Red nucleus mGluR1 and mGluR5 facilitate the development of neuropathic pain through stimulating the expressions of TNF-α and IL-1ß.

Our previous study has identified that glutamate in the red nucleus (RN) facilitates the development of neuropathic pain through metabotropic glutamate receptors (mGluR). Here, we further explored the actions and possible molecular mechanisms of red nucleus mGluR Ⅰ (mGluR1 and mGluR5) in the development of neuropathic pain induced by spared nerve injury (SNI). Our data indicated that both mGluR1 and mGluR5 were constitutively expressed in the RN of normal rats. Two weeks after SNI, the expressions of mGluR1 and mGluR5 were significantly boosted in the RN contralateral to the nerve injury. Administration of mGluR1 antagonist LY367385 or mGluR5 antagonist MTEP to the RN contralateral to the nerve injury at 2 weeks post-SNI significantly ameliorated SNI-induced neuropathic pain. However, unilateral administration of mGluRⅠ agonist DHPG to the RN of normal rats provoked a significant mechanical allodynia, this effect could be blocked by LY367385 or MTEP. Further studies indicated that the expressions of TNF-α and IL-1ß in the RN were also elevated at 2 weeks post-SNI. Administration of mGluR1 antagonist LY367385 or mGluR5 antagonist MTEP to the RN at 2 weeks post-SNI significantly inhibited the elevations of TNF-α and IL-1ß. However, administration of mGluR Ⅰ agonist DHPG to the RN of normal rats significantly enhanced the expressions of TNF-α and IL-1ß, these effects were blocked by LY367385 or MTEP. These results suggest that activation of red nucleus mGluR1 and mGluR5 facilitate the development of neuropathic pain by stimulating the expressions of TNF-α and IL-1ß. mGluR Ⅰ maybe potential targets for drug development and clinical treatment of neuropathic pain.

Fluorescent aptasensors for sensitive detection of lead ions based on structure-switching DNA beacon probe and exonuclease I-mediated signal amplification.

Herein, two simple fluorescent signal-on sensing strategies for detecting lead ions (Pb2+) were established based on structure-switching aptamer probes and exonuclease-assisted signal amplification strategies. Two hairpin-structure fluorescent probes with blunt-ended stem arms were designed by extending the base sequence of Pb2+ aptamer (PS2.M) and labelling the probes with FAM (in probe 1) and 2-aminopurine (2-AP) (in probe 2), respectively. In method 1, graphene oxide (GO) was added to adsorb probe 1 and quench the fluorescence emission of FAM to achieve low fluorescent background. In method 2, fluorescent 2-AP molecule inserted into the double-stranded DNA of probe 2 was quenched as a result of base stacking interactions, leading to a simplified, quencher-free approach. The addition of Pb2+ can induce the probes to transform into G-quadruplex structures, exposing single DNA strands at the 3' end (the extended sequences). This exposure enables the activation of exonuclease I (Exo I) on the probes, leading to the cleavage effect and subsequent release of free bases and fluorophores, thereby resulting in amplified fluorescence signals. The two proposed methods exhibit good specificity and sensitivity, with detection limits of 0.327 nM and 0.049 nM Pb2+ for method 1 and method 2, respectively, and have been successfully applied to detect Pb2+ in river water and fish samples. Both detection methods employ the structure-switching aptamer probes and can be completed in two or three steps without the need for complex analytical instruments. Therefore, they have a broad prospect in the sensitive and simple detection of lead ion contamination in food and environmental samples.

Nanozymes: Potential Therapies for Reactive Oxygen Species Overproduction and Inflammation in Ischemic Stroke and Traumatic Brain Injury.

Nanozymes, which can selectively scavenge reactive oxygen species (ROS), have recently emerged as promising candidates for treating ischemic stroke and traumatic brain injury (TBI) in preclinical models. ROS overproduction during the early phase of these diseases leads to oxidative brain damage, which has been a major cause of mortality worldwide. However, the clinical application of ROS-scavenging enzymes is limited by their short in vivo half-life and inability to cross the blood-brain barrier. Nanozymes, which mimic the catalytic function of natural enzymes, have several advantages, including cost-effectiveness, high stability, and easy storage. These advantages render them superior to natural enzymes for disease diagnosis and therapeutic interventions. This review highlights recent advancements in nanozyme applications for ischemic stroke and TBI, emphasizing their potential to mitigate the detrimental effect of ROS overproduction, oxidative brain damage, inflammation, and blood-brain barrier compromise. Therefore, nanozymes represent a promising treatment modality for ROS overproduction conditions in future medical practices.

