Search

A growing number of studies have shown that aberrant microRNA (miRNA) expression is closely associated with the evolution and development of various complex human diseases. These key biomarkers’ identification and observation are significant for gaining a deeper understanding of disease pathogenesis and therapeutic mechanisms. Consequently, pinpointing potential miRNA–disease associations (MDA) has become a prominent bioinformatics subject, encouraging several new computational methods given the advances in graph neural networks (GNN). Nevertheless, these existing methods commonly fail to exploit the network nodes’ global feature information, leaving the generation of high-quality embedding representations using graph properties as a critical unsolved issue. Addressing these challenges, we introduce the DAEMDA, a computational method designed to optimize the current models’ efficacy. First, we construct similarity and heterogeneous networks involving miRNAs and diseases, relying on experimentally corroborated miRNA–disease association data and analogous information. Then, a newly-fashioned parallel dual-channel feature encoder, designed to better comprehend the global information within the heterogeneous network and generate varying embedding representations, follows this. Ultimately, employing a neural network classifier, we merge the dual-channel embedding representations and undertake association predictions between miRNA and disease nodes. The experimental results of five-fold cross-validation and case studies of major diseases based on the HMDD v3.2 database show that this method can generate high-quality embedded representations and effectively improve the accuracy of MDA prediction.

The agile earth observation satellite scheduling problem (AEOSSP) is a combinatorial optimization problem with time-dependent constraints. Recently, many construction heuristics and meta-heuristics have been proposed; however, existing methods cannot balance the requirements of efficiency and timeliness. In this paper, we propose a graph attention network-based decision neural network (GDNN) to solve the AEOSSP. Specifically, we first represent the task and time-dependent attitude transition constraints by a graph. We then describe the problem as a Markov decision process and perform feature engineering. On this basis, we design a GDNN to guide the construction of the solution sequence and train it with proximal policy optimization (PPO). Experimental results show that the proposed method outperforms construction heuristics at scheduling profit by at least 45%. The proposed method can also calculate the approximate profits of the state-of-the-art method with an error of less than 7% and reduce scheduling time markedly. Finally, we demonstrate the scalability of the proposed method.

Electricity load forecasting is of great significance for the overall operation of the power system and the orderly use of electricity at a later stage. However, traditional load forecasting does not consider the change in load quantity at each time point, while the information on the time difference of the load data can reflect the dynamic evolution information of the load data, which is a very important factor for load forecasting. In addition, the research topics in recent years mainly focus on the learning of the complex relationships of load sequences in time latitude by graph neural networks. The relationships between different variables of load sequences are not explicitly captured. In this paper, we propose a model that combines a differential learning network and a multidimensional feature graph attention layer, it can model the time dependence and dynamic evolution of load sequences by learning the amount of load variation at different time points, while representing the correlation of different variable features of load sequences through the graph attention layer. Comparative experiments show that the prediction errors of the proposed model have decreased by 5–26% compared to other advanced methods in the UC Irvine Machine Learning Repository Electricity Load Chart public dataset.

The prediction of drug–target interaction (DTI) is crucial to drug discovery. Although the interactions between the drug and target can be accurately verified by traditional biochemical experiments, the determination of DTI through biochemical experiments is a time-consuming, laborious, and expensive process. Therefore, we propose a learning-based framework named BG-DTI for drug–target interaction prediction. Our model combines two main approaches based on biological features and heterogeneous networks to identify interactions between drugs and targets. First, we extract original features from the sequence to encode each drug and target. Later, we further consider the relationships among various biological entities by constructing drug–drug similarity networks and target–target similarity networks. Furthermore, a graph convolutional network and a graph attention network in the graph representation learning module help us learn the features representation of drugs and targets. After obtaining the features from graph representation learning modules, these features are combined into fusion descriptors for drug–target pairs. Finally, we send the fusion descriptors and labels to a random forest classifier for predicting DTI. The evaluation results show that BG-DTI achieves an average AUC of 0.938 and an average AUPR of 0.930, which is better than those of five existing state-of-the-art methods. We believe that BG-DTI can facilitate the development of drug discovery or drug repurposing.

Agile-satellite mission planning is a crucial issue in the construction of satellite constellations. The large scale of remote sensing missions and the high complexity of constraints in agile-satellite mission planning pose challenges in the search for an optimal solution. To tackle the issue, a dynamic destroy deep-reinforcement learning (D3RL) model is designed to facilitate subsequent optimization operations via adaptive destruction to the existing solutions. Specifically, we first perform a clustering and embedding operation to reconstruct tasks into a clustering graph, thereby improving data utilization. Secondly, the D3RL model is established based on graph attention networks (GATs) to enhance the search efficiency for optimal solutions. Moreover, we present two applications of the D3RL model for intensive scenes: the deep-reinforcement learning (DRL) method and the D3RL-based large-neighborhood search method (DRL-LNS). Experimental simulation results illustrate that the D3RL-based approaches outperform the competition in terms of solutions’ quality and computational efficiency, particularly in more challenging large-scale scenarios. DRL-LNS outperforms ALNS with an average scheduling rate improvement of approximately 11% in Area instances. In contrast, the DRL approach performs better in World scenarios, with an average scheduling rate that is around 8% higher than that of ALNS.

