Two regulatory T cell populations in the visceral adipose tissue shape systemic metabolism.

Visceral adipose tissue (VAT) is an energy store and endocrine organ critical for metabolic homeostasis. Regulatory T (Treg) cells restrain inflammation to preserve VAT homeostasis and glucose tolerance. Here, we show that the VAT harbors two distinct Treg cell populations: prototypical serum stimulation 2-positive (ST2+) Treg cells that are enriched in males and a previously uncharacterized population of C-X-C motif chemokine receptor 3-positive (CXCR3+) Treg cells that are enriched in females. We show that the transcription factors GATA-binding protein 3 and peroxisome proliferator-activated receptor-γ, together with the cytokine interleukin-33, promote the differentiation of ST2+ VAT Treg cells but repress CXCR3+ Treg cells. Conversely, the differentiation of CXCR3+ Treg cells is mediated by the cytokine interferon-γ and the transcription factor T-bet, which also antagonize ST2+ Treg cells. Finally, we demonstrate that ST2+ Treg cells preserve glucose homeostasis, whereas CXCR3+ Treg cells restrain inflammation in lean VAT and prevent glucose intolerance under high-fat diet conditions. Overall, this study defines two molecularly and developmentally distinct VAT Treg cell types with unique context- and sex-specific functions.

Cryo-EM Structure of the Human Ribonuclease P Holoenzyme.

Ribonuclease (RNase) P is a ubiquitous ribozyme that cleaves the 5' leader from precursor tRNAs. Here, we report cryo-electron microscopy structures of the human nuclear RNase P alone and in complex with tRNAVal. Human RNase P is a large ribonucleoprotein complex that contains 10 protein components and one catalytic RNA. The protein components form an interlocked clamp that stabilizes the RNA in a conformation optimal for substrate binding. Human RNase P recognizes the tRNA using a double-anchor mechanism through both protein-RNA and RNA-RNA interactions. Structural comparison of the apo and tRNA-bound human RNase P reveals that binding of tRNA induces a local conformational change in the catalytic center, transforming the ribozyme into an active state. Our results also provide an evolutionary model depicting how auxiliary RNA elements in bacterial RNase P, essential for substrate binding, and catalysis, were replaced by the much more complex and multifunctional protein components in higher organisms.

Structural Insights into Yeast Telomerase Recruitment to Telomeres.

Telomerase maintains chromosome ends from humans to yeasts. Recruitment of yeast telomerase to telomeres occurs through its Ku and Est1 subunits via independent interactions with telomerase RNA (TLC1) and telomeric proteins Sir4 and Cdc13, respectively. However, the structures of the molecules comprising these telomerase-recruiting pathways remain unknown. Here, we report crystal structures of the Ku heterodimer and Est1 complexed with their key binding partners. Two major findings are as follows: (1) Ku specifically binds to telomerase RNA in a distinct, yet related, manner to how it binds DNA; and (2) Est1 employs two separate pockets to bind distinct motifs of Cdc13. The N-terminal Cdc13-binding site of Est1 cooperates with the TLC1-Ku-Sir4 pathway for telomerase recruitment, whereas the C-terminal interface is dispensable for binding Est1 in vitro yet is nevertheless essential for telomere maintenance in vivo. Overall, our results integrate previous models and provide fundamentally valuable structural information regarding telomere biology.

Mechanistic insight into allosteric activation of human pyruvate carboxylase by acetyl-CoA.

Pyruvate carboxylase (PC) catalyzes the two-step carboxylation of pyruvate to produce oxaloacetate, playing a key role in the maintenance of metabolic homeostasis in cells. Given its involvement in multiple diseases, PC has been regarded as a potential therapeutic target for obesity, diabetes, and cancer. Albeit acetyl-CoA has been recognized as the allosteric regulator of PC for over 60 years, the underlying mechanism of how acetyl-CoA induces PC activation remains enigmatic. Herein, by using time-resolved cryo-electron microscopy, we have captured the snapshots of PC transitional states during its catalytic cycle. These structures and the biochemical studies reveal that acetyl-CoA stabilizes PC in a catalytically competent conformation, which triggers a cascade of events, including ATP hydrolysis and the long-distance communication between the two reactive centers. These findings provide an integrated picture for PC catalysis and unveil the unique allosteric mechanism of acetyl-CoA in an essential biochemical reaction in all kingdoms of life.

