Search Results (103)

Ventricular arrhythmias (VAs) are critical cardiovascular diseases that require rapid and accurate detection. Conventional approaches relying on multi-lead ECG or deep learning models have limitations in computational cost, interpretability, and real-time applicability on wearable devices. To address these issues, a lightweight and interpretable framework based on multiple complex networks was proposed for the detection of life-threatening VAs using short-term single-lead ECG signals. The input signals were decomposed using the fixed-frequency-range empirical wavelet transform, and sub-bands were subsequently analyzed through multiscale visibility graphs, recurrence networks, cross-recurrence networks, and joint recurrence networks. Eight topological features were extracted and input into an XGBoost classifier for VA identification. Ten-fold cross-validation results on the MIT-BIH VFDB and CUDB databases demonstrated that the proposed method achieved a sensitivity of 99.02 ± 0.53%, a specificity of 98.44 ± 0.43%, and an accuracy of 98.73 ± 0.02% for 10 s ECG segments. The model also maintained robust performance on shorter segments, with 97.23 ± 0.76% sensitivity, 98.85 ± 0.95% specificity, and 96.62 ± 0.02% accuracy on 2 s segments. The results outperformed existing feature-based and deep learning approaches while preserving model interpretability. Furthermore, the proposed method supports mobile deployment, facilitating real-time use in wearable healthcare applications. Full article

A comprehensive bibliometric analysis of literature is imperative to elucidate current research landscapes and hotspots in the interplay between gut microbiota and hypertension, identify knowledge gaps, and establish theoretical foundations for the future. We used publications retrieved from the Web of Science Core Collection (WoSCC) and SCOPUS databases (January 2001–December 2024) to analyze the annual publication trends with GraphPad Prism 9.5.1, to evaluate co-authorship, keywords clusters, and co-citation patterns with VOSviewer 1.6.20, and conducted keyword burst detection and keyword co-occurrence utilizing CiteSpace v6.4.1. We have retrieved 2485 relevant publications published over the past 24 years. A 481-fold increase in global annual publications in this field was observed. China was identified as the most productive country, while the United States demonstrated the highest research impact. For the contributor, Yang Tao (University of Toledo, USA) and the University of Florida (USA) have emerged as the most influential contributors. Among journals, the highest number of articles was published in Nutrients (n = 135), which also achieved the highest citation count (n = 5397). The emergence of novel research hotspots was indicated by high-frequency keywords, mainly “hypertensive disorders of pregnancy”, “mendelian randomization”, “gut-heart axis”, and “hepatitis B virus”. “Trimethylamine N-oxide (TMAO)” and “receptor” may represent promising new research frontiers in the gut microbiota–hypertension nexus. The current research trends are shifting from exploring the factors influencing gut microbiota and hypertension to understanding the underlying mechanisms of these factors and the potential therapeutic applications of microbial modulation for hypertension management. Full article

Background: The ability of Graph Neural Networks (GNNs) to analyse brain structural patterns in various kinds of neurodegenerative diseases, including Parkinson’s disease (PD), has drawn a lot of interest recently. One emerging technique in this field is brain age prediction, which estimates biological age to identify ageing patterns that may serve as biomarkers for such disorders. However, a significant problem with most of the GNNs is their depth, which can lead to issues like oversmoothing and diminishing gradients. Methods: In this study, we propose SAGEFusionNet, a GNN architecture specifically designed to enhance brain age prediction and assess PD-related brain ageing patterns using T1-weighted structural MRI (sMRI). SAGEFusionNet learns important ROIs for brain age prediction by incorporating ROI-aware pooling at every layer to overcome the above challenges. Additionally, it incorporates multi-layer feature fusion to capture multi-scale structural information across the network hierarchy and auxiliary supervision to enhance gradient flow and feature learning at multiple depths. The dataset utilised in this study was sourced from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. It included a total of 580 T1-weighted sMRI scans from healthy individuals. The brain sMRI scans were parcellated into 56 regions of interest (ROIs) using the LPBA40 brain atlas in CAT12. The anatomical graph was constructed based on grey matter (GM) volume features. This graph served as input to the GNN models, along with GM and white matter (WM) volume as node features. All models were trained using 5-fold cross-validation to predict brain age and subsequently tested for performance evaluation. Results: The proposed framework achieved a mean absolute error (MAE) of $4.24\pm 0.38$ years and a mean Pearson’s Correlation Coefficient (PCC) of $0.72\pm 0.03$ during cross-validation. We also used 215 PD patient scans from the Parkinson’s Progression Markers Initiative (PPMI) database to assess the model’s performance and validate it. The initial findings revealed that out of 215 individuals with Parkinson’s disease, 213 showed higher and 2 showed lower predicted brain ages than their actual ages, with a mean MAE of 13.36 years (95% confidence interval: 12.51–14.28). Conclusions: These results suggest that brain age prediction using the proposed method may provide important insights into neurodegenerative diseases. Full article