Integrating lexical information into Chinese character embedding is a valid method to figure out the Chinese named entity recognition (NER) issue. However, most existing methods focus only on the discovery of named entity boundaries, considering only the words matched by the Chinese characters. They ignore the association between Chinese characters and their left and right matching words. They ignore the local semantic information of the character’s neighborhood, which is crucial for Chinese NER. The Chinese language incorporates a significant number of polysemous words, meaning that a single word can possess multiple meanings. Consequently, in the absence of sufficient contextual information, individuals may encounter difficulties in comprehending the intended meaning of a text, leading to the emergence of ambiguity. We consider how to handle the issue of entity ambiguity because of polysemous words in Chinese texts in different contexts more simply and effectively. We propose in this paper the use of graph attention networks to construct relatives among matching words and neighboring characters as well as matching words and adding left- and right-matching words directly using semantic information provided by the local lexicon. Moreover, this paper proposes a short-sequence convolutional neural network (SSCNN). It utilizes the generated shorter subsequence encoded with the sliding window module to enhance the perception of local information about the character. Compared with the widely used Chinese NER models, our approach achieves 1.18%, 0.29%, 0.18%, and 1.1% improvement on the four benchmark datasets Weibo, Resume, OntoNotes, and E-commerce, respectively, and proves the effectiveness of the model.

Text classification is one of the most fundamental tasks in text data analysis. Generally, textual data are extensive in scale and complex in the inherent relationship, leading to low accuracy in traditional classification models. This paper proposes a multi-label classification model based on multi-layer neural network architecture. We first construct a dual-attention mechanism graph neural network (named DGAT for short) to fuse the typological and informational features of the target node and the connected nodes. Secondly, we also build a multi-layer network architecture with multiple DGATs to expand the range of neighborhood nodes participating in the feature fusion to meet the needs of classifying different datasets. To ensure the learning ability of the model, we also use the residual network to solve the problem of error rise and gradient descent caused by multi-layer network architecture. Finally, we conducted a large number of experiments on five benchmark datasets. The results show that the accuracy of the proposed model is significantly better than that of the traditional models, and that there is a noticeable improvement when compared with other deep learning methods.

Traffic flow prediction is of great significance for traffic control, and it has been challenging for capturing the complex spatial-temporal correlation. However, most existing prediction methods only consider the spatial adjacency of the nodes (i.e., static spatial correlation), lacking sufficient analysis of non-stationary traffic conditions (i.e., dynamic spatial correlation). The combination of static spatial correlation and dynamic spatial correlation enables the model to comprehensively analyze the feature of traffic flow at each moment and improve the mining capability. To address this problem, we use the multi-head self-attention mechanism to establish a hybrid model integrating static and dynamic spatial correlation neural network (SDSCNN) for traffic flow prediction. Specifically, we first construct static adjacency matrix and dynamic adjacency matrix according to different methods. These two matrices are simultaneously input into Graph Attention Network for analysis. The two outputs are integrated by the sum operation. Then the fused static and dynamic spatial features are fed into the multi-head self-attention layer to analyze the temporal correlation. Also, multi-layer SDSCNNs are stacked to further analyze the dynamic correlations between road sections, as well as to improve the model’s multi-step prediction capability. Finally, Multi-layer Perceptron is used to output the prediction results. Extensive experiments are conducted using the datasets PEMS04, PEMS08, and METR-LA. And the results demonstrate that our model shows a good prediction performance.

In the real world, a large number of multivariate time series data are generated by Internet of Things systems, which are composed of many connected sensing devices. Therefore, it is impractical to consider only a single univariate time series for decision-making. High-dimensional time series decrease the performance of traditional anomaly detection methods. Moreover, many previously developed methods capture temporal correlations instead of spatial correlations. Therefore, it is necessary to learn the temporal and spatial correlations between different time series and timestamps. In this paper, to achieve improved anomaly detection performance for multivariate time series, we propose a novel architecture based on a graph attention network (GAT) with multihead dynamic attention (MDA). This framework simultaneously learns the dependencies between sensors in both the temporal and spatial dimensions. To tackle the overfitting problem in autoencoder (AE)-based methods, we propose a hybrid approach that combines a novel generative adversarial network (GAN) architecture as a reconstruction model with a multilayer perceptron (MLP) as a prediction-based model to detect anomalies together. The detection framework proposed in this paper is called the HAD-multihead dynamic GAT (MDGAT). Extensive experiments on different public benchmarks demonstrate the superior performance of HAD-MDGAT over state-of-the-art methods.

