PPHN and POAB as novel putative allosteric inhibitors by integrating allosteric binding site prediction, large-scale ligand database virtual screening, and bioactivity evaluation assays. Both of them showed a high binding affinity to BCKDK, with Kd values of 3.9 μM and 1.86 μM, respectively. In vivo experiments, the inhibitors demonstrated superior kinase inhibitory activity and notable antiproliferative and proapoptotic effects on diverse cancer cells. Finally, bulk RNA-seq analysis revealed that PPHN and POAB suppressed cell growth through a range of signalling pathways. Taken together, our findings highlight two novel BCKDK inhibitors as potent therapeutic candidates for metabolic diseases and cancers associated with BCAA dysfunctional metabolism.

Empowering AlphaFold2 for protein conformation selective drug discovery with AlphaFold2-RAVE

Small-molecule drug design hinges on obtaining co-crystallized ligand-protein structures. Despite AlphaFold2's strides in protein native structure prediction, its focus on apo structures overlooks ligands and associated holo structures. Moreover, designing selective drugs often benefits from the targeting of diverse metastable conformations. Therefore, direct application of AlphaFold2 models in virtual screening and drug discovery remains tentative. Here, we demonstrate an AlphaFold2-based framework combined with all-atom enhanced sampling molecular dynamics and Induced Fit docking, named AF2RAVE-Glide, to conduct computational model-based small-molecule binding of metastable protein kinase conformations, initiated from protein sequences. We demonstrate the AF2RAVE-Glide workflow on three different mammalian protein kinases and their type I and II inhibitors, with special emphasis on binding of known type II kinase inhibitors which target the metastable classical DFG-out state. These states are not easy to sample from AlphaFold2. Here, we demonstrate how with AF2RAVE these metastable conformations can be sampled for different kinases with high enough accuracy to enable subsequent docking of known type II kinase inhibitors with more than 50% success rates across docking calculations. We believe the protocol should be deployable for other kinases and more proteins generally.

An artificial intelligence accelerated virtual screening platform for drug discovery

Structure-based virtual screening is a key tool in early drug discovery, with growing interest in the screening of multi-billion chemical compound libraries. However, the success of virtual screening crucially depends on the accuracy of the binding pose and binding affinity predicted by computational docking. Here we develop a highly accurate structure-based virtual screen method, RosettaVS, for predicting docking poses and binding affinities. Our approach outperforms other state-of-the-art methods on a wide range of benchmarks, partially due to our ability to model receptor flexibility. We incorporate this into a new open-source artificial intelligence accelerated virtual screening platform for drug discovery. Using this platform, we screen multi-billion compound libraries against two unrelated targets, a ubiquitin ligase target KLHDC2 and the human voltage-gated sodium channel NaV1.7. For both targets, we discover hit compounds, including seven hits (14% hit rate) to KLHDC2 and four hits (44% hit rate) to NaV1.7, all with single digit micromolar binding affinities. Screening in both cases is completed in less than seven days. Finally, a high resolution X-ray crystallographic structure validates the predicted docking pose for the KLHDC2 ligand complex, demonstrating the effectiveness of our method in lead discovery.

MzDOCK: A free ready-to-use GUI-based pipeline for molecular docking simulations

Molecular docking is by far the most preferred approach in structure-based drug design for its effectiveness to predict the scoring and posing of a given bioactive small molecule into the binding site of its pharmacological target. Herein, we present MzDOCK, a new GUI-based pipeline for Windows operating system, designed with the intent of making molecular docking easier to use and higher reproducible even for inexperienced people. By harmonic integration of python and batch scripts, which employs various open source packages such as Smina (docking engine), OpenBabel (file conversion) and PLIP (analysis), MzDOCK includes many practical options such as: binding site configuration based on co-crystallized ligands; generation of enantiomers from SMILES input; application of different force fields (MMFF94, MMFF94s, UFF, GAFF, Ghemical) for energy minimization; retention of selectable ions and cofactors; sidechain flexibility of selectable binding site residues; multiple input file format (SMILES, PDB, SDF, Mol2, Mol); generation of reports and of pictures for interactive visualization. Users can download for free MzDOCK at the following link: https://github.com/Muzatheking12/MzDOCK.

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.

Leveraging multiple data types for improved compound-kinase bioactivity prediction

Machine learning provides efficient ways to map compound-kinase interactions. However, diverse bioactivity data types, including single-dose and multi-dose-response assay results, present challenges. Traditional models utilize only multi-dose data, overlooking information contained in single-dose measurements. Here, we propose a machine learning methodology for compound-kinase activity prediction that leverages both single-dose and dose-response data. We demonstrate that our two-stage approach yields accurate activity predictions and significantly improves model performance compared to training solely on dose-response labels. This superior performance is consistent across five diverse machine learning methods. Using the best performing model, we carried out extensive experimental profiling on a total of 347 selected compound-kinase pairs, achieving a high hit rate of 40% and a negative predictive value of 78%. We show that these rates can be improved further by incorporating model uncertainty estimates into the compound selection process. By integrating multiple activity data types, we demonstrate that our approach holds promise for facilitating the development of training activity datasets in a more efficient and cost-effective way.

From Static to Dynamic Structures: Improving Binding Affinity Prediction with Graph-Based Deep Learning

Accurate prediction of protein-ligand binding affinities is an essential challenge in structure-based drug design. Despite recent advances in data-driven methods for affinity prediction, their accuracy is still limited, partially because they only take advantage of static crystal structures while the actual binding affinities are generally determined by the thermodynamic ensembles between proteins and ligands. One effective way to approximate such a thermodynamic ensemble is to use molecular dynamics (MD) simulation. Here, an MD dataset containing 3,218 different protein-ligand complexes is curated, and Dynaformer, a graph-based deep learning model is further developed to predict the binding affinities by learning the geometric characteristics of the protein-ligand interactions from the MD trajectories. In silico experiments demonstrated that the model exhibits state-of-the-art scoring and ranking power on the CASF-2016 benchmark dataset, outperforming the methods hitherto reported. Moreover, in a virtual screening on heat shock protein 90 (HSP90) using Dynaformer, 20 candidates are identified and their binding affinities are further experimentally validated. Dynaformer displayed promising results in virtual drug screening, revealing 12 hit compounds (two are in the submicromolar range), including several novel scaffolds. Overall, these results demonstrated that the approach offer a promising avenue for accelerating the early drug discovery process.

