Large-scale Virtual Screening Research Articles

Discovery of a Potential Allosteric Site in the SARS-CoV-2 Spike Protein and Targeting Allosteric Inhibitor to Stabilize the RBD Down State using a Computational Approach.

The novel coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has led to a worldwide public health crisis. At present, the development of effective drugs and/or related therapeutics is still the most urgent and important task for combating the virus. The viral entry and associated infectivity mainly rely on its envelope spike protein to recognize and bind to the host cell receptor angiotensin-converting enzyme 2 (ACE2) through a conformational switch of the spike receptor binding domain (RBD) from inactive to active state. Thus, it is of great significance to design an allosteric inhibitor targeting spike to lock it in the inactive and ACE2-inaccessible state. This study aims to discover the potential broad-spectrum allosteric inhibitors capable of binding and stabilizing the diverse spike variants, including the wild type, Delta, and Omicron, in the inactive RBD down state. In this work, we first detected a potential allosteric pocket within the SARS-CoV-2 spike protein. Then, we performed large-scale structure-based virtual screening by targeting the putative allosteric pocket to identify allosteric inhibitors that could stabilize the spike inactive state. Molecular dynamics simulations were further carried out to evaluate the effects of compound binding on the stability of spike RBD. Finally, we identified three potential allosteric inhibitors, CPD3, CPD5, and CPD6, against diverse SARS-CoV-2 variants, including Wild-type, Delta, and Omicron variants. Our simulation results showed that the three compounds could stably bind the predicted allosteric site and effectively stabilize the spike in the inactive state. The three compounds provide novel chemical structures for rational drug design targeting spike protein, which is expected to greatly assist in the development of new drugs against SARS-CoV-2.

Understanding and Predicting Ligand Efficacy in the μ-Opioid Receptor through Quantitative Dynamical Analysis of Complex Structures.

The μ-opioid receptor (MOR) is a G-protein coupled receptor involved in nociception and the primary target of opioid drugs. Understanding the relationships among the ligand structure, receptor dynamics, and efficacy in activating MOR is crucial for drug discovery and development. Here, we use coarse-grained normal-mode analysis to predict ligand-induced changes in receptor dynamics with the Quantitative Dynamics Activity Relationship (QDAR) DynaSig-ML methodology, training a LASSO regression model on the entropic signatures (ESs) computed from ligand-receptor complexes. We train and validate the methodology using a data set of 179 MOR ligands with experimentally measured efficacies split into strictly chemically different cross-validation sets. By analyzing the coefficients of the ES LASSO model, we identified key residues involved in MOR activation, several of which have mutational data supporting their role in MOR activation. Additionally, we explored a contact-only LASSO model based on ligand-protein interactions. While the model showed predictive power, it failed at predicting efficacy for ligands with low structural similarity to the training set, emphasizing the importance of receptor dynamics for predicting ligand-induced receptor activation. Moreover, the low computational cost of our approach, at 3 CPU s per ligand-receptor complex, opens the door to its application in large-scale virtual screening contexts. Our work contributes to a better understanding of dynamics-function relationships in the μ-opioid receptor and provides a framework for predicting ligand efficacy based on ligand-induced changes in receptor dynamics.

ROSHAMBO: Open-Source Molecular Alignment and 3D Similarity Scoring.

Efficient virtual screening techniques are critical in drug discovery for identifying potential drug candidates. We present an open-source package for molecular alignment and 3D similarity calculations optimized for large-scale virtual screening of small molecules. This work parallels widely used proprietary tools and offers an approach complementary to structure-based virtual screening. Our package employs the PAPER software for optimizing molecular alignments based on Gaussian volume overlaps. GPU acceleration is utilized to significantly reduce computational time and resource requirements. After obtaining the optimal alignments between the target and the query molecules, both shape and color (based on pharmacophore features) scores are computed to assess molecular similarity, with aligned molecules optionally being output in sdf format. The package was benchmarked using the DUDE-Z public data sets. Results demonstrated the package's near-state-of-the-art performance and robustness across multiple target classes, with speed that enables many routine ligand-based drug discovery workflows. As an open-source and freely available resource (github.com/molecularinformatics/roshambo) with both a convenient Python API and command line interface, our package also addresses the need for accessible and efficient virtual screening tools in drug discovery.

