Browse
Submit Data
Databases
API
Help

Dataset Information

40 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Compressing deep graph convolution network with multi-staged knowledge distillation.

ABSTRACT: Given a trained deep graph convolution network (GCN), how can we effectively compress it into a compact network without significant loss of accuracy? Compressing a trained deep GCN into a compact GCN is of great importance for implementing the model to environments such as mobile or embedded systems, which have limited computing resources. However, previous works for compressing deep GCNs do not consider the multi-hop aggregation of the deep GCNs, though it is the main purpose for their multiple GCN layers. In this work, we propose MustaD (Multi-staged knowledge Distillation), a novel approach for compressing deep GCNs to single-layered GCNs through multi-staged knowledge distillation (KD). MustaD distills the knowledge of 1) the aggregation from multiple GCN layers as well as 2) task prediction while preserving the multi-hop feature aggregation of deep GCNs by a single effective layer. Extensive experiments on four real-world datasets show that MustaD provides the state-of-the-art performance compared to other KD based methods. Specifically, MustaD presents up to 4.21%p improvement of accuracy compared to the second-best KD models.

SUBMITTER: Kim J

PROVIDER: S-EPMC8363007 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Predicting adverse drug effects: A heterogeneous graph convolution network with a multi-layer perceptron approach.

Project description:We apply a heterogeneous graph convolution network (GCN) combined with a multi-layer perceptron (MLP) denoted by GCNMLP to explore the potential side effects of drugs. Here the SIDER, OFFSIDERS, and FAERS are used as the datasets. We integrate the drug information with similar characteristics from the datasets of known drugs and side effect networks. The heterogeneous graph networks explore the potential side effects of drugs by inferring the relationship between similar drugs and related side effects. This novel in silico method will shorten the time spent in uncovering the unseen side effects within routine drug prescriptions while highlighting the relevance of exploring drug mechanisms from well-documented drugs. In our experiments, we inquire about the drugs Vancomycin, Amlodipine, Cisplatin, and Glimepiride from a trained model, where the parameters are acquired from the dataset SIDER after training. Our results show that the performance of the GCNMLP on these three datasets is superior to the non-negative matrix factorization method (NMF) and some well-known machine learning methods with respect to various evaluation scales. Moreover, new side effects of drugs can be obtained using the GCNMLP.

| S-EPMC9750037 | biostudies-literature

A Deep Siamese Convolution Neural Network for Multi-Class Classification of Alzheimer Disease.

Project description:Alzheimer's disease (AD) may cause damage to the memory cells permanently, which results in the form of dementia. The diagnosis of Alzheimer's disease at an early stage is a problematic task for researchers. For this, machine learning and deep convolutional neural network (CNN) based approaches are readily available to solve various problems related to brain image data analysis. In clinical research, magnetic resonance imaging (MRI) is used to diagnose AD. For accurate classification of dementia stages, we need highly discriminative features obtained from MRI images. Recently advanced deep CNN-based models successfully proved their accuracy. However, due to a smaller number of image samples available in the datasets, there exist problems of over-fitting hindering the performance of deep learning approaches. In this research, we developed a Siamese convolutional neural network (SCNN) model inspired by VGG-16 (also called Oxford Net) to classify dementia stages. In our approach, we extend the insufficient and imbalanced data by using augmentation approaches. Experiments are performed on a publicly available dataset open access series of imaging studies (OASIS), by using the proposed approach, an excellent test accuracy of 99.05% is achieved for the classification of dementia stages. We compared our model with the state-of-the-art models and discovered that the proposed model outperformed the state-of-the-art models in terms of performance, efficiency, and accuracy.

| S-EPMC7071616 | biostudies-literature

Resting-State Functional MRI Adaptation with Attention Graph Convolution Network for Brain Disorder Identification

