MVGCN: data integration through multi-view graph convolutional network for predicting links in biomedical bipartite networks

Abstract Motivation There are various interaction/association bipartite networks in biomolecular systems. Identifying unobserved links in biomedical bipartite networks helps to understand the underlying molecular mechanisms of human complex diseases and thus benefits the diagnosis and treatment of diseases. Although a great number of computational methods have been proposed to predict links in biomedical bipartite networks, most of them heavily depend on features and structures involving the bioentities in one specific bipartite network, which limits the generalization capacity of applying the models to other bipartite networks. Meanwhile, bioentities usually have multiple features, and how to leverage them has also been challenging. Results In this study, we propose a novel multi-view graph convolution network (MVGCN) framework for link prediction in biomedical bipartite networks. We first construct a multi-view heterogeneous network (MVHN) by combining the similarity networks with the biomedical bipartite network, and then perform a self-supervised learning strategy on the bipartite network to obtain node attributes as initial embeddings. Further, a neighborhood information aggregation (NIA) layer is designed for iteratively updating the embeddings of nodes by aggregating information from inter- and intra-domain neighbors in every view of the MVHN. Next, we combine embeddings of multiple NIA layers in each view, and integrate multiple views to obtain the final node embeddings, which are then fed into a discriminator to predict the existence of links. Extensive experiments show MVGCN performs better than or on par with baseline methods and has the generalization capacity on six benchmark datasets involving three typical tasks. Availability and implementation Source code and data can be downloaded from https://github.com/fuhaitao95/MVGCN. Supplementary information Supplementary data are available at Bioinformatics online.

Download Full-text

Continual representation learning for evolving biomedical bipartite networks

Bioinformatics ◽

10.1093/bioinformatics/btab067 ◽

2021 ◽

Author(s):

Kishlay Jha ◽

Guangxu Xun ◽

Aidong Zhang

Keyword(s):

Network Structure ◽

Learning Strategy ◽

Structure Learning ◽

Fundamental Problem ◽

Representation Learning ◽

Research Area ◽

Bipartite Network ◽

Bipartite Networks ◽

Straightforward Application ◽

Low Dimensional

Abstract Motivation Many real-world biomedical interactions such as ‘gene-disease’, ‘disease-symptom’ and ‘drug-target’ are modeled as a bipartite network structure. Learning meaningful representations for such networks is a fundamental problem in the research area of Network Representation Learning (NRL). NRL approaches aim to translate the network structure into low-dimensional vector representations that are useful to a variety of biomedical applications. Despite significant advances, the existing approaches still have certain limitations. First, a majority of these approaches do not model the unique topological properties of bipartite networks. Consequently, their straightforward application to the bipartite graphs yields unsatisfactory results. Second, the existing approaches typically learn representations from static networks. This is limiting for the biomedical bipartite networks that evolve at a rapid pace, and thus necessitate the development of approaches that can update the representations in an online fashion. Results In this research, we propose a novel representation learning approach that accurately preserves the intricate bipartite structure, and efficiently updates the node representations. Specifically, we design a customized autoencoder that captures the proximity relationship between nodes participating in the bipartite bicliques (2 × 2 sub-graph), while preserving both the global and local structures. Moreover, the proposed structure-preserving technique is carefully interleaved with the central tenets of continual machine learning to design an incremental learning strategy that updates the node representations in an online manner. Taken together, the proposed approach produces meaningful representations with high fidelity and computational efficiency. Extensive experiments conducted on several biomedical bipartite networks validate the effectiveness and rationality of the proposed approach.