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.

The evolution of computational research in a data-centric world

Computational data-centric research techniques play a prevalent and multi-disciplinary role in life science research. In the past, scientists in wet labs generated the data, and computational researchers focused on creating tools for the analysis of those data. Computational researchers are now becoming more independent and taking leadership roles within biomedical projects, leveraging the increased availability of public data. We are now able to generate vast amounts of data, and the challenge has shifted from data generation to data analysis. Here we discuss the pitfalls, challenges, and opportunities facing the field of data-centric research in biology. We discuss the evolving perception of computational data-driven research and its rise as an independent domain in biomedical research while also addressing the significant collaborative opportunities that arise from integrating computational research with experimental and translational biology. Additionally, we discuss the future of data-centric research and its applications across various areas of the biomedical field.

Ultra-large scale virtual screening identifies a small molecule inhibitor of the Wnt transporter Wntless

Wnts are lipid-modified glycoproteins that play key roles in both embryonic development and adult homeostasis. Wnt signaling is dysregulated in many cancers and preclinical data shows that targeting Wnt biosynthesis and secretion can be effective in Wnt-addicted cancers. An integral membrane protein known as Wntless (WLS/Evi) is essential for Wnt secretion. However, WLS remains undrugged thus far. The cryo-EM structure of WLS in complex with WNT8A shows that WLS has a druggable G-protein coupled receptor (GPCR) domain. Using Active Learning/Glide, we performed an ultra-large scale virtual screening from Enamine's REAL 350/3 Lead-Like library containing nearly 500 million compounds. 68 hits were examined after on-demand synthesis in cell-based Wnt reporter and other functional assays. ETC-451 emerged as a potential first-in-class WLS inhibitor. ETC-451 blocked WLS-WNT3A interaction and decreased Wnt-addicted pancreatic cancer cell line proliferation. The current hit provides a starting chemical scaffold for further structure or ligand-based drug discovery targeting WLS.

Searching for Novel HDAC6/Hsp90 Dual Inhibitors with Anti-Prostate Cancer Activity: In Silico Screening and In Vitro Evaluation

Prostate cancer (PCA) is one of the most prevalent types of male cancers. While current treatments for early-stage PCA are available, their efficacy is limited in advanced PCA, mainly due to drug resistance or low efficacy. In this context, novel valuable therapeutic opportunities may arise from the combined inhibition of histone deacetylase 6 (HDAC6) and heat shock protein 90 (Hsp90). These targets are mutually involved in the regulation of several processes in cancer cells, and their inhibition is demonstrated to provide synergistic effects against PCA. On these premises, we performed an extensive in silico virtual screening campaign on commercial compounds in search of dual inhibitors of HDAC6 and Hsp90. In vitro tests against recombinant enzymes and PCA cells with different levels of aggressiveness allowed the identification of a subset of compounds with inhibitory activity against HDAC6 and antiproliferative effects towards LNCaP and PC-3 cells. None of the candidates showed appreciable Hsp90 inhibition. However, the discovered compounds have low molecular weight and a chemical structure similar to that of potent Hsp90 blockers. This provides an opportunity for structural and medicinal chemistry optimization in order to obtain HDAC6/Hsp90 dual modulators with antiproliferative effects against prostate cancer. These findings were discussed in detail in the study.

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.

Discovery of Crystallizable Organic Semiconductors with Machine Learning

Crystalline organic semiconductors are known to have improved charge carrier mobility and exciton diffusion length in comparison to their amorphous counterparts. Certain organic molecular thin films can be transitioned from initially prepared amorphous layers to large-scale crystalline films via abrupt thermal annealing. Ideally, these films crystallize as platelets with long-range-ordered domains on the scale of tens to hundreds of microns. However, other organic molecular thin films may instead crystallize as spherulites or resist crystallization entirely. Organic molecules that have the capability of transforming into a platelet morphology feature both high melting point (Tm) and crystallization driving force (ΔGc). In this work, we employed machine learning (ML) to identify candidate organic materials with the potential to crystallize into platelets by estimating the aforementioned thermal properties. Six organic molecules identified by the ML algorithm were experimentally evaluated; three crystallized as platelets, one crystallized as a spherulite, and two resisted thin film crystallization. These results demonstrate a successful application of ML in the scope of predicting thermal properties of organic molecules and reinforce the principles of Tm and ΔGc as metrics that aid in predicting the crystallization behavior of organic thin films.

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

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

Know your molecule: pharmacological characterization of drug candidates to enhance efficacy and reduce late-stage attrition

Despite advances in chemical, computational and biological sciences, the rate of attrition of drug candidates in clinical development is still high. A key point in the small-molecule discovery process that could provide opportunities to help address this challenge is the pharmacological characterization of hit and lead compounds, culminating in the selection of a drug candidate. Deeper characterization is increasingly important, because the 'quality' of drug efficacy, at least for G protein-coupled receptors (GPCRs), is now understood to be much more than activation of commonly evaluated pathways such as cAMP signalling, with many more 'efficacies' of ligands that could be harnessed therapeutically. Such characterization is being enabled by novel assays to characterize the complex behaviour of GPCRs, such as biased signalling and allosteric modulation, as well as advances in structural biology, such as cryo-electron microscopy. This article discusses key factors in the assessments of the pharmacology of hit and lead compounds in the context of GPCRs as a target class, highlighting opportunities to identify drug candidates with the potential to address limitations of current therapies and to improve the probability of them succeeding in clinical development.