From the Public Health Perspective: a Scalable Model for Improving Epidemiological Testing Efficacy in Low- and Middle-Income Areas.

The globe is an organically linked whole, and in the pandemic era, COVID-19 has brought heavy public safety threats and economic costs to humanity as almost all countries began to pay more attention to taking steps to minimize the risk of harm to society from sudden-onset diseases. It is worth noting that in some low- and middle-income areas, where the environment for epidemic detection is complex, the causative and comorbid factors are numerous, and where public health resources are scarce. It is often more difficult than in other areas to obtain timely and effective detection and control in the event of widespread virus transmission, which, in turn, is a constant threat to local and global public health security. Pandemics are preventable through effective disease surveillance systems, with nonpharmacological interventions (NPIs) as the mainstay of the control system, effectively controlling the spread of epidemics and preventing larger outbreaks. However, current state-of-the-art NPIs are not applicable in low- and middle-income areas and tend to be decentralized and costly. Based on a 3-year case study of SARS-CoV-2 preventive detection in low-income areas in south-central China, we explored a strategic model for enhancing disease detection efficacy in low- and middle-income areas. For the first time, we propose an integrated and comprehensive approach that covers structural, social, and personal strategies to optimize the epidemic surveillance system in low- and middle-income areas. This model can improve the local epidemic detection efficiency, ensure the health care needs of more people, reduce the public health costs in low- and middle-income areas in a coordinated manner, and ensure and strengthen local public health security sustainably.

Comparative analysis of gene expression between mice and humans in acetaminophen-induced liver injury by integrating bioinformatics analysis.

OBJECTIVE: Mice are routinely utilized as animal models of drug-induced liver injury (DILI), however, there are significant differences in the pathogenesis between mice and humans. This study aimed to compare gene expression between humans and mice in acetaminophen (APAP)-induced liver injury (AILI), and investigate the similarities and differences in biological processes between the two species. METHODS: A pair of public datasets (GSE218879 and GSE120652) obtained from GEO were analyzed using "Limma" package in R language, and differentially expressed genes (DEGs) were identified, including co-expressed DEGs (co-DEGs) and specific-expressed DEGS (specific-DEGs). Analysis of Gene Set Enrichment Analysis (GSEA), Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) were performed analyses for specific-DEGs and co-DEGs. The co-DEGs were also used to construct transcription factor (TF)-gene network, gene-miRNA interactions network and protein-protein interaction (PPI) network for analyzing hub genes. RESULTS: Mouse samples contained 1052 up-regulated genes and 1064 down-regulated genes, while human samples contained 1156 up-regulated genes and 1557 down-regulated genes. After taking the intersection between the DEGs, only 154 co-down-regulated and 89 co-up-regulated DEGs were identified, with a proportion of less than 10%. It was suggested that significant differences in gene expression between mice and humans in drug-induced liver injury. Mouse-specific-DEGs predominantly engaged in processes related to apoptosis and endoplasmic reticulum stress, while human-specific-DEGs were concentrated around catabolic process. Analysis of co-regulated genes reveals showed that they were mainly enriched in biosynthetic and metabolism-related processes. Then a PPI network which contains 189 nodes and 380 edges was constructed from the co-DEGs and two modules were obtained by Mcode. We screened out 10 hub genes by three algorithms of Degree, MCC and MNC, including CYP7A1, LSS, SREBF1, FASN, CD44, SPP1, ITGAV, ANXA5, LGALS3 and PDGFRA. Besides, TFs such as FOXC1, HINFP, NFKB1, miRNAs like mir-744-5p, mir-335-5p, mir-149-3p, mir-218-5p, mir-10a-5p may be the key regulatory factors of hub genes. CONCLUSIONS: The DEGs of AILI mice models and those of patients were compared, and common biological processes were identified. The signaling pathways and hub genes in co-expression were identified between mice and humans through a series of bioinformatics analyses, which may be more valuable to reveal molecular mechanisms of AILI.

CACNA1B protects naked mole-rat hippocampal neuron from apoptosis via altering the subcellular localization of Nrf2 after 60Co irradiation.

