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.

Allosteric Modulation of the YAP/TAZ-TEAD Interaction by Palmitoylation and Small-Molecule Inhibitors.

The Hippo signaling pathway is a highly conserved signaling network that plays a central role in regulating cellular growth, proliferation, and organ size. This pathway consists of a kinase cascade that integrates various upstream signals to control the activation or inactivation of YAP/TAZ proteins. Phosphorylated YAP/TAZ is sequestered in the cytoplasm; however, when the Hippo pathway is deactivated, it translocates into the nucleus, where it associates with TEAD transcription factors. This partnership is instrumental in regulating the transcription of progrowth and antiapoptotic genes. Thus, in many cancers, aberrantly hyperactivated YAP/TAZ promotes oncogenesis by contributing to cancer cell proliferation, metastasis, and therapy resistance. Because YAP and TAZ exert their oncogenic effects by binding with TEAD, it is critical to understand this key interaction to develop cancer therapeutics. Previous research has indicated that TEAD undergoes autopalmitoylation at a conserved cysteine, and small molecules that inhibit TEAD palmitoylation disrupt effective YAP/TAZ binding. However, how exactly palmitoylation contributes to YAP/TAZ-TEAD interactions and how the TEAD palmitoylation inhibitors disrupt this interaction remains unknown. Utilizing molecular dynamics simulations, our investigation not only provides detailed atomistic insight into the YAP/TAZ-TEAD dynamics but also unveils that the inhibitor studied influences the binding of YAP and TAZ to TEAD in distinct manners. This discovery has significant implications for the design and deployment of future molecular interventions targeting this interaction.

Mitochondria-Selective Dicationic Small-Molecule Ligand Targeting G-Quadruplex Structures for Human Colorectal Cancer Therapy.

Mitochondria are important drug targets for anticancer and other disease therapies. Certain human mitochondrial DNA sequences capable of forming G-quadruplex structures (G4s) are emerging drug targets of small molecules. Despite some mitochondria-selective ligands being reported for drug delivery against cancers, the ligand design is mostly limited to the triphenylphosphonium scaffold. The ligand designed with lipophilic small-sized scaffolds bearing multipositive charges targeting the unique feature of high mitochondrial membrane potential (MMP) is lacking and most mitochondria-selective ligands are not G4-targeting. Herein, we report a new small-sized dicationic lipophilic ligand to target MMP and mitochondrial DNA G4s to enhance drug delivery for anticancer. The ligand showed marked alteration of mitochondrial gene expression and substantial induction of ROS production, mitochondrial dysfunction, DNA damage, cellular senescence, and apoptosis. The ligand also exhibited high anticancer activity against HCT116 cancer cells (IC50, 3.4 µM) and high antitumor efficacy in the HCT116 tumor xenograft mouse model (∼70% tumor weight reduction).

Discovery of Small Molecule Interleukin 17A Inhibitors with Novel Binding Mode and Stoichiometry: Optimization of DNA-Encoded Chemical Library Hits to In Vivo Active Compounds.

Dysregulation of IL17A drives numerous inflammatory and autoimmune disorders with inhibition of IL17A using antibodies proven as an effective treatment. Oral anti-IL17 therapies are an attractive alternative option, and several preclinical small molecule IL17 inhibitors have previously been described. Herein, we report the discovery of a novel class of small molecule IL17A inhibitors, identified via a DNA-encoded chemical library screen, and their subsequent optimization to provide in vivo efficacious inhibitors. These new protein-protein interaction (PPI) inhibitors bind in a previously undescribed mode in the IL17A protein with two copies binding symmetrically to the central cavities of the IL17A homodimer.

Visualized Tracking and Multidimensional Assessing of Mitochondria-Associated Pyroptosis in Cancer Cells by a Small-Molecule Fluorescent Probe.

