RESUMEN

BACKGROUND: Applying graph convolutional networks (GCN) to the classification of free-form natural language texts leveraged by graph-of-words features (TextGCN) was studied and confirmed to be an effective means of describing complex natural language texts. However, the text classification models based on the TextGCN possess weaknesses in terms of memory consumption and model dissemination and distribution. In this paper, we present a fast message passing network (FastMPN), implementing a GCN with message passing architecture that provides versatility and flexibility by allowing trainable node embedding and edge weights, helping the GCN model find the better solution. We applied the FastMPN model to the task of clinical information extraction from cancer pathology reports, extracting the following six properties: main site, subsite, laterality, histology, behavior, and grade. RESULTS: We evaluated the clinical task performance of the FastMPN models in terms of micro- and macro-averaged F1 scores. A comparison was performed with the multi-task convolutional neural network (MT-CNN) model. Results show that the FastMPN model is equivalent to or better than the MT-CNN. CONCLUSIONS: Our implementation revealed that our FastMPN model, which is based on the PyTorch platform, can train a large corpus (667,290 training samples) with 202,373 unique words in less than 3 minutes per epoch using one NVIDIA V100 hardware accelerator. Our experiments demonstrated that using this implementation, the clinical task performance scores of information extraction related to tumors from cancer pathology reports were highly competitive.

Asunto(s)

RESUMEN

Accurate and timely forecasting of traffic on local road networks is crucial for deploying effective dynamic traffic control, advanced route planning, and navigation services. This task is particularly challenging due to complex spatio-temporal dependencies arising from non-Euclidean spatial relations in road networks and non-linear temporal dynamics influenced by changing road conditions. This paper introduces the spatio-temporal network embedding (STNE) model, a novel deep learning framework tailored for learning and forecasting graph-structured traffic data over extended input sequences. Unlike traditional convolutional neural networks (CNNs), the model employs graph convolutional networks (GCNs) to capture the spatial characteristics of local road network topologies. Moreover, the segmentation of very long input traffic data into multiple sub-sequences, based on significant temporal properties such as closeness, periodicity, and trend, is performed. Multi-dimensional long short-term memory neural networks (MDLSTM) are utilized to flexibly access multi-dimensional context. Experimental results demonstrate that the STNE model surpasses state-of-the-art traffic forecasting benchmarks on two large-scale real-world traffic datasets.

RESUMEN

Spatiotemporal (ST) graph modeling has garnered increasing attention recently. Most existing methods rely on a predefined graph structure or construct a single learnable graph throughout training. However, it is challenging to use a predefined graph structure to capture dynamic ST changes effectively due to evolving node relationships over time. Furthermore, these methods typically utilize only the original data, neglecting external temporal factors. Therefore, we put forward a novel time-varying graph convolutional network model that integrates external factors for multifeature ST series prediction. Firstly, we construct a time-varying adjacency matrix using attention to capture dynamic spatial relationships among nodes. The graph structure adapts over time during training, validation, and testing phases. Then, we model temporal dependence by dilated causal convolution, leveraging gated activation unit and residual connection. Notably, the prediction accuracy is enhanced through the incorporation of embedding absolute time and the fusion of multifeature. This model has been applied to three real-world multifeature datasets, achieving state-of-the-art performance in all cases. Experiments show that the method has high accuracy and robustness when applied to multifeature and multivariate ST series problems.

RESUMEN

The increasing availability of patient-derived multimodal biological data for various diseases has opened up avenues for finding the optimal methods for jointly leveraging the information extracted in a customizable and scalable manner. Here, we propose the Proximogram, a graph-based representation that provides a joint construct for embedding independently obtained omics and spatial data. To evaluate the representation, we generated proximograms from 2 distinct biological sources, namely, multiplexed immunofluorescence images and single-cell RNA-seq data obtained from patients across two pancreatic diseases that include normal and chronic Pancreatitis (CP) and pancreatic ductal adenocarcinoma (PDAC). The generated proximograms were used as inputs to 2 distinct graph deep-learning models. The improved classification results over simpler spatial-data-based input graphs point to the increased discriminatory power obtained by integrating structural information from single-cell ligand-receptor signaling data and the spatial architecture of cells in each disease class, which can help point to markers of high diagnostic significance.

