PINK1 alleviates myocardial hypoxia-reoxygenation injury by ameliorating mitochondrial dysfunction.

PTEN inducible kinase-1 (PINK1) mutant induces mitochondrial dysfunction of cells, resulting in an inherited form of Parkinson's disease. However its exact role in the cardiomyocytes is unclear. The present study examined the function of PINK1 in hypoxia-reoxygenation (H/R) induced H9c2 cell damage and its potential mechanism. The H/R model in H9c2 cells was established by 6 h of hypoxia and 12 h of reoxygenation. The CCK8 and LDH assay indicated that the cell viability was obviously reduced after H/R. The expression of PINK1 was decreased in H/R-induced H9c2 cells compared with control group. The vector overexpressing PINK1 was constructed to transfect into H/R-induced H9c2 cells. Our results showed that cell viability was increased, cell apoptosis and caspase 3, cytochrome C (Cyto C) levels were decreased after LV-PINK1 transfection. Furthermore, PINK1 overexpression stabilized electron transport chain (ETC) activity, increased ATP production, mPTP opening and mitochondrial membrane potential (MMP), inhibited ROS-generating mitochondria, implying PINK1 alleviates H/R induced mitochondrial dysfunction in cardiomyocytes. In addition, the TRAP-1 siRNA was transfected into PINK1 treated H9c2 cells after H/R to detected the molecular mechanism of PINK1 protecting cardiomyocytes. The results indicated that silence of TRAP-1 reversed the effects of PINK1 in H/R-induced H9c2 cells. In conclusion, these results suggest that PINK1 overexpression alleviates H/R-induced cell damage of H9c2 cells by phosphorylation of TRAP-1, and that is a valid approach for protection from myocardial I/R injury.

DyCARS: A dynamic context-aware recommendation system.

Dynamic recommendation systems aim to achieve real-time updates and dynamic migration of user interests, primarily utilizing user-item interaction sequences with timestamps to capture the dynamic changes in user interests and item attributes. Recent research has mainly centered on two aspects. First, it involves modeling the dynamic interaction relationships between users and items using dynamic graphs. Second, it focuses on mining their long-term and short-term interaction patterns. This is achieved through the joint learning of static and dynamic embeddings for both users and items. Although most existing methods have achieved some success in modeling the historical interaction sequences between users and items, there is still room for improvement, particularly in terms of modeling the long-term dependency structures of dynamic interaction histories and extracting the most relevant delayed interaction patterns. To address this issue, we proposed a Dynamic Context-Aware Recommendation System for dynamic recommendation. Specifically, our model is built on a dynamic graph and utilizes the static embeddings of recent user-item interactions as dynamic context. Additionally, we constructed a Gated Multi-Layer Perceptron encoder to capture the long-term dependency structure in the dynamic interaction history and extract high-level features. Then, we introduced an Attention Pooling network to learn similarity scores between high-level features in the user-item dynamic interaction history. By calculating bidirectional attention weights, we extracted the most relevant delayed interaction patterns from the historical sequence to predict the dynamic embeddings of users and items. Additionally, we proposed a loss function called the Pairwise Cosine Similarity loss for dynamic recommendation to jointly optimize the static and dynamic embeddings of two types of nodes. Finally, extensive experiments on two real-world datasets, LastFM, and the Global Terrorism Database showed that our model achieves consistent improvements over state-of-the-art baselines.

A deep graph convolutional neural network architecture for graph classification.

Graph Convolutional Networks (GCNs) are powerful deep learning methods for non-Euclidean structure data and achieve impressive performance in many fields. But most of the state-of-the-art GCN models are shallow structures with depths of no more than 3 to 4 layers, which greatly limits the ability of GCN models to extract high-level features of nodes. There are two main reasons for this: 1) Overlaying too many graph convolution layers will lead to the problem of over-smoothing. 2) Graph convolution is a kind of localized filter, which is easily affected by local properties. To solve the above problems, we first propose a novel general framework for graph neural networks called Non-local Message Passing (NLMP). Under this framework, very deep graph convolutional networks can be flexibly designed, and the over-smoothing phenomenon can be suppressed very effectively. Second, we propose a new spatial graph convolution layer to extract node multiscale high-level node features. Finally, we design an end-to-end Deep Graph Convolutional Neural Network II (DGCNNII) model for graph classification task, which is up to 32 layers deep. And the effectiveness of our proposed method is demonstrated by quantifying the graph smoothness of each layer and ablation studies. Experiments on benchmark graph classification datasets show that DGCNNII outperforms a large number of shallow graph neural network baseline methods.

