Related Datasets Research Articles

Identification and validation of NAD+ metabolism-related biomarkers in patients with diabetic peripheral neuropathy.

The mechanism of Nicotinamide Adenine Dinucleotide (NAD+) metabolism-related genes (NMRGs) in diabetic peripheral neuropathy (DPN) is unclear. This study aimed to find new NMRGs biomarkers in DPN. DPN related datasets GSE95849 and GSE185011 were acquired from the Gene Expression Omnibus (GEO) database. 51 NMRGs were collected from a previous article. To explore NMRGs expression in DPN and control samples, differential expression analysis was completed in GSE95849 to obtain differentially expressed genes (DEGs), and the intersection of DEGs and NMRGs was regarded as DE-NMRGs. Next, a protein-protein interaction (PPI) network based on DE-NMRGs was constructed and biomarkers were screened by eight algorithms. Additionally, Gene Set Enrichment Analysis (GSEA) enrichment analysis was completed, biomarker-based column line graphs were constructed, lncRNA-miRNA-mRNA and competing endogenouse (ce) RNA networks were constructed, and drug prediction was completed. Finally, biomarkers expression validation was completed in GSE95849 and GSE185011. 5217 DEGs were obtained from GSE95849 and 21 overlapping genes of DEGs and NMRGs were DE-NMRGs. Functional enrichment analysis revealed that DE-NMRGs were associated with glycosyl compound metabolic process. The PPI network contained 93 protein-interaction pairs and 21 nodes, with strong interactions between NMNAT1 and NAMPT, NADK and NMNAT3, ENPP3 and NUDT12 as biomarkers based on 8 algorithms. Expression validation suggested that ENPP3 and NUDT12 were upregulated in DPN samples (P < 0.05). Moreover, an alignment diagram with good diagnostic efficacy based on ENPP3 and NUDT12 were identified was constructed. GSEA suggested that ENPP3 was enriched in Toll like receptor (TLR) pathway, NUDT12 was enriched in maturity onset diabetes of the young and insulin pathway. Furthermore, 18 potential miRNAs and 36 Transcription factors (TFs) were predicted and the miRNA-mRNA-TF networks were constructed, suggesting that ENPP3 might regulate hsa-miR-34a-5p by affecting MYNN. The ceRNA network suggested that XLOC_013024 might regulate hsa-let-7b-5p by affecting NUDT12. 15 drugs were predicted, with 8 drugs affecting NUDT12 such as resveratrol, and 13 drugs affecting ENPP3 such as troglitazone. ENPP3 and NUDT12 might play key roles in DPN, which provides reference for further research on DPN.

Navigating energy diplomacy in times of recovery and conflict: A study of cross-border energy trade dynamics

Recent geopolitical crises have underlined the importance of understanding when and how energy interdependence affects international politics. While scholars have extensively debated the link between international politics and international trade in general terms, systematic analyses gauging how energy interdependence shapes interstate relations have recently begun to emerge. To facilitate research on this topic, this study asks whether energy relations between states shape their foreign policy decisions. Using the recently released Global Energy Relations Dataset and United Nations General Assembly Voting Data, our study shows strong support for the hypothesis that energy interdependence increases dyadic foreign policy affinity. Moreover, out of four primary energy resources (i.e. coal, oil, natural gas, and electricity), trade in oil appears to be a strong motivator for trading states' foreign policy preferences to converge.

Deep learning-based low overlap point cloud registration for complex scenario: The review

Most studies on point cloud registration have established the problem in the case of ideal point cloud data. Although the state-of-the-art approaches have achieved amazing results on multiple public datasets, the issue of low overlap point cloud data invalidating state-of-the-art methods is acting as a latent challenge that has not been solved. Therefore, a profound analysis about why existing registration architectures break down in the low-overlap regime and how to select the appropriate strategies to improve the low overlap point cloud correspondence estimation is necessary and useful. Unfortunately, there are few survey works about low overlap cloud registration solving strategies and the corresponding datasets are very limited. This work briefly reviews mainstream deep learning-based point cloud registration and provides an in-depth analysis of the reasons why these architectures are not generalizable to scenarios with low overlapping areas. It is the first survey that mainly focuses on representative low overlap registration methods, their techniques, and related datasets for training/testing. It is worth noting that we also design and construct a large 3D dataset to eliminate the gap in Semantic-assisted point cloud registration with low overlap. Finally, challenges about low overlap point cloud registration and future directions in addressing these challenges are also pointed out. [dataset]