Scalable crystal structure relaxation using an iteration-free deep generative model with uncertainty quantification

In computational molecular and materials science, determining equilibrium structures is the crucial first step for accurate subsequent property calculations. However, the recent discovery of millions of new crystals and super large twisted structures has challenged traditional computational methods, both ab initio and machine-learning-based, due to their computationally intensive iterative processes. To address these scalability issues, here we introduce DeepRelax, a deep generative model capable of performing geometric crystal structure relaxation rapidly and without iterations. DeepRelax learns the equilibrium structural distribution, enabling it to predict relaxed structures directly from their unrelaxed ones. The ability to perform structural relaxation at the millisecond level per structure, combined with the scalability of parallel processing, makes DeepRelax particularly useful for large-scale virtual screening. We demonstrate DeepRelax’s reliability and robustness by applying it to five diverse databases, including oxides, Materials Project, two-dimensional materials, van der Waals crystals, and crystals with point defects. DeepRelax consistently shows high accuracy and efficiency, validated by density functional theory calculations. Finally, we enhance its trustworthiness by integrating uncertainty quantification. This work significantly accelerates computational workflows, offering a robust and trustworthy machine-learning method for material discovery and advancing the application of AI for science.

Discovery of Novel Nonpeptidic Proteasome Inhibitors Using Covalent Virtual Screening and Biological Evaluation.

Many reported proteasome inhibitors, including the three clinically approved inhibitors, bortezomib, carfilzomib, and ixazomib, have peptidic structures. In this study, using a hybrid and versatile strategy for covalent virtual screening by combining warhead screening and preprocessing with GOLD and CovDock software that were applied to the ZINC virtual library, we identified multiple proteasome inhibitors with new nonpeptidic structural scaffolds. Proteasome inhibition assays confirmed the inhibitory activities of these new compounds. These results demonstrate the effectiveness of our computational strategy for large-scale covalent virtual screening. Furthermore, these identified proteasome inhibitors may serve as starting points for the development of a new class of nonpeptidic therapeutic agents.

Do Molecular Fingerprints Identify Diverse Active Drugs in Large-Scale Virtual Screening? (No).

Computational approaches for small-molecule drug discovery now regularly scale to the consideration of libraries containing billions of candidate small molecules. One promising approach to increased the speed of evaluating billion-molecule libraries is to develop succinct representations of each molecule that enable the rapid identification of molecules with similar properties. Molecular fingerprints are thought to provide a mechanism for producing such representations. Here, we explore the utility of commonly used fingerprints in the context of predicting similar molecular activity. We show that fingerprint similarity provides little discriminative power between active and inactive molecules for a target protein based on a known active-while they may sometimes provide some enrichment for active molecules in a drug screen, a screened data set will still be dominated by inactive molecules. We also demonstrate that high-similarity actives appear to share a scaffold with the query active, meaning that they could more easily be identified by structural enumeration. Furthermore, even when limited to only active molecules, fingerprint similarity values do not correlate with compound potency. In sum, these results highlight the need for a new wave of molecular representations that will improve the capacity to detect biologically active molecules based on their similarity to other such molecules.

Enhancing generalizability and performance in drug-target interaction identification by integrating pharmacophore and pre-trained models.

In drug discovery, it is crucial to assess the drug-target binding affinity (DTA). Although molecular docking is widely used, computational efficiency limits its application in large-scale virtual screening. Deep learning-based methods learn virtual scoring functions from labeled datasets and can quickly predict affinity. However, there are three limitations. First, existing methods only consider the atom-bond graph or one-dimensional sequence representations of compounds, ignoring the information about functional groups (pharmacophores) with specific biological activities. Second, relying on limited labeled datasets fails to learn comprehensive embedding representations of compounds and proteins, resulting in poor generalization performance in complex scenarios. Third, existing feature fusion methods cannot adequately capture contextual interaction information. Therefore, we propose a novel DTA prediction method named HeteroDTA. Specifically, a multi-view compound feature extraction module is constructed to model the atom-bond graph and pharmacophore graph. The residue concat graph and protein sequence are also utilized to model protein structure and function. Moreover, to enhance the generalization capability and reduce the dependence on task-specific labeled data, pre-trained models are utilized to initialize the atomic features of the compounds and the embedding representations of the protein sequence. A context-aware nonlinear feature fusion method is also proposed to learn interaction patterns between compounds and proteins. Experimental results on public benchmark datasets show that HeteroDTA significantly outperforms existing methods. In addition, HeteroDTA shows excellent generalization performance in cold-start experiments and superiority in the representation learning ability of drug-target pairs. Finally, the effectiveness of HeteroDTA is demonstrated in a real-world drug discovery study. The source code and data are available at https://github.com/daydayupzzl/HeteroDTA.