Although radiotherapy is the most effective treatment modality for brain tumors, it always injures the central nervous system, leading to potential sequelae such as cognitive dysfunction. Radiation induces molecular, cellular, and functional changes in neuronal and glial cells. The hippocampus plays a critical role in learning and memory; therefore, concerns about radiation-induced injury are widespread. Multiple studies have focused on this complex problem, but the results have not been fully elucidated. Naked mole rat brains were irradiated with 60Co at a dose of 10 Gy. On 7 days, 14 days, and 28 days after irradiation, hippocampi in the control groups were obtained for next-generation sequencing. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses were subsequently performed. Venn diagrams revealed 580 differentially expressed genes (DEGs) that were common at different times after irradiation. GO and KEGG analyses revealed that the 580 common DEGs were enriched in molecular transducer activity. In particular, CACNA1B mediated regulatory effects after irradiation. CACNA1B expression increased significantly after irradiation. Downregulation of CACNA1B led to a reduction in apoptosis and reactive oxygen species levels in hippocampal neurons. This was due to the interaction between CACNA1B and Nrf2, which disturbed the normal nuclear localization of Nrf2. In addition, CACNA1B downregulation led to a decrease in the cognitive functions of naked mole rats. These findings reveal the pivotal role of CACNA1B in regulating radiation-induced brain injury and will lead to the development of a novel strategy to prevent brain injury after irradiation.

CRISPR/Cas12a-derived ratiometric fluorescence sensor for high-sensitive Pb2+ detection based on CDs@ZIF-8 and DNAzyme.

Benefiting from specific target recognition and trans-cleavage capabilities, the CRISPR/Cas12a system has great application prospects in the design of highly sensitive and rapid fluorescence biosensors. The CRISPR/Cas12a-based fluorophore-quencher molecular beacons exhibit single-color emission and are easily exposed to interference from environmental factors. Herein, we design a CRISPR/Cas12a-derived ratiometric fluorescence sensor for Pb2+ detection based on embedded carbon dots@zeolitic imidazolate framework-8 (CDs@ZIF-8) composites and DNAzyme. The functions of ZIF-8 about encapsulating red emissive CDs in the inner cavity and adsorbing DNA on the outer surface are integrated to establish dual fluorescence signals, thereby reducing the possibility of interference and improving sensing accuracy. The presence of Pb2+ is converted into the change of activator by the GR5 DNAzyme to activate the CRISPR/Cas12a system, which provides signal amplification through multiple turnovers of side branch cutting, achieving highly sensitive detection of Pb2+ with a low detection limit of 18 pM. This method has the advantages of simplicity, universality, and excellent quantitative ability, and has broad prospects in sensing applications.

Sinoflavonoids NJ and NK, anti-inflammatory prenylated flavonoids from the fruits of Podophyllum hexandrum Royle.

Two new prenylated flavonoids named sinoflavonoids NJ and NK (1-2), along with ten known compounds were isolated from the fruits of Podophyllum hexandrum Royle. The chemical structures were determined through NMR spectroscopic data and MS analysis. Sinoflavonoid NJ (1) with an unusual 5,11-dioxabenzo[b]fluoren-10-one skeleton was firstly reported from Berberidaceae. The isolated flavonoids were tested with LPS-induced RAW 264.7 mouse macrophages model for their anti-inflammatory activity. Sinoflavonoid NJ (1) showed the most potent inhibition on nitric oxide production with IC50 value as 0.06 µM.

Recycling Waste Glyceroborate to Aqueous Lubricant for Tribological Applications.

The present study attempts to explore the direct recyclability of glyceroborate from medicine pharmaceutical production wastewater into an aqueous lubricant instead of conventional waste processing methods from the tribological view. In order to determine the tribological feasibility, the physicochemical properties of crude pharmaceutical wastewater are investigated and compared with those of pure glycerol to access their potential lubrication properties. The results demonstrated that the crude pharmaceutical wastewater has better friction-reducing and antiwear properties under the same working conditions. Besides outstanding lubricating properties, the friction-induced formation of borate tribo-film and intermediate FeOOH compound favors lowering of the shear stress between the rubbing surfaces. This finding better provides an alternative to transform glyceroborate from medicine pharmaceutical production wastewater after simple distillation processing to a potential aqueous lubricant.

