Predicting potential microbe-disease associations based on auto-encoder and graph convolution network
Abstract The increasing body of research has consistently demonstrated the intricate correlation between the human microbiome and human well-being. Microbes can impact the efficacy and toxicity of drugs through various pathways, as well as influence the occurrence and metastasis of tumors. In clinic...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-12-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12859-023-05611-7 |
| _version_ | 1797388100455890944 |
|---|---|
| author | Shanghui Lu Yong Liang Le Li Rui Miao Shuilin Liao Yongfu Zou Chengjun Yang Dong Ouyang |
| author_facet | Shanghui Lu Yong Liang Le Li Rui Miao Shuilin Liao Yongfu Zou Chengjun Yang Dong Ouyang |
| author_sort | Shanghui Lu |
| collection | DOAJ |
| description | Abstract The increasing body of research has consistently demonstrated the intricate correlation between the human microbiome and human well-being. Microbes can impact the efficacy and toxicity of drugs through various pathways, as well as influence the occurrence and metastasis of tumors. In clinical practice, it is crucial to elucidate the association between microbes and diseases. Although traditional biological experiments accurately identify this association, they are time-consuming, expensive, and susceptible to experimental conditions. Consequently, conducting extensive biological experiments to screen potential microbe-disease associations becomes challenging. The computational methods can solve the above problems well, but the previous computational methods still have the problems of low utilization of node features and the prediction accuracy needs to be improved. To address this issue, we propose the DAEGCNDF model predicting potential associations between microbes and diseases. Our model calculates four similar features for each microbe and disease. These features are fused to obtain a comprehensive feature matrix representing microbes and diseases. Our model first uses the graph convolutional network module to extract low-rank features with graph information of microbes and diseases, and then uses a deep sparse Auto-Encoder to extract high-rank features of microbe-disease pairs, after which the low-rank and high-rank features are spliced to improve the utilization of node features. Finally, Deep Forest was used for microbe-disease potential relationship prediction. The experimental results show that combining low-rank and high-rank features helps to improve the model performance and Deep Forest has better classification performance than the baseline model. |
| first_indexed | 2024-03-08T22:34:51Z |
| format | Article |
| id | doaj.art-f646298ab45944429e6b345213a42a01 |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-03-08T22:34:51Z |
| publishDate | 2023-12-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-f646298ab45944429e6b345213a42a012023-12-17T12:31:48ZengBMCBMC Bioinformatics1471-21052023-12-0124112410.1186/s12859-023-05611-7Predicting potential microbe-disease associations based on auto-encoder and graph convolution networkShanghui Lu0Yong Liang1Le Li2Rui Miao3Shuilin Liao4Yongfu Zou5Chengjun Yang6Dong Ouyang7Faculty of Innovation Enginee, Macau University of Science and TechnologyFaculty of Innovation Enginee, Macau University of Science and TechnologyFaculty of Innovation Enginee, Macau University of Science and TechnologyBasic Teaching Department, Zhuhai Campus of Zunyi Medical UniversityFaculty of Innovation Enginee, Macau University of Science and TechnologySchool of Mathematics and Physics, Hechi UniversitySchool of Artificial Intelligence and Manufacturing, Hechi UniversitySchool of Biomedical Engineering, Guangdong Medical UniversityAbstract The increasing body of research has consistently demonstrated the intricate correlation between the human microbiome and human well-being. Microbes can impact the efficacy and toxicity of drugs through various pathways, as well as influence the occurrence and metastasis of tumors. In clinical practice, it is crucial to elucidate the association between microbes and diseases. Although traditional biological experiments accurately identify this association, they are time-consuming, expensive, and susceptible to experimental conditions. Consequently, conducting extensive biological experiments to screen potential microbe-disease associations becomes challenging. The computational methods can solve the above problems well, but the previous computational methods still have the problems of low utilization of node features and the prediction accuracy needs to be improved. To address this issue, we propose the DAEGCNDF model predicting potential associations between microbes and diseases. Our model calculates four similar features for each microbe and disease. These features are fused to obtain a comprehensive feature matrix representing microbes and diseases. Our model first uses the graph convolutional network module to extract low-rank features with graph information of microbes and diseases, and then uses a deep sparse Auto-Encoder to extract high-rank features of microbe-disease pairs, after which the low-rank and high-rank features are spliced to improve the utilization of node features. Finally, Deep Forest was used for microbe-disease potential relationship prediction. The experimental results show that combining low-rank and high-rank features helps to improve the model performance and Deep Forest has better classification performance than the baseline model.https://doi.org/10.1186/s12859-023-05611-7Microbe-disease associationsAuto-enconderGraph convolution networkDeep forest |
| spellingShingle | Shanghui Lu Yong Liang Le Li Rui Miao Shuilin Liao Yongfu Zou Chengjun Yang Dong Ouyang Predicting potential microbe-disease associations based on auto-encoder and graph convolution network BMC Bioinformatics Microbe-disease associations Auto-enconder Graph convolution network Deep forest |
| title | Predicting potential microbe-disease associations based on auto-encoder and graph convolution network |
| title_full | Predicting potential microbe-disease associations based on auto-encoder and graph convolution network |
| title_fullStr | Predicting potential microbe-disease associations based on auto-encoder and graph convolution network |
| title_full_unstemmed | Predicting potential microbe-disease associations based on auto-encoder and graph convolution network |
| title_short | Predicting potential microbe-disease associations based on auto-encoder and graph convolution network |
| title_sort | predicting potential microbe disease associations based on auto encoder and graph convolution network |
| topic | Microbe-disease associations Auto-enconder Graph convolution network Deep forest |
| url | https://doi.org/10.1186/s12859-023-05611-7 |
| work_keys_str_mv | AT shanghuilu predictingpotentialmicrobediseaseassociationsbasedonautoencoderandgraphconvolutionnetwork AT yongliang predictingpotentialmicrobediseaseassociationsbasedonautoencoderandgraphconvolutionnetwork AT leli predictingpotentialmicrobediseaseassociationsbasedonautoencoderandgraphconvolutionnetwork AT ruimiao predictingpotentialmicrobediseaseassociationsbasedonautoencoderandgraphconvolutionnetwork AT shuilinliao predictingpotentialmicrobediseaseassociationsbasedonautoencoderandgraphconvolutionnetwork AT yongfuzou predictingpotentialmicrobediseaseassociationsbasedonautoencoderandgraphconvolutionnetwork AT chengjunyang predictingpotentialmicrobediseaseassociationsbasedonautoencoderandgraphconvolutionnetwork AT dongouyang predictingpotentialmicrobediseaseassociationsbasedonautoencoderandgraphconvolutionnetwork |