Aggregation Node Research Articles

Digital tools and technologies used in food fortification: A scoping review.

Food fortification (i.e., industrial fortification and biofortification) increases the micronutrient content of foods to improve population nutrition. Implementing effective fortification programs requires the generation and use of data to inform decision making. The use of digital tools and technologies (DTTs) for such purposes in broader nutrition programs is growing; however, there is limited consolidation of those used in fortification. This scoping review aimed to identify and describe DTTs used in fortification programs. We searched peer-reviewed and gray literature and conducted 17 stakeholder surveys. We then mapped DTTs identified against the fortification and nutrition data value chains. Of 11,741 articles identified, 158 met the inclusion criteria. From the included articles and stakeholder surveys, 125 DTTs were identified across three categories: software and tooling (n = 58), data and information lifecycle (n = 50), and hardware and infrastructure (n = 17). Gaps were identified in processing, post-harvest storage, aggregation, and transport nodes of the fortification value chain, and data prioritization, translation/dissemination, and decision-making nodes of the nutrition data value chain. DTTs have the potential to address challenges faced by fortification stakeholders to generate and use data to improve program decision making and nutritional impact. Further work is needed to standardize terminology, identify relevant DTTs from other sectors, and explore stakeholder needs.

Distributed Data Privacy Protection via Collaborative Anomaly Detection

Current anomaly detection methods for charging stations primarily rely on centralized network architectures with federated learning frameworks. However, the rapid increase in the number of charging stations and the expanding scale of these networks impose significant communication traffic loads. Consequently, it is essential to explore the relationship between data aggregation among charging stations and the anomaly detection accuracy at individual stations. In this paper, we address efficient anomaly detection in charging stations and propose a distributed anomaly detection algorithm powered by federated learning. To be specific, we introduce a distributed privacy-preserving data aggregation scheme, where a Transformer model is adopted to effectively smooth abnormal data fluctuations, minimizing disruptions to network aggregation nodes. Furthermore, we develop a distributed federated learning framework incorporating an efficient parameter update method without requiring prior knowledge or a central node. Compared with some existing detection solutions, the proposed approach significantly reduces communication bandwidth requirements while maintaining anomaly detection accuracy and mitigating data isolation issues. Extensive experiments demonstrate that the proposed algorithm not only achieves high accuracy in detecting anomalies in electric vehicle charging stations but also ensures robust user data privacy protection.

Data-Oriented Octree Inverse Hierarchical Order Aggregation Hybrid Transformer-CNN for 3D Medical Segmentation.

The hybrid CNN-transformer structures harness the global contextualization of transformers with the local feature acuity of CNNs, propelling medical image segmentation to the next level. However, the majority of research has focused on the design and composition of hybrid structures, neglecting the data structure, which enhance segmentation performance, optimize resource efficiency, and bolster model generalization and interpretability. In this work, we propose a data-oriented octree inverse hierarchical order aggregation hybrid transformer-CNN (nnU-OctTN), which focuses on delving deeply into the data itself to identify and harness potential. The nnU-OctTN employs the U-Net as a foundational framework, with the node aggregation transformer serving as the encoder. Data features are stored within an octree data structure with each node computed autonomously yet interconnected through a block-to-block local information exchange mechanism. Oriented towards multi-resolution feature data map learning, a cross-fusion module has been designed that associates the encoder and decoder in a staggered vertical and horizontal approach. Inspired by nnUNet, our framework automatically adapts network parameters to the dataset instead of using pre-trained weights for initialization. The nnU-OctTN method was evaluated on the BTCV, ACDC, and BraTS datasets and achieved excellent performance with dice score coefficient (DSC) 86.95, 92.82, and 90.61, respectively, demonstrating its generalizability and effectiveness. Cross-fusion module effectiveness and model scalability are validated through ablation experiments on BTCV and Kidney. Extensive qualitative and quantitative experimental results demonstrate that nnU-OctTN achieves high-quality 3D medical segmentation that has competitive performance against current state-of-the-art methods, providing a promising idea for clinical applications.

