OBJECTIVE To provide help for further exploring the mechanism of action of traditional Chinese herb by constructing a complex network of traditional Chinese herb-gene-protein,optimizing the mining method of potential associated genes of traditional Chinese herb and improving the mining efficiency of traditional Chinese herb system biology information.METHODS A graph neural network model HERBGAT with an attention mechanism was proposed.A small amount of traditional Chinese herb-related gene data in the public data platform was used as input,and deep mining was performed in the traditional Chinese herb-gene-protein complex net-work to output potential traditional Chinese herb-related genes.The prediction results were analyzed by disease association analysis and KEGG signaling pathway analysis on the bioinformatics platform to clarify their mechanism of action,and the prediction results were verified by the literature retrieval platform.RESULTS The training results showed that the average prediction accuracy of the HERB-GAT model could reach 94%.Compared with the other two advanced complex network mining methods,HERBGAT showed better per-formance in the three indicators of ACC,AUC and AUPR.In the literature verification stage,the model prediction results were verified by TCM clinical literature and modern pharmacology literature,showing the good effect of HERBGAT in practical application.At the end of this paper,taking the HERBGAT model and the improved EMOGI model to explore the mechanism of action of Pinellia ternata in treating lung cancer as an example,199 potential associated genes of Pinellia ternata in treating lung cancer were found,and these potential associated genes were preliminarily analyzed and discussed with the help of bioinformatics methods.CONCLUSION The HERBGAT model can effectively mine potential traditional Chinese herb-associated genes,improve the mining efficiency of traditional Chinese herb-gene-protein complex networks,provide new ideas and references for the optimization of traditional Chinese herb system biology information mining methods,and provide data basis and experimental direction for exploring the mechanism of action of tradi-tional Chinese herb.

OBJECTIVE To provide help for further exploring the mechanism of action of traditional Chinese herb by constructing a complex network of traditional Chinese herb-gene-protein,optimizing the mining method of potential associated genes of traditional Chinese herb and improving the mining efficiency of traditional Chinese herb system biology information.METHODS A graph neural network model HERBGAT with an attention mechanism was proposed.A small amount of traditional Chinese herb-related gene data in the public data platform was used as input,and deep mining was performed in the traditional Chinese herb-gene-protein complex net-work to output potential traditional Chinese herb-related genes.The prediction results were analyzed by disease association analysis and KEGG signaling pathway analysis on the bioinformatics platform to clarify their mechanism of action,and the prediction results were verified by the literature retrieval platform.RESULTS The training results showed that the average prediction accuracy of the HERB-GAT model could reach 94%.Compared with the other two advanced complex network mining methods,HERBGAT showed better per-formance in the three indicators of ACC,AUC and AUPR.In the literature verification stage,the model prediction results were verified by TCM clinical literature and modern pharmacology literature,showing the good effect of HERBGAT in practical application.At the end of this paper,taking the HERBGAT model and the improved EMOGI model to explore the mechanism of action of Pinellia ternata in treating lung cancer as an example,199 potential associated genes of Pinellia ternata in treating lung cancer were found,and these potential associated genes were preliminarily analyzed and discussed with the help of bioinformatics methods.CONCLUSION The HERBGAT model can effectively mine potential traditional Chinese herb-associated genes,improve the mining efficiency of traditional Chinese herb-gene-protein complex networks,provide new ideas and references for the optimization of traditional Chinese herb system biology information mining methods,and provide data basis and experimental direction for exploring the mechanism of action of tradi-tional Chinese herb.

In recent years,graph representation learning methods have attracted significant attention for their ability to effectively handle graph-structured data.Chinese herbal medicine(CHM),with its multi-component,multi-target,and multi-pathway charac-teristics,demonstrates significant advantages in the treatment of complex diseases,particularly as different combinations of Chinese herbs can produce unique synergistic effects.Graph representation learning provides a new perspective for the in-depth study of CHM combinations.This paper first outlines the relevant methods of graph representation learning,explores the current application status of these methods in CHM combinations,and discusses the challenges and corresponding solutions.By reviewing the research dynamics and cutting-edge trends in this field,this paper aims to provide valuable references and insights for future in-depth research.

The accumulation and spread of prion-like proteins is a key feature of neurodegenerative diseases (NDs) such as Alzheimer's disease, Parkinson's disease, or Amyotrophic Lateral Sclerosis. In a process known as 'seeding', prion-like proteins such as amyloid beta, microtubule-associated protein tau, α-synuclein, silence superoxide dismutase 1, or transactive response DNA-binding protein 43 kDa, propagate their misfolded conformations by transforming their respective soluble monomers into fibrils. Cellular and molecular evidence of prion-like propagation in NDs, the clinical relevance of their 'seeding' capacities, and their levels of contribution towards disease progression have been intensively studied over recent years. This review unpacks the cyclic prion-like propagation in cells including factors of aggregate internalization, endo-lysosomal leaking, aggregate degradation, and secretion. Debates on the importance of the role of prion-like protein aggregates in NDs, whether causal or consequent, are also discussed. Applications lead to a greater understanding of ND pathogenesis and increased potential for therapeutic strategies.
Humans ; Prions ; Neurodegenerative Diseases/pathology* ; Amyloid beta-Peptides ; Alzheimer Disease ; alpha-Synuclein ; tau Proteins ; Parkinson Disease

Purpose/Significance To summarize the research results of network pharmacology in traditional Chinese medicine(TCM)in recent years,and to propose a large-scale biomedical data analysis method in the era of artificial intelligence(AI),so as to provide ideas and references for the development trend and future application of network pharmacology in TCM.Method/Process Based on literature analysis,the research process of network pharmacology and its research progress in the material basis of TCM efficacy,mechanism of TCM efficacy and analysis of molecular mechanism of disease are reviewed.The application and trend of AI represented by graph neural network in TCM network pharmacology are discussed.Result/Conclusion The graph neural network is introduced into the research of TCM network pharmacology,and the AI model is used to further enrich the research methods of network pharmacology,ana-lyze the mechanism of TCM in depth,and provide technical support for the construction of modern TCM basic theoretical system.