Uranium Dissemination with Phosphate Fertilizers Globally: A Systematic Review with Focus on East Africa

Growing concern has been expressed about uranium (U) accumulation in agricultural soils caused by the long-term application of mineral fertilizers. More than 80% of naturally occurring U transfers from phosphate rock (PR), the raw material used in mineral fertilizer production, to phosphorus (P) fertilizers. These fertilizers are then distributed on agricultural soils, where the U could accumulate over time and become a risk to the environment. The objective of this work was to review the reported content of U in P fertilizers, its potential dispersion in soils, and its uptake by plants in different countries in the world as reported in the literature. The articles for this systematic review were selected from the Scopus database published between 2003 and 2022. The preferred reporting items for systematic reviews and meta-analyses (PRISMA) protocol were used. A total of 54 articles were assessed based on the standard inclusion and exclusion criteria. U concentrations in P fertilizers, agricultural soil dissemination, and plant uptake for available data were obtained and assessed. In order to compare a set of related data from the collected articles, box and whisker plots showing the distribution of U in P fertilizers are presented by region. The results from the reviewed articles show that the U concentrations in P fertilizer were in the range of 0.1–653 mg kg−1. Interestingly, Minjingu P fertilizers from Tanzania, which are used in six East African countries, showed the highest U concentrations (159 to 653 mg kg−1, average 390 mg kg−1). The reported U concentrations for these fertilizers are, in fact, comparable to those of conventional low-grade uranium deposits mined in Namibia and elsewhere. Additionally, approximately 96% of the reviewed articles indicate that fertilized soil has higher U concentrations than non-fertilized soils, hinting at a measurable effect of mineral fertilizer use. The review recommends U extraction during mineral fertilizer production so that potential environmental risks can be reduced and U resources that would otherwise be lost can be recovered and used to substitute conventional U mining elsewhere.

A Scalable Method for Readable Tree Layouts.

Large tree structures are ubiquitous and real-world relational datasets often have information associated with nodes (e.g., labels or other attributes) and edges (e.g., weights or distances) that need to be communicated to the viewers. Yet, scalable, easy to read tree layouts are difficult to achieve. We consider tree layouts to be readable if they meet some basic requirements: node labels should not overlap, edges should not cross, edge lengths should be preserved, and the output should be compact. There are many algorithms for drawing trees, although very few take node labels or edge lengths into account, and none optimizes all requirements above. With this in mind, we propose a new scalable method for readable tree layouts. The algorithm guarantees that the layout has no edge crossings and no label overlaps, and optimizes one of the remaining aspects: desired edge lengths and compactness. We evaluate the performance of the new algorithm by comparison with related earlier approaches using several real-world datasets, ranging from a few thousand nodes to hundreds of thousands of nodes. Tree layout algorithms can be used to visualize large general graphs, by extracting a hierarchy of progressively larger trees. We illustrate this functionality by presenting several map-like visualizations generated by the new tree layout algorithm.

Three‐dimensional mapping and immersive human–robot interfacing utilize Kinect‐style depth cameras and virtual reality for agricultural mobile robots

AbstractNavigation and autonomous operation in farmland or greenhouse environments present significant challenges for agricultural mobile robots on account of unstructured scene conditions and complex task requirements. The immersive interfaces based on human–robot interaction have been extensively developed, which bridge the high‐level decision of human beings and the precise sensing and high motion ability of robots. In this study, we propose a human–robot interaction framework based on three‐dimensional mapping and virtual reality (VR) visualization. On the construction client, dense three‐dimensional point‐cloud maps are created based on the simultaneous localization and mapping real‐time appearance‐based mapping algorithm with a Kinect‐style depth camera. Subsequently, point‐cloud filtering and mesh creation methods are introduced for postprocessing the map models. A data communication network is employed to transmit the optimized models to the VR‐based exploration client. Utilizing VR visualization, the operator can gain an intuitive and comprehensive understanding of the environments to be explored. The three‐dimensional agricultural scenes are mapped into VR models through the system, which can combine the physical worlds with the VR spaces in a better manner. Compared with the video streaming‐based method for three‐dimensional mapping, the map models with colors and textures are entirely displayed in the VR headset, thus providing robust and global human–robot interaction interfaces and enhancing the immersive exploration for human beings to a considerable extent. Experimental results indicate that the three‐dimensional map models exhibit relatively sufficient construction integrity and yield favorable optimization effects. Additionally, according to a user questionnaire survey, immersive VR‐based interfaces can be more effectively utilized for the three‐dimensional mapping of mobile robots. Research evidence and results demonstrate that our proposed system framework offers positive assistance and support for enhancing human–robot interaction and executing specific robotic tasks in unstructured field agricultural environments. Code implementation and related data sets are shared at the link https://github.com/WangDongBUAA/Mapping_Interfacing.