Metrological parameter planning method based on a multi-head sparse graph attention network for airborne products

The airborne system plays a crucial role in upholding the operational capabilities of an aircraft, and the caliber of its products significantly influences the overall reliability and safety of the aircraft. The foundational task in guaranteeing product quality is metrology, wherein metrological parameters play a pivotal role in shaping the ultimate product quality and determining metrological efficiency. Because the metrology documents are scattered in various departments and the data are highly isolated, manual planning methods are highly subjective, resulting in error-prone and inefficient results. The existing parameter planning methods based on deep learning suffer from the problems of strong training data dependency and poor model interpretability. For this reason, this paper proposes a metrological parameter planning method based on a multi-head sparse graph attention network (MHSGAT) for airborne products. First, an attribute graph structure is designed to represent product metrology information, and a metrology parameter graph dataset is constructed based on historical documents. Then, the proposed MHSGAT assigns sparse attention coefficients to the neighbors of nodes for feature aggregation. Finally, the metrology parameter planning results are output in the dense layer. The experimental results show that the proposed method outperforms the other four baseline methods. The significance of the proposed method in enhancing the metrological accuracy of airborne products and ensuring their quality is demonstrated by application cases.

A multi-scale path-planning method for large-scale scenes based on a framed scale-elastic grid map

ABSTRACT Environment modeling serves as the foundation for path planning in unmanned systems. Single-scale maps have many nodes and impose large memory requirements; tree-based multi-scale grid maps used for representing large-scale urban scenes have limited aggregation ability in the presence of dimensional anisotropy. This study proposes a novel multi-scale map-construction method based on a scale-elastic discrete grid structure. The method provides more flexible node aggregation in grid-based representations, reducing the number of grid and border-grid nodes while maintaining the same modeling accuracy. Furthermore, a novel multi-scale A* path-planning algorithm that modifies the neighborhood-expansion phase of A* is proposed to reduce the number of algorithm search nodes in framed multi-scale maps while ensuring optimal path planning. The experimental results demonstrate that the proposed map-construction method requires 71.5% fewer grids and 10.8% fewer border grids than framed-octree grid maps in three-dimensional scenarios with the same modeling accuracy. Consequently, memory requirements are smaller, making this method more efficient on devices with limited performance. The multi-scale A* algorithm also improves path-planning efficiency by reducing the number of search nodes. The proposed method is suitable for path planning in large-scale and complex urban scenes.

An improved practical Byzantine fault tolerance algorithm for aggregating node preferences

Consensus algorithms play a critical role in maintaining the consistency of blockchain data, directly affecting the system’s security and stability, and are used to determine the binary consensus of whether proposals are correct. With the development of blockchain-related technologies, social choice issues such as Bitcoin scaling and main chain forks, as well as the proliferation of decentralized autonomous organization (DAO) applications based on blockchain technology, require consensus algorithms to reach consensus on a specific proposal among multiple proposals based on node preferences, thereby addressing the multi-value consensus problem. However, existing consensus algorithms, including Practical Byzantine Fault Tolerance (PBFT), do not support nodes expressing preferences. Instead, the proposal to reach consensus is directly decided by specific nodes, with other nodes merely verifying the proposal’s validity, which can easily result in monopolistic or dictatorial outcomes. In response, we proposed the Aggregating Preferences with Practical Byzantine Fault Tolerance (AP-PBFT) consensus algorithm, which allows nodes to express preferences for multiple proposals. AP-PBFT ensures the validity of consensus results through a consensus output protocol, and incentivizes nodes to act honestly during the consensus process by incentive mechanism. First, AP-PBFT leverages Verifiable Random Function to select both consensus nodes and a primary node from the candidates. The primary node gathers proposals, assembles them into a proposal package, and broadcasts it to other consensus nodes. The consensus nodes independently vote to express their preferences for different proposals in the package, execute the consensus output protocol to reach local consensus, and the primary node aggregates these results to form the global consensus. Once the global consensus is finalized, AP-PBFT evaluates node behavior based on the consensus output protocol, penalizes nodes that acted maliciously, and rewards those that adhered to the protocol. Additionally, nodes can interact and adopt different strategies while executing the consensus output protocol, which can influence the consensus outcome. Therefore, we established an evolutionary game model based on hypergraph to analyze these interactions. Theoretical analysis shows that the incentive mechanism in AP-PBFT effectively encourages nodes to honestly follow the consensus output protocol, ensuring that AP-PBFT satisfies the properties of consistency, validity, and termination. Finally, the simulation results demonstrate that the AP-PBFT algorithm possesses good scalability and the capability to handle dynamic changes in nodes, surpassing some mainstream consensus algorithms in terms of transaction throughput and consensus achievement time. Moreover, AP-PBFT can incentivize honest behavior among consensus nodes, thereby enhancing the reliability of consensus and strengthening the security of the network.