Cell-cell communication and initial population composition shape the structure of potato spindle tuber viroid quasispecies.

RNA viruses and viroids replicate with high mutation rates, forming quasispecies, population of variants centered around dominant sequences. The mechanisms governing quasispecies remain unclear. Plasmodesmata regulate viroid movement and were hypothesized to impact viroid quasispecies. Here, we sequenced the progeny of potato spindle tuber viroid intermediate (PSTVd-I) strain from mature guard cells lacking plasmodesmal connections and from in vitro-cultivated mesophyll cell protoplasts from systemic leaves of early-infected tomato (Solanum lycopersicum) plants. Remarkably, more variants accumulated in guard cells compared to whole leaves. Similarly, after extended cell culture, we observed more variants in cultivated mesophyll protoplasts. Coinfection and single-cell sequencing experiments demonstrated that the same plant cell can be infected multiple times by the same or different PSTVd sequences. To study the impact of initial population composition on PSTVd-I quasispecies, we conducted coinfections with PSTVd-I and variants. Two inoculum ratios (10:1 or 1:10) established quasispecies with or without PSTVd-I as the master sequence. In the absence of the master sequence, the percentage of novel variants initially increased. Moreover, a 1:1 PSTVd-I/variant RNA ratio resulted in PSTVd-I dominating (>50%), while the variants reached 20%. After PSTVd-I-only infection, the variants reached around 10%, while after variant-only infection, the variants were significantly more than 10%. These results emphasize the role of cell-to-cell communication and initial population composition in shaping PSTVd quasispecies.

Molecular Basis for Control of Diverse Genome Stability Factors by the Multi-BRCT Scaffold Rtt107.

BRCT domains support myriad protein-protein interactions involved in genome maintenance. Although di-BRCT recognition of phospho-proteins is well known to support the genotoxic response, whether multi-BRCT domains can acquire distinct structures and functions is unclear. Here we present the tetra-BRCT structures from the conserved yeast protein Rtt107 in free and ligand-bound forms. The four BRCT repeats fold into a tetrahedral structure that recognizes unmodified ligands using a bi-partite mechanism, suggesting repeat origami enabling function acquisition. Functional studies show that Rtt107 binding of partner proteins of diverse activities promotes genome replication and stability in both distinct and concerted manners. A unified theme is that tetra- and di-BRCT domains of Rtt107 collaborate to recruit partner proteins to chromatin. Our work thus illustrates how a master regulator uses two types of BRCT domains to recognize distinct genome factors and direct them to chromatin for constitutive genome protection.

The origin of methyl group in methanogen-mediated mercury methylation: From the Wolfe cycle.

Methylmercury (MeHg) is a bioaccumulating neurotoxin mainly produced by anaerobic microorganisms, with methanogen being one of the important methylators. A critical aspect for understanding the mechanism for microbial mercury (Hg) methylation is the origin of the methyl group. However, the origin of methyl group in methanogen-mediated Hg methylation remains unclear. This study aims to identify the source of methyl group for MeHg synthesis in methanogens. Our study revealed that Hg methylation in Methanospirillum hungatei JF-1 is closely related to methanogenesis process, according to the results of proteomic study and substrate limitation study. Next, we proved that nearly all methyl group in MeHg derives from the Wolfe cycle in this species, rather than the previously demonstrated acetyl-coenzyme A pathway, based on the results of 13C labeling study. We then proposed the Wolfe cycle-dependent Hg methylation mechanism in this species. Further genome analyses and 13C labeling experiments indicated that the involvement of the Wolfe cycle in Hg methylation is probably a universal feature among Hg-methylating methanogens. These findings reveal a unique Hg methylation mechanism in methanogens. Our study broadens the carbon substrates and controlling factors for MeHg synthesis in the environment, which can inform the prediction of MeHg production potential and remediation strategies for MeHg contamination.

NAD activates olfactory receptor 1386 to regulate type I interferon responses in Plasmodium yoelii YM infection.

