Deep Graph Convolutional Network Research Articles

A novel candidate disease gene prioritization method using deep graph convolutional networks and semi-supervised learning

BackgroundSelecting and prioritizing candidate disease genes is necessary before conducting laboratory studies as identifying disease genes from a large number of candidate genes using laboratory methods, is a very costly and time-consuming task. There are many machine learning-based gene prioritization methods. These methods differ in various aspects including the feature vectors of genes, the used datasets with different structures, and the learning model. Creating a suitable feature vector for genes and an appropriate learning model on a variety of data with different and non-Euclidean structures, including graphs, as well as the lack of negative data are very important challenges of these methods. The use of graph neural networks has recently emerged in machine learning and other related fields, and they have demonstrated superior performance for a broad range of problems.MethodsIn this study, a new semi-supervised learning method based on graph convolutional networks is presented using the novel constructing feature vector for each gene. In the proposed method, first, we construct three feature vectors for each gene using terms from the Gene Ontology (GO) database. Then, we train a graph convolution network on these vectors using protein–protein interaction (PPI) network data to identify disease candidate genes. Our model discovers hidden layer representations encoding in both local graph structure as well as features of nodes. This method is characterized by the simultaneous consideration of topological information of the biological network (e.g., PPI) and other sources of evidence. Finally, a validation has been done to demonstrate the efficiency of our method.ResultsSeveral experiments are performed on 16 diseases to evaluate the proposed method's performance. The experiments demonstrate that our proposed method achieves the best results, in terms of precision, the area under the ROC curve (AUCs), and F1-score values, when compared with eight state-of-the-art network and machine learning-based disease gene prioritization methods.ConclusionThis study shows that the proposed semi-supervised learning method appropriately classifies and ranks candidate disease genes using a graph convolutional network and an innovative method to create three feature vectors for genes based on the molecular function, cellular component, and biological process terms from GO data.

Heart disease detection based on internet of things data using linear quadratic discriminant analysis and a deep graph convolutional neural network.

Heart disease is an emerging health issue in the medical field, according to WHO every year around 10 billion people are affected with heart abnormalities. Arteries in the heart generate oxygenated blood to all body parts, however sometimes blood vessels become clogged or restrained due to cardiac issues. Past heart diagnosis applications are outdated and suffer from poor performance. Therefore, an intelligent heart disease diagnosis application design is required. In this research work, internet of things (IoT) sensor data with a deep learning-based heart diagnosis application is designed. The heart disease IoT sensor data is collected from the University of California Irvine machine learning repository free open-source dataset which is useful for training the deep graph convolutional network (DG_ConvoNet) deep learning network. The testing data has been collected from the Cleveland Clinic Foundation; it is a collection of 350 real-time clinical instances from heart patients through IoT sensors. The K-means technique is employed to remove noise in sensor data and clustered the unstructured data. The features are extracted to employ Linear Quadratic Discriminant Analysis. DG_ConvoNet is a deep learning process to classify and predict heart diseases. The diagnostic application achieves an accuracy of 96%, sensitivity of 80%, specificity of 73%, precision of 90%, F-Score of 79%, and area under the ROC curve of 75% implementing the proposed model.

NSCGCN: A novel deep GCN model to diagnosis COVID-19

AimCorona Virus Disease 2019 (COVID-19) was a lung disease with high mortality and was highly contagious. Early diagnosis of COVID-19 and distinguishing it from pneumonia was beneficial for subsequent treatment. ObjectivesRecently, Graph Convolutional Network (GCN) has driven a significant contribution to disease diagnosis. However, limited by the nature of the graph convolution algorithm, deep GCN has an over-smoothing problem. Most of the current GCN models are shallow neural networks, which do not exceed five layers. Furthermore, the objective of this study is to develop a novel deep GCN model based on the DenseGCN and the pre-trained model of deep Convolutional Neural Network (CNN) to complete the diagnosis of chest X-ray (CXR) images. MethodsWe apply the pre-trained model of deep CNN to perform feature extraction on the data to complete the extraction of pixel-level features in the image. And then, to extract the potential relationship between the obtained features, we propose Neighbourhood Feature Reconstruction Algorithm to reconstruct them into graph-structured data. Finally, we design a deep GCN model that exploits the graph-structured data to diagnose COVID-19 effectively. In the deep GCN model, we propose a Node-Self Convolution Algorithm (NSC) based on feature fusion to construct a deep GCN model called NSCGCN (Node-Self Convolution Graph Convolutional Network). ResultsExperiments were carried out on the Computed Tomography (CT) and CXR datasets. The results on the CT dataset confirmed that: compared with the six state-of-the-art (SOTA) shallow GCN models, the accuracy and sensitivity of the proposed NSCGCN had improve 8% as sensitivity (Sen.) = 87.50%, F1 score = 97.37%, precision (Pre.) = 89.10%, accuracy (Acc.) = 97.50%, area under the ROC curve (AUC) = 97.09%. Moreover, the results on the CXR dataset confirmed that: compared with the fourteen SOTA GCN models, sixteen SOTA CNN transfer learning models and eight SOTA COVID-19 diagnosis methods on the COVID-19 dataset. Our proposed method had best performances as Sen. = 96.45%, F1 score = 96.45%, Pre. = 96.61%, Acc. = 96.45%, AUC = 99.22%. ConclusionOur proposed NSCGCN model is effective and performed better than the thirty-eight SOTA methods. Thus, the proposed NSC could help build deep GCN models. Our proposed COVID-19 diagnosis method based on the NSCGCN model could help radiologists detect pneumonia from CXR images and distinguish COVID-19 from Ordinary Pneumonia (OPN). The source code of this work will be publicly available at https://github.com/TangChaosheng/NSCGCN.

