Diabetic Kidney Disease (DKD) is a common chronic complication of diabetes. Despite advancements in accurately identifying biomarkers for detecting and diagnosing this harmful disease, there remains an urgent need for...Diabetic Kidney Disease (DKD) is a common chronic complication of diabetes. Despite advancements in accurately identifying biomarkers for detecting and diagnosing this harmful disease, there remains an urgent need for new biomarkers to enable early detection of DKD. In this study, we modeled publicly available transcriptome datasets as a graph problem and used GraphSAGE Neural Networks (GNNs) to identify potential biomarkers. The GraphSAGE model effectively learned representations that captured the intricate interactions, dependencies among genes, and disease-specific gene expression patterns necessary to classify samples as DKD and Control. We finally extracted the features of importance;the identified set of genes exhibited an impressive ability to distinguish between healthy and unhealthy samples, even though these genes differ from previous research findings. The unexpected biomarker variations in this study suggest more exploration and validation studies for discovering biomarkers in DKD. In conclusion, our study showcases the effectiveness of modeling transcriptome data as a graph problem, demonstrates the use of GraphSAGE models for biomarker discovery in DKD, and advocates for integrating advanced machine-learning techniques in DKD biomarker research, emphasizing the need for a holistic approach to unravel the intricacies of biological systems.展开更多
Graph Neural Networks(GNNs),as a deep learning framework specifically designed for graph-structured data,have achieved deep representation learning of graph data through message passing mechanisms and have become a co...Graph Neural Networks(GNNs),as a deep learning framework specifically designed for graph-structured data,have achieved deep representation learning of graph data through message passing mechanisms and have become a core technology in the field of graph analysis.However,current reviews on GNN models are mainly focused on smaller domains,and there is a lack of systematic reviews on the classification and applications of GNN models.This review systematically synthesizes the three canonical branches of GNN,Graph Convolutional Network(GCN),Graph Attention Network(GAT),and Graph Sampling Aggregation Network(GraphSAGE),and analyzes their integration pathways from both structural and feature perspectives.Drawing on representative studies,we identify three major integration patterns:cascaded fusion,where heterogeneous modules such as Convolutional Neural Network(CNN),Long Short-Term Memory(LSTM),and GraphSAGE are sequentially combined for hierarchical feature learning;parallel fusion,where multi-branch architectures jointly encode complementary graph features;and feature-level fusion,which employs concatenation,weighted summation,or attention-based gating to adaptively merge multi-source embeddings.Through these patterns,integrated GNNs achieve enhanced expressiveness,robustness,and scalability across domains including transportation,biomedicine,and cybersecurity.展开更多
文摘Diabetic Kidney Disease (DKD) is a common chronic complication of diabetes. Despite advancements in accurately identifying biomarkers for detecting and diagnosing this harmful disease, there remains an urgent need for new biomarkers to enable early detection of DKD. In this study, we modeled publicly available transcriptome datasets as a graph problem and used GraphSAGE Neural Networks (GNNs) to identify potential biomarkers. The GraphSAGE model effectively learned representations that captured the intricate interactions, dependencies among genes, and disease-specific gene expression patterns necessary to classify samples as DKD and Control. We finally extracted the features of importance;the identified set of genes exhibited an impressive ability to distinguish between healthy and unhealthy samples, even though these genes differ from previous research findings. The unexpected biomarker variations in this study suggest more exploration and validation studies for discovering biomarkers in DKD. In conclusion, our study showcases the effectiveness of modeling transcriptome data as a graph problem, demonstrates the use of GraphSAGE models for biomarker discovery in DKD, and advocates for integrating advanced machine-learning techniques in DKD biomarker research, emphasizing the need for a holistic approach to unravel the intricacies of biological systems.
基金funded by Guangzhou Huashang University(2024HSZD01,HS2023JYSZH01).
文摘Graph Neural Networks(GNNs),as a deep learning framework specifically designed for graph-structured data,have achieved deep representation learning of graph data through message passing mechanisms and have become a core technology in the field of graph analysis.However,current reviews on GNN models are mainly focused on smaller domains,and there is a lack of systematic reviews on the classification and applications of GNN models.This review systematically synthesizes the three canonical branches of GNN,Graph Convolutional Network(GCN),Graph Attention Network(GAT),and Graph Sampling Aggregation Network(GraphSAGE),and analyzes their integration pathways from both structural and feature perspectives.Drawing on representative studies,we identify three major integration patterns:cascaded fusion,where heterogeneous modules such as Convolutional Neural Network(CNN),Long Short-Term Memory(LSTM),and GraphSAGE are sequentially combined for hierarchical feature learning;parallel fusion,where multi-branch architectures jointly encode complementary graph features;and feature-level fusion,which employs concatenation,weighted summation,or attention-based gating to adaptively merge multi-source embeddings.Through these patterns,integrated GNNs achieve enhanced expressiveness,robustness,and scalability across domains including transportation,biomedicine,and cybersecurity.