MLSFF: Multi-level structural features fusion for multi-modal knowledge graph completion.

With the rise of multi-modal methods, multi-modal knowledge graphs have become a better choice for storing human knowledge. However, knowledge graphs often suffer from the problem of incompleteness due to the infinite and constantly updating nature of knowledge, and thus the task of knowledge graph completion has been proposed. Existing multi-modal knowledge graph completion methods mostly rely on either embedding-based representations or graph neural networks, and there is still room for improvement in terms of interpretability and the ability to handle multi-hop tasks. Therefore, we propose a new method for multi-modal knowledge graph completion. Our method aims to learn multi-level graph structural features to fully explore hidden relationships within the knowledge graph and to improve reasoning accuracy. Specifically, we first use a Transformer architecture to separately learn about data representations for both the image and text modalities. Then, with the help of multimodal gating units, we filter out irrelevant information and perform feature fusion to obtain a unified encoding of knowledge representations. Furthermore, we extract multi-level path features using a width-adjustable sliding window and learn about structural feature information in the knowledge graph using graph convolutional operations. Finally, we use a scoring function to evaluate the probability of the truthfulness of encoded triplets and to complete the prediction task. To demonstrate the effectiveness of the model, we conduct experiments on two publicly available datasets, FB15K-237-IMG and WN18-IMG, and achieve improvements of 1.8 and 0.7%, respectively, in the Hits@1 metric.

MLNet: a multi-level multimodal named entity recognition architecture.

In the field of human-computer interaction, accurate identification of talking objects can help robots to accomplish subsequent tasks such as decision-making or recommendation; therefore, object determination is of great interest as a pre-requisite task. Whether it is named entity recognition (NER) in natural language processing (NLP) work or object detection (OD) task in the computer vision (CV) field, the essence is to achieve object recognition. Currently, multimodal approaches are widely used in basic image recognition and natural language processing tasks. This multimodal architecture can perform entity recognition tasks more accurately, but when faced with short texts and images containing more noise, we find that there is still room for optimization in the image-text-based multimodal named entity recognition (MNER) architecture. In this study, we propose a new multi-level multimodal named entity recognition architecture, which is a network capable of extracting useful visual information for boosting semantic understanding and subsequently improving entity identification efficacy. Specifically, we first performed image and text encoding separately and then built a symmetric neural network architecture based on Transformer for multimodal feature fusion. We utilized a gating mechanism to filter visual information that is significantly related to the textual content, in order to enhance text understanding and achieve semantic disambiguation. Furthermore, we incorporated character-level vector encoding to reduce text noise. Finally, we employed Conditional Random Fields for label classification task. Experiments on the Twitter dataset show that our model works to increase the accuracy of the MNER task.

Attention-based message passing and dynamic graph convolution for spatiotemporal data imputation.

Although numerous spatiotemporal approaches have been presented to address the problem of missing spatiotemporal data, there are still limitations in concurrently capturing the underlying spatiotemporal dependence of spatiotemporal graph data. Furthermore, most imputation methods miss the hidden dynamic connection associations that exist between graph nodes over time. To address the aforementioned spatiotemporal data imputation challenge, we present an attention-based message passing and dynamic graph convolution network (ADGCN). Specifically, this paper uses attention mechanisms to unify temporal and spatial continuity and aggregate node neighbor information in multiple directions. Furthermore, a dynamic graph convolution module is designed to capture constantly changing spatial correlations in sensors utilizing a new dynamic graph generation method with gating to transmit node information. Extensive imputation tests in the air quality and traffic flow domains were carried out on four real missing data sets. Experiments show that the ADGCN outperforms the state-of-the-art baseline.

A dynamic graph Hawkes process based on linear complexity self-attention for dynamic recommender systems.