In this paper a pure-attention bottom-up approach, called ViGAT, that utilizes an object detector together with a Vision Transformer (ViT) backbone network to derive object and frame features, and a head network to process these features for the task of event recognition and explanation in video, is proposed. The ViGAT head consists of graph attention network (GAT) blocks factorized along the spatial and temporal dimensions in order to capture effectively both local and long-term dependencies between objects or frames. Moreover, using the weighted in-degrees (WiDs) derived from the adjacency matrices at the various GAT blocks, we show that the proposed architecture can identify the most salient objects and frames that explain the decision of the network. A comprehensive evaluation study is performed, demonstrating that the proposed approach provides state-of-the-art results on three large, publicly available video datasets (FCVID, MiniKinetics, ActivityNet). Source code is made publicly available at: https://github.com/bmezaris/ViGAT

Abstract Background Long non-coding RNAs (lncRNAs) are related to human diseases by regulating gene expression. Identifying lncRNA-disease associations (LDAs) will contribute to diagnose, treatment, and prognosis of diseases. However, the identification of LDAs by the biological experiments is time-consuming, costly and inefficient. Therefore, the development of efficient and high-accuracy computational methods for predicting LDAs is of great significance. Results In this paper, we propose a novel computational method (gGATLDA) to predict LDAs based on graph-level graph attention network. Firstly, we extract the enclosing subgraphs of each lncRNA-disease pair. Secondly, we construct the feature vectors by integrating lncRNA similarity and disease similarity as node attributes in subgraphs. Finally, we train a graph neural network (GNN) model by feeding the subgraphs and feature vectors to it, and use the trained GNN model to predict lncRNA-disease potential association scores. The experimental results show that our method can achieve higher area under the receiver operation characteristic curve (AUC), area under the precision recall curve (AUPR), accuracy and F1-Score than the state-of-the-art methods in five fold cross-validation. Case studies show that our method can effectively identify lncRNAs associated with breast cancer, gastric cancer, prostate cancer, and renal cancer. Conclusion The experimental results indicate that our method is a useful approach for predicting potential LDAs.

As an indispensable technology of intelligent education, intelligent tutorial algorithms for solving mathematical or physical problems have attracted much attention in recent years. Nevertheless, since solving mechanics problems requires complex force analysis and motion analysis, current researches are mainly focus on solving geometry proof problems and direct circuit problems. There are some inherent challenges on developing such algorithms, including the low intelligence, mobility and interpretability of the comprehension algorithm. Therefore, this article develops a novel algorithm for solving mechanics problems. First, we propose a comprehension model for mechanics problems and convert problem understanding into relation extraction. Furthermore, a novel neural model combining pretrained model BERT and graph attention network (GAT) is proposed to extract the direct conditions of input mechanics problems. Second, a hidden information mining method is proposed for supplementing the conditions of the input problem. Third, a predicate logic based algorithm is proposed for force analysis. Finally, a solving algorithm is presented for choosing equations to acquire the solutions. Solving experiments and sensitivity analysis are provided to demonstrate the effectiveness of the proposed algorithm.

Background: Automatic and accurate recognition of various biomedical named entities from literature is an important task of biomedical text mining, which is the foundation of extracting biomedical knowledge from unstructured texts into structured formats. Using the sequence labeling framework and deep neural networks to implement biomedical named entity recognition (BioNER) is a common method at present. However, the above method often underutilizes syntactic features such as dependencies and topology of sentences. Therefore, it is an urgent problem to be solved to integrate semantic and syntactic features into the BioNER model. Results: In this paper, we propose a novel biomedical named entity recognition model, named BioByGANS (BioBERT/SpaCy-Graph Attention Network-Softmax), which uses a graph to model the dependencies and topology of a sentence and formulate the BioNER task as a node classification problem. This formulation can introduce more topological features of language and no longer be only concerned about the distance between words in the sequence. First, we use periods to segment sentences and spaces and symbols to segment words. Second, contextual features are encoded by BioBERT, and syntactic features such as part of speeches, dependencies and topology are preprocessed by SpaCy respectively. A graph attention network is then used to generate a fusing representation considering both the contextual features and syntactic features. Last, a softmax function is used to calculate the probabilities and get the results. We conduct experiments on 8 benchmark datasets, and our proposed model outperforms existing BioNER state-of-the-art methods on the BC2GM, JNLPBA, BC4CHEMD, BC5CDR-chem, BC5CDR-disease, NCBI-disease, Species-800, and LINNAEUS datasets, and achieves F1-scores of 85.15%, 78.16%, 92.97%, 94.74%, 87.74%, 91.57%, 75.01%, 90.99%, respectively. Conclusion: The experimental results on 8 biomedical benchmark datasets demonstrate the effectiveness of our model, and indicate that formulating the BioNER task into a node classification problem and combining syntactic features into the graph attention networks can significantly improve model performance. [ABSTRACT FROM AUTHOR]