RESUMEN

BACKGROUND AND OBJECTIVE: Accurate prognosis prediction for cancer patients plays a significant role in the formulation of treatment strategies, considerably impacting personalized medicine. Recent advancements in this field indicate that integrating information from various modalities, such as genetic and clinical data, and developing multi-modal deep learning models can enhance prediction accuracy. However, most existing multi-modal deep learning methods either overlook patient similarities that benefit prognosis prediction or fail to effectively capture diverse information due to measuring patient similarities from a single perspective. To address these issues, a novel framework called multi-modal multi-view graph convolutional networks (MMGCN) is proposed for cancer prognosis prediction. METHODS: Initially, we utilize the similarity network fusion (SNF) algorithm to merge patient similarity networks (PSNs), individually constructed using gene expression, copy number alteration, and clinical data, into a fused PSN for integrating multi-modal information. To capture diverse perspectives of patient similarities, we treat the fused PSN as a multi-view graph by considering each single-edge-type subgraph as a view graph, and propose multi-view graph convolutional networks (GCNs) with a view-level attention mechanism. Moreover, an edge homophily prediction module is designed to alleviate the adverse effects of heterophilic edges on the representation power of GCNs. Finally, comprehensive representations of patient nodes are obtained to predict cancer prognosis. RESULTS: Experimental results demonstrate that MMGCN outperforms state-of-the-art baselines on four public datasets, including METABRIC, TCGA-BRCA, TCGA-LGG, and TCGA-LUSC, with the area under the receiver operating characteristic curve achieving 0.827 ± 0.005, 0.805 ± 0.014, 0.925 ± 0.007, and 0.746 ± 0.013, respectively. CONCLUSIONS: Our study reveals the effectiveness of the proposed MMGCN, which deeply explores patient similarities related to different modalities from a broad perspective, in enhancing the performance of multi-modal cancer prognosis prediction. The source code is publicly available at https://github.com/ping-y/MMGCN.

RESUMEN

BACKGROUND AND OBJECTIVE: Biomedical relation extraction aims to reveal the relation between entities in medical texts. Currently, the relation extraction models that have attracted much attention are mainly to fine-tune the pre-trained language models (PLMs) or add template prompt learning, which also limits the ability of the model to deal with grammatical dependencies. Graph convolutional networks (GCNs) can play an important role in processing syntactic dependencies in biomedical texts. METHODS: In this work, we propose a biomedical relation extraction model that fuses GCNs enhanced prompt learning to handle limitations in syntactic dependencies and achieve good performance. Specifically, we propose a model that combines prompt learning with GCNs for relation extraction, by integrating the syntactic dependency information analyzed by GCNs into the prompt learning model, by predicting the correspondence with [MASK] tokens labels for relation extraction. RESULTS: Our model achieved F1 scores of 85.57%, 80.15%, 95.10%, and 84.11% in the biomedical relation extraction datasets GAD, ChemProt, PGR, and DDI, respectively, all of which outperform some existing baseline models. CONCLUSIONS: In this paper, we propose enhancing prompt learning through GCNs, integrating syntactic information into biomedical relation extraction tasks. Experimental results show that our proposed method achieves excellent performance in the biomedical relation extraction task.

Asunto(s)