EnTdecker - A Machine Learning-Based Platform for Guiding Substrate Discovery in Energy Transfer Catalysis.

Due to the magnitude of chemical space, the discovery of novel substrates in energy transfer (EnT) catalysis remains a daunting task. Experimental and computational strategies to identify compounds that successfully undergo EnT-mediated reactions are limited by their time and cost efficiency. To accelerate the discovery process in EnT catalysis, we herein present the EnTdecker platform, which facilitates the large-scale virtual screening of potential substrates using machine-learning (ML) based predictions of their excited state properties. To achieve this, a data set is created containing more than 34,000 molecules aiming to cover a vast fraction of synthetically relevant compound space for EnT catalysis. Using this data predictive models are trained, and their aptitude for an in-lab application is demonstrated by rediscovering successful substrates from literature as well as experimental validation through luminescence-based screening. By reducing the computational effort needed to obtain excited state properties, the EnTdecker platform represents a tool to efficiently guide substrate selection and increase the experimental success rate for EnT catalysis. Moreover, through an easy-to-use web application, EnTdecker is made publicly accessible under entdecker.uni-muenster.de.

Abstract LB388: Super potent and efficacious ALK/ROS1/TRK inhibitor that overcomes multiple drug-resistant mutations

Abstract Abnormal activation of ALK, ROS1 and TRK is implicated in tumorigenesis, progression, invasion, and metastasis of malignancies through various mechanisms. The first generation TRK inhibitors including larotrectinib and entrectinib have limited applications due to acquired resistance in clinical settings. Multiple on-target mutations occur at the solvent-front, gatekeeper, and xDFG motif inside the ATP binding pocket of the TRK kinase domain. While some candidates under current clinical development aim to address the solvent-front mutation, they are ineffective against the xDFG mutations (e.g.NTRK1.G667X). There is strong unmet medical needs for next generation TRK inhibitors that can address resistance mutations. We employ the synergistic advantages of domain expertise and modern technology to accelerate early stage drug discovery. On our deep learning (DL) centric AI platform, extensive scientific computing supports large scale virtual screening, generative design, drug property prediction and multi-objective lead optimization. Only the optimized candidate compounds are passed along for synthesis and testing to save time and cost. In Ba/F3-TPM3 cellular assays, LB-2159 showed superior potencies that are hundreds to thousands of fold higher than larotrectinib and/or entrectinib, with IC50 values of 0.02 nM for NTRK1.WT, 0.3 nM for NTRK1.G595R and 0.88 nM for NTRK1.G667C. Similar cellular potencies were demonstrated for ALK and ROS1. In xenograft models LB-2159 at 10 mg/kg bid resulted in complete tumor regression in Ba/F3-TPM3-NTRK1-WT tumors, 96% TGI in Ba/F3-TPM3-NTRK1-G595R tumors, 84% TGI and 100% survival in mice bearing Ba/F3-TPM3-NTRK1-G667C tumors. The pharmacokinetic profiles of LB-2159 are overall favorable, demonstrating extended stability and half life. In vitro safety screens yielded clean profiles without any DDI signal or hERG liability. Preclinical safety evaluations exhibited good tolerance in rats. In multiple dose escalation studies LB-2159 was well tolerated at 50 mg/kg/day and beyond. Empowered by our proprietary AI platform, we have discovered the novel ALK/ROS1/TRK inhibitors that overcome clinically known resistance mutations. Our drug candidate exhibited good tolerance in animals in preclinical safety evaluations. In xenograft models that are resistant to current treatments the compound demonstrates strong tumor suppression efficacy. LB-2159 is advancing through IND enabling studies, and its preclinical profiles support the potential for best-in-class treatment for NTRK fusion-positive solid tumors. Citation Format: Li Xing, Jingbing Wang, Wei Zhu. Super potent and efficacious ALK/ROS1/TRK inhibitor that overcomes multiple drug-resistant mutations [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 2 (Late-Breaking, Clinical Trial, and Invited Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(7_Suppl):Abstract nr LB388.