A Robust Induced Fit Docking Approach with the Combination of the Hybrid All-Atom/United-Atom/Coarse-Grained Model and Simulated Annealing

Molecular docking remains an indispensable tool in computational biology and structure-based drug discovery. However, the correct prediction of binding poses remains a major challenge for molecular docking, especially for target proteins where a substrate binding induces significant reorganization of the active site. Here, we introduce an Induced Fit Docking (IFD) approach named AA/UA/CG-SA-IFD, which combines a hybrid All-Atom/United-Atom/Coarse-Grained model with Simulated Annealing. In this approach, the core region is represented by the All-Atom(AA) model, while the protein environment beyond the core region and the solvent are treated with either the United-Atom (UA) or the Coarse-Grained (CG) model. By combining the Elastic Network Model (ENM) for the CG region, the hybrid model ensures a reasonable description of ligand binding and the environmental effects of the protein, facilitating highly efficient and reliable sampling of ligand binding through Simulated Annealing (SA) at a high temperature. Upon validation with two testing sets, the AA/UA/CG-SA-IFD approach demonstrates remarkable accuracy and efficiency in induced fit docking, even for challenging cases where the docked poses significantly deviate from crystal structures.

Proximity Graph Networks: Predicting Ligand Affinity with Message Passing Neural Networks

Message passing neural networks (MPNNs) on molecular graphs generate continuous and differentiable encodings of small molecules with state-of-the-art performance on protein-ligand complex scoring tasks. Here, we describe the proximity graph network (PGN) package, an open-source toolkit that constructs ligand-receptor graphs based on atom proximity and allows users to rapidly apply and evaluate MPNN architectures for a broad range of tasks. We demonstrate the utility of PGN by introducing benchmarks for affinity and docking score prediction tasks. Graph networks generalize better than fingerprint-based models and perform strongly for the docking score prediction task. Overall, MPNNs with proximity graph data structures augment the prediction of ligand-receptor complex properties when ligand-receptor data are available.

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.

Structure-based discovery of CFTR potentiators and inhibitors

The cystic fibrosis transmembrane conductance regulator (CFTR) is a crucial ion channel whose loss of function leads to cystic fibrosis, whereas its hyperactivation leads to secretory diarrhea. Small molecules that improve CFTR folding (correctors) or function (potentiators) are clinically available. However, the only potentiator, ivacaftor, has suboptimal pharmacokinetics and inhibitors have yet to be clinically developed. Here, we combine molecular docking, electrophysiology, cryo-EM, and medicinal chemistry to identify CFTR modulators. We docked ∼155 million molecules into the potentiator site on CFTR, synthesized 53 test ligands, and used structure-based optimization to identify candidate modulators. This approach uncovered mid-nanomolar potentiators, as well as inhibitors, that bind to the same allosteric site. These molecules represent potential leads for the development of more effective drugs for cystic fibrosis and secretory diarrhea, demonstrating the feasibility of large-scale docking for ion channel drug discovery.

The impact of Library Size and Scale of Testing on Virtual Screening

Virtual libraries for ligand discovery have recently increased 10,000-fold, and this is thought to have improved hit rates and potencies from library docking. This idea has not, however, been experimentally tested in direct comparisons of larger-vs-smaller libraries. Meanwhile, though libraries have exploded, the scale of experimental testing has little changed, with often only dozens of high-ranked molecules investigated, making interpretation of hit rates and affinities uncertain. Accordingly, we docked a 1.7 billion molecule virtual library against the model enzyme AmpC β-lactamase, testing 1,521 new molecules and comparing the results to the same screen with a library of 99 million molecules, where only 44 molecules were tested. Encouragingly, the larger screen outperformed the smaller one: hit rates improved by two-fold, more new scaffolds were discovered, and potency improved. Overall, 50-fold more inhibitors were found, supporting the idea that there are many more compounds to be discovered than are being tested. With so many compounds evaluated, we could ask how the results vary with number tested, sampling smaller sets at random from the 1521. Hit rates and affinities were highly variable when we only sampled dozens of molecules, and it was only when we included several hundred molecules that results converged. As docking scores improved, so too did the likelihood of a molecule binding; hit rates improved steadily with docking score, as did affinities. This also appeared true on reanalysis of large-scale results against the σ2 and dopamine D4 receptors. It may be that as the scale of both the virtual libraries and their testing grows, not only are better ligands found but so too does our ability to rank them.

Structure-aware dual-target drug design through collaborative learning of pharmacophore combination and molecular simulation

Dual-target drug design has gained significant attention in the treatment of complex diseases, such as cancers and autoimmune disorders. A widely employed design strategy is combining pharmacophores to leverage the knowledge of structure-activity relationships of both targets. Unfortunately, pharmacophore combination often struggles with long and expensive trial and error, because the protein pockets of the two targets impose complex structural constraints. In this study, we propose AIxFuse, a structure-aware dual-target drug design method that learns pharmacophore fusion patterns to satisfy the dual-target structural constraints simulated by molecular docking. AIxFuse employs two self-play reinforcement learning (RL) agents to learn pharmacophore selection and fusion by comprehensive feedback including dual-target molecular docking scores. Collaboratively, the molecular docking scores are learned by active learning (AL). Through collaborative RL and AL, AIxFuse learns to generate molecules with multiple desired properties. AIxFuse is shown to outperform state-of-the-art methods in generating dual-target drugs against glycogen synthase kinase-3 beta (GSK3β) and c-Jun N-terminal kinase 3 (JNK3). When applied to another task against retinoic acid receptor-related orphan receptor γ-t (RORγt) and dihydroorotate dehydrogenase (DHODH), AIxFuse exhibits consistent performance while compared methods suffer from performance drops, leading to a 5 times higher performance in success rate. Docking studies demonstrate that AIxFuse can generate molecules concurrently satisfying the binding mode required by both targets. Further free energy perturbation calculation indicates that the generated candidates have promising binding free energies against both targets.