Download Full-text

EOESGC: predicting miRNA-disease associations based on embedding of embedding and simplified graph convolutional network

BMC Medical Informatics and Decision Making ◽

10.1186/s12911-021-01671-y ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Shanchen Pang ◽

Yu Zhuang ◽

Xinzeng Wang ◽

Fuyu Wang ◽

Sibo Qiao

Keyword(s):

Information Aggregation ◽

Disease Association ◽

Supplementary Information ◽

Graph Structure ◽

Association Network ◽

Convolutional Network ◽

Edge Information ◽

Biological Studies ◽

Convolution Model ◽

Disease Associations

Abstract Background A large number of biological studies have shown that miRNAs are inextricably linked to many complex diseases. Studying the miRNA-disease associations could provide us a root cause understanding of the underlying pathogenesis in which promotes the progress of drug development. However, traditional biological experiments are very time-consuming and costly. Therefore, we come up with an efficient models to solve this challenge. Results In this work, we propose a deep learning model called EOESGC to predict potential miRNA-disease associations based on embedding of embedding and simplified convolutional network. Firstly, integrated disease similarity, integrated miRNA similarity, and miRNA-disease association network are used to construct a coupled heterogeneous graph, and the edges with low similarity are removed to simplify the graph structure and ensure the effectiveness of edges. Secondly, the Embedding of embedding model (EOE) is used to learn edge information in the coupled heterogeneous graph. The training rule of the model is that the associated nodes are close to each other and the unassociated nodes are far away from each other. Based on this rule, edge information learned is added into node embedding as supplementary information to enrich node information. Then, node embedding of EOE model training as a new feature of miRNA and disease, and information aggregation is performed by simplified graph convolution model, in which each level of convolution can aggregate multi-hop neighbor information. In this step, we only use the miRNA-disease association network to further simplify the graph structure, thus reducing the computational complexity. Finally, feature embeddings of both miRNA and disease are spliced into the MLP for prediction. On the EOESGC evaluation part, the AUC, AUPR, and F1-score of our model are 0.9658, 0.8543 and 0.8644 by 5-fold cross-validation respectively. Compared with the latest published models, our model shows better results. In addition, we predict the top 20 potential miRNAs for breast cancer and lung cancer, most of which are validated in the dbDEMC and HMDD3.2 databases. Conclusion The comprehensive experimental results show that EOESGC can effectively identify the potential miRNA-disease associations.

Download Full-text

Knowledge and Geo-Object Based Graph Convolutional Network for Remote Sensing Semantic Segmentation

Sensors ◽

10.3390/s21113848 ◽

2021 ◽

Vol 21 (11) ◽

pp. 3848

Author(s):

Wei Cui ◽

Meng Yao ◽

Yuanjie Hao ◽

Ziwei Wang ◽

Xin He ◽

...

Keyword(s):

Remote Sensing ◽

Prior Knowledge ◽

Contextual Information ◽

Information Aggregation ◽

Semantic Segmentation ◽

Spatial Correlations ◽

Convolutional Network ◽

Object Based ◽

Graph Neural Networks ◽

Salt And Pepper

Pixel-based semantic segmentation models fail to effectively express geographic objects and their topological relationships. Therefore, in semantic segmentation of remote sensing images, these models fail to avoid salt-and-pepper effects and cannot achieve high accuracy either. To solve these problems, object-based models such as graph neural networks (GNNs) are considered. However, traditional GNNs directly use similarity or spatial correlations between nodes to aggregate nodes’ information, which rely too much on the contextual information of the sample. The contextual information of the sample is often distorted, which results in a reduction in the node classification accuracy. To solve this problem, a knowledge and geo-object-based graph convolutional network (KGGCN) is proposed. The KGGCN uses superpixel blocks as nodes of the graph network and combines prior knowledge with spatial correlations during information aggregation. By incorporating the prior knowledge obtained from all samples of the study area, the receptive field of the node is extended from its sample context to the study area. Thus, the distortion of the sample context is overcome effectively. Experiments demonstrate that our model is improved by 3.7% compared with the baseline model named Cluster GCN and 4.1% compared with U-Net.