Graph Convolutional Neural Networks With Diverse Negative Samples via Decomposed Determinant Point Processes.

Graph convolutional neural networks (GCNs) have achieved great success in graph representation learning by extracting high-level features from nodes and their topology. Since GCNs generally follow a message-passing mechanism, each node aggregates information from its first-order neighbor to update its representation. As a result, the representations of nodes with edges between them should be positively correlated and thus can be considered positive samples. However, there are more non-neighbor nodes in the whole graph, which provide diverse and useful information for the representation update. Two non-adjacent nodes usually have different representations, which can be seen as negative samples. Besides the node representations, the structural information of the graph is also crucial for learning. In this article, we used quality-diversity decomposition in determinant point processes (DPPs) to obtain diverse negative samples. When defining a distribution on diverse subsets of all non-neighboring nodes, we incorporate both graph structure information and node representations. Since the DPP sampling process requires matrix eigenvalue decomposition, we propose a new shortest-path-base method to improve computational efficiency. Finally, we incorporate the obtained negative samples into the graph convolution operation. The ideas are evaluated empirically in experiments on node classification tasks. These experiments show that the newly proposed methods not only improve the overall performance of standard representation learning but also significantly alleviate over-smoothing problems.

A robust federated learning algorithm for partially trusted environments

Due to the distributed nature of federated learning, it is vulnerable to poisoning attacks during the training process. The model’s resistance to poisoning attacks can be improved using robust aggregation algorithms. Current research on federated learning to resist poisoning attacks is mainly based on two settings: No trust or Byzantine robustness. However, both settings are not close enough to reality in practical scenarios. In many practical applications, some participants in federated learning are trustworthy. For example, participants who have participated in the training of this model before and performed very well, or participants with strong compliance and credibility such as governments and some national agencies participate in the training. In existing research, these trusted participants still have to accept the judgment of the aggregation node, which generates unnecessary computation, increases overhead, and does not take advantage of a trusted environment. Since there is no attack behavior on the trusted client, its training results are used to classify the trustworthiness of other untrusted clients and identify attack nodes with higher accuracy. Therefore, this paper proposes a robust federated learning algorithm for partially trusted environments. The proposed scheme uses the experimental results of trusted clients to judge the behavior of untrustworthy clients by the cosine similarity and the Local Outlier Factor and further identify and detect malicious clients. Experiments are performed on MNIST and CIFAR datasets. Comparison with other six aggregation algorithms under 30% attack scenario. And compared with the other four aggregation algorithms under 70% attack conditions. Our algorithm is more accurate than almost all of the other aggregation algorithms. The paper is the first to conduct robust research on federated learning in a partially trusted environment, and the proposed algorithm can more effectively resist poisoning attacks.

DGSIST: Clustering spatial transcriptome data based on deep graph structure Infomax

Although spatial transcriptomics data provide valuable insights into gene expression profiles and the spatial structure of tissues, most studies rely solely on gene expression information, underutilizing the spatial data. To fully leverage the potential of spatial transcriptomics and graph neural networks, the DGSI (Deep Graph Structure Infomax) model is proposed. This innovative graph data processing model uses graph convolutional neural networks and employs an unsupervised learning approach. It maximizes the mutual information between graph-level and node-level representations, emphasizing flexible sampling and aggregation of nodes and their neighbors. This effectively captures and incorporates local information from nodes into the overall graph structure. Additionally, this paper developed the DGSIST framework, an unsupervised cell clustering method that integrates the DGSI model, SVD dimensionality reduction algorithm, and k-means++ clustering algorithm. This aims to identify cell types accurately. DGSIST fully uses spatial transcriptomics data and outperforms existing methods in accuracy. Demonstrations of DGSIST’s capability across various tissue types and technological platforms have shown its effectiveness in accurately identifying spatial domains in multiple tissue sections. Compared to other spatial clustering methods, DGSIST excels in cell clustering and effectively eliminates batch effects without needing batch correction. DGSIST excels in spatial clustering analysis, spatial variation identification, and differential gene expression detection and directly applies to graph analysis tasks, such as node classification, link prediction, or graph clustering. Anticipation lies in the contribution of the DGSIST framework to a deeper understanding of the spatial organizational structures of diseases such as cancer.