Pyroptosis is closely related to the development and treatment of various cancers; thus, comprehensive studies of the correlations between pyroptosis and its inductive or inhibitive factors can provide new ideas for the intervention and diagnosis of tumors. The dysfunction of mitochondria may induce pyroptosis in cancer cells, which can be reflected by the fluctuations of the microenvironmental parameters in mitochondria as well as the changes of mitochondrial DNA level and morphology, etc. To precisely track and assess the mitochondria-associated pyroptosis process, simultaneous visualization of changes in multiphysiological parameters in mitochondria is highly desirable. In this work, we reported a nonreaction-based, multifunctional small-molecule fluorescent probe Mito-DK with the capability of crosstalk-free response to polarity and mtDNA as well as mitochondrial morphology. Accurate assessment of mitochondria-associated pyroptosis induced by palmitic acid/H2O2 was achieved through monitoring changes in mitochondrial multiple parameters with the help of Mito-DK. In particular, the pyroptosis-inducing ability of an antibiotic doxorubicin and the pyroptosis-inhibiting capacity of an anticancer agent puerarin were evaluated by Mito-DK. These results provide new perspectives for visualizing mitochondria-associated pyroptosis and offer new approaches for screening pyroptosis-related anticancer agents.

MolProphet: A One-Stop, General Purpose, and AI-Based Platform for the Early Stages of Drug Discovery.

Artificial intelligence (AI) is an effective tool to accelerate drug discovery and cut costs in discovery processes. Many successful AI applications are reported in the early stages of small molecule drug discovery. However, most of those applications require a deep understanding of software and hardware, and focus on a single field that implies data normalization and transfer between those applications is still a challenge for normal users. It usually limits the application of AI in drug discovery. Here, based on a series of robust models, we formed a one-stop, general purpose, and AI-based drug discovery platform, MolProphet, to provide complete functionalities in the early stages of small molecule drug discovery, including AI-based target pocket prediction, hit discovery and lead optimization, and compound targeting, as well as abundant analyzing tools to check the results. MolProphet is an accessible and user-friendly web-based platform that is fully designed according to the practices in the drug discovery industry. The molecule screened, generated, or optimized by the MolProphet is purchasable and synthesizable at low cost but with good drug-likeness. More than 400 users from industry and academia have used MolProphet in their work. We hope this platform can provide a powerful solution to assist each normal researcher in drug design and related research areas. It is available for everyone at https://www.molprophet.com/.

AI is a viable alternative to high throughput screening: a 318-target study.

High throughput screening (HTS) is routinely used to identify bioactive small molecules. This requires physical compounds, which limits coverage of accessible chemical space. Computational approaches combined with vast on-demand chemical libraries can access far greater chemical space, provided that the predictive accuracy is sufficient to identify useful molecules. Through the largest and most diverse virtual HTS campaign reported to date, comprising 318 individual projects, we demonstrate that our AtomNet® convolutional neural network successfully finds novel hits across every major therapeutic area and protein class. We address historical limitations of computational screening by demonstrating success for target proteins without known binders, high-quality X-ray crystal structures, or manual cherry-picking of compounds. We show that the molecules selected by the AtomNet® model are novel drug-like scaffolds rather than minor modifications to known bioactive compounds. Our empirical results suggest that computational methods can substantially replace HTS as the first step of small-molecule drug discovery.

Cell Painting-based bioactivity prediction boosts high-throughput screening hit-rates and compound diversity.

Identifying active compounds for a target is a time- and resource-intensive task in early drug discovery. Accurate bioactivity prediction using morphological profiles could streamline the process, enabling smaller, more focused compound screens. We investigate the potential of deep learning on unrefined single-concentration activity readouts and Cell Painting data, to predict compound activity across 140 diverse assays. We observe an average ROC-AUC of 0.744 ± 0.108 with 62% of assays achieving ≥0.7, 30% ≥0.8, and 7% ≥0.9. In many cases, the high prediction performance can be achieved using only brightfield images instead of multichannel fluorescence images. A comprehensive analysis shows that Cell Painting-based bioactivity prediction is robust across assay types, technologies, and target classes, with cell-based assays and kinase targets being particularly well-suited for prediction. Experimental validation confirms the enrichment of active compounds. Our findings indicate that models trained on Cell Painting data, combined with a small set of single-concentration data points, can reliably predict the activity of a compound library across diverse targets and assays while maintaining high hit rates and scaffold diversity. This approach has the potential to reduce the size of screening campaigns, saving time and resources, and enabling primary screening with more complex assays.

Predicting Elimination of Small-Molecule Drug Half-Life in Pharmacokinetics Using Ensemble and Consensus Machine Learning Methods.