Olfactory receptors (Olfr) are G protein-coupled receptors that are normally expressed on olfactory sensory neurons to detect volatile chemicals or odorants. Interestingly, many Olfrs are also expressed in diverse tissues and function in cell-cell recognition, migration, and proliferation as well as immune responses and disease processes. Here, we showed that many Olfr genes were expressed in the mouse spleen, linked to Plasmodium yoelii genetic loci significantly, and/or had genome-wide patterns of LOD scores (GPLSs) similar to those of host Toll-like receptor genes. Expression of specific Olfr genes such as Olfr1386 in HEK293T cells significantly increased luciferase signals driven by IFN-ß and NF-κB promoters, with elevated levels of phosphorylated TBK1, IRF3, P38, and JNK. Mice without Olfr1386 were generated using the CRISPR/Cas9 method, and the Olfr1386-/- mice showed significantly lower IFN-α/ß levels and longer survival than wild-type (WT) littermates after infection with P. yoelii YM parasites. Inhibition of G protein signaling and P38 activity could affect cyclic AMP-responsive element promoter-driven luciferase signals and IFN-ß mRNA levels in HEK293T cells expressing the Olfr1386 gene, respectively. Screening of malaria parasite metabolites identified nicotinamide adenine dinucleotide (NAD) as a potential ligand for Olfr1386, and NAD could stimulate IFN-ß responses and phosphorylation of TBK1 and STAT1/2 in RAW264.7 cells. Additionally, parasite RNA (pRNA) could significantly increase Olfr1386 mRNA levels. This study links multiple Olfrs to host immune response pathways, identifies a candidate ligand for Olfr1386, and demonstrates the important roles of Olfr1386 in regulating type I interferon (IFN-I) responses during malaria parasite infections.

The Art of Finding the Right Drug Target: Emerging Methods and Strategies.

Drug targets are specific molecules in biological tissues and body fluids that interact with drugs. Drug target discovery is a key component of drug discovery and is essential for the development of new drugs in areas such as cancer therapy and precision medicine. Traditional in vitro or in vivo target discovery methods are time-consuming and labor-intensive, limiting the pace of drug discovery. With the development of modern discovery methods, the discovery and application of various emerging technologies have greatly improved the efficiency of drug discovery, shortened the cycle time, and reduced the cost. This review provides a comprehensive overview of various emerging drug target discovery strategies, including computer-assisted approaches, drug affinity response target stability, multiomics analysis, gene editing, and nonsense-mediated mRNA degradation, and discusses the effectiveness and limitations of the various approaches, as well as their application in real cases. Through the review of the aforementioned contents, a general overview of the development of novel drug targets and disease treatment strategies will be provided, and a theoretical basis will be provided for those who are engaged in pharmaceutical science research. SIGNIFICANCE STATEMENT: Target-based drug discovery has been the main approach to drug discovery in the pharmaceutical industry for the past three decades. Traditional drug target discovery methods based on in vivo or in vitro validation are time-consuming and costly, greatly limiting the development of new drugs. Therefore, the development and selection of new methods in the drug target discovery process is crucial.

SynergyX: a multi-modality mutual attention network for interpretable drug synergy prediction.

Discovering effective anti-tumor drug combinations is crucial for advancing cancer therapy. Taking full account of intricate biological interactions is highly important in accurately predicting drug synergy. However, the extremely limited prior knowledge poses great challenges in developing current computational methods. To address this, we introduce SynergyX, a multi-modality mutual attention network to improve anti-tumor drug synergy prediction. It dynamically captures cross-modal interactions, allowing for the modeling of complex biological networks and drug interactions. A convolution-augmented attention structure is adopted to integrate multi-omic data in this framework effectively. Compared with other state-of-the-art models, SynergyX demonstrates superior predictive accuracy in both the General Test and Blind Test and cross-dataset validation. By exhaustively screening combinations of approved drugs, SynergyX reveals its ability to identify promising drug combination candidates for potential lung cancer treatment. Another notable advantage lies in its multidimensional interpretability. Taking Sorafenib and Vorinostat as an example, SynergyX serves as a powerful tool for uncovering drug-gene interactions and deciphering cell selectivity mechanisms. In summary, SynergyX provides an illuminating and interpretable framework, poised to catalyze the expedition of drug synergy discovery and deepen our comprehension of rational combination therapy.

RNA three-dimensional structure drives the sequence organization of potato spindle tuber viroid quasispecies.