A multi-modal attention neural network for traffic flow prediction by capturing long-short term sequence correlation.

Accurate traffic flow prediction information can help traffic managers and drivers make more rational decisions and choices. To make an effective and accurate traffic flow prediction, we need to consider not only the spatio-temporal dependencies between data, but also the temporal correlation between data. However, most existing methods only consider temporal continuity and ignore temporal correlation. In this paper, we propose a multi-modal attention neural network for traffic flow prediction by capturing long-short term sequence correlation (LSTSC). In the model, we employed attention mechanisms to capture the spatio-temporal correlations of the sequences, and the model based on multiple decision forms demonstrated higher accuracy and reliability. The superiority of the model is demonstrated on two datasets, PeMS08 and PeMSD7(M), particularly for long-term predictions.

Geranylgeranylacetone Ameliorates Skin Inflammation by Regulating and Inducing Thioredoxin via the Thioredoxin Redox System.

Geranylgeranylacetone (GGA) exerts cytoprotective activity against various toxic stressors via the thioredoxin (TRX) redox system; however, its effect on skin inflammation and molecular mechanism on inducing the TRX of GGA is still unknown. We investigated the effects of GGA in a murine irritant contact dermatitis (ICD) model induced by croton oil. Both a topical application and oral administration of GGA induced TRX production and Nrf2 activation. GGA ameliorated ear swelling, neutrophil infiltration, and inhibited the expression of TNF-α, IL-1ß, GM-CSF, and 8-OHdG. GGA's cytoprotective effect was stronger orally than topically in mice. In vitro studies also showed that GGA suppressed the expression of NLRP3, TNF-α, IL-1ß, and GM-CSF and scavenged ROS in PAM212 cells after phorbol myristate acetate stimulation. Moreover, GGA induced endogenous TRX production and Nrf2 nuclear translocation in PAM212 cells (dependent on the presence of ROS) and activated the PI3K-Akt signaling pathway. GGA significantly downregulated thioredoxin-interacting protein (TXNIP) levels in PAM212 cells treated with or without Nrf2 siRNA. After knocking down Nrf2 in PAM212 cells, the effect of GGA on TRX induction was significantly inhibited. This suggests that GGA suppress ICD by inducing endogenous TRX, which may be regulated by PI3K/Akt/Nrf2 mediation of the TRX redox system.

Preparation of Self-Coating Al2O3 Bonded SiAlON Porous Ceramics Using Aluminum Dross and Silicon Solid Waste under Ambient Air Atmosphere.

Al2O3-bonded SiAlON ceramic with self-coating was prepared using aluminum dross and silicon solid waste as starting materials under ambient air conditions. The changes in phase, microstructure, and physical properties of the ceramic with temperature were analyzed and the formation mechanism of the SiAlON phase was elucidated. The results showed that higher temperature was more suitable for the preparation of SiAlON ceramics. As the temperature increased from 1400 to 1600 °C, the main phases in the ceramic transformed from mullite, Al2O3, and SiAlON to Al2O3 and SiAlON. An Al2O3-rich layer spontaneously coated the surface of the porous ceramic as Al melted and oxidized at high temperature. The thickness of this layer decreased as the temperature increased. The presence of Al2O3-rich coating layer impeded air flow, allowing nitriding of Si and Al, and the formation of the SiAlON phase in ambient air conditions. This study not only presents a strategy to successfully recycle aluminum dross and silicon solid waste but also offers a straightforward approach to preparing SiAlON material in air atmosphere.

Facile and sensitive detection of mercury ions based on fluorescent structure-switching aptamer probe and exonuclease â ¢-assisted signal amplification.

Hg2+ is highly toxic to human health and ecosystem. In this work, based on the unique fluorescent property of 2-Aminopurine (2-AP), the formation of T-Hg2+-T mismatch structure and the signal amplification of exonuclease III (Exo III) assisted target cycle, a fluorescent probe for facile and sensitive detection of Hg2+ is constructed. The hairpin-looped DNA probe is rationally designed with 2-AP embedded in the stem and thymine-rich recognition overhangs extended at the termini. The cleavage of the double stranded DNA stem with stable T-Hg2+-T pairs catalyzed by Exo III is prompted to happen upon recognition of trace Hg2+. Under the optimal reaction conditions, there is an excellent linear relationship between Hg2+ concentration and fluorescence intensity in the range of 7.5-200 nM with a detection limit of 0.38 nM. In addition, the detection results of Hg2+ in Songhua River water and fish samples are satisfactory. The fluorescent probe avoids labeling additional quenchers or quenching materials and has strong anti-interference ability. Thus, the fluorescent probe has a broad prospect in practical application.