Causal association between 637 human metabolites and ovarian cancer: a mendelian randomization study

BackgroundCurrent evidence suggests a significant association between metabolites and ovarian cancer (OC); however, the causal relationship between the two remains unclear. This study employs Mendelian randomization (MR) to investigate the causal effects between different metabolites and OC.MethodsIn this study, a total of 637 metabolites were selected as the exposure variables from the Genome-wide Association Study (GWAS) database (http://gwas.mrcieu.ac.uk/datasets/). The OC related GWAS dataset (ieu-b-4963) was chosen as the outcome variable. R software and the TwoSampleMR package were utilized for the analysis in this study. MR analysis employed the inverse variance-weighted method (IVW), MR-Egger and weighted median (WM) for regression fitting, taking into consideration potential biases caused by linkage disequilibrium and weak instrument variables. Metabolites that did not pass the tests for heterogeneity and horizontal pleiotropy were considered to have no significant causal effect on the outcome. Steiger’s upstream test was used to determine the causal direction between the exposure and outcome variables.ResultsThe results from IVW analysis revealed that a total of 31 human metabolites showed a significant causal effect on OC (P < 0.05). Among them, 9 metabolites exhibited consistent and stable causal effects, which were confirmed by Steiger’s upstream test (P < 0.05). Among these 9 metabolites, Androsterone sulfate, Propionylcarnitine, 5alpha-androstan-3beta,17beta-diol disulfate, Total lipids in medium VLDL and Concentration of medium VLDL particles demonstrated a significant positive causal effect on OC, indicating that these metabolites promote the occurrence of OC. On the other hand, X-12,093, Octanoylcarnitine, N2,N2-dimethylguanosine, and Cis-4-decenoyl carnitine showed a significant negative causal association with OC, suggesting that these metabolites can inhibit the occurrence of OC.ConclusionsThe study revealed the complex effect of metabolites on OC through Mendelian randomization. As promising biomarkers, these metabolites are worthy of further clinical validation.

Logic-Based Explainable and Incremental Machine Learning

Mainstream machine learning methods lack interpretability, explainability, incrementality, and data-economy. We propose using logic programming (LP) to rectify these problems. We discuss the FOLD family of rule-based machine learning algorithms that learn models from relational datasets as a set of default rules. These models are competitive with state-of-the-art machine learning systems in terms of accuracy and execution efficiency. We also motivate how logic programming can be useful for theory revision and explanation based learning.

Data Issues in High-Definition Maps Furniture – A Survey

The rapid advancements in sensing techniques, networking, and artificial intelligence (AI) algorithms in recent years have brought autonomous driving vehicles closer to common use in vehicular transportation. One of the fundamental components to enable autonomous driving functionalities are High-Definition (HD) maps – a type of map that carries highly accurate and much richer information than conventional maps. The creation and use of HD maps rely on advances in multiple disciplines, such as computer vision/object perception, geographic information systems, sensing, simultaneous localization and mapping, machine learning, etc. To date, several survey papers have been published describing the literature related to HD maps and their use in specialized contexts. In this survey, we aim to provide (1) a comprehensive overview of the issues and solutions related to HD maps and their use without attachment to a particular context; (2) a detailed coverage of the important domain knowledge of HD map furniture, from acquisition techniques and extraction approaches, through HD map–related datasets, to furniture quality assessment metrics, for the purpose of providing a comprehensive understanding of the entire workflow of HD map furniture generation, as well as its use.