Background: Drug-target interactions (DTIs) prediction becomes more and more important for accelerating drug research and drug repositioning. Drug-target interaction network is a typical model for DTIs prediction. As many different types of relationships exist between drug and target, drug-target interaction network can be used for modeling drug-target interaction relationship. Recent works on drug-target interaction network are mostly concentrate on drug node or target node and neglecting the relationships between drug-target. Results: We propose a novel prediction method for modeling the relationship between drug and target independently. Firstly, we use different level relationships of drugs and targets to construct feature of drug-target interaction. Then, we use line graph to model drug-target interaction. After that, we introduce graph transformer network to predict drug-target interaction. Conclusions: This method introduces a line graph to model the relationship between drug and target. After transforming drug-target interactions from links to nodes, a graph transformer network is used to accomplish the task of predicting drug-target interactions. [ABSTRACT FROM AUTHOR]

Most of the existing anomaly detection methods are only applicable to the anomaly detection in single-dimensional or simple patterns. These methods do not apply to multi-dimensional and complex data. Therefore, a method to solve the anomaly detection of complex time series was proposed, which involves cutting the time series into several sub-sequences and clustering similar sub-sequences to deviate the data from the context. Then, based on gated recurrent unit（GRU）, and graph attention network（GAT）, the method also includes training its unique prediction model on each category series, and modeling simultaneously at the time level and feature level to improve the credibility of time point prediction. Finally, the predicted value was compared with the actual value, and the threshold value was selected using the 3σ criterion to determine the outlier. The results show that the accuracy of the method on SMD and ASD data sets reaches 94.86% and 92.71% in the context of anomaly. [ABSTRACT FROM AUTHOR]

Epilepsy is a neurological disorder caused by brain dysfunction, which could cause uncontrolled behavior, loss of consciousness and other hazards. Electroencephalography (EEG) is an indispensable auxiliary tool for clinical diagnosis. Great progress has been made by current seizure identification methods. However, the performance of the methods on different patients varies a lot. In order to deal with this problem, we propose an automatic seizure identification method based on brain connectivity learning. The connectivity of different brain regions is modeled by a graph. Different from the manually defined graph structure, our method can extract the optimal graph structure and EEG features in an end-to-end manner. Combined with the popular graph attention neural network (GAT), this method achieves high performance and stability on different patients from the CHB-MIT dataset. The average values of accuracy, sensitivity, specificity, F1-score and AUC of the proposed model are 98.90%, 98.33%, 98.48%, 97.72% and 98.54%, respectively. The standard deviations of the above five indicators are 0.0049, 0.0125, 0.0116 and 0.0094, respectively. Compared with the existing seizure identification methods, the stability of the proposed model is improved by 78–95%. [ABSTRACT FROM AUTHOR]

It has become a tendency to use a combination of autoencoders and graph neural networks for attribute graph clustering to solve the community detection problem. However, the existing methods do not consider the influence differences between node neighborhood information and high-order neighborhood information, and the fusion of structural and attribute features is insufficient. In order to make better use of structural information and attribute information, we propose a model named community detection fusing graph attention network (CDFG). Specifically, we firstly use an autoencoder to learn attribute features. Then the graph attention network not only calculates the influence weight of the neighborhood node on the target node but also adds the high-order neighborhood information to learn the structural features. After that, the two features are initially fused by the balance parameter. The feature fusion module extracts the hidden layer representation of the graph attention layer to calculate the self-correlation matrix, which is multiplied by the node representation obtained by the preliminary fusion to achieve secondary fusion. Finally, the self-supervision mechanism makes it face the community detection task. Experiments are conducted on six real datasets. Using four evaluation metrics, the CDFG model performs better on most datasets, especially for the networks with longer average paths and diameters and smaller clustering coefficients. [ABSTRACT FROM AUTHOR]

Network alignment, which is also known as user identity linkage, is a kind of network analysis task that predicts overlapping users between two different social networks. This research direction has attracted much attention from the research community, and it is considered to be one of the most important research directions in the field of social network analysis. There are many different models for finding users that overlap between two networks, but most of these models use separate and different techniques to solve prediction problems, with very little work that has combined them. In this paper, we propose a method that combines different embedding techniques to solve the network alignment problem. Each association network alignment technique has its advantages and disadvantages, so combining them together will take full advantage and can overcome those disadvantages. Our model combines three-level embedding techniques of text-based user attributes, a graph attention network, a graph-drawing embedding technique, and fuzzy c-mean clustering to embed each piece of network information into a low-dimensional representation. We then project them into a common space by using canonical correlation analysis and compute the similarity matrix between them to make predictions. We tested our network alignment model on two real-life datasets, and the experimental results showed that our method can considerably improve the accuracy by about 10–15% compared to the baseline models. In addition, when experimenting with different ratios of training data, our proposed model could also handle the over-fitting problem effectively. [ABSTRACT FROM AUTHOR]

Entity linking is a process of linking mentions in a document with entities in a knowledge base. Collective entity disambiguation refers to mapping of multiple mentions in a document with their corresponding entities in a knowledge base. Most previous research has been based on the assumption that all mentions in the same document represent the same topic. However, mentions usually correspond to different topics. In this article, we proposes a new global model to explore the extraction of multitopic coherence in the same document. Herein, we present mention association graphs and candidate entity association graphs to obtain multitopic coherence features of the same document using graph neural networks (GNNs). In particular, we propose a variant GNN for our model and a particular graph readout function. We conducted extensive experiments on several datasets to demonstrate the effectiveness to the proposed model. [ABSTRACT FROM AUTHOR]