Download Full-text

Insights into the molecular mechanisms of Huangqi decoction on liver fibrosis via computational systems pharmacology approaches

Chinese Medicine ◽

10.1186/s13020-021-00473-8 ◽

2021 ◽

Vol 16 (1) ◽

Author(s):

Biting Wang ◽

Zengrui Wu ◽

Weihua Li ◽

Guixia Liu ◽

Yun Tang

Keyword(s):

Molecular Docking ◽

Liver Fibrosis ◽

Molecular Mechanisms ◽

Docking Simulation ◽

Chinese Herbs ◽

Network Pharmacology ◽

Bipartite Network ◽

Metabolomics Data ◽

Metabolic Products ◽

Compound Target

Abstract Background The traditional Chinese medicine Huangqi decoction (HQD) consists of Radix Astragali and Radix Glycyrrhizae in a ratio of 6: 1, which has been used for the treatment of liver fibrosis. In this study, we tried to elucidate its action of mechanism (MoA) via a combination of metabolomics data, network pharmacology and molecular docking methods. Methods Firstly, we collected prototype components and metabolic products after administration of HQD from a publication. With known and predicted targets, compound-target interactions were obtained. Then, the global compound-liver fibrosis target bipartite network and the HQD-liver fibrosis protein–protein interaction network were constructed, separately. KEGG pathway analysis was applied to further understand the mechanisms related to the target proteins of HQD. Additionally, molecular docking simulation was performed to determine the binding efficiency of compounds with targets. Finally, considering the concentrations of prototype compounds and metabolites of HQD, the critical compound-liver fibrosis target bipartite network was constructed. Results 68 compounds including 17 prototype components and 51 metabolic products were collected. 540 compound-target interactions were obtained between the 68 compounds and 95 targets. Combining network analysis, molecular docking and concentration of compounds, our final results demonstrated that eight compounds (three prototype compounds and five metabolites) and eight targets (CDK1, MMP9, PPARD, PPARG, PTGS2, SERPINE1, TP53, and HIF1A) might contribute to the effects of HQD on liver fibrosis. These interactions would maintain the balance of ECM, reduce liver damage, inhibit hepatocyte apoptosis, and alleviate liver inflammation through five signaling pathways including p53, PPAR, HIF-1, IL-17, and TNF signaling pathway. Conclusions This study provides a new way to understand the MoA of HQD on liver fibrosis by considering the concentrations of components and metabolites, which might be a model for investigation of MoA of other Chinese herbs.

Download Full-text

Using single-cell cytometry to illustrate integrated multi-perspective evaluation of clustering algorithms using Pareto fronts

Bioinformatics ◽

10.1093/bioinformatics/btab038 ◽

2021 ◽

Author(s):

Givanna H Putri ◽

Irena Koprinska ◽

Thomas M Ashhurst ◽

Nicholas J C King ◽

Mark N Read

Keyword(s):

Single Cell ◽

Performance Metrics ◽

Clustering Algorithms ◽

Latin Hypercube Sampling ◽

Supplementary Information ◽

Sequencing Data ◽

Evaluation Protocol ◽

Benchmark Datasets ◽

Pareto Fronts ◽

Parameter Values

Abstract Motivation Many ‘automated gating’ algorithms now exist to cluster cytometry and single-cell sequencing data into discrete populations. Comparative algorithm evaluations on benchmark datasets rely either on a single performance metric, or a few metrics considered independently of one another. However, single metrics emphasize different aspects of clustering performance and do not rank clustering solutions in the same order. This underlies the lack of consensus between comparative studies regarding optimal clustering algorithms and undermines the translatability of results onto other non-benchmark datasets. Results We propose the Pareto fronts framework as an integrative evaluation protocol, wherein individual metrics are instead leveraged as complementary perspectives. Judged superior are algorithms that provide the best trade-off between the multiple metrics considered simultaneously. This yields a more comprehensive and complete view of clustering performance. Moreover, by broadly and systematically sampling algorithm parameter values using the Latin Hypercube sampling method, our evaluation protocol minimizes (un)fortunate parameter value selections as confounding factors. Furthermore, it reveals how meticulously each algorithm must be tuned in order to obtain good results, vital knowledge for users with novel data. We exemplify the protocol by conducting a comparative study between three clustering algorithms (ChronoClust, FlowSOM and Phenograph) using four common performance metrics applied across four cytometry benchmark datasets. To our knowledge, this is the first time Pareto fronts have been used to evaluate the performance of clustering algorithms in any application domain. Availability and implementation Implementation of our Pareto front methodology and all scripts and datasets to reproduce this article are available at https://github.com/ghar1821/ParetoBench. Supplementary information Supplementary data are available at Bioinformatics online.