Gypenosides Synergistically Reduce the Extracellular Matrix of Hepatic Stellate Cells and Ameliorate Hepatic Fibrosis in Mice.

Liver fibrosis resulting from chronic liver damage is becoming one of the major threats to health worldwide. Active saponin constituents isolated from Gynostemma pentaphyllum were found to possess a protective effect in liver diseases. Here, we obtained a naturally abundant gypenoside, XLVI, and evaluated its liver protection activity in both animal and cellular models. The results showed that it ameliorated acute and chronic liver injuries and lightened the process of fibrogenesis in vivo. XLVI can inhibit TGF-ß-induced activation of hepatic stellate cells and ECM deposition in vitro. The underlying mechanism study verified that it upregulated the protein expression of protein phosphatase 2C alpha and strengthened the vitality of the phosphatase together with a PP2Cα agonist gypenoside NPLC0393. These results shed new light on the molecular mechanisms and the potential therapeutic function of the traditional herb Gynostemma pentaphyllum in the treatment of liver fibrosis.

Expandable Li Percolation Network: The Effects of Site Distortion in Cation-Disordered Rock-Salt Cathode Material.

Cation-disordered rock-salt (DRX) materials receive intensive attention as a new class of cathode candidates for high-capacity lithium-ion batteries (LIBs). Unlike traditional layered cathode materials, DRX materials have a three-dimensional (3D) percolation network for Li+ transportation. The disordered structure poses a grand challenge to a thorough understanding of the percolation network due to its multiscale complexity. In this work, we introduce the large supercell modeling for DRX material Li1.16Ti0.37Ni0.37Nb0.10O2 (LTNNO) via the reverse Monte Carlo (RMC) method combined with neutron total scattering. Through a quantitative statistical analysis of the material's local atomic environment, we experimentally verified the existence of short-range ordering (SRO) and uncovered an element-dependent behavior of transition metal (TM) site distortion. A displacement from the original octahedral site for Ti4+ cations is pervasive throughout the DRX lattice. Density functional theory (DFT) calculations revealed that site distortions quantified by the centroid offsets could alter the migration barrier for Li+ diffusion through the tetrahedral channels, which can expand the previously proposed theoretical percolating network of Li. The estimated accessible Li content is highly consistent with the observed charging capacity. The newly developed characterization method here uncovers the expandable nature of the Li percolation network in DRX materials, which may provide valuable guidelines for the design of superior DRX materials.

A ratiometric fluorescence platform for lead ion detection via RNA cleavage-inhibited self-assembly of three-arm branched junction.

Heavy metal pollution can pose a threat to food safety and human health, and accurate quantification of heavy metal ions is a vital requirement. Emerging DNA nanostructures-based biosensors offer attractive tools toward ultra-sensitive or rapid analysis of heavy metal ions. However, the problems including complex design, severe reaction conditions and undesirable reliability are inevitable obstacle in advancing their extension and application. Herein, a ratiometric fluorescent platform was established for monitoring lead ion (Pb2+) in food based on dual Förster resonance energy transfer (FRET) and RNA cleavage-inhibited self-assembly of three-arm branched junction (TBJ). GR-5 DNAzyme was employed for Pb2+ recognition, and enzyme-free amplification technique catalytic hairpin assembly (CHA) served to form FRET probes-carried TBJ. The substrate strand (S) of DNAzyme triggered the generation of CHA-TBJ, and Pb2+-responsive cleavage of S hindered the assembly of CHA-TBJ, causing opposite changes in the FRET states of FAM/BHQ1 and ROX/BHQ2 pairs. The fluorescence responses were recorded through synchronous fluorescence spectrometry to indicate Pb2+ concentration, allowing sensitive and reliable identification of Pb2+ in the linear range of 0.05-5 ng mL-1 with the detection limit of 0.03 ng mL-1. The Pb2+ detection can be achieved under conventional reaction conditions, simple mixing procedures and one-step measurement operation. The approach can afford excellent specificity for Pb2+ against competing metal ions, and can be applied to analyze Pb2+ in tea samples with satisfactory results. This facile fluorescence platform shows a capable method for Pb2+ detection, and provides new avenue in the development of ratiometric approaches and DNAzyme strategies for monitoring heavy metal pollution, facilitating the transformation of DNAzyme-based biosensors for food safety control.