Integrating bacterial molecular genetics with chemical biology for renewed antibacterial drug discovery

The application of dyes to understanding the aetiology of infection inspired antimicrobial chemotherapy and the first wave of antibacterial drugs. The second wave of antibacterial drug discovery was driven by rapid discovery of natural products, now making up 69% of current antibacterial drugs. But now with the most prevalent natural products already discovered, ∼107 new soil-dwelling bacterial species must be screened to discover one new class of natural product. Therefore, instead of a third wave of antibacterial drug discovery, there is now a discovery bottleneck. Unlike natural products which are curated by billions of years of microbial antagonism, the vast synthetic chemical space still requires artificial curation through the therapeutics science of antibacterial drugs - a systematic understanding of how small molecules interact with bacterial physiology, effect desired phenotypes, and benefit the host. Bacterial molecular genetics can elucidate pathogen biology relevant to therapeutics development, but it can also be applied directly to understanding mechanisms and liabilities of new chemical agents with new mechanisms of action. Therefore, the next phase of antibacterial drug discovery could be enabled by integrating chemical expertise with systematic dissection of bacterial infection biology. Facing the ambitious endeavour to find new molecules from nature or new-to-nature which cure bacterial infections, the capabilities furnished by modern chemical biology and molecular genetics can be applied to prospecting for chemical modulators of new targets which circumvent prevalent resistance mechanisms.

In silico fragment-based discovery of CIB1-directed anti-tumor agents by FRASE-bot

Chemical probes are an indispensable tool for translating biological discoveries into new therapies, though are increasingly difficult to identify since novel therapeutic targets are often hard-to-drug proteins. We introduce FRASE-based hit-finding robot (FRASE-bot), to expedite drug discovery for unconventional therapeutic targets. FRASE-bot mines available 3D structures of ligand-protein complexes to create a database of FRAgments in Structural Environments (FRASE). The FRASE database can be screened to identify structural environments similar to those in the target protein and seed the target structure with relevant ligand fragments. A neural network model is used to retain fragments with the highest likelihood of being native binders. The seeded fragments then inform ultra-large-scale virtual screening of commercially available compounds. We apply FRASE-bot to identify ligands for Calcium and Integrin Binding protein 1 (CIB1), a promising drug target implicated in triple negative breast cancer. FRASE-based virtual screening identifies a small-molecule CIB1 ligand (with binding confirmed in a TR-FRET assay) showing specific cell-killing activity in CIB1-dependent cancer cells, but not in CIB1-depletion-insensitive cells.

Systematic Investigation of Dual-Target-Directed Ligands

Multitarget-directed ligands (MTDLs) are compounds rationally designed to affect multiple targets, aiming for a better therapeutic profile. For over 20 years, MTDLs have garnered increasing attention, the idea being that their full potential would have been achieved, thanks to unprecedented target combinations and advanced medicinal chemistry strategies. This study presents a literature mining effort resulting in a data set of dual-target-directed ligands (DTDLs), the fundamental example of MTDLs. We used this data set to evaluate the rationale behind target selection and the chemical novelty of DTDLs targeting specific protein combinations. Our analysis focused on DTDL targets in terms of biological function, disease association, structure, and chemogenomic traits. We also compared DTDLs with single-target compounds. We found that well-known target pathology associations often guide DTDL design, leveraging existing chemical scaffolds and binding pocket similarities. These findings highlight the current state of the field and suggest substantial untapped potential for rational polypharmacology.

Augmented Memory: Sample-Efficient Generative Molecular Design with Reinforcement Learning

Sample efficiency is a fundamental challenge in de novo molecular design. Ideally, molecular generative models should learn to satisfy a desired objective under minimal calls to oracles (computational property predictors). This problem becomes more apparent when using oracles that can provide increased predictive accuracy but impose significant computational cost. Consequently, designing molecules that are optimized for such oracles cannot be achieved under a practical computational budget. Molecular generative models based on simplified molecular-input line-entry system (SMILES) have shown remarkable sample efficiency when coupled with reinforcement learning, as demonstrated in the practical molecular optimization (PMO) benchmark. Here, we first show that experience replay drastically improves the performance of multiple previously proposed algorithms. Next, we propose a novel algorithm called Augmented Memory that combines data augmentation with experience replay. We show that scores obtained from oracle calls can be reused to update the model multiple times. We compare Augmented Memory to previously proposed algorithms and show significantly enhanced sample efficiency in an exploitation task, a drug discovery case study requiring both exploration and exploitation, and a materials design case study optimizing explicitly for quantum-mechanical properties. Our method achieves a new state-of-the-art in sample-efficient de novo molecular design, outperforming all of the previously reported methods. The code is available at https://github.com/schwallergroup/augmented_memory.

AlphaFold2 structures guide prospective ligand discovery

AlphaFold2 (AF2) models have had wide impact but mixed success in retrospective ligand recognition. We prospectively docked large libraries against unrefined AF2 models of the σ2 and serotonin 2A (5-HT2A) receptors, testing hundreds of new molecules and comparing results with those obtained from docking against the experimental structures. Hit rates were high and similar for the experimental and AF2 structures, as were affinities. Success in docking against the AF2 models was achieved despite differences between orthosteric residue conformations in the AF2 models and the experimental structures. Determination of the cryo-electron microscopy structure for one of the more potent 5-HT2A ligands from the AF2 docking revealed residue accommodations that resembled the AF2 prediction. AF2 models may sample conformations that differ from experimental structures but remain low energy and relevant for ligand discovery, extending the domain of structure-based drug design.

Carbenoid-involved reactions integrated with scaffold-based screening generates a Nav1.7 inhibitor

The discovery of selective Nav1.7 inhibitors is a promising approach for developing anti-nociceptive drugs. In this study, we present a novel oxindole-based readily accessible library (OREAL), which is characterized by readily accessibility, unique chemical space, ideal drug-like properties, and structural diversity. We used a scaffold-based approach to screen the OREAL and discovered compound C4 as a potent Nav1.7 inhibitor. The bioactivity characterization of C4 reveals that it is a selective Nav1.7 inhibitor and effectively reverses Paclitaxel-induced neuropathic pain (PINP) in rodent models. Preliminary toxicology study shows C4 is negative to hERG. The consistent results of molecular docking and molecular simulations further support the reasonability of the in-silico screening and show the insight of the binding mode of C4. Our discovery of C4 paves the way for pushing the Nav1.7-based anti-nociceptive drugs forward to the clinic.