Abstract LB389: Highly potent and selective RET inhibitor with robust anti-tumor activities against wild-type and acquired drug-resistant mutations

Abstract RET gene mutations and fusions are the driving events for the generation and deterioration of many cancer types. The first generation RET inhibitors, selpercatinib (Loxo-292) and pralsetinib (Blu-667), demonstrated clinically acquired resistance (e.g., solvent frontier mutations G810X, double mutations V804X-G810X etc.). Novel treatment that overcomes multiple resistance mutations is needed to improve patient outcomes. Leveraging our in-house AI technology platform, we have discovered the next generation RET inhibitors that overcome multiple resistance mutations including solvent front, gatekeeper and various double mutations. We employ the synergistic advantages of domain expertise and modern technology to accelerate early stage drug discovery. On our deep learning (DL) centric AI platform, extensive scientific computing supports large scale virtual screening, generative design, drug property prediction and multi-objective lead optimization. Only the optimized candidate compounds are passed along for synthesis and testing to save time and cost. In cell proliferation assays, our compound effectively inhibited KIF5B-RET Ba/F3 WT, V804M, G810S, G810R, V804M-G810S with IC50 values of 0.4 nM, 1.3 nM, 1.1 nM, 3.4 nM, 6.3 nM, respectively, demonstrating significant improvement over selpercatinib in the range of several hundred fold in activities. Importantly, the compound is highly selective against VEGFR2, an off-target responsible for cardiovascular adverse effects in the approved RET inhibitors. The superior cellular potencies translated consistently into animal models. In Ba/F3 KIF5B-RET-G810R xenograft model, treatment of 25 mg/kg bid resulted in >90% TGI with a100% survival rate. The compound showed favorable pharmacokinetic properties, lack of drug-drug interaction (DDI), and devoid of hERG liability (IC50 > 10uM). Preclinical safety evaluations in rats exhibited good tolerance margin. We have discovered the second generation compound that potently inhibits a diverse range of RET alterations. The compound exhibits preferable pharmaceutical profiles and is advancing toward IND application. Citation Format: Li Xing, Wei Zhu, Jingbing Wang. Highly potent and selective RET inhibitor with robust anti-tumor activities against wild-type and acquired drug-resistant mutations [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 2 (Late-Breaking, Clinical Trial, and Invited Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(7_Suppl):Abstract nr LB389.

Heterogeneous sampled subgraph neural networks with knowledge distillation to enhance double-blind compound-protein interaction prediction

Identifying binding compounds against a target protein is crucial for large-scale virtual screening in drug development. Recently, network-based methods have been developed for compound-protein interaction (CPI) prediction. However, they are difficult to be applied to unseen (i.e., never-seen-before) proteins and compounds. In this study, we propose SgCPI to incorporate local known interacting networks to predict CPI interactions. SgCPI randomly samples the local CPI network of the query compound-protein pair as a subgraph and applies a heterogeneous graph neural network (HGNN) to embed the active/inactive message of the subgraph. For unseen compounds and proteins, SgCPI-KD takes SgCPI as the teacher model to distillate its knowledge by estimating the potential neighbors. Experimental results indicate: (1) the sampled subgraphs of the CPI network introduce efficient knowledge for unseen molecular prediction with the HGNNs, and (2) the knowledge distillation strategy is beneficial to the double-blind interaction prediction by estimating molecular neighbors and distilling knowledge.

Kinome-Wide Virtual Screening by Multi-Task Deep Learning.

Deep learning is a machine learning technique to model high-level abstractions in data by utilizing a graph composed of multiple processing layers that experience various linear and non-linear transformations. This technique has been shown to perform well for applications in drug discovery, utilizing structural features of small molecules to predict activity. Here, we report a large-scale study to predict the activity of small molecules across the human kinome-a major family of drug targets, particularly in anti-cancer agents. While small-molecule kinase inhibitors exhibit impressive clinical efficacy in several different diseases, resistance often arises through adaptive kinome reprogramming or subpopulation diversity. Polypharmacology and combination therapies offer potential therapeutic strategies for patients with resistant diseases. Their development would benefit from a more comprehensive and dense knowledge of small-molecule inhibition across the human kinome. Leveraging over 650,000 bioactivity annotations for more than 300,000 small molecules, we evaluated multiple machine learning methods to predict the small-molecule inhibition of 342 kinases across the human kinome. Our results demonstrated that multi-task deep neural networks outperformed classical single-task methods, offering the potential for conducting large-scale virtual screening, predicting activity profiles, and bridging the gaps in the available data.