RESUMEN

BACKGROUND: Prolonged improper posture can lead to forward head posture (FHP), causing headaches, impaired respiratory function, and fatigue. This is especially relevant in sedentary scenarios, where individuals often maintain static postures for extended periods-a significant part of daily life for many. The development of a system capable of detecting FHP is crucial, as it would not only alert users to correct their posture but also serve the broader goal of contributing to public health by preventing the progression of chronic injuries associated with this condition. However, despite significant advancements in estimating human poses from standard 2D images, most computational pose models do not include measurements of the craniovertebral angle, which involves the C7 vertebra, crucial for diagnosing FHP. OBJECTIVE: Accurate diagnosis of FHP typically requires dedicated devices, such as clinical postural assessments or specialized imaging equipment, but their use is impractical for continuous, real-time monitoring in everyday settings. Therefore, developing an accessible, efficient method for regular posture assessment that can be easily integrated into daily activities, providing real-time feedback, and promoting corrective action, is necessary. METHODS: The system sequentially estimates 2D and 3D human anatomical key points from a provided 2D image, using the Detectron2D and VideoPose3D algorithms, respectively. It then uses a graph convolutional network (GCN), explicitly crafted to analyze the spatial configuration and alignment of the upper body's anatomical key points in 3D space. This GCN aims to implicitly learn the intricate relationship between the estimated 3D key points and the correct posture, specifically to identify FHP. RESULTS: The test accuracy was 78.27% when inputs included all joints corresponding to the upper body key points. The GCN model demonstrated slightly superior balanced performance across classes with an F1-score (macro) of 77.54%, compared to the baseline feedforward neural network (FFNN) model's 75.88%. Specifically, the GCN model showed a more balanced precision and recall between the classes, suggesting its potential for better generalization in FHP detection across diverse postures. Meanwhile, the baseline FFNN model demonstrates a higher precision for FHP cases but at the cost of lower recall, indicating that while it is more accurate in confirming FHP when detected, it misses a significant number of actual FHP instances. This assertion is further substantiated by the examination of the latent feature space using t-distributed stochastic neighbor embedding, where the GCN model presented an isotropic distribution, unlike the FFNN model, which showed an anisotropic distribution. CONCLUSIONS: Based on 2D image input using 3D human pose estimation joint inputs, it was found that it is possible to learn FHP-related features using the proposed GCN-based network to develop a posture correction system. We conclude the paper by addressing the limitations of our current system and proposing potential avenues for future work in this area.

Asunto(s)

RESUMEN

Spatially resolved transcriptomics integrates high-throughput transcriptome measurements with preserved spatial cellular organization information. However, many technologies cannot reach single-cell resolution. We present STdGCN, a graph model leveraging single-cell RNA sequencing (scRNA-seq) as reference for cell-type deconvolution in spatial transcriptomic (ST) data. STdGCN incorporates expression profiles from scRNA-seq and spatial localization from ST data for deconvolution. Extensive benchmarking on multiple datasets demonstrates that STdGCN outperforms 17 state-of-the-art models. In a human breast cancer Visium dataset, STdGCN delineates stroma, lymphocytes, and cancer cells, aiding tumor microenvironment analysis. In human heart ST data, STdGCN identifies changes in endothelial-cardiomyocyte communications during tissue development.

Asunto(s)

RESUMEN

Liver segmentation technologies play vital roles in clinical diagnosis, disease monitoring, and surgical planning due to the complex anatomical structure and physiological functions of the liver. This paper provides a comprehensive review of the developments, challenges, and future directions in liver segmentation technology. We systematically analyzed high-quality research published between 2014 and 2024, focusing on liver segmentation methods, public datasets, and evaluation metrics. This review highlights the transition from manual to semi-automatic and fully automatic segmentation methods, describes the capabilities and limitations of available technologies, and provides future outlooks.

RESUMEN

BACKGROUND: Predicting an individual's risk of death from COVID-19 is essential for planning and optimising resources. However, since the real-world mortality rate is relatively low, particularly in places like Hong Kong, this makes building an accurate prediction model difficult due to the imbalanced nature of the dataset. This study introduces an innovative application of graph convolutional networks (GCNs) to predict COVID-19 patient survival using a highly imbalanced dataset. Unlike traditional models, GCNs leverage structural relationships within the data, enhancing predictive accuracy and robustness. By integrating demographic and laboratory data into a GCN framework, our approach addresses class imbalance and demonstrates significant improvements in prediction accuracy. METHODS: The cohort included all consecutive positive COVID-19 patients fulfilling study criteria admitted to 42 public hospitals in Hong Kong between January 23 and December 31, 2020 (n = 7,606). We proposed the population-based graph convolutional neural network (GCN) model which took blood test results, age and sex as inputs to predict the survival outcomes. Furthermore, we compared our proposed model to the Cox Proportional Hazard (CPH) model, conventional machine learning models, and oversampling machine learning models. Additionally, a subgroup analysis was performed on the test set in order to acquire a deeper understanding of the relationship between each patient node and its neighbours, revealing possible underlying causes of the inaccurate predictions. RESULTS: The GCN model was the top-performing model, with an AUC of 0.944, considerably outperforming all other models (p < 0.05), including the oversampled CPH model (0.708), linear regression (0.877), Linear Discriminant Analysis (0.860), K-nearest neighbours (0.834), Gaussian predictor (0.745) and support vector machine (0.847). With Kaplan-Meier estimates, the GCN model demonstrated good discriminability between low- and high-risk individuals (p < 0.0001). Based on subanalysis using the weighted-in score, although the GCN model was able to discriminate well between different predicted groups, the separation was inadequate between false negative (FN) and true negative (TN) groups. CONCLUSION: The GCN model considerably outperformed all other machine learning methods and baseline CPH models. Thus, when applied to this imbalanced COVID survival dataset, adopting a population graph representation may be an approach to achieving good prediction.