In recent years,graph representation learning methods have attracted significant attention for their ability to effectively handle graph-structured data.Chinese herbal medicine(CHM),with its multi-component,multi-target,and multi-pathway charac-teristics,demonstrates significant advantages in the treatment of complex diseases,particularly as different combinations of Chinese herbs can produce unique synergistic effects.Graph representation learning provides a new perspective for the in-depth study of CHM combinations.This paper first outlines the relevant methods of graph representation learning,explores the current application status of these methods in CHM combinations,and discusses the challenges and corresponding solutions.By reviewing the research dynamics and cutting-edge trends in this field,this paper aims to provide valuable references and insights for future in-depth research.

Objective This study proposes a Chinese Herbal Medicine(CHM)clustering method based on graph neural network(CHM-GCNK),aiming to discover potential compatibility of CHM at the biological network level.Methods Firstly,collect data of CHM,target,and their interactions,and construct a network of CHM and targets.Secondly,the graph neural network is used to learn the constructed network and obtain the embedded representation of CHM nodes.Then,use the Kmeans algorithm to clustering.Finally,use nonlinear dimensionality reduction technology t-SNE to visualize clustering results.Results The CHM-GCNK,Node2Vec-Kmeans,and SVD-Kmeans methods were applied to cluster 40 CHM for the treatment of lung cancer.The clustering results were five clusters,and CHM-GCNK was superior to the other two methods.The evaluation indicators SS,DBI,and CH showed results of 0.4006,0.7631,and 59.0001,respectively.Conclusion The clustering effect of CHM-GCNK is better and can be applied to the study of CHM compatibility,providing reference for the analysis methods of CHM biological networks in the era of artificial intelligence and multi omics data.

Objective This study proposes a Chinese Herbal Medicine(CHM)clustering method based on graph neural network(CHM-GCNK),aiming to discover potential compatibility of CHM at the biological network level.Methods Firstly,collect data of CHM,target,and their interactions,and construct a network of CHM and targets.Secondly,the graph neural network is used to learn the constructed network and obtain the embedded representation of CHM nodes.Then,use the Kmeans algorithm to clustering.Finally,use nonlinear dimensionality reduction technology t-SNE to visualize clustering results.Results The CHM-GCNK,Node2Vec-Kmeans,and SVD-Kmeans methods were applied to cluster 40 CHM for the treatment of lung cancer.The clustering results were five clusters,and CHM-GCNK was superior to the other two methods.The evaluation indicators SS,DBI,and CH showed results of 0.4006,0.7631,and 59.0001,respectively.Conclusion The clustering effect of CHM-GCNK is better and can be applied to the study of CHM compatibility,providing reference for the analysis methods of CHM biological networks in the era of artificial intelligence and multi omics data.

Endogenously eliminating the hematoma is a favorable strategy in addressing intracerebral hemorrhage (ICH). This study sought to determine the role of retinoid X receptor-α (RXR-α) in the context of hematoma absorption after ICH. Our results showed that pharmacologically activating RXR-α with bexarotene significantly accelerated hematoma clearance and alleviated neurological dysfunction after ICH. RXR-α was expressed in microglia/macrophages, neurons, and astrocytes. Mechanistically, bexarotene promoted the nuclear translocation of RXR-α and PPAR-γ, as well as reducing neuroinflammation by modulating microglia/macrophage reprograming from the M1 into the M2 phenotype. Furthermore, all the beneficial effects of RXR-α in ICH were reversed by the PPAR-γ inhibitor GW9662. In conclusion, the pharmacological activation of RXR-α confers robust neuroprotection against ICH by accelerating hematoma clearance and repolarizing microglia/macrophages towards the M2 phenotype through PPAR-γ-related mechanisms. Our data support the notion that RXR-α might be a promising therapeutic target for ICH.
Anilides/pharmacology* ; Cerebral Hemorrhage/drug therapy* ; Hematoma/drug therapy* ; Humans ; Macrophages ; Microglia ; Neuroprotection ; PPAR gamma ; Retinoid X Receptor alpha

Endogenously eliminating the hematoma is a favorable strategy in addressing intracerebral hemorrhage (ICH). This study sought to determine the role of retinoid X receptor-α (RXR-α) in the context of hematoma absorption after ICH. Our results showed that pharmacologically activating RXR-α with bexarotene significantly accelerated hematoma clearance and alleviated neurological dysfunction after ICH. RXR-α was expressed in microglia/macrophages, neurons, and astrocytes. Mechanistically, bexarotene promoted the nuclear translocation of RXR-α and PPAR-γ, as well as reducing neuroinflammation by modulating microglia/macrophage reprograming from the M1 into the M2 phenotype. Furthermore, all the beneficial effects of RXR-α in ICH were reversed by the PPAR-γ inhibitor GW9662. In conclusion, the pharmacological activation of RXR-α confers robust neuroprotection against ICH by accelerating hematoma clearance and repolarizing microglia/macrophages towards the M2 phenotype through PPAR-γ-related mechanisms. Our data support the notion that RXR-α might be a promising therapeutic target for ICH.