Decentralized collaborative machine learning for protecting electricity data

In recent years, there has been a noticeable surge in electric power load due to economic development and improved living standards. The growing need for smart power solutions, such as leveraging user electricity data to forecast power peaks and utilizing power data statistics to enhance end-user services, has been on the rise. However, the misuse and unauthorized access of data have prompted stringent regulations to safeguard data integrity. This paper presents a novel decentralized collaborative machine learning framework aimed at predicting peak power loads while protecting the privacy of users’ power data. In this scheme, multiple users engage in collaborative machine learning training within a peer-to-peer network free from a centralized server, with the objective of predicting peak power loads without compromising users’ local data privacy. The proposed approach leverages blockchain technology and advanced cryptographic techniques, including multi-key homomorphic encryption and consistent hashing. Key contributions of this framework include the development of a secure dual-aggregate node aggregation algorithm and the establishment of a verifiable process within a decentralized architecture. Experimental validation has been conducted to assess the feasibility and effectiveness of the proposed scheme, demonstrating its potential to address the challenges associated with predicting peak power loads securely and preserving user data privacy.

B2DFL: Bringing butterfly to decentralized federated learning assisted with blockchain

We propose a novel decentralized federated learning framework called B2DFL. It decomposes the aggregation process of vanilla FL into layered and serialized sub-aggregation processes and offloads the communication and computation from a single point to distributed nodes, thus addressing the single point of failure issue in centralized FL. The decentralization of B2DFL is based on the Butterfly, a distributed network topology, to organize and orchestrate the order and rules of node aggregation. Additionally, to mitigate potential risks such as dropouts or tampering, we leverage the blockchain and IPFS systems. Specifically, after each node completes its computation (including training and aggregation), it generates a hash value of the results as proof. We maintain a Tamper-evident Data Structure (TDS) on the blockchain, which records these proofs to ensure tamper-proofing and fast verification. To reduce the storage burden on the blockchain and improve throughput, we store the aggregated results on IPFS, a system that enables quick data location through hash values of data, for data backup. We also design a node replacement mechanism for quick dropout handling. We conduct a comprehensive performance evaluation and experimental results demonstrate that B2DFL presents a significant performance improvement while achieving privacy and decentralization.

A dual graph neural networks model using sequence embedding as graph nodes for vulnerability detection

Context:Detecting critical to ensure software system security. The traditional static vulnerability detection methods are limited by staff expertise and perform poorly with today’s increasingly complex software systems. Researchers have successfully applied the techniques used in NLP to vulnerability detection as deep learning has developed. The existing deep learning-based vulnerability detection models can be divided into sequence-based and graph-based categories. Sequence-based embedding models cannot use structured information embedded in the code, and graph-based embedding models lack effective node representations. Objective:To solve these problems, we propose a deep learning-based method, DGVD (Double Graph Neural Network for Vulnerability Detection). Methods:We use the sequential neural network approach to extract local semantic features of the code as nodes embedded in the control flow graph. First, we propose a dual graph neural network module (DualGNN) that consists of GCN and GAT. The altered module utilizes two different graph neural networks to obtain the global structural information of the control flow and the relationship between the nodes and fuses the two. Second, we propose a convolution-based feature enhancement module (TC-FE) that uses different convolution kernels of different sizes to capture information at different scales so that subsequent readout layers can better aggregate node information. Results:Experiments demonstrate that DGVD outperforms existing models, obtaining 64.23% vulnerability detection accuracy on CodeXGLUE’s real benchmark dataset. Conclusion:The proposed DGVD achieves better performance than the state-of-the-art DGVD has a more effective source code feature extraction capability on real-world datasets.