(Retracted) Deep graph convolutional network-based high-performance detection method for spectral domain gesture image stream

The use of vision-based high-performance detection technology has become an innovative technical methodology. Gestures can express more actions and even emotions, which is more in line with the design idea of large-scale integrated human–computer interaction software, and then assists the development of emotion recognition and other fields. The emerging deep graph convolutional network can capture the interdependence between instances, and then infer the complete information of the image based on specific features. The two-dimensional discrete wavelet and multi-resolution analysis are used to replace the traditional Fourier transform to realize the convolution operation, which improves the accuracy of the generated graph data. This work studies the spectral clustering method of Graph Wavelet Neural Network and adds the local correlation preserving support vector machine as a classifier. This classifier has a simplified structure compared with the cascade classifier and can achieve faster and stable classification results. On the test set, the average accuracy of the algorithm is 93.40%, the recall rate is 96.27%, and the average detection time per frame is 359 ms.

Heterogeneous deep graph convolutional network with citation relational BERT for COVID-19 inline citation recommendation

The outbreak of COVID-19 brings almost the biggest explosions of scientific literature ever. Facing such volume literature, it is hard for researches to find desired citation when carrying out COVID-19 related research, especially for junior researchers. This paper presents a novel neural network based method, called citation relational BERT with heterogeneous deep graph convolutional network (CRB-HDGCN), for COVID-19 inline citation recommendation task. The CRB-HDGCN contains two main stages. The first stage is to enhance the representation learning of BERT model for COVID-19 inline citation recommendation task through CRB. To achieve the above goal, an augmented citation sentence corpus, which replaces the citation placeholder with the title of the cited papers, is used to lightly retrain BERT model. In addition, we extract three types of sentence pair according citation relation, and establish sentence prediction tasks to further fine-tune the BERT model. The second stage is to learn effective dense vector of nodes among COVID-19 bibliographic graph through HDGCN. The HDGCN contains four layers which are essentially all sub neural networks. The first layer is initial embedding layer which generates initial input vectors with fixed size through CRB and a multilayer perceptron. The second layer is a heterogeneous graph convolutional layer. In this layer, we expand traditional homogeneous graph convolutional network into heterogeneous by subtly adding heterogeneous nodes and relations. The third layer is a deep attention layer. This layer uses trainable project vectors to reweight the node importance simultaneously according to both node types and convolution layers, which further promotes the performance of learnt node vectors. The last decoder layer recovers the graph structure and let the whole network trainable. The recommendation is finally achieved by integrating the high performance heterogeneous vectors learnt from CRB-HDGCN with the query vectors. We conduct experiments on the CORD-19 and LitCovid datasets. The results show that compared with the second best method CO-Search, CRB-HDGCN improves MAP, MRR, P@100 and R@100 with 21.8%, 22.7%, 37.6% and 21.2% on CORD-19, and 29.1%, 25.9%, 15.3% and 11.3% on LitCovid, respectively.