Project description:Multi-site resting-state functional magnetic resonance imaging (rs-fMRI) data can facilitate learning-based approaches to train reliable models on more data. However, significant data heterogeneity between imaging sites, caused by different scanners or protocols, can negatively impact the generalization ability of learned models. In addition, previous studies have shown that graph convolution neural networks (GCNs) are effective in mining fMRI biomarkers. However, they generally ignore the potentially different contributions of brain regions- of-interest (ROIs) to automated disease diagnosis/prognosis. In this work, we propose a multi-site rs-fMRI adaptation framework with attention GCN (A2GCN) for brain disorder identification. Specifically, the proposed A2GCN consists of three major components: (1) a node representation learning module based on GCN to extract rs-fMRI features from functional connectivity networks, (2) a node attention mechanism module to capture the contributions of ROIs, and (3) a domain adaptation module to alleviate the differences in data distribution between sites through the constraint of mean absolute error and covariance. The A2GCN not only reduces data heterogeneity across sites, but also improves the interpretability of the learning algorithm by exploring important ROIs. Experimental results on the public ABIDE database demonstrate that our method achieves remarkable performance in fMRI-based recognition of autism spectrum disorders.

| S-EPMC9599902 | biostudies-literature

STTG-net: a Spatio-temporal network for human motion prediction based on transformer and graph convolution network.

Project description:In recent years, human motion prediction has become an active research topic in computer vision. However, owing to the complexity and stochastic nature of human motion, it remains a challenging problem. In previous works, human motion prediction has always been treated as a typical inter-sequence problem, and most works have aimed to capture the temporal dependence between successive frames. However, although these approaches focused on the effects of the temporal dimension, they rarely considered the correlation between different joints in space. Thus, the spatio-temporal coupling of human joints is considered, to propose a novel spatio-temporal network based on a transformer and a gragh convolutional network (GCN) (STTG-Net). The temporal transformer is used to capture the global temporal dependencies, and the spatial GCN module is used to establish local spatial correlations between the joints for each frame. To overcome the problems of error accumulation and discontinuity in the motion prediction, a revision method based on fusion strategy is also proposed, in which the current prediction frame is fused with the previous frame. The experimental results show that the proposed prediction method has less prediction error and the prediction motion is smoother than previous prediction methods. The effectiveness of the proposed method is also demonstrated comparing it with the state-of-the-art method on the Human3.6 M dataset.

| S-EPMC9338210 | biostudies-literature

Multi-level pooling encoder-decoder convolution neural network for MRI reconstruction.

Project description:MRI reconstruction is one of the critical processes of MRI machines, along with the acquisition. Due to a slow processing time of signal acquiring, parallel imaging and reconstruction techniques are applied for acceleration. To accelerate the acquisition process, fewer raw data are sampled simultaneously with all RF coils acquisition. Then, the reconstruction uses under-sampled data from all RF coils to restore the final MR image that resembles the fully sampled MR image. These processes have been a traditional procedure inside the MRI system since the invention of the multi-coils MRI machine. This paper proposes the deep learning technique with a lightweight network. The deep neural network is capable of generating the high-quality reconstructed MR image with a high peak signal-to-noise ratio (PSNR). This also opens a high acceleration factor for MR data acquisition. The lightweight network is called Multi-Level Pooling Encoder-Decoder Net (MLPED Net). The proposed network outperforms the traditional encoder-decoder networks on 4-fold acceleration with a significant margin on every evaluation metric. The network can be trained end-to-end, and it is a lightweight structure that can reduce training time significantly. Experimental results are based on a publicly available MRI Knee dataset from the fastMRI competition.

| S-EPMC9044365 | biostudies-literature

Deep convolution neural network for screening carotid calcification in dental panoramic radiographs.

Project description:Ischemic stroke, a leading global cause of death and disability, is commonly caused by carotid arteries atherosclerosis. Carotid artery calcification (CAC) is a well-known marker of atherosclerosis. Such calcifications are classically detected by ultrasound screening. In recent years it was shown that these calcifications can also be inferred from routine panoramic dental radiographs. In this work, we focused on panoramic dental radiographs taken from 500 patients, manually labelling each of the patients' sides (each radiograph was treated as two sides), which were used to develop an artificial intelligence (AI)-based algorithm to automatically detect carotid calcifications. The algorithm uses deep learning convolutional neural networks (CNN), with transfer learning (TL) approach that achieved true labels for each corner, and reached a sensitivity (recall) of 0.82 and a specificity of 0.97 for individual arteries, and a recall of 0.87 and specificity of 0.97 for individual patients. Applying and integrating the algorithm in healthcare units and dental clinics has the potential of reducing stroke events and their mortality and morbidity consequences.

| S-EPMC10096511 | biostudies-literature

Geometric Feature Extraction of Point Cloud of Chemical Reactor Based on Dynamic Graph Convolution Neural Network.