We address the problem of the distributed computation of arbitrary functions of two correlated sources, $X_1$ and $X_2$, residing in two distributed source nodes, respectively. We exploit the structure of a computation task by coding source characteristic graphs (and multiple instances using the n-fold OR product of this graph with itself). For regular graphs and general graphs, we establish bounds on the optimal rate—characterized by the chromatic entropy for the n-fold graph products—that allows a receiver for asymptotically lossless computation of arbitrary functions over finite fields. For the special class of cycle graphs (i.e., 2-regular graphs), we establish an exact characterization of chromatic numbers and derive bounds on the required rates. Next, focusing on the more general class of d-regular graphs, we establish connections between d-regular graphs and expansion rates for n-fold graph products using graph spectra. Finally, for general graphs, we leverage the Gershgorin Circle Theorem (GCT) to provide a characterization of the spectra, which allows us to derive new bounds on the optimal rate. Our codes leverage the spectra of the computation and provide a graph expansion-based characterization to succinctly capture the computation structure, providing new insights into the problem of distributed computation of arbitrary functions. Full article

Kinase is an enzyme responsible for cell signaling and other complex processes. Mutations or changes in kinase can cause cancer and other diseases in humans, including leukemia, neuroblastomas, glioblastomas, and more. Considering these concerns, inhibiting overexpressed or dysregulated kinases through small drug molecules is very important. In the past, many machine learning and deep learning approaches have been used to inhibit unregulated kinase enzymes. In this work, we employ a Graph Neural Network (GNN) to predict the inhibition activities of kinases. A separate Graph Convolution Network (GCN) and combined Graph Convolution and Graph Attention Network (GCN_GAT) are developed and trained on two large datasets (Kinase Datasets 1 and 2) consisting of small drug molecules against the targeted kinase using 10-fold cross-validation. Furthermore, a wide range of molecules are used as independent datasets on which the performance of the models is evaluated. On both independent kinase datasets, our model combining GCN and GAT provides the best evaluation and outperforms previous models in terms of accuracy, Matthews Correlation Coefficient (MCC), sensitivity, specificity, and precision. On the independent Kinase Dataset 1, the values of accuracy, MCC, sensitivity, specificity, and precision are 0.96, 0.89, 0.90, 0.98, and 0.91, respectively. Similarly, the performance of our model combining GCN and GAT on the independent Kinase Dataset 2 is 0.97, 0.90, 0.91, 0.99, and 0.92 in terms of accuracy, MCC, sensitivity, specificity, and precision, respectively. Full article