MAMF-GCN: Multi-scale adaptive multi-channel fusion deep graph convolutional network for predicting mental disorder

PurposeExisting diagnoses of mental disorders rely on symptoms, patient descriptions, and scales, which are not objective enough. We attempt to explore an objective diagnostic method on fMRI data. Graph neural networks (GNN) have been paid more attention recently because of their advantages in processing unstructured relational data, especially for fMRI data. However, how to deeply embed and well-integrate with different modalities and scales on GNN is still a challenge. Instead of reaching a high degree of fusion, existing GCN methods simply combine image and non-image data. Most graph convolutional network (GCN) models use shallow structures, making it challenging to learn about potential information. Furthermore, current graph construction approaches usually use a single specific brain atlas, limiting the analysis and results. MethodIn this paper, a multi-scale adaptive multi-channel fusion deep graph convolutional network based on an attention mechanism (MAMF-GCN) is proposed to better integrate features of modalities and different atlas by exploiting multi-channel correlation. An encoder automatically combines one channel with non-imaging data to generate similarity weights between subjects using a similarity perception mechanism. Other channels generate multi-scale imaging features of fMRI data after processing in the different atlas. Multi-modal information is fused using an adaptive convolution module that applies a deep graph convolutional network (GCN) to extract information from richer hidden layers. ResultsTo demonstrate the effectiveness of our approach, we evaluate the performance of the proposed method on the Autism Brain Imaging Data Exchange (ABIDE) dataset and the Major Depressive Disorder (MDD) dataset. The experimental result shows that the proposed method outperforms many state-of-the-art methods in node classification performance. An extensive group of experiments on two disease prediction tasks demonstrates that the performance of the proposed MAMF-GCN on MDD/ABIDE dataset is improved by 3.37%–39.83% and 12.59%–32.92%, respectively. Moreover, our proposed method has also shown very effective performance in real-life clinical diagnosis. The comprehensive experiments demonstrate that our method is effective for node classification with brain disorders diagnosis. ConclusionThe proposed MAMF-GCN method simultaneously extracts specific and common embeddings from the topology composed of multi-scale imaging features, phenotypic information, and their combinations, then learning adaptive embedding weights by attention mechanism, which can capture and fuse the multi-scale essential embeddings to improve the classification performance of brain disorder diagnosis.

ZINB-Based Graph Embedding Autoencoder for Single-Cell RNA-Seq Interpretations

Single-cell RNA sequencing (scRNA-seq) provides high-throughput information about the genome-wide gene expression levels at the single-cell resolution, bringing a precise understanding on the transcriptome of individual cells. Unfortunately, the rapidly growing scRNA-seq data and the prevalence of dropout events pose substantial challenges for cell type annotation. Here, we propose a single-cell model-based deep graph embedding clustering (scTAG) method, which simultaneously learns cell–cell topology representations and identifies cell clusters based on deep graph convolutional network. scTAG integrates the zero-inflated negative binomial (ZINB) model into a topology adaptive graph convolutional autoencoder to learn the low-dimensional latent representation and adopts Kullback–Leibler (KL) divergence for the clustering tasks. By simultaneously optimizing the clustering loss, ZINB loss, and the cell graph reconstruction loss, scTAG jointly optimizes cluster label assignment and feature learning with the topological structures preserved in an end-to-end manner. Extensive experiments on 16 single-cell RNA-seq datasets from diverse yet representative single-cell sequencing platforms demonstrate the superiority of scTAG over various state-of-the-art clustering methods.

GIS partial discharge pattern recognition via a novel capsule deep graph convolutional network

Deep learning (DL) has attracted significant attention in partial discharge (PD) pattern recognition of gas-insulated switchgear (GIS). However, the existing DL method extracts numerical information and ignores spatial correlation information. In addition, once the sample size is reduced, model performance is severely degraded. To address these issues, a novel capsule deep graph convolutional network (CDGCN) is employed for GIS PD pattern recognition. First, the GIS PD data is transformed to graph data. Then, the CDGCN is established for GIS PD pattern recognition. The introduction of a ChannelSortPooling layer enriches the graph representation information and filters out the feature values with higher information content. In addition, the multi-view graph representation is converted to a capsule form, and a capsule network with stronger feature extraction capability is introduced to improve the accuracy of the final graph representation. The results reveal that the proposed CDGCN can effectively diagnose the GIS PD and is more accurate than the traditional DL method. The proposed CDGCN can handle small samples pattern recognition problems and provides a reliable reference for GIS PD pattern recognition.