Computable models as a fundamental candidate for traditional biological experiments have been applied in inferring lncRNA-disease association (LDA) for many years, without time-consuming and laborious limitations. However, sparsity inherently existing in known heterogeneous bio-data is an obstacle to computable models to improve prediction accuracy further. Therefore, a new computational model composed of multiple mechanisms for lncRNA-disease association (MM-LDA) prediction was proposed, based on the fusion of the graph attention network (GAT) and inductive matrix completion (IMC). MM-LDA has two key steps to improve prediction accuracy: first, a multiple-operator aggregation was designed in the n-heads attention mechanism of the GAT. With this step, features of lncRNA nodes and disease nodes were enhanced. Second, IMC was introduced into the enhanced node features obtained in the first step, and then the LDA network was reconstructed to solve the cold start problem when data deficiency of the entire row or column happened in a known association matrix. Our MM-LDA achieved the following progress: first, using the Adam optimizer that adaptively adjusted the model learning rate could increase the convergent speed and not fall into local optima as well. Second, more excellent predictive ability was achieved against other similar models (with an AUC value of 0.9395 and an AUPR value of 0.8057 obtained from 5-fold cross-validation). Third, a 6.45% lower time cost was consumed against the advanced model GAMCLDA. In short, our MM-LDA achieved a more comprehensive prediction performance in terms of prediction accuracy and time cost. [ABSTRACT FROM AUTHOR]

Drug-drug interaction prediction plays an important role in pharmacology and clinical applications. Most traditional methods predict drug interactions based on drug attributes or network structure. They usually have three limitations: 1) failing to integrate drug features and network structures well, resulting in less informative drug embeddings; 2) being restricted to a single view of drug interaction relationships; 3) ignoring the importance of different neighbors. To tackle these challenges, this paper proposed a multiview fusion based on dual-level attention to predict drug interactions (called MFDA). The MFDA first constructed multiple views for the drug interaction relationship, and then adopted a cross-fusion strategy to deeply fuse drug features with the drug interaction network under each view. To distinguish the importance of different neighbors and views, MFDA adopted a dual-level attention mechanism(node level and viewlevel) to obtain the unified drug embedding for drug interaction prediction. Extensive experiments were conducted on real datasets, and the MFDA demonstrated superior performance compared to state-of-the-art baselines. In the multitask analysis of new drug reactions, MFDA obtained higher scores on multiple metrics. In addition, its prediction results corresponded to specific drug reaction events, which achieved more accurate predictions. [ABSTRACT FROM AUTHOR]

In recent years, pre-trained language models, represented by the bidirectional encoder representations from transformers (BERT) model, have achieved remarkable success in machine reading comprehension (MRC). However, limited by the structure of BERT-based MRC models (for example, restrictions on word count), such models cannot effectively integrate significant features, such as syntax relations, semantic connections, and long-distance semantics between sentences, leading to the inability of the available models to better understand the intrinsic connections between text and questions to be answered based on it. In this paper, a multi-granularity syntax guidance (MgSG) module that consists of a "graph with dependence" module and a "graph with entity" module is proposed. MgSG selects both sentence and word granularities to guide the text model to decipher the text. In particular, syntactic constraints are used to guide the text model while exploiting the global nature of graph neural networks to enhance the model's ability to construct long-range semantics. Simultaneously, named entities play an important role in text and answers and focusing on entities can improve the model's understanding of the text's major idea. Ultimately, fusing multiple embedding representations to form a representation yields the semantics of the context and the questions. Experiments demonstrate that the performance of the proposed method on the Stanford Question Answering Dataset is better when compared with the traditional BERT baseline model. The experimental results illustrate that our proposed "MgSG" module effectively utilizes the graph structure to learn the internal features of sentences, solve the problem of long-distance semantics, while effectively improving the performance of PrLM in machine reading comprehension. [ABSTRACT FROM AUTHOR]

The spatial structure of geochemical patterns is influenced by various geological processes, one of which may be mineralization. Thus, analysis of spatial geochemical patterns facilitates understanding of regional metallogenic mechanisms and recognition of geochemical anomalies related to mineralization. Convolutional neural networks (CNNs) used in previous studies to extract spatial features require regular data (e.g., raster maps) as input. Due to the complex and diverse geological environment, geochemical samples are inevitably irregularly distributed and even partially missing in many spaces, leading to the inapplicability of CNN-based methods for geochemical anomaly identification. Also, interpolation from samples to regular grids often introduces uncertainties. To address these problems, this study innovatively transformed geochemical sampled point data into graphs and introduced graph learning to extract the geochemical patterns. Correspondingly, a novel framework of geochemical identification named GAUGE (recognition of Geochemical Anomalies Using Graph lEarning) is proposed. To assess the performance of the proposed method, this study recognized anomalies related to Au deposits in the Longyan area, the Wuyishan polymetallic metallogenic belt, China. For a set of regularly distributed samples, GAUGE achieved an accuracy similar to that of a traditional convolution autoencoder. More importantly, GAUGE achieved an area under the curve of 0.833, outperforming one-class support vector machine, isolation forest, autoencoder, and deep autoencoder network for a set of irregularly distributed samples by 10.6, 5.2, 4.8, and 2.5%, respectively. By introducing graph learning into geochemical anomaly recognition, this study provides a new perspective of extracting both spatial structure and compositional relationships of multivariate geochemical patterns, which can be applied directly to irregularly distributed samples in irregularly shaped regions without the need for interpolation. Such an improvement greatly enhances the applicability of machine learning methods in geochemical anomaly recognition, providing support for mineral resources evaluation and exploration. [ABSTRACT FROM AUTHOR]