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

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

Assessment of Nucleobase Protomeric and Tautomeric States in Nucleic Acid Structures for Interaction Analysis and Structure-Based Ligand Design

With increasing interest in RNA as a therapeutic and a potential target, the role of RNA structures has become more important. Even slight changes in nucleobases, such as modifications or protomeric and tautomeric states, can have a large impact on RNA structure and function, while local environments in turn affect protonation and tautomerization. In this work, the application of empirical tools for pKa and tautomer prediction for RNA modifications was elucidated and compared with ab initio quantum mechanics (QM) methods and expanded toward macromolecular RNA structures, where QM is no longer feasible. In this regard, the Protonate3D functionality within the molecular operating environment (MOE) was expanded for nucleobase protomer and tautomer predictions and applied to reported examples of altered protonation states depending on the local environment. Overall, observations of nonstandard protomers and tautomers were well reproduced, including structural C+G:C(A) and A+GG motifs, several mismatches, and protonation of adenosine or cytidine as the general acid in nucleolytic ribozymes. Special cases, such as cobalt hexamine-soaked complexes or the deprotonation of guanosine as the general base in nucleolytic ribozymes, proved to be challenging. The collected set of examples shall serve as a starting point for the development of further RNA protonation prediction tools, while the presented Protonate3D implementation already delivers reasonable protonation predictions for RNA and DNA macromolecules. For cases where higher accuracy is needed, like following catalytic pathways of ribozymes, incorporation of QM-based methods can build upon the Protonate3D-generated starting structures. Likewise, this protonation prediction can be used for structure-based RNA-ligand design approaches.

Screening of Mpro Protease (SARS-CoV-2) Covalent Inhibitors from an Anthocyanin-Rich Blueberry Extract Using an HRMS-Based Analytical Platform

BACKGROUND

The viral main protease (Mpro) of SARS-CoV-2 has been recently proposed as a key target to inhibit virus replication in the host. Therefore, molecules that can bind the catalytic site of Mpro could be considered as potential drug candidates in the treatment of SARS-CoV-2 infections. Here we proposed the application of a state-of-the-art analytical platform which combines metabolomics and protein structure analysis to fish-out potential active compounds deriving from a natural matrix, i.e., a blueberry extract.

METHODS

The experiments focus on finding MS covalent inhibitors of Mpro that contain in their structure a catechol/pyrogallol moiety capable of binding to the nucleophilic amino acids of the enzyme's catalytic site.

RESULTS

Among the potential candidates identified, the delphinidin-3-glucoside showed the most promising results. Its antiviral activity has been confirmed in vitro on Vero E6 cells infected with SARS-CoV-2, showing a dose-dependent inhibitory effect almost comparable to the known Mpro inhibitor baicalin. The interaction of delphinidin-3-glucoside with the Mpro pocket observed was also evaluated by computational studies.

CONCLUSIONS

The HRMS analytical platform described proved to be effective in identifying compounds that covalently bind Mpro and are active in the inhibition of SARS-CoV-2 replication, such as delphinidin-3-glucoside.

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

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

Accelerating Molecular Docking using Machine Learning Methods

Virtual screening (VS) is one of the well-established approaches in drug discovery which speeds up the search for a bioactive molecule and, reduces costs and efforts associated with experiments. VS helps to narrow down the search space of chemical space and allows selecting fewer and more probable candidate compounds for experimental testing. Docking calculations are one of the commonly used and highly appreciated structure-based drug discovery methods. Databases for chemical structures of small molecules have been growing rapidly. However, at the moment virtual screening of large libraries via docking is not very common. In this work, we aim to accelerate docking studies by predicting docking scores without explicitly performing docking calculations. We experimented with an attention based long short-term memory (LSTM) neural network for an efficient prediction of docking scores as well as other machine learning models such as XGBoost. By using docking scores of a small number of ligands we trained our models and predicted docking scores of a few million molecules. Specifically, we tested our approaches on 11 datasets that were produced from in-house drug discovery studies. On average, by training models using only 7000 molecules we predicted docking scores of approximately 3.8 million molecules with R2 (coefficient of determination) of 0.77 and Spearman rank correlation coefficient of 0.85. We designed the system with ease of use in mind. All the user needs to provide is a csv file containing SMILES and their respective docking scores, the system then outputs a model that the user can use for the prediction of docking score for a new molecule.

New perspective of small-molecule antiviral drugs development for RNA viruses

High variability and adaptability of RNA viruses allows them to spread between humans and animals, causing large-scale infectious diseases which seriously threat human and animal health and social development. At present, AIDS, viral hepatitis and other viral diseases with high incidence and low cure rate are still spreading around the world. The outbreaks of Ebola, Zika, dengue and in particular of the global pandemic of COVID-19 have presented serious challenges to the global public health system. The development of highly effective and broad-spectrum antiviral drugs is a substantial and urgent research subject to deal with the current RNA virus infection and the possible new viral infections in the future. In recent years, with the rapid development of modern disciplines such as artificial intelligence technology, bioinformatics, molecular biology, and structural biology, some new strategies and targets for antivirals development have emerged. Here we review the main strategies and new targets for developing small-molecule antiviral drugs against RNA viruses through the analysis of the new drug development progress against several highly pathogenic RNA viruses, to provide clues for development of future antivirals.

A divergent intermediate strategy yields biologically diverse pseudo-natural products

The efficient exploration of biologically relevant chemical space is essential for the discovery of bioactive compounds. A molecular design principle that possesses both biological relevance and structural diversity may more efficiently lead to compound collections that are enriched in diverse bioactivities. Here the diverse pseudo-natural product (PNP) strategy, which combines the biological relevance of the PNP concept with synthetic diversification strategies from diversity-oriented synthesis, is reported. A diverse PNP collection was synthesized from a common divergent intermediate through developed indole dearomatization methodologies to afford three-dimensional molecular frameworks that could be further diversified via intramolecular coupling and/or carbon monoxide insertion. In total, 154 PNPs were synthesized representing eight different classes. Cheminformatic analyses showed that the PNPs are structurally diverse between classes. Biological investigations revealed the extent of diverse bioactivity enrichment of the collection in which four inhibitors of Hedgehog signalling, DNA synthesis, de novo pyrimidine biosynthesis and tubulin polymerization were identified from four different PNP classes.