Predicting target–ligand interactions with graph convolutional networks for interpretable pharmaceutical discovery

Drug Discovery is an active research area that demands great investments and generates low returns due to its inherent complexity and great costs. To identify potential therapeutic candidates more effectively, we propose protein–ligand with adversarial augmentations network (PLA-Net), a deep learning-based approach to predict target–ligand interactions. PLA-Net consists of a two-module deep graph convolutional network that considers ligands’ and targets’ most relevant chemical information, successfully combining them to find their binding capability. Moreover, we generate adversarial data augmentations that preserve relevant biological backgrounds and improve the interpretability of our model, highlighting the relevant substructures of the ligands reported to interact with the protein targets. Our experiments demonstrate that the joint ligand–target information and the adversarial augmentations significantly increase the interaction prediction performance. PLA-Net achieves 86.52% in mean average precision for 102 target proteins with perfect performance for 30 of them, in a curated version of actives as decoys dataset. Lastly, we accurately predict pharmacologically-relevant molecules when screening the ligands of ChEMBL and drug repurposing Hub datasets with the perfect-scoring targets.

Fundamental Limits of Deep Graph Convolutional Networks for Graph Classification

Graph convolutional networks (GCNs) are a widely used method for graph representation learning. To elucidate their capabilities and limitations for graph classification, we investigate their power to generate well-separated embedding vectors for graphs sampled from different random graph models, which correspond to different class-conditional distributions in a classification problem. It has been recognized that metric properties of learned representations are important for reduction of complexity of classifiers trained on them. Additionally, we show that inability to generate well-separated embedding vectors for two different graph models implies information-theoretic indistinguishability of these models based on noise-perturbed embedding vectors of sample graphs. We consider graph models arising from graphons, which parametrize all infinite exchangeable graph models. We precisely characterize, in terms of degree profile closeness, the set of graphon pairs that are indistinguishable (in metric and information-theoretic senses) by a GCN with depth at least logarithmic in sample graph size. Outside this set, a very simple architecture suffices for distinguishability. We then exhibit a concrete, infinite set of graphon pairs that are well-separated in cut distance and are indistinguishable by a GCN. These results theoretically match empirical observations of several prior works. Finally, we give empirical results on synthetic and real graph classification datasets, giving some indication that degree profile closeness gives rise to indistinguishability of graph distributions in real datasets, even beyond our theoretical framework.

An effective superpixel-based graph convolutional network for small waterbody extraction from remotely sensed imagery

• We develop a water detection method which is particularly efficient in small water. • Graph convolutional network is innovatively used in image semantic segmentation. • Robustness of SG-waterNet is proven over urban, agricultural and mountainous scenes. Small waterbodies sustain susceptible ecosystems and are influenced by variable dynamics associated with human activities and environmental disturbances. Although remote sensing has displayed efficiency in mapping surface waterbodies on a regular basis, the identification of small waterbodies such as ponds or irrigation ditches remains a challenge, as small waterbodies are often confused with other low-reflectivity surfaces. In this study, a superpixel-based graph convolutional network (GCN) for small waterbody extraction (SG-waterNet) is proposed. Specifically, the SG-waterNet method includes a new object-based representation of an image called a superpixel graph. The superpixel graph contains compact spectral and contextual information and can be exploited by the GCN. A deep GCN architecture is used to efficiently preserve small waterbody features and detect surface waterbodies with high completeness and correctness. We tested the proposed approach on a frequently used open-access Gaofen Image Dataset (GID) and Gaofen-1 image from Hubei Province in China (a total of 11,660 km 2 for research). The extraction accuracy of SG-waterNet for small waterbodies (<2 ha) was between 84.31% and 89.77% at the five evaluation sites, and the method extracted waterbodies 300 m 2 and larger with high confidence. Compared with six state-of-the-art methods, SG-waterNet exhibited significant sensitivity to small waterbodies (especially smaller than 100 m 2 ) and detected small waterbody boundaries with the highest completeness and correctness. The average accuracy improvement achieved with SG-waterNet at the evaluation sites ranged from 11.10% to 13.87%. The proposed method is a significant advancement in small waterbody monitoring and can provide promising and practical solutions for real-world applications.

Treeago: Tree-structure aggregation and optimization for graph neural network

Graph Convolutional Networks (GCNs) have achieved much success in various graph learning tasks. However, as the number of layers increases, the smoothing of GCNs will over-mix the neighbors’ information, leading output towards space with low expressivity. It is known as the over-smoothing issue. Although several works have refined deep GCNs by optimizing network structure, receptive field, and topology, the over-smoothing issue cannot be completely avoided. In this paper, we propose a recurrent neural network framework for learning graph representation while avoiding over-smoothing effectively, which is the tree-structure aggregation and optimization framework named Treeago. Treeago firstly transforms the irregularly distributed graph into sequential trees. Then, Treeago adopts Tree-LSTM with attention to aggregate important neighbors’ feature information to the graph representation. Tree-LSTM with attention can prevent the mixing of noise neighbors’ information to avoid the over-smoothing issue. Finally, Treeago uses an edge pruning optimization framework based on reinforcement learning to enhance the model’s performance further. Experimental results on multiple real-world datasets show that Treeago effectively avoids over-smoothing and yields state-of-the-art results.

