A new approach for microbe-disease association prediction: incorporating representation learning of latent relationships

Abstract Background Predicting associations between microbes and diseases is crucial for clinical diagnosis and therapy. However, biological experiments are time-intensive, necessitating efficient computational models. Traditional models rely on existing microbe-disease associations, but limited dat...

Full description

Saved in:
Bibliographic Details
Main Authors: Shaopeng Liu, Wanlu Hu, Chun-Chun Wang, Linlin Zhuo, Xu Lu
Format: Article
Language:English
Published: BMC 2025-07-01
Series:BMC Medical Informatics and Decision Making
Subjects:
Online Access:https://doi.org/10.1186/s12911-025-03093-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849333031576272896
author Shaopeng Liu
Wanlu Hu
Chun-Chun Wang
Linlin Zhuo
Xu Lu
author_facet Shaopeng Liu
Wanlu Hu
Chun-Chun Wang
Linlin Zhuo
Xu Lu
author_sort Shaopeng Liu
collection DOAJ
description Abstract Background Predicting associations between microbes and diseases is crucial for clinical diagnosis and therapy. However, biological experiments are time-intensive, necessitating efficient computational models. Traditional models rely on existing microbe-disease associations, but limited data often restricts their effectiveness. This scarcity of information hinders the construction of a comprehensive association network, prompting the need for innovative solutions. Methods We propose RKGATMDA, a deep learning framework for microbe-disease association prediction. Utilizing a graph attention network, RKGATMDA learns representations from the microbe-disease association network. To address the limitation of insufficient association information, we introduce Random K-Nearest Neighbors to uncover latent relationships, enhancing representation learning. During each training iteration, associations are expanded based on attention scores, and a multi-head attention mechanism integrates diverse features, enabling RKGATMDA to capture comprehensive interactions between microbes and diseases. Results Results Experimental results show that RKGATMDA achieves AUC values of 0.8906 in 5-fold cross-validation, 0.8999 in global leave-one-out cross-validation, and 0.7246 in local leave-one-out cross-validation, outperforming previous methods such as ABHMDA, KATZHMDA, LRLSHMDA, BiRWHMDA, and NTSHMDA. Case studies on asthma, colon cancer, and colorectal carcinoma further validate its predictive power. Conclusion Our findings demonstrate that RKGATMDA effectively predicts microbe-disease associations, with at least 9 out of the top 10 prediction pairs validated by biological evidence. This highlights the potential of RKGATMDA as a valuable tool in microbial-disease research, offering a promising approach for identifying novel associations and advancing our understanding of microbial pathogenesis.
format Article
id doaj-art-eef85487b2164a668a6ce9c693061d5e
institution Kabale University
issn 1472-6947
language English
publishDate 2025-07-01
publisher BMC
record_format Article
series BMC Medical Informatics and Decision Making
spelling doaj-art-eef85487b2164a668a6ce9c693061d5e2025-08-20T03:46:00ZengBMCBMC Medical Informatics and Decision Making1472-69472025-07-0125111410.1186/s12911-025-03093-6A new approach for microbe-disease association prediction: incorporating representation learning of latent relationshipsShaopeng Liu0Wanlu Hu1Chun-Chun Wang2Linlin Zhuo3Xu Lu4School of Computer Science, Guangdong Polytechnic Normal UniversitySchool of Computer Science, Guangdong Polytechnic Normal UniversitySchool of Science, Jiangnan UniversitySchool of Data Science and Artificial Intelligence, Wenzhou University of TechnologySchool of Computer Science, Guangdong Polytechnic Normal UniversityAbstract Background Predicting associations between microbes and diseases is crucial for clinical diagnosis and therapy. However, biological experiments are time-intensive, necessitating efficient computational models. Traditional models rely on existing microbe-disease associations, but limited data often restricts their effectiveness. This scarcity of information hinders the construction of a comprehensive association network, prompting the need for innovative solutions. Methods We propose RKGATMDA, a deep learning framework for microbe-disease association prediction. Utilizing a graph attention network, RKGATMDA learns representations from the microbe-disease association network. To address the limitation of insufficient association information, we introduce Random K-Nearest Neighbors to uncover latent relationships, enhancing representation learning. During each training iteration, associations are expanded based on attention scores, and a multi-head attention mechanism integrates diverse features, enabling RKGATMDA to capture comprehensive interactions between microbes and diseases. Results Results Experimental results show that RKGATMDA achieves AUC values of 0.8906 in 5-fold cross-validation, 0.8999 in global leave-one-out cross-validation, and 0.7246 in local leave-one-out cross-validation, outperforming previous methods such as ABHMDA, KATZHMDA, LRLSHMDA, BiRWHMDA, and NTSHMDA. Case studies on asthma, colon cancer, and colorectal carcinoma further validate its predictive power. Conclusion Our findings demonstrate that RKGATMDA effectively predicts microbe-disease associations, with at least 9 out of the top 10 prediction pairs validated by biological evidence. This highlights the potential of RKGATMDA as a valuable tool in microbial-disease research, offering a promising approach for identifying novel associations and advancing our understanding of microbial pathogenesis.https://doi.org/10.1186/s12911-025-03093-6MicrobeDiseaseAssociation predictionGraph attention networks
spellingShingle Shaopeng Liu
Wanlu Hu
Chun-Chun Wang
Linlin Zhuo
Xu Lu
A new approach for microbe-disease association prediction: incorporating representation learning of latent relationships
BMC Medical Informatics and Decision Making
Microbe
Disease
Association prediction
Graph attention networks
title A new approach for microbe-disease association prediction: incorporating representation learning of latent relationships
title_full A new approach for microbe-disease association prediction: incorporating representation learning of latent relationships
title_fullStr A new approach for microbe-disease association prediction: incorporating representation learning of latent relationships
title_full_unstemmed A new approach for microbe-disease association prediction: incorporating representation learning of latent relationships
title_short A new approach for microbe-disease association prediction: incorporating representation learning of latent relationships
title_sort new approach for microbe disease association prediction incorporating representation learning of latent relationships
topic Microbe
Disease
Association prediction
Graph attention networks
url https://doi.org/10.1186/s12911-025-03093-6
work_keys_str_mv AT shaopengliu anewapproachformicrobediseaseassociationpredictionincorporatingrepresentationlearningoflatentrelationships
AT wanluhu anewapproachformicrobediseaseassociationpredictionincorporatingrepresentationlearningoflatentrelationships
AT chunchunwang anewapproachformicrobediseaseassociationpredictionincorporatingrepresentationlearningoflatentrelationships
AT linlinzhuo anewapproachformicrobediseaseassociationpredictionincorporatingrepresentationlearningoflatentrelationships
AT xulu anewapproachformicrobediseaseassociationpredictionincorporatingrepresentationlearningoflatentrelationships
AT shaopengliu newapproachformicrobediseaseassociationpredictionincorporatingrepresentationlearningoflatentrelationships
AT wanluhu newapproachformicrobediseaseassociationpredictionincorporatingrepresentationlearningoflatentrelationships
AT chunchunwang newapproachformicrobediseaseassociationpredictionincorporatingrepresentationlearningoflatentrelationships
AT linlinzhuo newapproachformicrobediseaseassociationpredictionincorporatingrepresentationlearningoflatentrelationships
AT xulu newapproachformicrobediseaseassociationpredictionincorporatingrepresentationlearningoflatentrelationships