The impact of the innovative performance of the country on its economic development

Innovations are a way how to improve the quality of life, support sustainable solutions, attract talent, increase competitiveness, or increase GDP. The aim of the article is to verify the dependence of GDP per capita on the innovation performance of the country by the regression and correlation analysis. The secondary data contained in the European Innovation Scoreboard 2023 (for the innovation performance) and the related EUROSTAT datasets within the EU countries (for the level of countries‵ wealth) were used. According to the results, there is a significant interdependence between innovation performance of the country and its wealth. There have not been many empirical studies realized in Slovakia yet. The author herself dealt with the evaluation of the innovation performance of the SR in her previous studies. Her motivation is to use quantitative method to analyse this issue in a more detail.

CMF defects database: A craniomaxillofacial defects dataset and a data-driven repair method

Due to the large number of medical images generated each year, data-driven machine learning methods hold great promise in the field of medical image diagnosis and analysis. In recent years, the application of deep neural networks in oral and cranio-maxillofacial surgery has gradually increased, helping surgeons to obtain more comprehensive information and develop more accurate treatment planning, including segmentation and recognition of anatomical structures, disease diagnosis, and automatic surgical planning. This paper presents a new dataset of maxillofacial defect images, containing computed tomography (CT) data of 125 normal human cranial skeletal 3D reconstructions and 2625 corresponding craniomaxillofacial bone defects. The data are classified according to seven different types of defects which are anterior skull and forehead, zygomatic arch, zygomatic bone, Naso-orbital-ethmoidal (NOE), wall of the maxillary sinus, mandibular body, mandibular ramus, and condylar respectively. Each kind of defect is further divided into three categories according to the different locations, including left side, right side, and bilateral sides (or defect passes through the midline of the face). There are three main contributions: first, a dataset is publicly available to assist researchers in the development of data-based methods for generating missing portions of the skull; second, a repair method is proposed to evaluate the dataset; third, a review of various related datasets. The release of this dataset aims to advance artificial intelligence methods in the field of oral and cranio-maxillofacial surgery and plastic surgery helping physicians to reduce the difficulty and time consumption while improving the efficiency and accuracy of prosthesis design.

Instance Segmentation of Underwater Images by Using Deep Learning

Based on deep learning, an underwater image instance segmentation method is proposed. Firstly, in view of the scarcity of underwater related data sets, the size of the data set is expanded by measures including image rotation and flipping, and image generation by a generative adversarial network (GAN). Next, the underwater image data set is finally constructed by manual labeling. Then, in order to solve the problems of color shift, blur and the poor contrast of optical images caused by the complex underwater environment and the attenuation and scattering of light, an underwater image enhancement algorithm is used to first preprocess the data set, and several algorithms are discussed, including multi-scale Retinex (MSRCR) with color recovery, integrated color model (ICM), relative global histogram stretching (RGHS) and unsupervised color correction (UCM), as well as the color shift removal proposed in this work. Specifically, the results indicate that the proposed method can largely increase the segmentation mAP (mean average precision) by 85.7% compared with without the pretreatment method. In addition, based on the characteristics of the constructed underwater dataset, the feature pyramid network (FPN) is improved to some extent, and the preprocessing method is further combined with the improved network for experiments and compared with other neural networks to verify the effectiveness of the proposed method, thus achieving the effect and purpose of improving underwater image instance segmentation and target recognition. The experimental analysis results show that the proposed model can achieve a mAP of 0.245, which is about 1.1 times higher than other target recognition models.

A social media analysis of quarantined passengers’ social-supported coping and resilience-building experiences

Cruise lines are adopting onboard quarantine as part of emergency response measures to the global pandemic. However, little is known about the social support embedded in the social-mediated communication process to assist passengers in coping and building resilience. Guided by the conservation of resource theory, this study adopted the netnography approach to analyze the online interactions between quarantined passengers on Diamond Princess and netizens. A qualitative approach was employed to analyze the content of a relational dataset consisting of 14 research subjects, 3,368 posts, and 67,964 comments. The results not merely showed the changing foci of the comments over time but also revealed the supporting role played by social media. The constant engagement with netizens provided passengers with information and social support, which contributed to their coping and resilience-building. These findings offer a new theoretical perspective on incorporating social media in tourism crisis management, as well as practical implications for cruise lines and tourism organizations to optimize their resource utilization for marketing recovery.