Half-life is a significant pharmacokinetic parameter included in the excretion phase of absorption, distribution, metabolism, and excretion. It is one of the key factors for the successful marketing of drug candidates. Therefore, predicting half-life is of great significance in drug design. In this study, we employed eXtreme Gradient Boosting (XGboost), randomForest (RF), gradient boosting machine (GBM), and supporting vector machine (SVM) to build quantitative structure-activity relationship (QSAR) models on 3512 compounds and evaluated model performance by using root-mean-square error (RMSE), R2, and mean absolute error (MAE) metrics and interpreted features by SHapley Additive exPlanation (SHAP). Furthermore, we developed consensus models through integrating four individual models and validated their performance using a Y-randomization test and applicability domain analysis. Finally, matched molecular pair analysis was used to extract the transformation rules. Our results revealed that XGboost outperformed other individual models (RMSE = 0.176, R2 = 0.845, MAE = 0.141). The consensus model integrating all four models continued to enhance prediction performance (RMSE = 0.172, R2 = 0.856, MAE = 0.138). We evaluated the reliability, robustness, and generalization ability via Y-randomization test and applicability domain analysis. Meanwhile, we utilized SHAP to interpret features and employed matched molecular pair analysis to extract chemical transformation rules that provide suggestions for optimizing drug structure. In conclusion, we believe that the consensus model developed in this study serve as a reliable tool to evaluate half-life in drug discovery, and the chemical transformation rules concluded in this study could provide valuable suggestions in drug discovery.

DeepP450: Predicting Human P450 Activities of Small Molecules by Integrating Pretrained Protein Language Model and Molecular Representation.

Cytochrome P450 enzymes (CYPs) play a crucial role in Phase I drug metabolism in the human body, and CYP activity toward compounds can significantly affect druggability, making early prediction of CYP activity and substrate identification essential for therapeutic development. Here, we established a deep learning model for assessing potential CYP substrates, DeepP450, by fine-tuning protein and molecule pretrained models through feature integration with cross-attention and self-attention layers. This model exhibited high prediction accuracy (0.92) on the test set, with area under the receiver operating characteristic curve (AUROC) values ranging from 0.89 to 0.98 in substrate/nonsubstrate predictions across the nine major human CYPs, surpassing current benchmarks for CYP activity prediction. Notably, DeepP450 uses only one model to predict substrates/nonsubstrates for any of the nine CYPs and exhibits certain generalizability on novel compounds and different categories of human CYPs, which could greatly facilitate early stage drug design by avoiding CYP-reactive compounds.

SpaceGrow: efficient shape-based virtual screening of billion-sized combinatorial fragment spaces.

The growing size of make-on-demand chemical libraries is posing new challenges to cheminformatics. These ultra-large chemical libraries became too large for exhaustive enumeration. Using a combinatorial approach instead, the resource requirement scales approximately with the number of synthons instead of the number of molecules. This gives access to billions or trillions of compounds as so-called chemical spaces with moderate hardware and in a reasonable time frame. While extremely performant ligand-based 2D methods exist in this context, 3D methods still largely rely on exhaustive enumeration and therefore fail to apply. Here, we present SpaceGrow: a novel shape-based 3D approach for ligand-based virtual screening of billions of compounds within hours on a single CPU. Compared to a conventional superposition tool, SpaceGrow shows comparable pose reproduction capacity based on RMSD and superior ranking performance while being orders of magnitude faster. Result assessment of two differently sized subsets of the eXplore space reveals a higher probability of finding superior results in larger spaces highlighting the potential of searching in ultra-large spaces. Furthermore, the application of SpaceGrow in a drug discovery workflow was investigated in four examples involving G protein-coupled receptors (GPCRs) with the aim to identify compounds with similar binding capabilities and molecular novelty.

Target-specific novel molecules with their recipe: Incorporating synthesizability in the design process.

Application of Artificial intelligence (AI) in drug discovery has led to several success stories in recent times. While traditional methods mostly relied upon screening large chemical libraries for early-stage drug-design, de novo design can help identify novel target-specific molecules by sampling from a much larger chemical space. Although this has increased the possibility of finding diverse and novel molecules from previously unexplored chemical space, this has also posed a great challenge for medicinal chemists to synthesize at least some of the de novo designed novel molecules for experimental validation. To address this challenge, in this work, we propose a novel forward synthesis-based generative AI method, which is used to explore the synthesizable chemical space. The method uses a structure-based drug design framework, where the target protein structure and a target-specific seed fragment from co-crystal structures can be the initial inputs. A random fragment from a purchasable fragment library can also be the input if a target-specific fragment is unavailable. Then a template-based forward synthesis route prediction and molecule generation is performed in parallel using the Monte Carlo Tree Search (MCTS) method where, the subsequent fragments for molecule growth can again be obtained from a purchasable fragment library. The rewards for each iteration of MCTS are computed using a drug-target affinity (DTA) model based on the docking pose of the generated reaction intermediates at the binding site of the target protein of interest. With the help of the proposed method, it is now possible to overcome one of the major obstacles posed to the AI-based drug design approaches through the ability of the method to design novel target-specific synthesizable molecules.