Asunto(s)

RESUMEN

The cultivation of the Chinese mitten crab (Eriocheir sinensis) is an important component of China's aquaculture industry and also a field of concern worldwide. It focuses on the selection of high-quality, disease-free juvenile crabs. However, the early maturity rate of more than 18.2% and the mortality rate of more than 60% make it difficult to select suitable juveniles for adult culture. The juveniles exhibit subtle distinguishing features, and the methods for differentiating between sexes vary significantly; without training from professional breeders, it is challenging for laypersons to identify and select the appropriate juveniles. Therefore, we propose a task-aligned detection algorithm for identifying one-year-old precocious Chinese mitten crabs, named R-TNET. Initially, the required images were obtained by capturing key frames, and then they were annotated and preprocessed by professionals to build a training dataset. Subsequently, the ResNeXt network was selected as the backbone feature extraction network, with Convolutional Block Attention Modules (CBAMs) and a Deformable Convolution Network (DCN) embedded in its residual blocks to enhance its capability to extract complex features. Adaptive spatial feature fusion (ASFF) was then integrated into the feature fusion network to preserve the detailed features of small targets such as one-year-old precocious Chinese mitten crab juveniles. Finally, based on the detection head proposed by task-aligned one-stage object detection, the parameters of its anchor alignment metric were adjusted to detect, locate, and classify the crab juveniles. The experimental results showed that this method achieves a mean average precision (mAP) of 88.78% and an F1-score of 97.89%. This exceeded the best-performing mainstream object detection algorithm, YOLOv7, by 4.17% in mAP and 1.77% in the F1-score. Ultimately, in practical application scenarios, the algorithm effectively identified one-year-old precocious Chinese mitten crabs, providing technical support for the automated selection of high-quality crab juveniles in the cultivation process, thereby promoting the rapid development of aquaculture and agricultural intelligence in China.

RESUMEN

Deep generative models are becoming a tool of choice for exploring the molecular space. One important application area of deep generative models is the reverse design of drug compounds for given attributes (solubility, ease of synthesis, etc.). Although there are many generative models, these models cannot generate specific intervals of attributes. This paper proposes a AC-ModNet model that effectively combines VAE with AC-GAN to generate molecular structures in specific attribute intervals. The AC-ModNet is trained and evaluated using the open 250K ZINC dataset. In comparison with related models, our method performs best in the FCD and Frag model evaluation indicators. Moreover, we prove the AC-ModNet created molecules have potential application value in drug design by comparing and analyzing them with medical records in the PubChem database. The results of this paper will provide a new method for machine learning drug reverse design.

Asunto(s)

RESUMEN

Next Point-of-Interest (POI) recommendation aims to predict the next POI for users from their historical activities. Existing methods typically rely on location-level POI check-in trajectories to explore user sequential transition patterns, which suffer from the severe check-in data sparsity issue. However, taking into account region-level and category-level POI sequences can help address this issue. Moreover, collaborative information between different granularities of POI sequences is not well utilized, which can facilitate mutual enhancement and benefit to augment user preference learning. To address these challenges, we propose multi-granularity contrastive learning (MGCL) for next POI recommendation, which utilizes multi-granularity representation and contrastive learning to improve the next POI recommendation performance. Specifically, location-level POI graph, category-level, and region-level sequences are first constructed. Then, we use graph convolutional networks on POI graph to extract cross-user sequential transition patterns. Furthermore, self-attention networks are used to learn individual user sequential transition patterns for each granularity level. To capture the collaborative signals between multi-granularity, we apply the contrastive learning approach. Finally, we jointly train the recommendation and contrastive learning tasks. Extensive experiments demonstrate that MGCL is more effective than state-of-the-art methods.

