Drug repositioning based on heterogeneous networks and variational graph autoencoders

Song, Lei; Lei, Xiujuan

doi:10.3389/fphar.2022.1056605

Cited by 5 publications

(4 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lei's team (Zhang et al, 2022b) proposed a new method based on Graph SAGE and clustering constraints (DRGCC) to investigate the potential therapeutic properties of drugs for drug repositioning. The team (Lei et al, 2022) also proposed a drug repositioning method for predicting drug-disease associations using a graph auto coder. These methods can be used to predict anti-COVID-19 drugs based on the existing drug and disease data.…”

Section: Research Hot Spots and Trendsmentioning

confidence: 99%

Knowledge mapping of graph neural networks for drug discovery: a bibliometric and visualized analysis

Yao,

Shen,

et al. 2024

Front. Pharmacol.

View full text Add to dashboard Cite

IntroductionIn recent years, graph neural network has been extensively applied to drug discovery research. Although researchers have made significant progress in this field, there is less research on bibliometrics. The purpose of this study is to conduct a comprehensive bibliometric analysis of graph neural network applications in drug discovery in order to identify current research hotspots and trends, as well as serve as a reference for future research.MethodsPublications from 2017 to 2023 about the application of graph neural network in drug discovery were collected from the Web of Science Core Collection. Bibliometrix, VOSviewer, and Citespace were mainly used for bibliometric studies.Results and DiscussionIn this paper, a total of 652 papers from 48 countries/regions were included. Research interest in this field is continuously increasing. China and the United States have a significant advantage in terms of funding, the number of publications, and collaborations with other institutions and countries. Although some cooperation networks have been formed in this field, extensive worldwide cooperation still needs to be strengthened. The results of the keyword analysis clarified that graph neural network has primarily been applied to drug-target interaction, drug repurposing, and drug-drug interaction, while graph convolutional neural network and its related optimization methods are currently the core algorithms in this field. Data availability and ethical supervision, balancing computing resources, and developing novel graph neural network models with better interpretability are the key technical issues currently faced. This paper analyzes the current state, hot spots, and trends of graph neural network applications in drug discovery through bibliometric approaches, as well as the current issues and challenges in this field. These findings provide researchers with valuable insights on the current status and future directions of this field.

show abstract

Section: Research Hot Spots and Trendsmentioning

confidence: 99%

Knowledge mapping of graph neural networks for drug discovery: a bibliometric and visualized analysis

Yao,

Shen,

et al. 2024

Front. Pharmacol.

View full text Add to dashboard Cite

show abstract

“…In addition, network pharmacological algorithms and tools are particularly important for mining these databases. Lei [21] et al proposed an algorithm that can effectively predict the association between drugs and diseases-vgaedr, which is based on variational graph automatic encoder and heterogeneous network. At the same time, algorithms such as DeepDR、SCMFDD、BNNR, and GRGMF are also used to predict the relationship between diseases and drugs.…”

Section: Network Pharmacology-related Databases and Research Toolsmentioning

confidence: 99%

Development of network pharmacology in sepsis treatment

Chen

2023

Preprint

View full text Add to dashboard Cite

So far, sepsis is still a global disease and health problem facing mankind. Due to the complexity of the pathophysiology and pathogenesis of sepsis, the idea that a drug corresponds to a single target - a single disease is no longer suitable for the treatment of complex diseases such as sepsis. The application of network pharmacology to explore the signal network relationship between diseases, targets, and drugs has gradually become a new disease treatment methodology. This effective treatment for disease targets can improve the effectiveness and success of drug therapy, and it is possible to develop from the current treatment of symptoms of complex diseases to the real cure of complex diseases. This paper will discuss the application and discovery of network pharmacology in the treatment of sepsis, to provide a certain scientific theoretical basis for the subsequent basic and clinical research of sepsis treatment.

show abstract

“…However, due to the complexity of multi-omics data, traditional statistical or mathematical models still face huge challenges in accurately modeling high-dimensional multi-omics data. The earliest method SNF ( Wang et al, 2014 ), ERDCN ( Lei et al, 2022 ) process the multi-omics data by constructing a sample similarity network about the co-expression patterns of cancer genes. However, these methods are susceptible to data noise and feature heterogeneity.…”

Section: Introductionmentioning

confidence: 99%

CAEM-GBDT: a cancer subtype identifying method using multi-omics data and convolutional autoencoder network

Shen,

Guo,

Bai

et al. 2024

Front. Bioinform.

View full text Add to dashboard Cite

The identification of cancer subtypes plays a very important role in the field of medicine. Accurate identification of cancer subtypes is helpful for both cancer treatment and prognosis Currently, most methods for cancer subtype identification are based on single-omics data, such as gene expression data. However, multi-omics data can show various characteristics about cancer, which also can improve the accuracy of cancer subtype identification. Therefore, how to extract features from multi-omics data for cancer subtype identification is the main challenge currently faced by researchers. In this paper, we propose a cancer subtype identification method named CAEM-GBDT, which takes gene expression data, miRNA expression data, and DNA methylation data as input, and adopts convolutional autoencoder network to identify cancer subtypes. Through a convolutional encoder layer, the method performs feature extraction on the input data. Within the convolutional encoder layer, a convolutional self-attention module is embedded to recognize higher-level representations of the multi-omics data. The extracted high-level representations from the convolutional encoder are then concatenated with the input to the decoder. The GBDT (Gradient Boosting Decision Tree) is utilized for cancer subtype identification. In the experiments, we compare CAEM-GBDT with existing cancer subtype identifying methods. Experimental results demonstrate that the proposed CAEM-GBDT outperforms other methods. The source code is available from GitHub at https://github.com/gxh-1/CAEM-GBDT.git.

show abstract

Drug repositioning based on heterogeneous networks and variational graph autoencoders

Cited by 5 publications

References 52 publications

Knowledge mapping of graph neural networks for drug discovery: a bibliometric and visualized analysis

Knowledge mapping of graph neural networks for drug discovery: a bibliometric and visualized analysis

Development of network pharmacology in sepsis treatment

CAEM-GBDT: a cancer subtype identifying method using multi-omics data and convolutional autoencoder network

Contact Info

Product

Resources

About