DeepGCNs-Att: Point cloud semantic segmentation with contextual point representations

Graph Convolutional Networks are able to characterize non-Euclidean spaces effectively compared with traditional Convolutional Neural Networks, which can extract the local features of the point cloud using deep neural networks, but it cannot make full use of the global features of the point cloud for semantic segmentation. To solve this problem, this paper proposes a novel network structure called DeepGCNs-Att that enables deep Graph Convolutional Network to aggregate global context features efficiently. Moreover, to speed up the computation, we add an Attention layer after the Graph Convolutional Network Backbone Block to mutually enhance the connection between the distant points of the non-Euclidean space. Our model is tested on the standard benchmark S3DIS. By comparing with other deep Graph Convolutional Networks, our DeepGCNs-Att’s mIoU has at least two percent higher than that of all other models and even shows excellent results in space complexity and computational complexity under the same number of Graph Convolutional Network layers.

Hybrid deep graph convolutional networks

Hybrid deep graph convolutional networks

DeepMDDI: A deep graph convolutional network framework for multi-label prediction of drug-drug interactions

It is crucial to identify DDIs and explore their underlying mechanism (e.g., DDIs types) for polypharmacy safety. However, the detection of DDIs in assays is still time-consuming and costly, due to the need for experimental search over a large space of drug combinations. Thus, many computational methods have been developed to predict DDIs, most of them focusing on whether a drug interacts with another or not. And a few deep learning-based methods address a more realistic screening task for identifying various DDI types, but they assume a DDI only triggers one pharmacological effect, while a DDI can trigger more types of pharmacological effects. Thus, here we proposed a novel end-to-end deep learning-based method (called deepMDDI) for the Multi-label prediction of Drug-Drug Interactions. deepMDDI contains an encoder derived from relational graph convolutional networks and a tensor-like decoder to uniformly model interactions. deepMDDI is not only efficient for DDI transductive prediction, but also inductive prediction. The experimental results show that our model is superior to other state-of-the-art deep learning-based methods. We also validated the power of deepMDDI in the DDIs multi-label prediction and found several new valid DDIs in the case study. In conclusion, deepMDDI is beneficial to uncover the mechanism and regularity of DDIs.

Adaptive Aggregation-Transformation Decoupled Graph Convolutional Network for Semi-Supervised Learning

Graph Convolutional Network (GCN) has achieved significant success in many graph representation learning tasks. GCN usually learns graph representations by performing Neighbor Aggregation (NA) and Feature Transformation (FT) operations. Deep Adaptive Graph Neural Network (DAGNN) improves NA operation in the aggregation-transformation decoupled GCN, which enables the model to obtain a large receiver field. However, the problem with GCN is that when the model is trained to a deeper level, the performance decreases. In particular, the influence of NA and FT on model degradation has not been fully considered. In this work, we propose a new decoupled GCN architecture to enhance the performance of deep GCN. First, we conduct an experimental analysis of the impact of NA and FT operations on the degradation of the deep GCN model. Subsequently, we propose an Adaptive Aggregation-Transform Decoupled Graph Convolutional Network (AATD-GCN) which divides the model into two depths <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$D_{NA}$ </tex-math></inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$D_{FT}$ </tex-math></inline-formula> , and proposes improved approaches in NA and FT, respectively. The AATD-GCN reduces the influence of NA and FT operations on performance degradation of deep GCN, and obtains a large receiver field while extracting complex feature information. We investigate the requirements of model depth <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$D_{NA}$ </tex-math></inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$D_{FT}$ </tex-math></inline-formula> for graphs of different structures and sizes. Finally, the effectiveness of the proposed architecture is verified through extensive experiments on real-world datasets, the experimental results show that AATD-GCN is superior in terms of accuracy and robustness.