Adaptive and Priority-Based Data Aggregation and Scheduling Model for Wireless Sensor Network

Wireless Sensor Networks (WSN) use sensor nodes placed in potential places to collect sensitive information. These sensor nodes monitor necessary data and send it to the sink node. Sensor nodes have resource constraints, especially energy and power depletion. The majority of sensor and battery power is wasted on redundant data transmission. The redundant data transmission consumes a significant amount of the sensor and battery life, decreasing the total lifespan of the sensor nodes. Data aggregation is an approach that expands the useful lifetime of sensor nodes overall and removes unnecessary data and delays. There are many types of data aggregation techniques, such as centralized, tree-based, in-network, and cluster-based. The available tree-based data aggregation mechanism performs well, but the whole tree may be down due to single-node failure. Due to bottlenecks, node data aggregation suffers from an increased packet failure ratio. Another limitation is that every node aggregates data into slices, which consumes more energy. For this purpose, an adaptive and priority-based data aggregation and scheduling model (APB-DASM) for WSNs is proposed in this paper to address these issues. It is proposed that APB-DASM be used to improve quality of service (QoS) with regard to energy consumption and data transmission. The APB-DASM model aggregates sensor data into cluster heads and divides it into three formats: The first format categorizes the most important data that consists of four slices, and the second format categorizes the important data that consists of three slices. Format three data is represented in two slices, which is normal data. These three types of format data are aggregated on a priority basis, such that the highest priority is given to the first format, i.e., most important data; moderate priority is given to the second format, i.e., important data; and then low priority is given to the normal data. Due to an efficient priority-based data aggregation and scheduling algorithm, our proposed model sends the most important data first, and so on. Theoretical study and simulation research demonstrate that our proposed approach improves the existing tree-based models. By using APB-DASM, significant decreases in energy usage, packet delivery ratio, and overall QoS are achieved, and as a result, the WSNs' lifetime is thus increased. The proposed model is implemented in MATLAB, and the results are compared with existing tree-based models. Simulations comparing our model to the most recent models indicate that it worked effectively, reducing the packet failure ratio and energy usage by 36.8% and 30%, respectively, for CBF-ADA, D-SMART, and WDARS. This article emphasizes how the suggested methodology can be effectively used in the aggregation of coronavirus patient data. It demonstrates how adaptable and applicable our method is in the real world.

Predicting lncRNA-Disease Associations Based on a Dual-Path Feature Extraction Network with Multiple Sources of Information Integration.

Identifying the associations between long noncoding RNAs (lncRNAs) and disease is critical for disease prevention, diagnosis and treatment. However, conducting wet experiments to discover these associations is time-consuming and costly. Therefore, computational modeling for predicting lncRNA-disease associations (LDAs) has become an important alternative. To enhance the accuracy of LDAs prediction and alleviate the issue of node feature oversmoothing when exploring the potential features of nodes using graph neural networks, we introduce DPFELDA, a dual-path feature extraction network that leverages the integration of information from multiple sources to predict LDA. Initially, we establish a dual-view structure of lncRNAs and disease and a heterogeneous network of lncRNA-disease-microRNA (miRNA) interactions. Subsequently, features are extracted using a dual-path feature extraction network. In particular, we employ a combination of a graph convolutional network, a convolutional block attention module, and a node aggregation layer to perform multilayer topology feature extraction for the dual-view structure of lncRNAs and diseases. Additionally, we utilize a Transformer model to construct the node topology feature residual network for obtaining node-specific features in heterogeneous networks. Finally, XGBoost is employed for LDA prediction. The experimental results demonstrate that DPFELDA outperforms the benchmark model on various benchmark data sets. In the course of model exploration, it becomes evident that DPFELDA successfully alleviates the issue of node feature oversmoothing induced by graph-based learning. Ablation experiments confirm the effectiveness of the innovative module, and a case study substantiates the accuracy of DPFELDA model in predicting novel LDAs for characteristic diseases.