RESUMEN

Exercise-based rehabilitation programs have proven to be effective in enhancing the quality of life and reducing mortality and rehospitalization rates. AI-driven virtual rehabilitation, which allows patients to independently complete exercises at home, utilizes AI algorithms to analyze exercise data, providing feedback to patients and updating clinicians on their progress. These programs commonly prescribe a variety of exercise types, leading to a distinct challenge in rehabilitation exercise assessment datasets: while abundant in overall training samples, these datasets often have a limited number of samples for each individual exercise type. This disparity hampers the ability of existing approaches to train generalizable models with such a small sample size per exercise type. Addressing this issue, this paper introduces a novel supervised contrastive learning framework with hard and soft negative samples that effectively utilizes the entire dataset to train a single model applicable to all exercise types. This model, with a Spatial-Temporal Graph Convolutional Network (ST-GCN) architecture, demonstrated enhanced generalizability across exercises and a decrease in overall complexity. Through extensive experiments on three publicly available rehabilitation exercise assessment datasets, UI-PRMD, IRDS, and KIMORE, our method has proven to surpass existing methods, setting a new benchmark in rehabilitation exercise quality assessment.

RESUMEN

BACKGROUND: Colorectal cancer (CRC) is a malignant tumor within the digestive tract with both a high incidence rate and mortality. Early detection and intervention could improve patient clinical outcomes and survival. METHODS: This study computationally investigates a set of prognostic tissue and cell features from diagnostic tissue slides. With the combination of clinical prognostic variables, the pathological image features could predict the prognosis in CRC patients. Our CRC prognosis prediction pipeline sequentially consisted of three modules: (1) A MultiTissue Net to delineate outlines of different tissue types within the WSI of CRC for further ROI selection by pathologists. (2) Development of three-level quantitative image metrics related to tissue compositions, cell shape, and hidden features from a deep network. (3) Fusion of multi-level features to build a prognostic CRC model for predicting survival for CRC. RESULTS: Experimental results suggest that each group of features has a particular relationship with the prognosis of patients in the independent test set. In the fusion features combination experiment, the accuracy rate of predicting patients' prognosis and survival status is 81.52%, and the AUC value is 0.77. CONCLUSION: This paper constructs a model that can predict the postoperative survival of patients by using image features and clinical information. Some features were found to be associated with the prognosis and survival of patients.

Asunto(s)

RESUMEN

Accurately identifying essential proteins is vital for drug research and disease diagnosis. Traditional centrality methods and machine learning approaches often face challenges in accurately discerning essential proteins, primarily relying on information derived from protein-protein interaction (PPI) networks. Despite attempts by some researchers to integrate biological data and PPI networks for predicting essential proteins, designing effective integration methods remains a challenge. In response to these challenges, this paper presents the ACDMBI model, specifically designed to overcome the aforementioned issues. ACDMBI is comprised of two key modules: feature extraction and classification. In terms of capturing relevant information, we draw insights from three distinct data sources. Initially, structural features of proteins are extracted from the PPI network through community division. Subsequently, these features are further optimized using Graph Convolutional Networks (GCN) and Graph Attention Networks (GAT). Moving forward, protein features are extracted from gene expression data utilizing Bidirectional Long Short-Term Memory networks (BiLSTM) and a multi-head self-attention mechanism. Finally, protein features are derived by mapping subcellular localization data to a one-dimensional vector and processing it through fully connected layers. In the classification phase, we integrate features extracted from three different data sources, crafting a multi-layer deep neural network (DNN) for protein classification prediction. Experimental results on brewing yeast data showcase the ACDMBI model's superior performance, with AUC reaching 0.9533 and AUPR reaching 0.9153. Ablation experiments further reveal that the effective integration of features from diverse biological information significantly boosts the model's performance.