Identification of SARS-CoV-2 Main Protease Inhibitors Using Chemical Similarity Analysis Combined with Machine Learning.

SARS-CoV-2 Main Protease (Mpro) is an enzyme that cleaves viral polyproteins translated from the viral genome, which is critical for viral replication. Mpro is a target for anti-SARS-CoV-2 drug development. Herein, we performed a large-scale virtual screening by comparing multiple structural descriptors of reference molecules with reported anti-coronavirus activity against a library with >17 million compounds. Further filtering, performed by applying two machine learning algorithms, identified eighteen computational hits as anti-SARS-CoV-2 compounds with high structural diversity and drug-like properties. The activities of twelve compounds on Mpro's enzymatic activity were evaluated by fluorescence resonance energy transfer (FRET) assays. Compound 13 (ZINC13878776) significantly inhibited SARS-CoV-2 Mpro activity and was employed as a reference for an experimentally hit expansion. The structural analogues 13a (ZINC4248385), 13b (ZNC13523222), and 13c (ZINC4248365) were tested as Mpro inhibitors, reducing the enzymatic activity of recombinant Mpro with potency as follows: 13c > 13 > 13b > 13a. Then, their anti-SARS-CoV-2 activities were evaluated in plaque reduction assays using Vero CCL81 cells. Subtoxic concentrations of compounds 13a, 13c, and 13b displayed in vitro antiviral activity with IC50 in the mid micromolar range. Compounds 13a-c could become lead compounds for the development of new Mpro inhibitors with improved activity against anti-SARS-CoV-2.

Deep Learning-Based Chemical Similarity for Accelerated Organic Light-Emitting Diode Materials Discovery.

Thermally activated delayed fluorescence (TADF) material has attracted great attention as a promising metal-free organic light-emitting diode material with a high theoretical efficiency. To accelerate the discovery of novel TADF materials, computer-aided material design strategies have been developed. However, they have clear limitations due to the accessibility of only a few computationally tractable properties. Here, we propose TADF-likeness, a quantitative score to evaluate the TADF potential of molecules based on a data-driven concept of chemical similarity to existing TADF molecules. We used a deep autoencoder to characterize the common features of existing TADF molecules with common chemical descriptors. The score was highly correlated with the four essential electronic properties of TADF molecules and had a high success rate in large-scale virtual screening of millions of molecules to identify promising candidates at almost no cost, validating its feasibility for accelerating TADF discovery. The concept of TADF-likeness can be extended to other fields of materials discovery.

Sorting drug conformers in enzyme active sites: the XTB way.

In the present study, we have used the MEI196 set of interaction energies to investigate low-cost computational chemistry approaches for the calculation of binding between a molecule and its environment. Density functional theory (DFT) methods, when used with the vDZP basis set, yield good agreement with the reference energies. On the other hand, semi-empirical methods are less accurate as expected. By examining different groups of systems within MEI196 that contain species of a similar nature, we find that chemical similarity leads to cancellation of errors in the calculation of relative binding energies. Importantly, the semi-empirical method GFN1-xTB (XTB1) yields reasonable results for this purpose. We have thus further assessed the performance of XTB1 for calculating relative energies of docking poses of substrates in enzyme active sites represented by cluster models or within the ONIOM protocol. The results support the observations on error cancellation. This paves the way for the use of XTB1 in parts of large-scale virtual screening workflows to accelerate the drug discovery process.

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.

Computational and Experimental Drug Repurposing of FDA-Approved Compounds Targeting the Cannabinoid Receptor CB1.