DNA-Encoded Library Technology─A Catalyst for Covalent Ligand Discovery.

The identification of novel covalent ligands for therapeutic purposes has long depended on serendipity, with dedicated hit finding techniques emerging only in the early 2000s. Advances in chemoproteomics have enabled robust characterization of putative drugs to derisk the unique liabilities associated with covalent hit molecules, leading to a renewed interest in this targeting modality. DNA-encoded library (DEL) technology has similarly emerged over the past two decades as a highly efficient method to identify new chemical equity toward protein targets of interest. A number of commercial and academic groups have reported methods in covalent DEL synthesis and hit identification; however, it is evident that there is still much to be done to fully realize the power of this technology for covalent ligand discovery. This perspective will explore the current approaches in covalent DEL technology and reflect on the next steps to advance this field.

Large-Scale Pretraining Improves Sample Efficiency of Active Learning-Based Virtual Screening.

Virtual screening of large compound libraries to identify potential hit candidates is one of the earliest steps in drug discovery. As the size of commercially available compound collections grows exponentially to the scale of billions, active learning and Bayesian optimization have recently been proven as effective methods of narrowing down the search space. An essential component of those methods is a surrogate machine learning model that predicts the desired properties of compounds. An accurate model can achieve high sample efficiency by finding hits with only a fraction of the entire library being virtually screened. In this study, we examined the performance of a pretrained transformer-based language model and graph neural network in a Bayesian optimization active learning framework. The best pretrained model identifies 58.97% of the top-50,000 compounds after screening only 0.6% of an ultralarge library containing 99.5 million compounds, improving 8% over the previous state-of-the-art baseline. Through extensive benchmarks, we show that the superior performance of pretrained models persists in both structure-based and ligand-based drug discovery. Pretrained models can serve as a boost to the accuracy and sample efficiency of active learning-based virtual screening.

High-Throughput Methods for the Discovery of Small Molecule Modulators of Pancreatic Beta-Cell Function and Regeneration.

The progression of type II diabetes (T2D) is characterized by a complex and highly variable loss of beta-cell mass, resulting in impaired insulin secretion. Many T2D drug discovery efforts aimed at discovering molecules that can protect or restore beta-cell mass and function have been developed using limited beta-cell lines and primary rodent/human pancreatic islets. Various high-throughput screening methods have been used in the context of drug discovery, including luciferase-based reporter assays, glucose-stimulated insulin secretion, and high-content screening. In this context, a cornerstone of small molecule discovery has been the use of immortalized rodent beta-cell lines. Although insightful, this usage has led to a more comprehensive understanding of rodent beta-cell proliferation pathways rather than their human counterparts. Advantages gained in enhanced physiological relevance are offered by three-dimensional (3D) primary islets and pseudoislets in contrast to monolayer cultures, but these approaches have been limited to use in low-throughput experiments. Emerging methods, such as high-throughput 3D islet imaging coupled with machine learning, aim to increase the feasibility of integrating 3D microtissue structures into high-throughput screening. This review explores the current methods used in high-throughput screening for small molecule modulators of beta-cell mass and function, a potentially pivotal strategy for diabetes drug discovery.

Computational analysis of PD-L1 dimerization mechanism induced by small molecules and potential dynamical properties.

The design of small molecule inhibitors that target the programmed death ligand-1 (PD-L1) is a forefront issue in immune checkpoint blocking therapy. Small-molecule inhibitors have been shown to exert therapeutic effects by inducing dimerization of the PD-L1 protein, however, the specific mechanisms underlying this dimerization process remain largely unexplored. Furthermore, there is a notable lack of comparative studies examining the binding modes of structurally diverse inhibitors. In view of the research gaps, this work employed molecular dynamics simulations to meticulously examine the interactions between two distinct types of inhibitors and PD-L1 in both monomeric and dimeric forms, and predicted the dimerization mechanism. The results revealed that inhibitors initially bind to a PD-L1 monomer, subsequently attracting another monomer to form a dimer. Notably, symmetric inhibitors observed superior binding efficiency compared to other inhibitors. Key residues, including Ile54, Tyr56, Met115 and Tyr123 played a leading role in binding. Structurally, symmetric inhibitors were capable of thoroughly engaging the binding pocket, promoting a more symmetrical formation of PD-L1 dimers. Furthermore, symmetric inhibitors formed more extensive hydrophobic interactions with protein residues. The insights garnered from this research are expected to significantly contribute to the rational design and optimization of small molecule inhibitors targeting PD-L1.

