Identification of microbe–disease signed associations via multi-scale variational graph autoencoder based on signed message propagation

Background Plenty of clinical and biomedical research has unequivocally highlighted the tremendous significance of the human microbiome in relation to human health. Identifying microbes associated with diseases is crucial for early disease diagnosis and advancing precision medicine. Results Consider...

Full description

Saved in:
Bibliographic Details
Published in:BMC biology Vol. 22; no. 1; pp. 172 - 15
Main Authors: Zhu, Huan, Hao, Hongxia, Yu, Liang
Format: Journal Article
Language:English
Published: London BioMed Central 15.08.2024
BioMed Central Ltd
Springer Nature B.V
BMC
Subjects:
Ablation
Accuracy
Algorithms
Background noise
Biomedical and Life Sciences
Biomedical data
Computational Biology - methods
Disease
Drugs
Dysbiosis
Graph representations
Graph theory
Graphical representations
Health aspects
Heterogeneity
Humans
Influence
Information processing
Life Sciences
Medical research
Messages
Microbe-disease association
Microbial metabolism
Microbiomes
Microbiota
Microorganisms
Neural networks
Noise prediction
Noise propagation
Performance evaluation
Precision medicine
Propagation
Regularization methods
Research Article
Signal processing
Signed message propagation
Similarity
Social networks
Variational graph autoencoder
XGBoost
China
Signed message propagation
Microbe-disease association
Variational graph autoencoder
XGBoost
ISSN:1741-7007, 1741-7007
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Background Plenty of clinical and biomedical research has unequivocally highlighted the tremendous significance of the human microbiome in relation to human health. Identifying microbes associated with diseases is crucial for early disease diagnosis and advancing precision medicine. Results Considering that the information about changes in microbial quantities under fine-grained disease states helps to enhance a comprehensive understanding of the overall data distribution, this study introduces MSignVGAE, a framework for predicting microbe-disease sign associations using signed message propagation. MSignVGAE employs a graph variational autoencoder to model noisy signed association data and extends the multi-scale concept to enhance representation capabilities. A novel strategy for propagating signed message in signed networks addresses heterogeneity and consistency among nodes connected by signed edges. Additionally, we utilize the idea of denoising autoencoder to handle the noise in similarity feature information, which helps overcome biases in the fused similarity data. MSignVGAE represents microbe-disease associations as a heterogeneous graph using similarity information as node features. The multi-class classifier XGBoost is utilized to predict sign associations between diseases and microbes. Conclusions MSignVGAE achieves AUROC and AUPR values of 0.9742 and 0.9601, respectively. Case studies on three diseases demonstrate that MSignVGAE can effectively capture a comprehensive distribution of associations by leveraging signed information.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1741-7007
1741-7007
DOI:10.1186/s12915-024-01968-0