RNA viruses and viroids exist and evolve as quasispecies due to error-prone replication. Quasispecies consist of a few dominant master sequences alongside numerous variants that contribute to genetic diversity. Upon environmental changes, certain variants within quasispecies have the potential to become the dominant sequences, leading to the emergence of novel infectious strains. However, the emergence of new infectious variants remains unpredictable. Using mutant pools prepared by saturation mutagenesis of selected stem and loop regions, our study of potato spindle tuber viroid (PSTVd) demonstrates that mutants forming local three-dimensional (3D) structures similar to the wild type (WT) are more likely to accumulate in PSTVd quasispecies. The selection mechanisms underlying this biased accumulation are likely associated with cell-to-cell movement and long-distance trafficking. Moreover, certain trafficking-defective PSTVd mutants can be spread by functional sister genomes in the quasispecies. Our study reveals that the RNA 3D structure of stems and loops constrains the evolution of viroid quasispecies. Mutants with a structure similar to WT have a higher likelihood of being maintained within the quasispecies and can potentially give rise to novel infectious variants. These findings emphasize the potential of targeting RNA 3D structure as a more robust approach to defend against viroid infections.

Structural basis of ligand recognition and self-activation of orphan GPR52.

GPR52 is a class-A orphan G-protein-coupled receptor that is highly expressed in the brain and represents a promising therapeutic target for the treatment of Huntington's disease and several psychiatric disorders1,2. Pathological malfunction of GPR52 signalling occurs primarily through the heterotrimeric Gs protein2, but it is unclear how GPR52 and Gs couple for signal transduction and whether a native ligand or other activating input is required. Here we present the high-resolution structures of human GPR52 in three states: a ligand-free state, a Gs-coupled self-activation state and a potential allosteric ligand-bound state. Together, our structures reveal that extracellular loop 2 occupies the orthosteric binding pocket and operates as a built-in agonist, conferring an intrinsically high level of basal activity to GPR523. A fully active state is achieved when Gs is coupled to GPR52 in the absence of an external agonist. The receptor also features a side pocket for ligand binding. These insights into the structure and function of GPR52 could improve our understanding of other self-activated GPCRs, enable the identification of endogenous and tool ligands, and guide drug discovery efforts that target GPR52.

KDM6A-SND1 interaction maintains genomic stability by protecting the nascent DNA and contributes to cancer chemoresistance.

Genomic instability is one of the hallmarks of cancer. While loss of histone demethylase KDM6A increases the risk of tumorigenesis, its specific role in maintaining genomic stability remains poorly understood. Here, we propose a mechanism in which KDM6A maintains genomic stability independently on its demethylase activity. This occurs through its interaction with SND1, resulting in the establishment of a protective chromatin state that prevents replication fork collapse by recruiting of RPA and Ku70 to nascent DNA strand. Notably, KDM6A-SND1 interaction is up-regulated by KDM6A SUMOylation, while KDM6AK90A mutation almost abolish the interaction. Loss of KDM6A or SND1 leads to increased enrichment of H3K9ac and H4K8ac but attenuates the enrichment of Ku70 and H3K4me3 at nascent DNA strand. This subsequently results in enhanced cellular sensitivity to genotoxins and genomic instability. Consistent with these findings, knockdown of KDM6A and SND1 in esophageal squamous cell carcinoma (ESCC) cells increases genotoxin sensitivity. Intriguingly, KDM6A H101D & P110S, N1156T and D1216N mutations identified in ESCC patients promote genotoxin resistance via increased SND1 association. Our finding provides novel insights into the pivotal role of KDM6A-SND1 in genomic stability and chemoresistance, implying that targeting KDM6A and/or its interaction with SND1 may be a promising strategy to overcome the chemoresistance.

Regulating cathode surface hydroxyl chemistry enables superior potassium storage.

Potassium vanadium fluorophosphate (KVPO4F) is regarded as a promising cathode candidate for potassium-ion batteries due to its high working voltage and satisfactory theoretical capacity. However, the usage of electrochemically inactive binders and redundant current collectors typically results in inferior electrochemical performance and low energy density, thus implying the important role of rational electrode structure design. Herein, we have reported a scalable and cost-effective synthesis of a cellulose-derived KVPO4F self-supporting electrode, which features a special surface hydroxyl chemistry, three-dimensional porous and conductive framework, as well as super flexible and stable architecture. The cellulose not only serves as a flexible substrate, a pore-forming agent, and a versatile binder for KVPO4F/conductive carbon but also enhances the K-ion migration ability. Benefiting from the special hydroxyl chemistry-induced storage mechanism and electrode structural stability, the flexible freestanding KVPO4F cathode exhibits high-rate performance (53.0% capacity retention with current densities increased 50-fold, from 0.2 C to 10 C) and impressive cycling stability (capacity retention up to 74.9% can be achieved over 1,000 cycles at a rate of 5 C). Such electrode design and surface engineering strategies, along with a deeper understanding of potassium storage mechanisms, provide invaluable guidance for better electrode design to boost the performance of potassium-ion energy storage systems.