RPEMHC: improved prediction of MHC-peptide binding affinity by a deep learning approach based on residue-residue pair encoding.

Binding of peptides to major histocompatibility complex (MHC) molecules plays a crucial role in triggering T cell recognition mechanisms essential for immune response. Accurate prediction of MHC-peptide binding is vital for the development of cancer therapeutic vaccines. While recent deep learning-based methods have achieved significant performance in predicting MHC-peptide binding affinity, most of them separately encode MHC molecules and peptides as inputs, potentially overlooking critical interaction information between the two. In this work, we propose RPEMHC, a new deep learning approach based on residue-residue pair encoding to predict the binding affinity between peptides and MHC, which encode an MHC molecule and a peptide as a residue-residue pair map. We evaluate the performance of RPEMHC on various MHC-II-related datasets for MHC-peptide binding prediction, demonstrating that RPEMHC achieves better or comparable performance against other state-of-the-art baselines. Moreover, we further construct experiments on MHC-I-related datasets, and experimental results demonstrate that our method can work on both two MHC classes. These extensive validations have manifested that RPEMHC is an effective tool for studying MHC-peptide interactions and can potentially facilitate the vaccine development. The source code of the method along with trained models is freely available at https://github.com/lennylv/RPEMHC.

Combinatorial discovery of antibacterials via a feature-fusion based machine learning workflow.

The discovery of new antibacterials within the vast chemical space is crucial in combating drug-resistant bacteria such as methicillin-resistant Staphylococcus aureus (MRSA). However, the traditional approach of screening the entire chemical library in an ergodic manner can be laborious and time-consuming. Machine learning-assisted screening of antibacterials alleviates the exploration effort but suffers from the lack of reliable and related datasets. To address these challenges, we devised a combinatorial library comprising over 110 000 candidates based on the Ugi reaction. A focused library was subsequently generated through uniform sampling of the entire library to narrow down the preliminary screening scale. A novel feature-fusion architecture called the latent space constraint neural network was developed which incorporated both fingerprint and physicochemical molecular descriptors to predict the antibacterial properties. This integration allowed the model to leverage the complementary information provided by these descriptors and improve the accuracy of predictions. Three lead compounds that demonstrated excellent efficacy against MRSA while alleviating drug resistance were identified. This workflow highlights the integration of machine learning with the combinatorial chemical library to expedite high-quality data collection and extensive data mining for antibacterial screening.

NeSyKHG: Neuro-Symbolic Knowledge Hypergraphs

In the rapidly evolving landscape of artificial intelligence, there is an escalating demand for enhanced reasoning capabilities and robust representation of higher-order relationships. Despite their prowess in pattern identification and generalization, Neural networks often grapple with challenges linked to interpretability and the absence of explicit relational reasoning. Symbolic logic, on the other hand, excels in formal knowledge representation and inference yet remains limited in deriving knowledge directly from data. We introduce the Neuro-Symbolic Knowledge Hypergraphs (NeSyKHG) framework to bridge this gap. This innovative model synergistically merges the strengths of neural networks and symbolic logic, offering an optimized representation and reasoning system for higher-order relationships using knowledge hypergraphs. Our empirical evaluations on the Chinese Medical High-order Relational (CMHR) dataset revealed that NeSyKHG significantly outperforms several established baseline models. Specifically, when compared to models such as Hypergraph Neural Networks (HGNN), Hypergraph Convolutional Networks (HyperGCN), Logical Hypergraph Link Prediction (LHP), and Universal Graph Convolutional Networks (UniGCN), NeSyKHG achieved an F1-score of 0.845, an accuracy (ACC) of 0.947, and an area under the curve (AUC) of 0.965. These metrics underscore NeSyKHG's exceptional ability in higher-order relational learning and reasoning.

A Multimodal Semantic Analysis of the Integration of Contemporary Literary Appreciation into College Teaching and Learning

Abstract With the development of the times, the cultivation of literary appreciation ability in the education system of colleges and universities has been gradually emphasized. This paper constructs a multimodal semantic analysis model based on text feature extraction, image feature extraction and audio feature extraction, and after fusing multiple modalities, combines them with sentiment semantic Analysis, optimizes them through the self-attention mechanism module, and finally constructs a sentiment semantic analysis model based on multimodal feature fusion. Through the performance analysis of the multimodal feature emotion semantic model, the algorithm model accuracy of this paper is as high as 89%, and the recognition accuracy of emotion is stable at about 80~85%. The multimodal sentiment semantic model proposed in this paper has an accuracy rate higher than 80% on literature appreciation related datasets. In the empirical evidence of literature appreciation, the average recognition accuracy rate of emotions expressed in literature is 62.80%. The study provides an achievable path for the multimodal semantic Analysis of contemporary literature appreciation integrated into college teaching, which is of practical significance for developing literature appreciation teaching in colleges and universities.