The cannabinoid receptor 1 (CB1R) plays a pivotal role in regulating various physiopathological processes, thus positioning itself as a promising and sought-after therapeutic target. However, the search for specific and effective CB1R ligands has been challenging, prompting the exploration of drug repurposing (DR) strategies. In this study, we present an innovative DR approach that combines computational screening and experimental validation to identify potential Food and Drug Administration (FDA)-approved compounds that can interact with the CB1R. Initially, a large-scale virtual screening was conducted using molecular docking simulations, where a library of FDA-approved drugs was screened against the CB1R's three-dimensional structures. This in silico analysis allowed us to prioritize compounds based on their binding affinity through two different filters. Subsequently, the shortlisted compounds were subjected to in vitro assays using cellular and biochemical models to validate their interaction with the CB1R and determine their functional impact. Our results reveal FDA-approved compounds that exhibit promising interactions with the CB1R. These findings open up exciting opportunities for DR in various disorders where CB1R signaling is implicated. In conclusion, our integrated computational and experimental approach demonstrates the feasibility of DR for discovering CB1R modulators from existing FDA-approved compounds. By leveraging the wealth of existing pharmacological data, this strategy accelerates the identification of potential therapeutics while reducing development costs and timelines. The findings from this study hold the potential to advance novel treatments for a range of CB1R -associated diseases, presenting a significant step forward in drug discovery research.

Deep Learning with Geometry-Enhanced Molecular Representation for Augmentation of Large-Scale Docking-Based Virtual Screening.

Structure-based virtual screening has been a crucial tool in drug discovery for decades. However, as the chemical space expands, the existing structure-based virtual screening techniques based on molecular docking and scoring struggle to handle billion-entry ultralarge libraries due to the high computational cost. To address this challenge, people have resorted to machine learning techniques to enhance structure-based virtual screening for efficiently exploring the vast chemical space. In those cases, compounds are usually treated as sequential strings or two-dimensional topology graphs, limiting their ability to incorporate three-dimensional structural information for downstream tasks. We herein propose a novel deep learning protocol, GEM-Screen, which utilizes the geometry-enhanced molecular representation of the compounds docking to a specific target and is trained on docking scores of a small fraction of a library through an active learning strategy to approximate the docking outcome for yet nontraining entries. This protocol is applied to virtual screening campaigns against the AmpC and D4 targets, demonstrating that GEM-Screen enriches more than 90% of the hit scaffolds for AmpC in the top 4% of model predictions and more than 80% of the hit scaffolds for D4 in the same top-ranking size of library. GEM-Screen can be used in conjunction with traditional docking programs for docking of only the top-ranked compounds to avoid the exhaustive docking of the whole library, thus allowing for discovering top-scoring compounds from billion-entry libraries in a rapid yet accurate fashion.

Shape-Based Virtual Screening of a Billion-Compound Library Identifies Mycobacterial Lipoamide Dehydrogenase Inhibitors.

Lpd (lipoamide dehydrogenase) in Mycobacterium tuberculosis (Mtb) is required for virulence and is a genetically validated tuberculosis (TB) target. Numerous screens have been performed over the last decade, yet only two inhibitor series have been identified. Recent advances in large-scale virtual screening methods combined with make-on-demand compound libraries have shown the potential for finding novel hits. In this study, the Enamine REAL library consisting of ∼1.12 billion compounds was efficiently screened using the GPU Shape screen method against Mtb Lpd to find additional chemical matter that would expand on the known sulfonamide inhibitor series. We identified six new inhibitors with IC50 in the range of 5-100 μM. While these compounds remained chemically close to the already known sulfonamide series inhibitors, some diversity was found in the cores of the hits. The two most potent hits were further validated by one-step potency optimization to submicromolar levels. The co-crystal structure of optimized analogue TDI-13537 provided new insights into the potency determinants of the series.

WarpDOCK: Large-Scale Virtual Drug Discovery Using Cloud Infrastructure.

warpDOCK is an open-source pipeline for virtual small-molecule drug discovery using cloud infrastructure. warpDOCK is designed from the ground up for the Oracle Cloud Infrastructure (OCI), enabling harmonious parallelism of docking calculations over thousands to hundreds of thousands of cores. This enables cost-effective sampling of ultra-large chemical libraries, potentially reducing the time to identify lead drug candidates by orders of magnitude. By utilizing established docking software and automating each step of the process, warpDOCK makes large-scale virtual screening accessible to a broad user group. The warpDOCK code can be found at the BruningLab GitHub repository (https://github.com/BruningLab/warpDOCK).