Human immunodeficiency virus (HIV) continues to be a threat to public health. An emerging technique with promise in the context of fighting HIV type 1 (HIV-1) focuses on targeting ribosomal frameshifting. A crucial –1 programmed ribosomal frameshift (PRF) has been observed in several pathogenic viruses, including HIV-1. Altered folds of the HIV-1 RNA frameshift element (FSE) have been shown to alter frameshifting efficiency. Here, we use RNA-As-Graphs (RAG), a graph-theory based framework for representing and analyzing RNA secondary structures, to perform conformational analysis in motif space to propose how sequence length may influence folding patterns. This combined analysis, along with all-atom modeling and experimental testing of our designed mutants, has already proven valuable for the SARS-CoV-2 FSE. As a first step to launching the same computational/experimental approach for HIV-1, we compare prior experiments and perform SHAPE-guided 2D-fold predictions for the HIV-1 FSE embedded in increasing sequence contexts and predict structure-altering mutations. We find a highly stable upper stem and highly flexible lower stem for the core FSE, with a three-way junction connecting to other motifs at increasing lengths. In particular, we find little support for a pseudoknot or triplex interaction in the core FSE, although pseudoknots can form separately as a connective motif at longer sequences. We also identify sensitive residues in the upper stem and central loop that, when minimally mutated, alter the core stem loop folding. These insights into the FSE fold and structure-altering mutations can be further pursued by all-atom simulations and experimental testing to advance the mechanistic understanding and therapeutic strategies for HIV-1. Full article

Ineffective treatment and side effects are associated with high burdens for the patient and society. We investigated the application of graph representation learning (GRL) for predicting medication usage based on individual genetic data in the United Kingdom Biobank (UKBB). A graph convolutional network (GCN) was used to integrate interconnected biomedical entities in the form of a knowledge graph as part of a machine learning (ML) prediction model. Data from The Pharmacogenomics Knowledgebase (PharmGKB) was used to construct a biomedical knowledge graph. Individual genetic data (n = 485,754) from the UKBB was obtained and preprocessed to match with pharmacogenetic variants in the PharmGKB. Self-reported medication usage labels were obtained from UKBB data field 20003. We hypothesize that pharmacogenetic variants can predict the impact of medications on individuals. We assume that an individual using a medication on a regular basis experiences a net benefit (vs. side-effects) from the medication. ML models were trained to predict medication usage for 264 medications. The GCN model significantly outperformed both a baseline logistic regression model (p-value: 1.53 × 10⁻⁹) and a deep neural network model (p-value: 8.68 × 10⁻⁸). The GCN model also significantly outperformed a GCN model trained using a random graph (GCN-random) (p-value: 5.44 × 10⁻⁹). A consistent trend of medications with higher sample sizes having better performance was observed, and for several medications, a high relative rank of the medication (among multiple medications) was associated with greater than 2-fold higher odds of usage of the medication. In conclusion, a graph-based ML approach could be useful in advancing precision medicine by prioritizing medications that a patient may need based on their genetic data. However, further research is needed to improve the quality and quantity of genetic data and to validate our approach using more reliable medication labels. Full article

As critical strategic mineral resources underpinning high-tech industries and national defense security, rare earth elements have become a central focus of international competition, with their global industrial chain configuration deeply intertwined with geopolitical dynamics. Leveraging a novel multilateral database encompassing 140 countries’ geopolitical relationships and rare earth trade flows (2001–2023), this study employs social network analysis and temporal exponential random graph models (TERGMs) to decode structural interdependencies across upstream mineral concentrates, midstream smelting, and downstream permanent magnet sectors. Empirical results show that topological density trajectories reveal intensified network coupling, with upstream/downstream sectors demonstrating strong clustering. Geopolitical cooperation and conflict exert differential impacts along the value chain: downstream trade exhibits heightened sensitivity to cooperative effects, whereas midstream trade suffers the most pronounced obstruction from conflicts. Cooperation fosters long-term trade relationships, whereas conflicts primarily impose short-term suppression. In addition, centrality metrics reveal asymmetric mechanisms. Each unit increase in cooperation degree centrality amplifies the mid/downstream trade by 3.29 times, whereas conflict centrality depresses the midstream trade by 4.76%. The eigenvector centrality of cooperation hub nations enhances the midstream trade probability by 5.37-fold per unit gain, in contrast with the 25.09% midstream trade erosion from conflict-prone nations’ centrality increments. These insights provide implications for mitigating geopolitical risks and achieving sustainable governance in key mineral resource supply chains. Full article