The lack of negative association between TE load and subgenome dominance in synthesized Brassica allotetraploids.

Polyploidization is important to the evolution of plants. Subgenome dominance is a distinct phenomenon associated with most allopolyploids. A gene on the dominant subgenome tends to express to higher RNA levels in all organs as compared to the expression of its syntenic paralogue (homoeolog). The mechanism that underlies the formation of subgenome dominance remains unknown, but there is evidence for the involvement of transposon/DNA methylation density differences nearby the genes of parents as being causal. The subgenome with lower density of transposon and methylation near genes is positively associated with subgenome dominance. Here, we generated eight generations of allotetraploid progenies from the merging of parental genomes Brassica rapa and Brassica oleracea. We found that transposon/methylation density differ near genes between the parental (rapa:oleracea) existed in the wide hybrid, persisted in the neotetraploids (the synthetic Brassica napus), but these neotetraploids expressed no expected subgenome dominance. This absence of B. rapa vs. B. oleracea subgenome dominance is particularly significant because, while there is no negative relationship between transposon/methylation level and subgenome dominance in the neotetraploids, the more ancient parental subgenomes for all Brassica did show differences in transposon/methylation densities near genes and did express, in the same samples of cells, biased gene expression diagnostic of subgenome dominance. We conclude that subgenome differences in methylated transposon near genes are not sufficient to initiate the biased gene expressions defining subgenome dominance. Our result was unexpected, and we suggest a "nuclear chimera" model to explain our data.

Dysfunction of CD169+ macrophages and blockage of erythrocyte maturation as a mechanism of anemia in Plasmodium yoelii infection.

Plasmodium parasites cause malaria with disease outcomes ranging from mild illness to deadly complications such as severe malarial anemia (SMA), pulmonary edema, acute renal failure, and cerebral malaria. In young children, SMA often requires blood transfusion and is a major cause of hospitalization. Malaria parasite infection leads to the destruction of infected and noninfected erythrocytes as well as dyserythropoiesis; however, the mechanism of dyserythropoiesis accompanied by splenomegaly is not completely understood. Using Plasmodium yoelii yoelii 17XNL as a model, we show that both a defect in erythroblastic island (EBI) macrophages in supporting red blood cell (RBC) maturation and the destruction of reticulocytes/RBCs by the parasites contribute to SMA and splenomegaly. After malaria parasite infection, the destruction of both infected and noninfected RBCs stimulates extramedullary erythropoiesis in mice. The continuous decline of RBCs stimulates active erythropoiesis and drives the expansion of EBIs in the spleen, contributing to splenomegaly. Phagocytosis of malaria parasites by macrophages in the bone marrow and spleen may alter their functional properties and abilities to support erythropoiesis, including reduced expression of the adherence molecule CD169 and inability to support erythroblast differentiation, particularly RBC maturation in vitro and in vivo. Therefore, macrophage dysfunction is a key mechanism contributing to SMA. Mitigating and/or alleviating the inhibition of RBC maturation may provide a treatment strategy for SMA.

Coupling of Sharp Wave Events between Zebrafish Hippocampal and Amygdala Homologs.

The mammalian hippocampus exhibits spontaneous sharp wave events (1-30 Hz) with an often-present superimposed fast ripple oscillation (120-220 Hz) to form a sharp wave ripple (SWR) complex. During slow-wave sleep or quiet restfulness, SWRs result from the sequential spiking of hippocampal cell assemblies initially activated during learned or imagined experiences. Additional cortical/subcortical areas exhibit SWR events that are coupled to hippocampal SWRs, and studies in mammals suggest that coupling may be critical for the consolidation and recall of specific memories. In the present study, we have examined juvenile male and female zebrafish and show that SWR events are intrinsically generated and maintained within the telencephalon and that their hippocampal homolog, the anterodorsolateral lobe (ADL), exhibits SW events with ∼9% containing an embedded ripple (SWR). Single-cell calcium imaging coupled to local field potential recordings revealed that ∼10% of active cells in the dorsal telencephalon participate in any given SW event. Furthermore, fluctuations in cholinergic tone modulate SW events consistent with mammalian studies. Moreover, the basolateral amygdala (BLA) homolog exhibits SW events with ∼5% containing an embedded ripple. Computing the SW peak coincidence difference between the ADL and BLA showed bidirectional communication. Simultaneous coupling occurred more frequently within the same hemisphere, and in coupled events across hemispheres, the ADL more commonly preceded BLA. Together, these data suggest conserved mechanisms across species by which SW and SWR events are modulated, and memories may be transferred and consolidated through regional coupling.