The dynamic recommender system realizes the real-time recommendation for users by learning the dynamic interest characteristics, which is especially suitable for the scenarios of rapid transfer of user interests, such as e-commerce and social media. The dynamic recommendation model mainly depends on the user-item history interaction sequence with timestamp, which contains historical records that reflect changes in the true interests of users and the popularity of items. Previous methods usually model interaction sequences to learn the dynamic embedding of users and items. However, these methods can not directly capture the excitation effects of different historical information on the evolution process of both sides of the interaction, i.e., the ability of events to influence the occurrence of another event. In this work, we propose a Dynamic Graph Hawkes Process based on Linear complexity Self-Attention (DGHP-LISA) for dynamic recommender systems, which is a new framework for modeling the dynamic relationship between users and items at the same time. Specifically, DGHP-LISA is built on dynamic graph and uses Hawkes process to capture the excitation effects between events. In addition, we propose a new self-attention with linear complexity to model the time correlation of different historical events and the dynamic correlation between different update mechanisms, which drives more accurate modeling of the evolution process of both sides of the interaction. Extensive experiments on three real-world datasets show that our model achieves consistent improvements over state-of-the-art baselines.

Co-embedding of edges and nodes with deep graph convolutional neural networks.

Graph neural networks (GNNs) have significant advantages in dealing with non-Euclidean data and have been widely used in various fields. However, most of the existing GNN models face two main challenges: (1) Most GNN models built upon the message-passing framework exhibit a shallow structure, which hampers their ability to efficiently transmit information between distant nodes. To address this, we aim to propose a novel message-passing framework, enabling the construction of GNN models with deep architectures akin to convolutional neural networks (CNNs), potentially comprising dozens or even hundreds of layers. (2) Existing models often approach the learning of edge and node features as separate tasks. To overcome this limitation, we aspire to develop a deep graph convolutional neural network learning framework capable of simultaneously acquiring edge embeddings and node embeddings. By utilizing the learned multi-dimensional edge feature matrix, we construct multi-channel filters to more effectively capture accurate node features. To address these challenges, we propose the Co-embedding of Edges and Nodes with Deep Graph Convolutional Neural Networks (CEN-DGCNN). In our approach, we propose a novel message-passing framework that can fully integrate and utilize both node features and multi-dimensional edge features. Based on this framework, we develop a deep graph convolutional neural network model that prevents over-smoothing and obtains node non-local structural features and refined high-order node features by extracting long-distance dependencies between nodes and utilizing multi-dimensional edge features. Moreover, we propose a novel graph convolutional layer that can learn node embeddings and multi-dimensional edge embeddings simultaneously. The layer updates multi-dimensional edge embeddings across layers based on node features and an attention mechanism, which enables efficient utilization and fusion of both node and edge features. Additionally, we propose a multi-dimensional edge feature encoding method based on directed edges, and use the resulting multi-dimensional edge feature matrix to construct a multi-channel filter to filter the node information. Lastly, extensive experiments show that CEN-DGCNN outperforms a large number of graph neural network baseline methods, demonstrating the effectiveness of our proposed method.

The protective effect of picroside II against hypoxia/reoxygenation injury in neonatal rat cardiomyocytes.

CONTEXT: Picroside II, an iridoid glucoside found in the root of Picrorhiza scrophulariiflora Pennell (Scrophulariaceae), has been demonstrated to possess potent antioxidant activity. However, whether picroside II has a protective effect against hypoxia/reoxygenation (H/R)-induced cardiomyocyte injury is poorly understood. OBJECTIVE: To explore the cardioprotective role of picroside II against oxidative stress induced by H/R injury in neonatal rat cardiacmyocytes. MATERIALS AND METHODS: The viability and cellular damage of cardiomyocytes were assessed by 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolim bromide (MTT) and lactate dehydrogenase (LDH) assays, respectively. The activities of superoxide dismutase (SOD) and glutathione peroxidase (GSH-Px), the levels of reduced (GSH) and oxidized glutathione (GSSG), and the contents of malondialdehyde (MDA) were determined by a colorimetric method. The levels of intracellular reactive oxygen species (ROS) and calcium were evaluated by flow cytometric analysis. RESULTS: We analyzed the effective half-maximal concentration for protection from the dose-response curves and obtained the concentration of 50 µg/mL as EC(50). Pretreated cardiomyocytes with picroside II (50-200 µg/mL), prior to H/R exposure, inhibited LDH activity in culture media and increased cell viability in a dose-dependent manner. This protective effect was accompanied by significantly increasing reduced GSH contents and the activities of SOD and GSH-Px and attenuating MDA and GSSG contents in response to H/R injury. Furthermore, treatment with picroside II also inhibited ROS production and calcium accumulation in cardiomyocytes. DISCUSSION AND CONCLUSION: The present study demonstrates that picroside II protects cardiomyocytes against oxidative-stress injury induced by H/R through reduction of ROS production and calcium accumulation and enhancement of the activity of antioxidant defense.