PM2.5 concentration prediction is of great significance to environmental protection and human health. Achieving accurate prediction of PM2.5 concentration has become an important research task. However, PM2.5 pollutants can spread in the earth's atmosphere, causing mutual influence between different cities. To effectively capture the air pollution relationship between cities, this paper proposes a novel spatiotemporal model combining graph attention neural network (GAT) and gated recurrent unit (GRU), named GAT-GRU for PM2.5 concentration prediction. Specifically, GAT is used to learn the spatial dependence of PM2.5 concentration data in different cities, and GRU is to extract the temporal dependence of the long-term data series. The proposed model integrates the learned spatio-temporal dependencies to capture long-term complex spatio-temporal features. Considering that air pollution is related to the meteorological conditions of the city, the knowledge acquired from meteorological data is used in the model to enhance PM2.5 prediction performance. The input of the GAT-GRU model consists of PM2.5 concentration data and meteorological data. In order to verify the effectiveness of the proposed GAT-GRU prediction model, this paper designs experiments on real-world datasets compared with other baselines. Experimental results prove that our model achieves excellent performance in PM2.5 concentration prediction. [ABSTRACT FROM AUTHOR]

Increasing evidence suggest that circRNA, as one of the most promising emerging biomarkers, has a very close relationship with diseases. Exploring the relationship between circRNA and diseases can provide novel perspective for diseases diagnosis and pathogenesis. The existing circRNA-disease association (CDA) prediction models, however, generally treat the data attributes equally, do not pay special attention to the attributes with more significant influence, and do not make full use of the correlation and symbiosis between attributes to dig into the latent semantic information of the data. Therefore, in response to the above problems, this paper proposes a natural semantic enhancement method NSECDA to predict CDA. In practical terms, we first recognize the circRNA sequence as a biological language, and analyze its natural semantic properties through the natural language understanding theory; then integrate it with disease attributes, circRNA and disease Gaussian Interaction Profile (GIP) kernel attributes, and use Graph Attention Network (GAT) to focus on the influential attributes, so as to mine the deeply hidden features; finally, the Rotation Forest (RoF) classifier was used to accurately determine CDA. In the gold standard data set CircR2Disease, NSECDA achieved 92.49% accuracy with 0.9225 AUC score. In comparison with the non-natural semantic enhancement model and other classifier models, NSECDA also shows competitive performance. Additionally, 25 of the CDA pairs with unknown associations in the top 30 prediction scores of NSECDA have been proven by newly reported studies. These achievements suggest that NSECDA is an effective model to predict CDA, which can provide credible candidate for subsequent wet experiments, thus significantly reducing the scope of investigations. [ABSTRACT FROM AUTHOR]

Background: Making clear what kinds of metabolic pathways a drug compound involves in can help researchers understand how the drug is absorbed, distributed, metabolized, and excreted. The characteristics of a compound such as structure, composition and so on directly determine the metabolic pathways it participates in. Methods: We developed a novel hybrid framework based on the graph attention network (GAT) to predict the metabolic pathway classes that a compound involves in, named HFGAT, by making use of its global and local characteristics. The framework mainly consists of a two-branch feature extracting layer and a fully connected (FC) layer. In the two-branch feature extracting layer, one branch is responsible to extract global features of the compound; and the other branch introduces a GAT consisting of two graph attention layers to extract local structural features of the compound. Both the global and the local features of the compound are then integrated into the FC layer which outputs the predicted result of metabolic pathway categories that the compound belongs to. Results: We compared the multi-class classification performance of HFGAT with six other representative methods, including five classic machine learning methods and one graph convolutional network (GCN) based deep learning method, on the benchmark dataset containing 6999 compounds belonging to 11 pathway categories. The results showed that the deep learning-based methods (HFGAT, GCN-based method) outperformed the traditional machine learning methods in the prediction of metabolic pathways and our proposed HFGAT method performed better than the GCN-based method. Moreover, HFGAT achieved higher F 1 scores on 8 of 11 classes than the GCN-based method. Conclusions: Our proposed HFGAT makes use of both the global and local information of the compounds to predict their metabolic pathway categories and has achieved a significant performance. Compared with the GCN model, the introduction of the GAT can help our model pay more attention to substructures of the compound that are useful for the prediction task. The study provided a potential method for drug discovery with all types of metabolic reactions that may be involved in the decomposition and synthesis of pharmaceutical compounds in the organism. [ABSTRACT FROM AUTHOR]

