Identifying disease-related microbes based on multi-scale variational graph autoencoder embedding Wasserstein distance

Background Enormous clinical and biomedical researches have demonstrated that microbes are crucial to human health. Identifying associations between microbes and diseases can not only reveal potential disease mechanisms, but also facilitate early diagnosis and promote precision medicine. Due to the...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	BMC biology Ročník 21; číslo 1; s. 294 - 15
Hlavní autoři:	Zhu, Huan, Hao, Hongxia, Yu, Liang
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	London BioMed Central 20.12.2023 Springer Nature B.V BMC
Témata:	Ablation Accuracy Alzheimer's disease Bacteria Biomedical and Life Sciences Colorectal cancer Colorectal Neoplasms Crohn's disease Embedding Experiments Graphical representations Humans Life Sciences Medical research Microbe-disease association Microorganisms Neighborhoods Neoplasms Neural networks Neurodegenerative diseases Performance evaluation Perturbation Precision Medicine Regularization methods Research Article Variational graph autoencoder Wasserstein distance XGBoost Microbe-disease association Wasserstein distance Variational graph autoencoder XGBoost
ISSN:	1741-7007, 1741-7007
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Background Enormous clinical and biomedical researches have demonstrated that microbes are crucial to human health. Identifying associations between microbes and diseases can not only reveal potential disease mechanisms, but also facilitate early diagnosis and promote precision medicine. Due to the data perturbation and unsatisfactory latent representation, there is a significant room for improvement. Results In this work, we proposed a novel framework, Multi-scale Variational Graph AutoEncoder embedding Wasserstein distance (MVGAEW) to predict disease-related microbes, which had the ability to resist data perturbation and effectively generate latent representations for both microbes and diseases from the perspective of distribution. First, we calculated multiple similarities and integrated them through similarity network confusion. Subsequently, we obtained node latent representations by improved variational graph autoencoder. Ultimately, XGBoost classifier was employed to predict potential disease-related microbes. We also introduced multi-order node embedding reconstruction to enhance the representation capacity. We also performed ablation studies to evaluate the contribution of each section of our model. Moreover, we conducted experiments on common drugs and case studies, including Alzheimer’s disease, Crohn’s disease, and colorectal neoplasms, to validate the effectiveness of our framework. Conclusions Significantly, our model exceeded other currently state-of-the-art methods, exhibiting a great improvement on the HMDAD database.
Bibliografie:	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/s12915-023-01796-8