Application of Bagging, Boosting and Stacking Ensemble and EasyEnsemble Methods for Landslide Susceptibility Mapping in the Three Gorges Reservoir Area of China.

Since the impoundment of the Three Gorges Reservoir area in 2003, the potential risks of geological disasters in the reservoir area have increased significantly, among which the hidden dangers of landslides are particularly prominent. To reduce casualties and damage, efficient and precise landslide susceptibility evaluation methods are important. Multiple ensemble models have been used to evaluate the susceptibility of the upper part of Badong County to landslides. In this study, EasyEnsemble technology was used to solve the imbalance between landslide and nonlandslide sample data. The extracted evaluation factors were input into three bagging, boosting, and stacking ensemble models for training, and landslide susceptibility mapping (LSM) was drawn. According to the importance analysis, the important factors affecting the occurrence of landslides are altitude, terrain surface texture (TST), distance to residences, distance to rivers and land use. The influences of different grid sizes on the susceptibility results were compared, and a larger grid was found to lead to the overfitting of the prediction results. Therefore, a 30 m grid was selected as the evaluation unit. The accuracy, area under the curve (AUC), recall rate, test set precision, and kappa coefficient of a multi-grained cascade forest (gcForest) model with the stacking method were 0.958, 0.991, 0.965, 0.946, and 0.91, respectively, which a significantly better than the values produced by the other models.

Size controllable single-crystalline Ni-rich cathodes for high-energy lithium-ion batteries.

A single-crystalline Ni-rich (SCNR) cathode with a large particle size can achieve higher energy density, and is safer, than polycrystalline counterparts. However, synthesizing large SCNR cathodes (>5 µm) without compromising electrochemical performance is very challenging due to the incompatibility between Ni-rich cathodes and high temperature calcination. Herein, we introduce Vegard's Slope as a guide for rationally selecting sintering aids, and we successfully synthesize size-controlled SCNR cathodes, the largest of which can be up to 10 µm. Comprehensive theoretical calculation and experimental characterization show that sintering aids continuously migrate to the particle surface, suppress sublattice oxygen release and reduce the surface energy of the typically exposed facets, which promotes grain boundary migration and elevates calcination critical temperature. The dense SCNR cathodes, fabricated by packing of different-sized SCNR cathode particles, achieve a highest electrode press density of 3.9 g cm-3 and a highest volumetric energy density of 3000 Wh L-1. The pouch cell demonstrates a high energy density of 303 Wh kg-1, 730 Wh L-1 and 76% capacity retention after 1200 cycles. SCNR cathodes with an optimized particle size distribution can meet the requirements for both electric vehicles and portable devices. Furthermore, the principle for controlling the growth of SCNR particles can be widely applied when synthesizing other materials for Li-ion, Na-ion and K-ion batteries.

MD-GCN: A Multi-Scale Temporal Dual Graph Convolution Network for Traffic Flow Prediction.

The spatial-temporal prediction of traffic flow is very important for traffic management and planning. The most difficult challenges of traffic flow prediction are the temporal feature extraction and the spatial correlation extraction of nodes. Due to the complex spatial correlation between different roads and the dynamic trend of time patterns, traditional forecasting methods still have limitations in obtaining spatial-temporal correlation, which makes it difficult to extract more valid information. In order to improve the accuracy of the forecasting, this paper proposes a multi-scale temporal dual graph convolution network for traffic flow prediction (MD-GCN). Firstly, we propose a gated temporal convolution based on a channel attention and inception structure to extract multi-scale temporal dependence. Then, aiming at the complexity of the traffic spatial structure, we develop a dual graph convolution module including the graph sampling and aggregation submodule (GraphSAGE) and the mix-hop propagation graph convolution submodule (MGCN) to extract the local correlation and global correlation between neighbor nodes. Finally, extensive experiments are carried out on several public traffic datasets, and the experimental results show that our proposed algorithm outperforms the existing methods.