This paper extends the concept of the total graph $T_{\mathsf{\Gamma }}\left(R\right)$ associated with a commutative ring to the three-fold Cartesian product $R={\mathbb{Z}}_n\times {\mathbb{Z}}_m\times {\mathbb{Z}}_p$, where $n,m,p>1$. We present complete and self-contained proofs for a wide range of graph-theoretic properties of $T_{\mathsf{\Gamma }}\left(R\right)$, including connectivity, diameter, regularity conditions, clique and independence numbers, and exact criteria for Hamiltonicity and Eulericity. We also derive improved lower bounds for the genus and characterize the automorphism group in both general and symmetric cases. Each result is illustrated through concrete numerical examples for clarity. Beyond theoretical contributions, we discuss potential applications in cryptographic key-exchange systems, fault-tolerant network architectures, and algebraic code design. This work generalizes and deepens prior studies on two-factor total graphs, and establishes a foundational framework for future exploration of higher-dimensional total graphs over finite commutative rings. Full article

The effects of proline co-solvent on helix folding are explored through the single discrete coordinate of the number of helical hydrogen bonds. The analysis is based on multi-microsecond length molecular dynamics simulations of alanine-based helix-forming peptides, (ALA)n, of length n = 4, 8, 15 and 21 residues, in an aqueous solution with 2 M concentration of proline. The effects of addition of proline on the free energy landscape for helix folding were analyzed using the graph-based Dijkstra algorithm, Optimal Dimensionality Reduction kinetic coarse graining, committor functions, as well as through the diffusion of the helix boundary. Viewed at a sufficiently long time-scale, helix folding in the coarse-grained hydrogen bond space follows a consecutive mechanism, with well-defined initiation and propagation phases, and an interesting set of intermediates. Proline addition slows down the folding relaxation of all four peptides, increases helix content and induces subtle mechanistic changes compared to pure water solvation. A general trend is for transition state shift towards earlier stages of folding in proline relative to water. For ALA5 and ALA8 direct folding is dominant. In ALA8 and ALA15 multiple pathways appear possible. For ALA21 a simple mechanism emerges, with a single path from helix to coil through a set of intermediates. Overall, this work provides new insights into effects of proline co-solvent on helix folding, complementary to more standard approaches based on three-dimensional molecular structures. Full article

Background: Cervical lesion classification is essential for early detection of cervical cancer. While deep learning methods have shown promise, most rely on single-modal data or require extensive manual annotations. This study proposes a novel Graph Neural Network (GNN)-based framework that integrates colposcopy images, segmentation masks, and graph representations for improved lesion classification. Methods: We developed a fully connected graph-based architecture using GCNConv layers with global mean pooling and optimized it via grid search. A five-fold cross-validation protocol was employed to evaluate performance before (1–100 epochs) and after fine-tuning (101–151 epochs). Performance metrics included macro-average F1-score and validation accuracy. Visualizations were used for model interpretability. Results: The model achieved a macro-average F1-score of 89.4% and validation accuracy of 92.1% before fine-tuning, which improved to 94.56% and 98.98%, respectively, after fine-tuning. LIME-based visual explanations validated models focus on discriminative lesion regions. Conclusions: This study highlights the potential of graph-based multi-modal learning for cervical lesion analysis. Collaborating with the MNJ Institute of Oncology, the framework shows promise for clinical use. Full article

Thermostable β-glucosidases (E.C. 3.2.1.21) are essential enzymes used in second-generation biofuel production. However, little is known about the structural characteristics that lead to their thermostability. In this study, I used graph-based structural signatures to represent three-dimensional structures of β-glucosidase enzymes extracted from thermophilic organisms. I collected 1717 structures from thermophilic (n = 890) and non-thermophilic (n = 827) organisms and divided them into two datasets: training (n = 1134) and test (n = 583). I then used seven machine learning algorithms to classify them. The best model achieved 77.1% accuracy using logistic regression in training with 10-fold cross-validation and 81.6% accuracy in testing using the CatBoost algorithm. I hypothesize that the signature model proposed here can help understand the structural patterns in thermostable enzymes and shed light on the design of more efficient enzymes for biofuel production. Full article