Feature Fusion via Deep Residual Graph Convolutional Network for Hyperspectral Image Classification

Recently, graph convolutional network (GCN) has been applied for hyperspectral image (HSI) classification and obtained better performance. The main issue in HSI classification is that the high-resolution HSI contains more complex spectral-spatial structure information. However, the previous GCN-based methods applied in HSI classification only adopted a shallow GCN layer and they can not extract the deeper discriminative features. In addition, these methods ignored the complementary and correlated information among multi-order neighboring information extracted by multiple GCN layers. In this letter, a novel feature fusion via deep residual graph convolutional network is proposed to explore the internal relationship among HSI data. On the one hand, benefiting from residual learning to alleviate the over-smoothing problem, we can construct deep GCN layers to excavate deeper abstract features of HSI. On the other hand, we fuse the outputs of different GCN layers, and thus, the local structural information within multi-order neighborhood nodes can be fully utilized. Extensive experiments on four real HSI data sets, including Indian Pines, Pavia University, Salinas, and Houston University, demonstrate the superiority of the proposed method compared with other state-of-the-art methods in various evaluation criteria.

Skeleton-based abnormal gait recognition with spatio-temporal attention enhanced gait-structural graph convolutional networks

Abnormal gait recognition is of great significance for medical monitoring and clinical diagnosis. Recent progress on skeleton-based abnormal gait recognition using recurrent neural networks (RNNs) and temporal-only convolutional networks (TCNs) has been substantial. These methods usually rely on hand-crafted features or treat the skeleton as a kind of grid-shape structure data, thus resulting in limited representation and difficulties of generalization. To solve this problem, we propose a spatio-temporal attention enhanced gait-structural graph convolutional network (AGS-GCN). First, we construct a gait skeleton graph according to clinical prior knowledges and reliability of deep sensors in the gait analysis. A novel partition strategy is designed for the gait graph to simultaneously extract multi-scale gait features from the raw skeleton data. Moreover, in order to extract discriminative gait representations, a spatio-temporal attention mechanism is proposed to layer-wise enhance the features of key joints. The soft attention mechanism can boost the ability to explore fine-grained gait features, and alleviate the over-smoothing of feature maps in deep graph convolutional networks. Extensive experiments on two abnormal gait datasets with different numbers of gait patterns and examples demonstrate that our system achieves better performance than the state-of-the-art works.

Deep Graph Convolutional Networks for Accurate Automatic Road Network Selection

The selection of road networks is very important for cartographic generalization. Traditional artificial intelligence methods have improved selection efficiency but cannot fully extract the spatial features of road networks. However, current selection methods, which are based on the theory of graphs or strokes, have low automaticity and are highly subjective. Graph convolutional networks (GCNs) combine graph theory with neural networks; thus, they can not only extract spatial information but also realize automatic selection. Therefore, in this study, we adopted GCNs for automatic road network selection and transformed the process into one of node classification. In addition, to solve the problem of gradient vanishing in GCNs, we compared and analyzed the results of various GCNs (GraphSAGE and graph attention networks [GAT]) by selecting small-scale road networks under different deep architectures (JK-Nets, ResNet, and DenseNet). Our results indicate that GAT provides better selection of road networks than other models. Additionally, the three abovementioned deep architectures can effectively improve the selection effect of models; JK-Nets demonstrated more improvement with higher accuracy (88.12%) than other methods. Thus, our study shows that GCN is an appropriate tool for road network selection; its application in cartography must be further explored.

HPODNets: deep graph convolutional networks for predicting human protein-phenotype associations.

Deciphering the relationship between human genes/proteins and abnormal phenotypes is of great importance in the prevention, diagnosis and treatment against diseases. The Human Phenotype Ontology (HPO) is a standardized vocabulary that describes the phenotype abnormalities encountered in human disorders. However, the current HPO annotations are still incomplete. Thus, it is necessary to computationally predict human protein-phenotype associations. In terms of current, cutting-edge computational methods for annotating proteins (such as functional annotation), three important features are (i) multiple network input, (ii) semi-supervised learning and (iii) deep graph convolutional network (GCN), whereas there are no methods with all these features for predicting HPO annotations of human protein. We develop HPODNets with all above three features for predicting human protein-phenotype associations. HPODNets adopts a deep GCN with eight layers which allows to capture high-order topological information from multiple interaction networks. Empirical results with both cross-validation and temporal validation demonstrate that HPODNets outperforms seven competing state-of-the-art methods for protein function prediction. HPODNets with the architecture of deep GCNs is confirmed to be effective for predicting HPO annotations of human protein and, more generally, node label ranking problem with multiple biomolecular networks input in bioinformatics. https://github.com/liulizhi1996/HPODNets. Supplementary data are available at Bioinformatics online.