A Prelimbic Cortex-Thalamus Circuit Bidirectionally Regulates Innate and Stress-Induced Anxiety-Like Behavior.

Anxiety-related disorders respond to cognitive behavioral therapies, which involved the medial prefrontal cortex (mPFC). Previous studies have suggested that subregions of the mPFC have different and even opposite roles in regulating innate anxiety. However, the specific causal targets of their descending projections in modulating innate anxiety and stress-induced anxiety have yet to be fully elucidated. Here, we found that among the various downstream pathways of the prelimbic cortex (PL), a subregion of the mPFC, PL-mediodorsal thalamic nucleus (MD) projection, and PL-ventral tegmental area (VTA) projection exhibited antagonistic effects on anxiety-like behavior, while the PL-MD projection but not PL-VTA projection was necessary for the animal to guide anxiety-related behavior. In addition, MD-projecting PL neurons bidirectionally regulated remote but not recent fear memory retrieval. Notably, restraint stress induced high-anxiety state accompanied by strengthening the excitatory inputs onto MD-projecting PL neurons, and inhibiting PL-MD pathway rescued the stress-induced anxiety. Our findings reveal that the activity of PL-MD pathway may be an essential factor to maintain certain level of anxiety, and stress increased the excitability of this pathway, leading to inappropriate emotional expression, and suggests that targeting specific PL circuits may aid the development of therapies for the treatment of stress-related disorders.

Coevolution of RNA and protein subunits in RNase P and RNase MRP, two RNA processing enzymes.

RNase P and RNase mitochondrial RNA processing (MRP) are ribonucleoproteins (RNPs) that consist of a catalytic RNA and a varying number of protein cofactors. RNase P is responsible for precursor tRNA maturation in all three domains of life, while RNase MRP, exclusive to eukaryotes, primarily functions in rRNA biogenesis. While eukaryotic RNase P is associated with more protein cofactors and has an RNA subunit with fewer auxiliary structural elements compared to its bacterial cousin, the double-anchor precursor tRNA recognition mechanism has remarkably been preserved during evolution. RNase MRP shares evolutionary and structural similarities with RNase P, preserving the catalytic core within the RNA moiety inherited from their common ancestor. By incorporating new protein cofactors and RNA elements, RNase MRP has established itself as a distinct RNP capable of processing ssRNA substrates. The structural information on RNase P and MRP helps build an evolutionary trajectory, depicting how emerging protein cofactors harmonize with the evolution of RNA to shape different functions for RNase P and MRP. Here, we outline the structural and functional relationship between RNase P and MRP to illustrate the coevolution of RNA and protein cofactors, a key driver for the extant, diverse RNP world.

ClusterX: a novel representation learning-based deep clustering framework for accurate visual inspection in virtual screening.

Molecular clustering analysis has been developed to facilitate visual inspection in the process of structure-based virtual screening. However, traditional methods based on molecular fingerprints or molecular descriptors limit the accuracy of selecting active hit compounds, which may be attributed to the lack of representations of receptor structural and protein-ligand interaction during the clustering. Here, a novel deep clustering framework named ClusterX is proposed to learn molecular representations of protein-ligand complexes and cluster the ligands. In ClusterX, the graph was used to represent the protein-ligand complex, and the joint optimisation can be used efficiently for learning the cluster-friendly features. Experiments on the KLIFs database show that the model can distinguish well between the binding modes of different kinase inhibitors. To validate the effectiveness of the model, the clustering results on the virtual screening dataset further demonstrated that ClusterX achieved better or more competitive performance against traditional methods, such as SIFt and extended connectivity fingerprints. This framework may provide a unique tool for clustering analysis and prove to assist computational medicinal chemists in visual decision-making.