Asunto(s)

RESUMEN

Bearing fault diagnosis is significant in ensuring large machinery and equipment's safe and stable operation. However, inconsistent operating environments can lead to data distribution differences between source and target domains. As a result, models trained solely on source-domain data may not perform well when applied to the target domain, especially when the target-domain data is unlabeled. Existing approaches focus on improving domain adaptive methods for effective transfer learning but neglect the importance of extracting comprehensive feature information. To tackle this challenge, we present a bearing fault diagnosis approach using dual-path convolutional neural networks (CNNs) and multi-parallel graph convolutional networks (GCNs), called DPC-MGCN, which can be applied to variable working conditions. To obtain complete feature information, DPC-MGCN leverages dual-path CNNs to extract local and global features from vibration signals in both the source and target domains. The attention mechanism is subsequently applied to identify crucial features, which are converted into adjacency matrices. Multi-parallel GCNs are then employed to further explore the structural information among these features. To minimize the distribution differences between the two domains, we incorporate the multi-kernel maximum mean discrepancy (MK-MMD) domain adaptation method. By applying the DPC-MGCN approach for diagnosing bearing faults under diverse working conditions and comparing it with other methods, we demonstrate its superior performance on various datasets.

RESUMEN

Link prediction is recognized as a crucial means to analyze dynamic social networks, revealing the principles of social relationship evolution. However, the complex topology and temporal evolution characteristics of dynamic social networks pose significant research challenges. This study introduces an innovative fusion framework that incorporates entropy, causality, and a GCN model, focusing specifically on link prediction in dynamic social networks. Firstly, the framework preprocesses the raw data, extracting and recording timestamp information between interactions. It then introduces the concept of "Temporal Information Entropy (TIE)", integrating it into the Node2Vec algorithm's random walk to generate initial feature vectors for nodes in the graph. A causality analysis model is subsequently applied for secondary processing of the generated feature vectors. Following this, an equal dataset is constructed by adjusting the ratio of positive and negative samples. Lastly, a dedicated GCN model is used for model training. Through extensive experimentation in multiple real social networks, the framework proposed in this study demonstrated a better performance than other methods in key evaluation indicators such as precision, recall, F1 score, and accuracy. This study provides a fresh perspective for understanding and predicting link dynamics in social networks and has significant practical value.

RESUMEN

This study proposes a novel long short-term memory (LSTM)-based model for predicting future physical properties based on partial data of molecular dynamics (MD) simulation. It extracts latent vectors from atomic coordinates of MD simulations using graph convolutional network, utilizes LSTM to learn temporal trends in latent vectors and make one-step-ahead predictions of physical properties through fully connected layers. Validating with MD simulations of Ni solid-liquid systems, the model achieved accurate one-step-ahead prediction for time variation of the potential energy during solidification and melting processes using residual connections. Recursive use of predicted values enabled long-term prediction from just the first 20 snapshots of the MD simulation. The prediction has captured the feature of potential energy bending at low temperatures, which represents completion of solidification, despite that the MD data in short time do not have such a bending characteristic. Remarkably, for long-time prediction over 900 ps, the computation time was reduced to 1/700th of a full MD simulation of the same duration. This approach has shown the potential to significantly reduce computational cost for prediction of physical properties by efficiently utilizing the data of MD simulation.

RESUMEN

BACKGROUND: Left ventricular enlargement (LVE) is a common manifestation of cardiac remodeling that is closely associated with cardiac dysfunction, heart failure (HF), and arrhythmias. This study aimed to propose a machine learning (ML)-based strategy to identify LVE in HF patients by means of pulse wave signals. METHOD: We constructed two high-quality pulse wave datasets comprising a non-LVE group and an LVE group based on the 264 HF patients. Fourier series calculations were employed to determine if significant frequency differences existed between the two datasets, thereby ensuring their validity. Then, the ML-based identification was undertaken by means of classification and regression models: a weighted random forest model was employed for binary classification of the datasets, and a densely connected convolutional network was utilized to directly estimate the left ventricular diastolic diameter index (LVDdI) through regression. Finally, the accuracy of the two models was validated by comparing their results with clinical measurements, using accuracy and the area under the receiver operating characteristic curve (AUC-ROC) to assess their capability for identifying LVE patients. RESULTS: The classification model exhibited superior performance with an accuracy of 0.91 and an AUC-ROC of 0.93. The regression model achieved an accuracy of 0.88 and an AUC-ROC of 0.89, indicating that both models can quickly and accurately identify LVE in HF patients. CONCLUSION: The proposed ML methods are verified to achieve effective classification and regression with good performance for identifying LVE in HF patients based on pulse wave signals. This study thus demonstrates the feasibility and potential of the ML-based strategy for clinical practice while offering an effective and robust tool for diagnosing and intervening ventricular remodeling.

Asunto(s)