Geometry Optimization Algorithms in Conjunction with the Machine Learning Potential ANI-2x Facilitate the Structure-Based Virtual Screening and Binding Mode Prediction

Structure-based virtual screening utilizes molecular docking to explore and analyze ligand-macromolecule interactions, crucial for identifying and developing potential drug candidates. Although there is availability of several widely used docking programs, the accurate prediction of binding affinity and binding mode still presents challenges. In this study, we introduced a novel protocol that combines our in-house geometry optimization algorithm, the conjugate gradient with backtracking line search (CG-BS), which is capable of restraining and constraining rotatable torsional angles and other geometric parameters with a highly accurate machine learning potential, ANI-2x, renowned for its precise molecular energy predictions reassembling the wB97X/6-31G(d) model. By integrating this protocol with binding pose prediction using the Glide, we conducted additional structural optimization and potential energy prediction on 11 small molecule-macromolecule and 12 peptide-macromolecule systems. We observed that ANI-2x/CG-BS greatly improved the docking power, not only optimizing binding poses more effectively, particularly when the RMSD of the predicted binding pose by Glide exceeded around 5 Å, but also achieving a 26% higher success rate in identifying those native-like binding poses at the top rank compared to Glide docking. As for the scoring and ranking powers, ANI-2x/CG-BS demonstrated an enhanced performance in predicting and ranking hundreds or thousands of ligands over Glide docking. For example, Pearson's and Spearman's correlation coefficients remarkedly increased from 0.24 and 0.14 with Glide docking to 0.85 and 0.69, respectively, with the addition of ANI-2x/CG-BS for optimizing and ranking small molecules binding to the bacterial ribosomal aminoacyl-tRNA receptor. These results suggest that ANI-2x/CG-BS holds considerable potential for being integrated into virtual screening pipelines due to its enhanced docking performance.

DiffBindFR: an SE(3) equivariant network for flexible protein-ligand docking

Molecular docking, a key technique in structure-based drug design, plays pivotal roles in protein-ligand interaction modeling, hit identification and optimization, in which accurate prediction of protein-ligand binding mode is essential. Conventional docking approaches perform well in redocking tasks with known protein binding pocket conformation in the complex state. However, in real-world docking scenario without knowing the protein binding conformation for a new ligand, accurately modeling the binding complex structure remains challenging as flexible docking is computationally expensive and inaccurate. Typical deep learning-based docking methods do not explicitly consider protein side chain conformations and fail to ensure the physical plausibility and detailed atomic interactions. In this study, we present DiffBindFR, a full-atom diffusion-based flexible docking model that operates over the product space of ligand overall movements and flexibility and pocket side chain torsion changes. We show that DiffBindFR has higher accuracy in producing native-like binding structures with physically plausible and detailed interactions than available docking methods. Furthermore, in the Apo and AlphaFold2 modeled structures, DiffBindFR demonstrates superior advantages in accurate ligand binding pose and protein binding conformation prediction, making it suitable for Apo and AlphaFold2 structure-based drug design. DiffBindFR provides a powerful flexible docking tool for modeling accurate protein-ligand binding structures.

Investigating and Quantifying Molecular Complexity Using Assembly Theory and Spectroscopy

Current approaches to evaluate molecular complexity use algorithmic complexity, rooted in computer science, and thus are not experimentally measurable. Directly evaluating molecular complexity could be used to study directed vs undirected processes in the creation of molecules, with potential applications in drug discovery, the origin of life, and artificial life. Assembly theory has been developed to quantify the complexity of a molecule by finding the shortest path to construct the molecule from building blocks, revealing its molecular assembly index (MA). In this study, we present an approach to rapidly infer the MA of molecules from spectroscopic measurements. We demonstrate that the MA can be experimentally measured by using three independent techniques: nuclear magnetic resonance (NMR), tandem mass spectrometry (MS/MS), and infrared spectroscopy (IR). By identifying and analyzing the number of absorbances in IR spectra, carbon resonances in NMR, or molecular fragments in tandem MS, the MA of an unknown molecule can be reliably estimated. This represents the first experimentally quantifiable approach to determining molecular assembly. This paves the way to use experimental techniques to explore the evolution of complex molecules as well as a unique marker of where an evolutionary process has been operating.

Identification of 1,3,8-Triazaspiro[4.5]Decane-2,4-Dione Derivatives as a Novel δ Opioid Receptor-Selective Agonist Chemotype

δ opioid receptors (DORs) hold potential as a target for neurologic and psychiatric disorders, yet no DOR agonist has proven efficacious in critical phase II clinical trials. The exact reasons for the failure to produce quality drug candidates for the DOR are unclear. However, it is known that certain DOR agonists can induce seizures and exhibit tachyphylaxis. Several studies have suggested that those adverse effects are more prevalent in delta agonists that share the (+)-4-[(αR)-α-((2S,5R)-4-allyl-2,5-dimethyl-1-piperazinyl)-3-methoxybenzyl]-N,N-diethylbenzamide (SNC80)/4-[(αR*)-α-((2S*,5R*)-4-allyl-2,5-dimethyl-1-piperazinyl)-3-hydroxybenzyl]-N,N-diethylbenzamide chemotype. There is a need to find novel lead candidates for drug development that have improved pharmacological properties to differentiate them from the current failed delta agonists. Our objective in this study was to identify novel DOR agonists. We used a β-arrestin assay to screen a small G-protein coupled receptors (GPCR)-focused chemical library. We identified a novel chemotype of DOR agonists that appears to bind to the orthosteric site based of docking and molecular dynamic simulation. The most potent agonist hit compound is selective for the DOR over a panel of 167 other GPCRs, is slightly biased toward G-protein signaling and has anti-allodynic efficacy in a complete Freund's adjuvant model of inflammatory pain in C57BL/6 male and female mice. The newly discovered chemotype contrasts with molecules like SNC80 that are highly efficacious β-arrestin recruiters and may suggest this novel class of DOR agonists could be expanded on to develop a clinical candidate drug. SIGNIFICANCE STATEMENT: δ opioid receptors are a clinical target for various neurological disorders, including migraine and chronic pain. Many of the clinically tested delta opioid agonists share a single chemotype, which carries risks during drug development. Through a small-scale high-throughput screening assay, this study identified a novel δ opioid receptor agonist chemotype, which may serve as alternative for the current analgesic clinical candidates.