Download Full-text

SGAN4AbSum: A Semantic-Enhanced Generative Adversarial Network for Abstractive Text Summarization

10.21203/rs.3.rs-648146/v1 ◽

2021 ◽

Author(s):

Tham Vo

Keyword(s):

Ground Truth ◽

Text Summarization ◽

Generative Adversarial Network ◽

Convolutional Network ◽

Training Strategy ◽

Adversarial Network ◽

Deep Recurrent Neural Network ◽

Benchmark Datasets ◽

Latent Representations ◽

Abstractive Summarization

Abstract In abstractive summarization task, most of proposed models adopt the deep recurrent neural network (RNN)-based encoder-decoder architecture to learn and generate meaningful summary for a given input document. However, most of recent RNN-based models always suffer the challenges related to the involvement of much capturing high-frequency/reparative phrases in long documents during the training process which leads to the outcome of trivial and generic summaries are generated. Moreover, the lack of thorough analysis on the sequential and long-range dependency relationships between words within different contexts while learning the textual representation also make the generated summaries unnatural and incoherent. To deal with these challenges, in this paper we proposed a novel semantic-enhanced generative adversarial network (GAN)-based approach for abstractive text summarization task, called as: SGAN4AbSum. We use an adversarial training strategy for our text summarization model in which train the generator and discriminator to simultaneously handle the summary generation and distinguishing the generated summary with the ground-truth one. The input of generator is the jointed rich-semantic and global structural latent representations of training documents which are achieved by applying a combined BERT and graph convolutional network (GCN) textual embedding mechanism. Extensive experiments in benchmark datasets demonstrate the effectiveness of our proposed SGAN4AbSum which achieve the competitive ROUGE-based scores in comparing with state-of-the-art abstractive text summarization baselines.

Download Full-text

Structure-aware protein–protein interaction site prediction using deep graph convolutional network

Bioinformatics ◽

10.1093/bioinformatics/btab643 ◽

2021 ◽

Author(s):

Qianmu Yuan ◽

Jianwen Chen ◽

Huiying Zhao ◽

Yaoqi Zhou ◽

Yuedong Yang

Keyword(s):

Protein Interactions ◽

Spatial Information ◽

Screening Tools ◽

Supplementary Information ◽

Protein Protein Interactions ◽

Convolutional Network ◽

Source Codes ◽

Site Prediction ◽

Protein Protein Interaction ◽

Mapping Techniques

Abstract Motivation Protein–protein interactions (PPI) play crucial roles in many biological processes, and identifying PPI sites is an important step for mechanistic understanding of diseases and design of novel drugs. Since experimental approaches for PPI site identification are expensive and time-consuming, many computational methods have been developed as screening tools. However, these methods are mostly based on neighbored features in sequence, and thus limited to capture spatial information. Results We propose a deep graph-based framework deep Graph convolutional network for Protein–Protein-Interacting Site prediction (GraphPPIS) for PPI site prediction, where the PPI site prediction problem was converted into a graph node classification task and solved by deep learning using the initial residual and identity mapping techniques. We showed that a deeper architecture (up to eight layers) allows significant performance improvement over other sequence-based and structure-based methods by more than 12.5% and 10.5% on AUPRC and MCC, respectively. Further analyses indicated that the predicted interacting sites by GraphPPIS are more spatially clustered and closer to the native ones even when false-positive predictions are made. The results highlight the importance of capturing spatially neighboring residues for interacting site prediction. Availability and implementation The datasets, the pre-computed features, and the source codes along with the pre-trained models of GraphPPIS are available at https://github.com/biomed-AI/GraphPPIS. The GraphPPIS web server is freely available at https://biomed.nscc-gz.cn/apps/GraphPPIS. Supplementary information Supplementary data are available at Bioinformatics online.

Download Full-text

Residual Invertible Spatio-Temporal Network for Video Super-Resolution

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33015981 ◽

2019 ◽

Vol 33 ◽

pp. 5981-5988 ◽

Cited By ~ 12

Author(s):

Xiaobin Zhu ◽

Zhuangzi Li ◽

Xiao-Yu Zhang ◽

Changsheng Li ◽

Yaqi Liu ◽

...