The use of high-throughput omics technologies is becoming increasingly popular in all facets of biomedical science. The mRNA sequencing (RNA-seq) method reports quantitative measures of more than tens of thousands of biological features. It provides a more comprehensive molecular perspective of studied cancer mechanisms compared to traditional approaches. Graph-based learning models have been proposed to learn important hidden representations from gene expression data and network structure to improve cancer outcome prediction, patient stratification, and cell clustering. However, these graph-based methods cannot rank the importance of the different neighbors for a particular sample in the downstream cancer subtype analyses. In this study, we introduce omicsGAT, a graph attention network (GAT) model to integrate graph-based learning with an attention mechanism for RNA-seq data analysis. The multi-head attention mechanism in omicsGAT can more effectively secure information of a particular sample by assigning different attention coefficients to its neighbors. Comprehensive experiments on The Cancer Genome Atlas (TCGA) breast cancer and bladder cancer bulk RNA-seq data and two single-cell RNA-seq datasets validate that (1) the proposed model can effectively integrate neighborhood information of a sample and learn an embedding vector to improve disease phenotype prediction, cancer patient stratification, and cell clustering of the sample and (2) the attention matrix generated from the multi-head attention coefficients provides more useful information compared to the sample correlation-based adjacency matrix. From the results, we can conclude that some neighbors play a more important role than others in cancer subtype analyses of a particular sample based on the attention coefficient. [ABSTRACT FROM AUTHOR]

Recently, graph neural networks (GNN), due to their compelling representation learning ability, have been exploited to deal with emotion-cause pair extraction (ECPE). However, current GNN-based ECPE methods mostly concentrate on modeling the local dependency relation between homogeneous nodes at the semantic granularity of clauses or clause pairs, while they fail to take full advantage of the rich semantic information in the document. To solve this problem, we propose a novel hierarchical heterogeneous graph attention network to model global semantic relations among nodes. Especially, our method introduces all types of semantic elements involved in the ECPE, not just clauses or clause pairs. Specifically, we first model the dependency between clauses and words, in which word nodes are also exploited as an intermediary for the association between clause nodes. Secondly, a pair-level subgraph is constructed to explore the correlation between the pair nodes and their different neighboring nodes. Representation learning of clauses and clause pairs is achieved by two-level heterogeneous graph attention networks. Experiments on the benchmark datasets show that our proposed model achieves a significant improvement over 13 compared methods. [ABSTRACT FROM AUTHOR]

Background: Development of new methods for analysis of protein–protein interactions (PPIs) at molecular and nanometer scales gives insights into intracellular signaling pathways and will improve understanding of protein functions, as well as other nanoscale structures of biological and abiological origins. Recent advances in computational tools, particularly the ones involving modern deep learning algorithms, have been shown to complement experimental approaches for describing and rationalizing PPIs. However, most of the existing works on PPI predictions use protein-sequence information, and thus have difficulties in accounting for the three-dimensional organization of the protein chains. Results: In this study, we address this problem and describe a PPI analysis based on a graph attention network, named Struct2Graph, for identifying PPIs directly from the structural data of folded protein globules. Our method is capable of predicting the PPI with an accuracy of 98.89% on the balanced set consisting of an equal number of positive and negative pairs. On the unbalanced set with the ratio of 1:10 between positive and negative pairs, Struct2Graph achieves a fivefold cross validation average accuracy of 99.42%. Moreover, Struct2Graph can potentially identify residues that likely contribute to the formation of the protein–protein complex. The identification of important residues is tested for two different interaction types: (a) Proteins with multiple ligands competing for the same binding area, (b) Dynamic protein–protein adhesion interaction. Struct2Graph identifies interacting residues with 30% sensitivity, 89% specificity, and 87% accuracy. Conclusions: In this manuscript, we address the problem of prediction of PPIs using a first of its kind, 3D-structure-based graph attention network (code available at https://github.com/baranwa2/Struct2Graph). Furthermore, the novel mutual attention mechanism provides insights into likely interaction sites through its unsupervised knowledge selection process. This study demonstrates that a relatively low-dimensional feature embedding learned from graph structures of individual proteins outperforms other modern machine learning classifiers based on global protein features. In addition, through the analysis of single amino acid variations, the attention mechanism shows preference for disease-causing residue variations over benign polymorphisms, demonstrating that it is not limited to interface residues. [ABSTRACT FROM AUTHOR]