Delocalized, asynchronous, closed-loop discovery of organic laser emitters

Contemporary materials discovery requires intricate sequences of synthesis, formulation, and characterization that often span multiple locations with specialized expertise or instrumentation. To accelerate these workflows, we present a cloud-based strategy that enabled delocalized and asynchronous design-make-test-analyze cycles. We showcased this approach through the exploration of molecular gain materials for organic solid-state lasers as a frontier application in molecular optoelectronics. Distributed robotic synthesis and in-line property characterization, orchestrated by a cloud-based artificial intelligence experiment planner, resulted in the discovery of 21 new state-of-the-art materials. Gram-scale synthesis ultimately allowed for the verification of best-in-class stimulated emission in a thin-film device. Demonstrating the asynchronous integration of five laboratories across the globe, this workflow provides a blueprint for delocalizing-and democratizing-scientific discovery.

Correlation of protein binding pocket properties with hits' chemistries used in generation of ultra-large virtual libraries

Although the size of virtual libraries of synthesizable compounds is growing rapidly, we are still enumerating only tiny fractions of the drug-like chemical universe. Our capability to mine these newly generated libraries also lags their growth. That is why fragment-based approaches that utilize on-demand virtual combinatorial libraries are gaining popularity in drug discovery. These à la carte libraries utilize synthetic blocks found to be effective binders in parts of target protein pockets and a variety of reliable chemistries to connect them. There is, however, no data on the potential impact of the chemistries used for making on-demand libraries on the hit rates during virtual screening. There are also no rules to guide in the selection of these synthetic methods for production of custom libraries. We have used the SAVI (Synthetically Accessible Virtual Inventory) library, constructed using 53 reliable reaction types (transforms), to evaluate the impact of these chemistries on docking hit rates for 40 well-characterized protein pockets. The data shows that the virtual hit rates differ significantly for different chemistries with cross coupling reactions such as Sonogashira, Suzuki-Miyaura, Hiyama and Liebeskind-Srogl coupling producing the highest hit rates. Virtual hit rates appear to depend not only on the property of the formed chemical bond but also on the diversity of available building blocks and the scope of the reaction. The data identifies reactions that deserve wider use through increasing the number of corresponding building blocks and suggests the reactions that are more effective for pockets with certain physical and hydrogen bond-forming properties.

Streamlining Computational Fragment-Based Drug Discovery through Evolutionary Optimization Informed by Ligand-Based Virtual Prescreening

Recent advances in computational methods provide the promise of dramatically accelerating drug discovery. While mathematical modeling and machine learning have become vital in predicting drug-target interactions and properties, there is untapped potential in computational drug discovery due to the vast and complex chemical space. This paper builds on our recently published computational fragment-based drug discovery (FBDD) method called fragment databases from screened ligand drug discovery (FDSL-DD). FDSL-DD uses in silico screening to identify ligands from a vast library, fragmenting them while attaching specific attributes based on predicted binding affinity and interaction with the target subdomain. In this paper, we further propose a two-stage optimization method that utilizes the information from prescreening to optimize computational ligand synthesis. We hypothesize that using prescreening information for optimization shrinks the search space and focuses on promising regions, thereby improving the optimization for candidate ligands. The first optimization stage assembles these fragments into larger compounds using genetic algorithms, followed by a second stage of iterative refinement to produce compounds with enhanced bioactivity. To demonstrate broad applicability, the methodology is demonstrated on three diverse protein targets found in human solid cancers, bacterial antimicrobial resistance, and the SARS-CoV-2 virus. Combined, the proposed FDSL-DD and a two-stage optimization approach yield high-affinity ligand candidates more efficiently than other state-of-the-art computational FBDD methods. We further show that a multiobjective optimization method accounting for drug-likeness can still produce potential candidate ligands with a high binding affinity. Overall, the results demonstrate that integrating detailed chemical information with a constrained search framework can markedly optimize the initial drug discovery process, offering a more precise and efficient route to developing new therapeutics.

Rational Design of Drugs Targeting G-Protein-Coupled Receptors: Ligand Search and Screening

G protein-coupled receptors (GPCRs) are transmembrane proteins that participate in many physiological processes and represent major pharmacological targets. Recent advances in structural biology of GPCRs have enabled the development of drugs based on the receptor structure (structure-based drug design, SBDD). SBDD utilizes information about the receptor-ligand complex to search for suitable compounds, thus expanding the chemical space of possible receptor ligands without the need for experimental screening. The review describes the use of structure-based virtual screening (SBVS) for GPCR ligands and approaches for the functional testing of potential drug compounds, as well as discusses recent advances and successful examples in the application of SBDD for the identification of GPCR ligands.

A virtual library of small molecules mimicking dipeptides

Virtual combinatorial libraries are prevalent in drug discovery due to improvements in the prediction of synthetic reactions that can be performed. This has gone hand in hand with the development of virtual screening capabilities to effectively screen the large chemical spaces spanned by exhaustive enumeration of reaction products. In this study, we generated a small-molecule dipeptide mimic library to target proteins binding small peptides. The library was created based on the general idea of peptide synthesis, that is, amino acid mimics were reacted in silico to form the dipeptide mimics, yielding 2,036,819 unique compounds. After docking calculations, two compounds from the library were synthesized and tested against WD repeat-containing protein 5 (WDR5) and histamine receptors H1-H4 to evaluate whether these molecules are viable in assays. The compounds showed the highest potency at the histamine H3 receptor, with Ki values in the two-digit micromolar range.