Project description:Geometric features are an important factor for the classification of drugs and other transport objects in chemical reactors. The moving speed of drugs and other transport objects in chemical reactors is fast, and it is difficult to obtain their features by imaging and other methods. In order to avoid the mistaken and missed distribution of drugs and other objects, a method of extracting geometric features of the drug's point cloud in a chemical reactor based on a dynamic graph convolution neural network (DGCNN) is proposed. In this study, we first use MATLAB R2019a to add a random number of noise points in each point cloud file and label the point cloud. Second, k-nearest neighbor (KNN) is used to construct the adjacency relationship of all nodes, and the effect of DGCNN under different k values and the confusion matrix under the optimal k value are analyzed. Finally, we compare the effect of DGCNN with PointNet and PointNet++. The experimental results show that when k is 20, the accuracy, precision, recall, and F1 score of DGCNN are higher than those of other k values, while the training time is much shorter than that of k = 25, 30, and 35; in addition, the effect of DGCNN in extracting geometric features of the point cloud is better than that of PointNet and PointNet++. The results show that it is feasible to use DGCNN to analyze the geometric characteristics of drug point clouds in a chemical reactor. This study fills the gap of the end-to-end extraction method for a point cloud's corresponding geometric features without a data set. In addition, this study promotes the institutionalization, standardization, and intelligent design of safe production and management of drugs and other objects in the chemical reactor, and it has positive significance for the production cost and resource utilization of the whole pharmaceutical process. At the same time, it provides a new method for the intelligent processing of point cloud data.

| S-EPMC8388001 | biostudies-literature

HTINet2: herb–target prediction via knowledge graph embedding and residual-like graph neural network

Project description: Not available

| S-EPMC11341278 | biostudies-literature

AIMedGraph: a comprehensive multi-relational knowledge graph for precision medicine.

Project description:The development of high-throughput molecular testing techniques has enabled the large-scale exploration of the underlying molecular causes of diseases and the development of targeted treatment for specific genetic alterations. However, knowledge to interpret the impact of genetic variants on disease or treatment is distributed in different databases, scientific literature studies and clinical guidelines. AIMedGraph was designed to comprehensively collect and interrogate standardized information about genes, genetic alterations and their therapeutic and diagnostic relevance and build a multi-relational, evidence-based knowledge graph. Graph database Neo4j was used to represent precision medicine knowledge as nodes and edges in AIMedGraph. Entities in the current release include 30 340 diseases/phenotypes, 26 140 genes, 187 541 genetic variants, 2821 drugs, 15 125 clinical trials and 797 911 supporting literature studies. Edges in this release cover 621 731 drug interactions, 9279 drug susceptibility impacts, 6330 pharmacogenomics effects, 30 339 variant pathogenicity and 1485 drug adverse reactions. The knowledge graph technique enables hidden knowledge inference and provides insight into potential disease or drug molecular mechanisms. Database URL: http://aimedgraph.tongshugene.net:8201.

| S-EPMC9976745 | biostudies-literature

Multi-domain knowledge graph embeddings for gene-disease association prediction.

Project description:BackgroundPredicting gene-disease associations typically requires exploring diverse sources of information as well as sophisticated computational approaches. Knowledge graph embeddings can help tackle these challenges by creating representations of genes and diseases based on the scientific knowledge described in ontologies, which can then be explored by machine learning algorithms. However, state-of-the-art knowledge graph embeddings are produced over a single ontology or multiple but disconnected ones, ignoring the impact that considering multiple interconnected domains can have on complex tasks such as gene-disease association prediction.ResultsWe propose a novel approach to predict gene-disease associations using rich semantic representations based on knowledge graph embeddings over multiple ontologies linked by logical definitions and compound ontology mappings. The experiments showed that considering richer knowledge graphs significantly improves gene-disease prediction and that different knowledge graph embeddings methods benefit more from distinct types of semantic richness.ConclusionsThis work demonstrated the potential for knowledge graph embeddings across multiple and interconnected biomedical ontologies to support gene-disease prediction. It also paved the way for considering other ontologies or tackling other tasks where multiple perspectives over the data can be beneficial. All software and data are freely available.

| S-EPMC10426189 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data