MDSVDNV: predicting microbe–drug associations by singular value decomposition and Node2vec
IntroductionRecent researches have demonstrated that microbes are crucial for the growth and development of the human body, the movement of nutrients, and human health. Diseases may arise as a result of disruptions and imbalances in the microbiome. The pathological investigation of associated diseas...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-01-01
|
| Series: | Frontiers in Microbiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmicb.2023.1303585/full |
| _version_ | 1827387759263744000 |
|---|---|
| author | Huilin Tan Zhen Zhang Xin Liu Yiming Chen Zinuo Yang Lei Wang |
| author_facet | Huilin Tan Zhen Zhang Xin Liu Yiming Chen Zinuo Yang Lei Wang |
| author_sort | Huilin Tan |
| collection | DOAJ |
| description | IntroductionRecent researches have demonstrated that microbes are crucial for the growth and development of the human body, the movement of nutrients, and human health. Diseases may arise as a result of disruptions and imbalances in the microbiome. The pathological investigation of associated diseases and the advancement of clinical medicine can both benefit from the identification of drug-associated microbes.MethodsIn this article, we proposed a new prediction model called MDSVDNV to infer potential microbe-drug associations, in which the Node2vec network embedding approach and the singular value decomposition (SVD) matrix decomposition method were first adopted to produce linear and non-linear representations of microbe interactions.Results and discussionCompared with state-of-the-art competitive methods, intensive experimental results demonstrated that MDSVDNV could achieve the best AUC value of 98.51% under a 5-fold CV, which indicated that MDSVDNV outperformed existing competing models and may be an effective method for discovering latent microbe–drug associations in the future. |
| first_indexed | 2024-03-08T16:07:58Z |
| format | Article |
| id | doaj.art-f74201c0e170472ba864640a539ceffd |
| institution | Directory Open Access Journal |
| issn | 1664-302X |
| language | English |
| last_indexed | 2024-03-08T16:07:58Z |
| publishDate | 2024-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Microbiology |
| spelling | doaj.art-f74201c0e170472ba864640a539ceffd2024-01-08T05:07:15ZengFrontiers Media S.A.Frontiers in Microbiology1664-302X2024-01-011410.3389/fmicb.2023.13035851303585MDSVDNV: predicting microbe–drug associations by singular value decomposition and Node2vecHuilin TanZhen ZhangXin LiuYiming ChenZinuo YangLei WangIntroductionRecent researches have demonstrated that microbes are crucial for the growth and development of the human body, the movement of nutrients, and human health. Diseases may arise as a result of disruptions and imbalances in the microbiome. The pathological investigation of associated diseases and the advancement of clinical medicine can both benefit from the identification of drug-associated microbes.MethodsIn this article, we proposed a new prediction model called MDSVDNV to infer potential microbe-drug associations, in which the Node2vec network embedding approach and the singular value decomposition (SVD) matrix decomposition method were first adopted to produce linear and non-linear representations of microbe interactions.Results and discussionCompared with state-of-the-art competitive methods, intensive experimental results demonstrated that MDSVDNV could achieve the best AUC value of 98.51% under a 5-fold CV, which indicated that MDSVDNV outperformed existing competing models and may be an effective method for discovering latent microbe–drug associations in the future.https://www.frontiersin.org/articles/10.3389/fmicb.2023.1303585/fullmicrobe–drug association predictioncomputational modelsingular value decompositionNode2vecXGBoost classifier |
| spellingShingle | Huilin Tan Zhen Zhang Xin Liu Yiming Chen Zinuo Yang Lei Wang MDSVDNV: predicting microbe–drug associations by singular value decomposition and Node2vec Frontiers in Microbiology microbe–drug association prediction computational model singular value decomposition Node2vec XGBoost classifier |
| title | MDSVDNV: predicting microbe–drug associations by singular value decomposition and Node2vec |
| title_full | MDSVDNV: predicting microbe–drug associations by singular value decomposition and Node2vec |
| title_fullStr | MDSVDNV: predicting microbe–drug associations by singular value decomposition and Node2vec |
| title_full_unstemmed | MDSVDNV: predicting microbe–drug associations by singular value decomposition and Node2vec |
| title_short | MDSVDNV: predicting microbe–drug associations by singular value decomposition and Node2vec |
| title_sort | mdsvdnv predicting microbe drug associations by singular value decomposition and node2vec |
| topic | microbe–drug association prediction computational model singular value decomposition Node2vec XGBoost classifier |
| url | https://www.frontiersin.org/articles/10.3389/fmicb.2023.1303585/full |
| work_keys_str_mv | AT huilintan mdsvdnvpredictingmicrobedrugassociationsbysingularvaluedecompositionandnode2vec AT zhenzhang mdsvdnvpredictingmicrobedrugassociationsbysingularvaluedecompositionandnode2vec AT xinliu mdsvdnvpredictingmicrobedrugassociationsbysingularvaluedecompositionandnode2vec AT yimingchen mdsvdnvpredictingmicrobedrugassociationsbysingularvaluedecompositionandnode2vec AT zinuoyang mdsvdnvpredictingmicrobedrugassociationsbysingularvaluedecompositionandnode2vec AT leiwang mdsvdnvpredictingmicrobedrugassociationsbysingularvaluedecompositionandnode2vec |