Motivation: CircularRNA (circRNA) is a class of noncoding RNA with high conservation and stability, which is considered as an important disease biomarker and drug target. Accumulating pieces of evidence have indicated that circRNA plays a crucial role in the pathogenesis and progression of many complex diseases. As the biological experiments are time-consuming and labor-intensive, developing an accurate computational prediction method has become indispensable to identify disease-related circRNAs. Results: We presented a hybrid graph representation learning framework, named GraphCDA, for predicting the potential circRNA–disease associations. Firstly, the circRNA–circRNA similarity network and disease–disease similarity network were constructed to characterize the relationships of circRNAs and diseases, respectively. Secondly, a hybrid graph embedding model combining Graph Convolutional Networks and Graph Attention Networks was introduced to learn the feature representations of circRNAs and diseases simultaneously. Finally, the learned representations were concatenated and employed to build the prediction model for identifying the circRNA–disease associations. A series of experimental results demonstrated that GraphCDA outperformed other state-of-the-art methods on several public databases. Moreover, GraphCDA could achieve good performance when only using a small number of known circRNA–disease associations as the training set. Besides, case studies conducted on several human diseases further confirmed the prediction capability of GraphCDA for predicting potential disease-related circRNAs. In conclusion, extensive experimental results indicated that GraphCDA could serve as a reliable tool for exploring the regulatory role of circRNAs in complex diseases. [ABSTRACT FROM AUTHOR]

Motivation Accurate and efficient prediction of the molecular property is one of the fundamental problems in drug research and development. Recent advancements in representation learning have been shown to greatly improve the performance of molecular property prediction. However, due to limited labeled data, supervised learning-based molecular representation algorithms can only search limited chemical space and suffer from poor generalizability. Results In this work, we proposed a self-supervised learning method, ATMOL, for molecular representation learning and properties prediction. We developed a novel molecular graph augmentation strategy, referred to as attention-wise graph masking, to generate challenging positive samples for contrastive learning. We adopted the graph attention network as the molecular graph encoder, and leveraged the learned attention weights as masking guidance to generate molecular augmentation graphs. By minimization of the contrastive loss between original graph and augmented graph, our model can capture important molecular structure and higher order semantic information. Extensive experiments showed that our attention-wise graph mask contrastive learning exhibited state-of-the-art performance in a couple of downstream molecular property prediction tasks. We also verified that our model pretrained on larger scale of unlabeled data improved the generalization of learned molecular representation. Moreover, visualization of the attention heatmaps showed meaningful patterns indicative of atoms and atomic groups important to specific molecular property. [ABSTRACT FROM AUTHOR]

Motivation The associations between biomarkers and human diseases play a key role in understanding complex pathology and developing targeted therapies. Wet lab experiments for biomarker discovery are costly, laborious and time-consuming. Computational prediction methods can be used to greatly expedite the identification of candidate biomarkers. Results Here, we present a novel computational model named GTGenie for predicting the biomarker–disease associations based on graph and text features. In GTGenie, a graph attention network is utilized to characterize diverse similarities of biomarkers and diseases from heterogeneous information resources. Meanwhile, a pretrained BERT-based model is applied to learn the text-based representation of biomarker–disease relation from biomedical literature. The captured graph and text features are then integrated in a bimodal fusion network to model the hybrid entity representation. Finally, inductive matrix completion is adopted to infer the missing entries for reconstructing relation matrix, with which the unknown biomarker–disease associations are predicted. Experimental results on HMDD, HMDAD and LncRNADisease data sets showed that GTGenie can obtain competitive prediction performance with other state-of-the-art methods. Availability The source code of GTGenie and the test data are available at: https://github.com/Wolverinerine/GTGenie. [ABSTRACT FROM AUTHOR]

For a long time, the detection and extraction of printed surface defects has been a hot issue in the print industry. Nowadays, defect detection of a large number of products still relies on traditional image processing algorithms such as scale invariant feature transform (SIFT) and oriented fast and rotated brief (ORB), and researchers need to design algorithms for specific products. At present, a large number of defect detection algorithms based on object detection have been applied but need lots of labeling samples with defects. Besides, there are many kinds of defects in printed surface, so it is difficult to enumerate all defects. Most defect detection based on unsupervised learning of positive samples use generative adversarial networks (GAN) and variational auto-encoders (VAE) algorithms, but these methods are not effective for complex printed surface. Aiming at these problems, In this paper, an unsupervised defect detection and extraction algorithm for printed surface based on positive samples in the complex printed surface is proposed innovatively. We propose a kind of defect detection and extraction network based on image matching network. This network is divided into the full convolution network of feature points extraction, and the graph attention network using self attention and cross attention. Though the key points extraction network, we can get robustness key points in the complex printed images, and the graph network can solve the problem of the deviation because of different camera positions and the influence of defect in the different production lines. Just one positive sample image is needed as the benchmark to detect the defects. The algorithm in this paper has been proved in "The First ZhengTu Cup on Campus Machine Vision AI Competition" and got excellent results in the finals. We are working with the company to apply it in production. [ABSTRACT FROM AUTHOR]

Copyright of Journal Of Sichuan University (Natural Sciences Division) / Sichuan Daxue Xuebao-Ziran Kexueban is the property of Editorial Department of Journal of Sichuan University Natural Science Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)