ERDAP: A Novel Method of Event Relation Data Augmentation Based on Relation Prediction

Event relation extraction is a key aspect in the fields of event evolutionary graph construction, knowledge question and answer, and intelligence analysis, etc. Currently, supervised learning methods that rely on large amounts of labeled data are mostly used; however, the size of existing event relation datasets is small and cannot provide sufficient training data for the models. To alleviate this challenging research question, this study proposes a novel data augmentation model, called Event Relation Data Augmentation based on relationship Prediction (ERDAP), that allows both semantic and structural features to be taken into account without changing the semantic relation label compatibility, uses event relation graph convolutional neural networks to predict event relations, and expands the generated high-quality event relation triples as new training data for the event relation texts. Experimental evaluation using event causality extraction method on Chinese emergent event dataset shows that our model significantly outperforms existing text augmentation methods and achieves desirable performance, which provides a new idea for event relation data augmentation

Ensemble decision of local similarity indices on the biological network for disease related gene prediction.

Link prediction (LP) is a task for the identification of potential, missing and spurious links in complex networks. Protein-protein interaction (PPI) networks are important for understanding the underlying biological mechanisms of diseases. Many complex networks have been constructed using LP methods; however, there are a limited number of studies that focus on disease-related gene predictions and evaluate these genes using various evaluation criteria. The main objective of the study is to investigate the effect of a simple ensemble method in disease related gene predictions. Local similarity indices (LSIs) based disease related gene predictions were integrated by a simple ensemble decision method, simple majority voting (SMV), on the PPI network to detect accurate disease related genes. Human PPI network was utilized to discover potential disease related genes using four LSIs for the gene prediction. LSIs discovered potential links between disease related genes, which were obtained from OMIM database for gastric, colorectal, breast, prostate and lung cancers. LSIs based disease related genes were ranked due to their LSI scores in descending order for retrieving the top 10, 50 and 100 disease related genes. SMV integrated four LSIs based predictions to obtain SMV based the top 10, 50 and 100 disease related genes. The performance of LSIs based and SMV based genes were evaluated separately by employing overlap analyses, which were performed with GeneCard disease-gene relation dataset and Gene Ontology (GO) terms. The GO-terms were used for biological assessment for the inferred gene lists by LSIs and SMV on all cancer types. Adamic-Adar (AA), Resource Allocation Index (RAI), and SMV based gene lists are generally achieved good performance results on all cancers in both overlap analyses. SMV also outperformed on breast cancer data. The increment in the selection of the number of the top ranked disease related genes also enhanced the performance results of SMV.

Adaptive Neural Message Passing for Inductive Learning on Hypergraphs.

Graphs are the most ubiquitous data structures for representing relational datasets and performing inferences in them. They model, however, only pairwise relations between nodes and are not designed for encoding the higher-order relations. This drawback is mitigated by hypergraphs, in which an edge can connect an arbitrary number of nodes. Most hypergraph learning approaches convert the hypergraph structure to that of a graph and then deploy existing geometric deep learning methods. This transformation leads to information loss, and sub-optimal exploitation of the hypergraph's expressive power. We present HyperMSG, a novel hypergraph learning framework that uses a modular two-level neural message passing strategy to accurately and efficiently propagate information within each hyperedge and across the hyperedges. HyperMSG adapts to the data and task by learning an attention weight associated with each node's degree centrality. Such a mechanism quantifies both local and global importance of a node, capturing the structural properties of a hypergraph. HyperMSG is inductive, allowing inference on previously unseen nodes. Further, it is robust and outperforms state-of-the-art hypergraph learning methods on a wide range of tasks and datasets. Finally, we demonstrate the effectiveness of HyperMSG in learning multimodal relations through detailed experimentation on a challenging multimedia dataset.