Morphological examination of the visual system and orbital region in the red panda (Ailurus fulgens fulgens)

ObjectivesThe red panda is currently the only surviving member of the Ailuridae family in the Caniformia suborder. In this study, we provide data on anatomical, morphometric, histological and histochemical examination of the orbital region, eyelids, orbital gland, and eye tunics in two adult males Ailurus fulgens fulgens from the Wroclaw Zoological Garden, Poland.MethodsThe study involved morphometric analysis of the eyeball and selected accessory organs of the eye, along with analysis of the bony orbit, including its morphometry, macroscopic, and microscopic evaluation. Microscopic evaluation encompassed histological and histochemical staining, with the former involving hematoxylin & eosin (H&E), Movat pentachrome, picro-Mallory trichrome, Fontana-Masson, and the latter including PAS, AB pH 1.0, AB pH 2.5; AB pH 2.5/PAS, and HDI.ResultsThe upper (UE) and lower (LE) eyelids presented well-developed tarsal glands, sebaceous glands, and a characteristic simple alveolar gland (producing a mucous secretion). The palpebral part of the lacrimal gland was present. A single lymphoid follicle was observed only in the upper eyelids. The superficial gland of the third eyelid (SGTE) was a multilobar acinar complex that produces mucous secretion and is contained within the interlobular ducts of numerous aggregates of lymph nodes. The third eyelid (TE) was T-shaped and composed of hyaline tissue, containing CALT. The lacrimal gland (LG) also revealed a multilobar acinar complex that produced mucous secretion, with a single lymphoid follicle. The cornea consisted of 4 layers, as Bowman’s membrane was absent. The Vogt palisades composed of 7–10 layers of epithelial cells were demonstrated. The pupil was horizontally ovoid at rest (post-mortem). The sphincter pupil and the dilator pupil were well developed. Macroscopically, the tapetum lucidum appeared as a milky, non-opalescent crescent. Histologically, the choroidal tapetum lucidum cellulosum consisted of 5 to 9 layers of loosely packed oval cells. The retina showed a composition similar to that of terrestrial nocturnal carnivores.ConclusionsThe results of our research indicate that the anatomical features of the eye and orbital region in the red panda share similarities with those described in the Musteloidea clade, as well as the Canidae and Ursidae families.

GNN-MgrPool: Enhanced graph neural networks with multi-granularity pooling for graph classification

Graph neural networks (GNNs) have gained sufficient attention and are applied to various domain tasks. At present, numerous pooling approaches are being proposed to aggregate node features and obtain node embeddings. However, current GNNs are black-box models that typically use a flat or single pooling step to aggregate nodes, which only considers the similarity between nodes within the cluster. These approaches ignore the influence of relationships within and between clusters in the learning process. To address this issue, we propose a novel multi-granular pooling method that aggregates nodes by simultaneously considering density and relationships among nodes and clusters. This method allows us to obtain multi-granular node-embedding clusters from GNN layers. The clusters in the current layer are built upon those in the previous layer, and these clusters change from fine to coarse as the number of clusters decreases during learning, which is achieved by using multi-granular pooling (MgrPool). Additionally, there is an inclusion relation between adjacent layers, and the node representation of each layer is established through the ratio of node distance within clusters to that between clusters. Finally, we conducted several experiments on node and graph classification tasks by combining GNN models with this pooling approach. The results demonstrate that our GNN-MgrPool model outperforms similar state-of-the-art algorithms and largely improves the interpretability of the learning process.

Monitoring and management of green information in water ecological environment based on sensors and big data

With the continuous development of industrial production, the pollution of water resources is becoming more and more serious, and the damage to aquatic organisms is also increasing. Therefore, strengthening water environment monitoring has become a key measure to prevent and solve this problem. Aiming at the limitation of traditional water environment monitoring methods, a water ecological environment monitoring scheme is proposed. This study uses advanced sensor technology, including water quality sensor, water level sensor, weather sensor, etc., to monitor the indicators of water in real time. Through data acquisition and storage technology, the data obtained by the sensor is integrated and analyzed. At the same time, big data analysis method is used to predict and simulate the change trend of water ecological environment. This scheme designs and develops a sensor network monitoring system, which can collect water temperature data in real time at the monitoring point, transmit the sampled information to the aggregation node through the sensor network, and finally transmit to the information intelligent monitoring equipment through GPRS, so as to realize timely display and early warning. At the same time, combined with the water quality monitoring instrument, it can realize the remote query and processing of monitoring data. The experimental results show that the water ecological environment monitoring and management system based on sensor and big data technology can efficiently and accurately monitor the indicators of water. Through the comprehensive monitoring of the water ecological environment, abnormal situations can be found in time, and corresponding measures can be taken to protect and repair. The results of big data analysis provided by the system can provide scientific basis and guidance for decision makers.