Flexible scaffold-based cheminformatics approach for polypharmacological drug design

Effective treatments for complex central nervous system (CNS) disorders require drugs with polypharmacology and multifunctionality, yet designing such drugs remains a challenge. Here, we present a flexible scaffold-based cheminformatics approach (FSCA) for the rational design of polypharmacological drugs. FSCA involves fitting a flexible scaffold to different receptors using different binding poses, as exemplified by IHCH-7179, which adopted a "bending-down" binding pose at 5-HT2AR to act as an antagonist and a "stretching-up" binding pose at 5-HT1AR to function as an agonist. IHCH-7179 demonstrated promising results in alleviating cognitive deficits and psychoactive symptoms in mice by blocking 5-HT2AR for psychoactive symptoms and activating 5-HT1AR to alleviate cognitive deficits. By analyzing aminergic receptor structures, we identified two featured motifs, the "agonist filter" and "conformation shaper," which determine ligand binding pose and predict activity at aminergic receptors. With these motifs, FSCA can be applied to the design of polypharmacological ligands at other receptors.

Virtual Screening of a Chemically Diverse "Superscaffold" Library Enables Ligand Discovery for a Key GPCR Target

The advent of ultra-large libraries of drug-like compounds has significantly broadened the possibilities in structure-based virtual screening, accelerating the discovery and optimization of high-quality lead chemotypes for diverse clinical targets. Compared to traditional high-throughput screening, which is constrained to libraries of approximately one million compounds, the ultra-large virtual screening approach offers substantial advantages in both cost and time efficiency. By expanding the chemical space with compounds synthesized from easily accessible and reproducible reactions and utilizing a large, diverse set of building blocks, we can enhance both the diversity and quality of the discovered lead chemotypes. In this study, we explore new chemical spaces using reactions of sulfur(VI) fluorides to create a combinatorial library consisting of several hundred million compounds. We screened this virtual library for cannabinoid type II receptor (CB2) antagonists using the high-resolution structure in conjunction with a rationally designed antagonist, AM10257. The top-predicted compounds were then synthesized and tested in vitro for CB2 binding and functional antagonism, achieving an experimentally validated hit rate of 55%. Our findings demonstrate the effectiveness of reliable reactions, such as sulfur fluoride exchange, in diversifying ultra-large chemical spaces and facilitate the discovery of new lead compounds for important biological targets.

Discovery of Protease-Activated Receptor 4 (PAR4)-Tethered Ligand Antagonists Using Ultralarge Virtual Screening

Here, we demonstrate a structure-based small molecule virtual screening and lead optimization pipeline using a homology model of a difficult-to-drug G-protein-coupled receptor (GPCR) target. Protease-activated receptor 4 (PAR4) is activated by thrombin cleavage, revealing a tethered ligand that activates the receptor, making PAR4 a challenging target. A virtual screen of a make-on-demand chemical library yielded a one-hit compound. From the single-hit compound, we developed a novel series of PAR4 antagonists. Subsequent lead optimization via simultaneous virtual library searches and structure-based rational design efforts led to potent antagonists of thrombin-induced activation. Interestingly, this series of antagonists was active against PAR4 activation by the native protease thrombin cleavage but not the synthetic PAR4 agonist peptide AYPGKF.

The Science and Art of Structure-Based Virtual Screening

Structure-based virtual screening has gained momentum again as the high attrition rate at every stage of drug discovery drives the need to explore a greater chemical space. From the Bayesian perspective, its shortcomings as a viable strategy for sustainable hit discovery are discussed, with regard to the prior hit rates of screening libraries and the performance of computational methods. Lessons are shared in selecting virtual hits for experimental validation learned from a series of eight successful campaigns, one of which impacted the discovery of a drug candidate currently in clinical trials.

A High-Quality Data Set of Protein-Ligand Binding Interactions Via Comparative Complex Structure Modeling

High-quality protein-ligand complex structures provide the basis for understanding the nature of noncovalent binding interactions at the atomic level and enable structure-based drug design. However, experimentally determined complex structures are scarce compared with the vast chemical space. In this study, we addressed this issue by constructing the BindingNet data set via comparative complex structure modeling, which contains 69,816 modeled high-quality protein-ligand complex structures with experimental binding affinity data. BindingNet provides valuable insights into investigating protein-ligand interactions, allowing visual inspection and interpretation of structural analogues' structure-activity relationships. It can also be used for evaluating machine-learning-based scoring functions. Our results indicate that machine learning models trained on BindingNet could reduce the bias caused by buried solvent-accessible surface area, as we previously found for models trained on the PDBbind data set. We also discussed strategies to improve BindingNet and its potential utilization for benchmarking the molecular docking methods and ligand binding free energy calculation approaches. The BindingNet complements PDBbind in constructing a sufficient and unbiased protein-ligand binding data set and is freely available at http://bindingnet.huanglab.org.cn.

DFRscore: Deep Learning-Based Scoring of Synthetic Complexity with Drug-Focused Retrosynthetic Analysis for High-Throughput Virtual Screening

Recently emerging generative AI models enable us to produce a vast number of compounds for potential applications. While they can provide novel molecular structures, the synthetic feasibility of the generated molecules is often questioned. To address this issue, a few recent studies have attempted to use deep learning models to estimate the synthetic accessibility of many molecules rapidly. However, retrosynthetic analysis tools used to train the models rely on reaction templates automatically extracted from a large reaction database that are not domain-specific and may exhibit low chemical correctness. To overcome this limitation, we introduce DFRscore (Drug-Focused Retrosynthetic score), a deep learning-based approach for a more practical assessment of synthetic accessibility in drug discovery. The DFRscore model is trained exclusively on drug-focused reactions, providing a predicted number of minimally required synthetic steps for each compound. This approach enables practitioners to filter out compounds that do not meet their desired level of synthetic accessibility at an early stage of high-throughput virtual screening for accelerated drug discovery. The proposed strategy can be easily adapted to other domains by adjusting the synthesis planning setup of the reaction templates and starting materials.