Permanent Scatterer Interferometric Synthetic Aperture Radar (PSInSAR), with millimeter-level accuracy and full-resolution capabilities, is essential for monitoring urban deformation. With the advancement of SAR sensors in spatial and temporal resolution and the expansion of wide-swath observation capabilities, the number of permanent scatterers (PSs) in high-density urban areas has surged exponentially. To address these computational and memory challenges in high-density urban PSInSAR processing, this paper proposes an efficient method for integrating regular grid partitioning and connected component constraints. First, adaptive dynamic regular grid partitioning was employed to divide monitoring areas into sub-blocks, balancing memory usage and computational efficiency. Second, a weighted least squares adjustment model using common PS points in overlapping regions eliminated systematic inter-sub-block biases, ensuring global consistency. A graph-based connected component constraint mechanism was introduced to resolve multi-component segmentation issues within sub-blocks to preserve discontinuous PS information. Experiments on TerraSAR-X data covering Fuzhou, China (590 km²), demonstrated that the method processed 1.4 × 10⁷ PS points under 32 GB memory constraints, where it achieved a 25-fold efficiency improvement over traditional global PSInSAR. The deformation rates and elevation residuals exhibited high consistency with conventional methods (correlation coefficient ≥ 0.98). This method effectively addresses the issues of memory overflow, connectivity loss between sub-blocks, and cumulative merging errors in large-scale PS networks. It provides an efficient solution for wide-area millimeter-scale deformation monitoring in high-density urban areas, supporting applications such as geohazard early warning and urban infrastructure safety assessment. Full article

The microbiome plays a crucial role in maintaining physiological homeostasis and is intricately linked to various diseases. Traditional culture-based microbiological experiments are expensive and time-consuming. Therefore, it is essential to prioritize the development of computational methods that enable further experimental validation of disease-associated microorganisms. Existing computational methods often struggle to effectively capture nonlinear interactions and heterogeneous network structures when predicting microbiome–disease associations. To address this issue, we propose HG-LGBM, an innovative joint prediction framework that combines heterogeneous graph neural networks with a gradient boosting mechanism. We employ a hierarchical heterogeneous graph transformer (HGT) encoder, which utilizes a multi-head attention mechanism to learn higher-order node representations, while LightGBM optimizes the classification task using gradient-boosted decision trees. Evaluated through five-fold cross-validation on the HMDAD and Disbiome datasets, HG-LGBM demonstrated a state-of-the-art performance. The experimental results showed that combining heterogeneous network learning with gradient boosting strategies effectively revealed potential microbiome–disease interactions, providing a powerful tool for biomedical research and precision medicine. Finally, case studies on colorectal cancer and inflammatory bowel disease (IBD) further validated the effectiveness of HG-LGBM. Full article

Based on some typical complex network analysis methods and machine learning techniques, a general multiple-measures composited strategy-guided epilepsy diagnosis analysis framework is proposed in this brief paper. Five typical network analysis methods for biology time series analysis are utilized for real applications, including the classical visibility graph (VG), horizontal visibility graph (HVG), the limited penetrable visibility graph (LPVG), the modified frequency degree method (MFDM), and the quantity graph (QG). By using the aforementioned typical transformation methods, the EEG signal sets to be classified are transferred into graph network object sets. The main network features and related indicators are calculated and extracted as features for classification tasks. Some key features are selected via variance analysis, and the eXtreme Gradient Boosting (XGBOOST) machine learning algorithm is used for related binary and five-class classification tasks for electroencephalographic time series. Numerical experiments demonstrate that, through ten-fold cross-validation on the entire dataset, the classification accuracy for two-class classification consistently reaches 97.8% (with a specificity of 97.5%), while for five-class classification, the accuracy stably reaches 82.4% (with a specificity of 95.6%). Therefore, our classification framework can be effectively used to assist hospital doctors and medical specialists in diagnosing related diseases, especially to help accelerate the treatment of epilepsy patients. Full article