Reinventing gene expression connectivity through regulatory and spatial structural empowerment via principal node aggregation graph neural network.

The intricacies of the human genome, manifested as a complex network of genes, transcend conventional representations in text or numerical matrices. The intricate gene-to-gene relationships inherent in this complexity find a more suitable depiction in graph structures. In the pursuit of predicting gene expression, an endeavor shared by predecessors like the L1000 and Enformer methods, we introduce a novel spatial graph-neural network (GNN) approach. This innovative strategy incorporates graph features, encompassing both regulatory and structural elements. The regulatory elements include pair-wise gene correlation, biological pathways, protein-protein interaction networks, and transcription factor regulation. The spatial structural elements include chromosomal distance, histone modification and Hi-C inferred 3D genomic features. Principal Node Aggregation models, validated independently, emerge as frontrunners, demonstrating superior performance compared to traditional regression and other deep learning models. By embracing the spatial GNN paradigm, our method significantly advances the description of the intricate network of gene interactions, surpassing the performance, predictable scope, and initial requirements set by previous methods.

Visualization analysis of research progress and trends in coexistence of lung cancer and pulmonary tuberculosis using bibliometrics

AbstractBackgroundThe incidence of lung cancer combined with pulmonary tuberculosis has been increasing, but there is relatively limited published literature on the topic of lung cancer combined with tuberculosis (LC‐PTB) from a bibliometric perspective. Therefore, in this study, we aimed to quantitatively analyze the LC‐PTB‐related literature to better understand the current status of this field and identify future research trends.MethodsWe searched for articles related to LC‐PTB using the Web of Science Core Collection (SCI‐E) and conducted a visual analysis of publication quantity, countries, institutions, authors, journals, references, and keywords using bibliometric software (CiteSpace, VOSviewer, and Scimago Graphica).ResultsAs of January 8, 2024, a total of 460 publications related to LC‐PTB were included for analysis from 3705 retrieved records. The number of publications has been increasing almost yearly, with most from China (n = 123), followed by the United States (n = 77). Taipei Medical University contributed the most publications (n = 11). Jing‐Yang Huang and Yung‐Po Liaw (eight documents each) ranked first among the included authors. The Journal of Thoracic Oncology was the most productive academic journal on LC‐PTB. The aggregation of key nodes in the co‐citation network and the chronological sequence indicated that LC‐PTB research has shifted from initial hotspots such as lung diseases, bronchitis, and exposure to recent areas, including immunotherapy, immune checkpoint inhibitors, and nivolumab.ConclusionIn this study, we visualized the current status of LC‐PTB research as well as future trends using bibliometric methods, providing new insights into the differential diagnosis of LC‐PTB and its related promoting mechanisms.

Multi-source data integration for explainable miRNA-driven drug discovery

Explainable drug discovery driven by miRNA offers substantial application potential due to the high targetability of miRNAs. Despite their effectiveness, the current graph neural network (GNN)-based methods encounters three significant challenges. Initially, GNN-based prediction models, disseminating messages throughout the miRNA–disease graph, are susceptible to “over-smoothing”. Secondly, these approaches frequently pinpoint potential miRNA drugs through established miRNA–disease associations (MDAs), neglecting the possible interdependence between unvalidated miRNAs and diseases. Thirdly, the lack of interpretability in these models, coupled with their dependence on specific dataset training, leads to suboptimal generalization capabilities. We present MS-EMD, an explainable model for miRNA-driven drug discovery that integrates subgraph estimation with an energy-constrained diffusion approach. This model aims to accurately forecast potential miRNA drugs by analyzing data from both local and global viewpoints. The MS-EMD model utilizes subgraph estimation to aggregate and update node representations using local subgraphs, thereby preventing over-smoothing. Simultaneously, it unveils potential miRNA–disease dependencies through a global attention mechanism driven by an energy-constrained diffusion process, improving model interpretability. Furthermore, we employ a data fusion technology that integrates diverse similarity data to strengthen the initial representations of miRNAs and diseases. Through various comparison and ablation studies, we verified the MS-EMD model’s efficiency and stability, highlighting its potential as an explainable tool for miRNA-driven drug discovery. Our code and data are available at: https://github.com/lizhen5000/MS-EMD.git.