[Dihydroartemisinin Induces AML cell Apoptosis by Inhibition of PTEN/AKT pathway].

OBJECTIVE: To study the effects of dihydroartemisinin (DHA) on the proliferation and apoptosis of acute myeloid leukemia (AML) cells. METHODS: The effects of DHA on the proliferation of acute myeloid leukemia cells and the inhibitory effect of Z-VAD-FMK on the DHA-induced cell apoptosis were detected by CCK-8 assay. The expression level of cleaved-caspased 3 was detected by indirect immunofluorescence. Western blot was used to quantify the protein expression of PTEN, p-Akt, AKT, ß-actin, and the apoptosis-associated proteins, such as C-PARP, Cleaved-caspase3 and Caspase3 respectively. RESULTS: DHA induced the AML cell apoptosis with concentration-dependent manner (rKasumi-1=-0.959, rKG-1=-0.956). The DHA could induce the accumulation of cleaved-caspase 3 and C-PARP in AML cells, activate PTEN gene and inhibited Akt phosphorylation. Apoptosis inhibitor Z-VAD-FMK could partially restored the activity of DHA-inhibited cell proliferation. CONCLUSION: Dihydroartemisinin induces AML cell apoptosis by inhibition of PTEN/AKT pathway. Dihydroartemisinin is expected to be a safe and effective drug for treatment of acute myeloid leukemia.

KLF5 overexpression attenuates cardiomyocyte inflammation induced by oxygen-glucose deprivation/reperfusion through the PPARγ/PGC-1α/TNF-α signaling pathway.

The primary physiological function of Krüppel-like zinc-finger transcription factor (KLF5) is the regulation of cardiovascular remodeling. Vascular remodeling is closely related to the amelioration of various ischemic diseases. However, the underlying correlation of KLF5 and ischemia is not clear. In this study, we aim to investigate the role of KLF5 in myocardial ischemia reperfusion (IR) injury and the potential mechanisms involved. Cultured H9C2 cells were subjected to oxygen-glucose deprivation/reperfusion (OGD/Rep) to mimic myocardial IR injury in vivo. Expressions of KLF5 and PPARγ were distinctly inhibited, and PGC-1α expression was activated at 24h after myocardial OGD/Rep injury. After myocardial OGD/Rep injury, we found that KLF5 overexpression down-regulated levels of TNF-α, IL-1ß, IL-6 and IL-8. Through the analysis of lactate dehydrogenase (LDH) release, we demonstrate that KLF5 overexpression reduced the release of OGD/Rep-induced LDH. KLF5 overexpression significantly enhanced cell activity and decreased cell apoptosis during OGD/Rep injury. Compared with the OGD/Rep group, cells overexpressing KLF5 showed anti-apoptotic effects, such as decreased expression of Bax and cleaved caspase-3 as well as increased Bcl-2 expression. KLF5 overexpression activated PPARγ, a protein involved in OGD/Rep injury, and increased levels of PGC-1α, while TNF-α expression was remarkably inhibited. In addition, GW9662, a PPARγ receptor antagonist, reversed the expression of PPARγ/PGC-1α/TNF-α and cell activity induced by KLF5 overexpression. The effects of KLF5 overexpression on PPARγ/PGC-1α/TNF-α and cell activity were abolished by co-treatment with GW9662. Taken together, these results suggest that KLF5 can efficiently alleviate OGD/Rep-induced myocardial injury, perhaps through regulation of the PPARγ/PGC-1α/TNF-α pathway.