A Novel NMR-Based Protocol to Screen Ultralow Molecular Weight Fragments.

Fragment-based lead discovery has emerged as one of the most efficient screening strategies for finding hit molecules in drug discovery. Recently, a novel strategy based on a class of fragments characterized by an ultralow molecular weight (ULMW) has been proposed. These fragments bind to the target with a very low affinity, requiring reliable biophysical methods for detection. The most notable application of ULMW used a set of 81 fragments, named MiniFrags, and screened them by X-ray crystallography. We extended the utilization of this novel class of fragments to another gold standard technique for fragment-based screening: nuclear magnetic resonance (NMR). Here, we present a novel NMR protocol to detect and analyze such weak interactions in a challenging real-world scenario: a flexible target with a flat, water-exposed binding site. We identified a subset of 69 highly water-soluble MiniFrags that were screened against the antiapoptotic protein human Bfl-1.

Shape-Aware Synthon Search (SASS) for Virtual Screening of Synthon-Based Chemical Spaces.

Virtual screening of large-scale chemical libraries has become increasingly useful for identifying high-quality candidates for drug discovery. While it is possible to exhaustively screen chemical spaces that number on the order of billions, indirect combinatorial approaches are needed to efficiently navigate larger, synthon-based virtual spaces. We describe Shape-Aware Synthon Search (SASS), a synthon-based virtual screening method that carries out shape similarity searches in the synthon space instead of the enumerated product space. SASS can replicate results from exhaustive searches in ultralarge, combinatorial spaces with high recall on a variety of query molecules while only scoring a small subspace of possible enumerated products, thereby significantly accelerating large-scale, shape-based virtual screening.

Compositional Deep Probabilistic Models of DNA-Encoded Libraries.

DNA-encoded library (DEL) has proven to be a powerful tool that utilizes combinatorially constructed small molecules to facilitate highly efficient screening experiments. These selection experiments, involving multiple stages of washing, elution, and identification of potent binders via unique DNA barcodes, often generate complex data. This complexity can potentially mask the underlying signals, necessitating the application of computational tools, such as machine learning, to uncover valuable insights. We introduce a compositional deep probabilistic model of DEL data, DEL-Compose, which decomposes molecular representations into their monosynthon, disynthon, and trisynthon building blocks and capitalizes on the inherent hierarchical structure of these molecules by modeling latent reactions between embedded synthons. Additionally, we investigate methods to improve the observation models for DEL count data, such as integrating covariate factors to more effectively account for data noise. Across two popular public benchmark data sets (CA-IX and HRP), our model demonstrates strong performance compared to count baselines, enriches the correct pharmacophores, and offers valuable insights via its intrinsic interpretable structure, thereby providing a robust tool for the analysis of DEL data.

Recent applications of artificial intelligence in RNA-targeted small molecule drug discovery.

INTRODUCTION: Targeting RNAs with small molecules offers an alternative to the conventional protein-targeted drug discovery and can potentially address unmet and emerging medical needs. The recent rise of interest in the strategy has already resulted in large amounts of data on disease associated RNAs, as well as on small molecules that bind to such RNAs. Artificial intelligence (AI) approaches, including machine learning and deep learning, present an opportunity to speed up the discovery of RNA-targeted small molecules by improving decision-making efficiency and quality. AREAS COVERED: The topics described in this review include the recent applications of AI in the identification of RNA targets, RNA structure determination, screening of chemical compound libraries, and hit-to-lead optimization. The impact and limitations of the recent AI applications are discussed, along with an outlook on the possible applications of next-generation AI tools for the discovery of novel RNA-targeted small molecule drugs. EXPERT OPINION: Key areas for improvement include developing AI tools for understanding RNA dynamics and RNA - small molecule interactions. High-quality and comprehensive data still need to be generated especially on the biological activity of small molecules that target RNAs.