Keyword(s):

Spatial Information ◽

Super Resolution ◽

Temporal Consistency ◽

Temporal Network ◽

Convolutional Network ◽

Feature Representations ◽

Video Frames ◽

Temporal Features ◽

Benchmark Datasets ◽

Spatio Temporal

Video super-resolution is a challenging task, which has attracted great attention in research and industry communities. In this paper, we propose a novel end-to-end architecture, called Residual Invertible Spatio-Temporal Network (RISTN) for video super-resolution. The RISTN can sufficiently exploit the spatial information from low-resolution to high-resolution, and effectively models the temporal consistency from consecutive video frames. Compared with existing recurrent convolutional network based approaches, RISTN is much deeper but more efficient. It consists of three major components: In the spatial component, a lightweight residual invertible block is designed to reduce information loss during feature transformation and provide robust feature representations. In the temporal component, a novel recurrent convolutional model with residual dense connections is proposed to construct deeper network and avoid feature degradation. In the reconstruction component, a new fusion method based on the sparse strategy is proposed to integrate the spatial and temporal features. Experiments on public benchmark datasets demonstrate that RISTN outperforms the state-ofthe-art methods.

Download Full-text

DeepPurpose: a deep learning library for drug–target interaction prediction

Bioinformatics ◽

10.1093/bioinformatics/btaa1005 ◽

2020 ◽

Author(s):

Kexin Huang ◽

Tianfan Fu ◽

Lucas M Glass ◽

Marinka Zitnik ◽

Cao Xiao ◽

...

Keyword(s):

Deep Learning ◽

Drug Target ◽

Prediction Models ◽

State Of The Art ◽

Supplementary Information ◽

Target Interaction ◽

Interaction Prediction ◽

Computer Scientists ◽

Benchmark Datasets ◽

Biomedical Field

Abstract Summary Accurate prediction of drug–target interactions (DTI) is crucial for drug discovery. Recently, deep learning (DL) models for show promising performance for DTI prediction. However, these models can be difficult to use for both computer scientists entering the biomedical field and bioinformaticians with limited DL experience. We present DeepPurpose, a comprehensive and easy-to-use DL library for DTI prediction. DeepPurpose supports training of customized DTI prediction models by implementing 15 compound and protein encoders and over 50 neural architectures, along with providing many other useful features. We demonstrate state-of-the-art performance of DeepPurpose on several benchmark datasets. Availability and implementation https://github.com/kexinhuang12345/DeepPurpose. Contact [email protected] Supplementary information Supplementary data are available at Bioinformatics online.

Download Full-text

Low-Rank Deep Convolutional Neural Network for Multitask Learning

Computational Intelligence and Neuroscience ◽

10.1155/2019/7410701 ◽

2019 ◽

Vol 2019 ◽

pp. 1-10

Author(s):

Fang Su ◽

Hai-Yang Shang ◽

Jing-Yan Wang

Keyword(s):

Language Processing ◽

Back Propagation ◽

Multitask Learning ◽

Low Rank ◽

Learning Problem ◽

Convolutional Network ◽

Deep Network ◽

Benchmark Datasets ◽

Deep Cnn ◽

Fully Connected

In this paper, we propose a novel multitask learning method based on the deep convolutional network. The proposed deep network has four convolutional layers, three max-pooling layers, and two parallel fully connected layers. To adjust the deep network to multitask learning problem, we propose to learn a low-rank deep network so that the relation among different tasks can be explored. We proposed to minimize the number of independent parameter rows of one fully connected layer to explore the relations among different tasks, which is measured by the nuclear norm of the parameter of one fully connected layer, and seek a low-rank parameter matrix. Meanwhile, we also propose to regularize another fully connected layer by sparsity penalty so that the useful features learned by the lower layers can be selected. The learning problem is solved by an iterative algorithm based on gradient descent and back-propagation algorithms. The proposed algorithm is evaluated over benchmark datasets of multiple face attribute prediction, multitask natural language processing, and joint economics index predictions. The evaluation results show the advantage of the low-rank deep CNN model over multitask problems.

Download Full-text