MODILM: towards better complex diseases classification using a novel multi-omics data integration learning model
Abstract Background Accurately classifying complex diseases is crucial for diagnosis and personalized treatment. Integrating multi-omics data has been demonstrated to enhance the accuracy of analyzing and classifying complex diseases. This can be attributed to the highly correlated nature of the dat...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-05-01
|
| Series: | BMC Medical Informatics and Decision Making |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12911-023-02173-9 |
| _version_ | 1797832045598081024 |
|---|---|
| author | Yating Zhong Yuzhong Peng Yanmei Lin Dingjia Chen Hao Zhang Wen Zheng Yuanyuan Chen Changliang Wu |
| author_facet | Yating Zhong Yuzhong Peng Yanmei Lin Dingjia Chen Hao Zhang Wen Zheng Yuanyuan Chen Changliang Wu |
| author_sort | Yating Zhong |
| collection | DOAJ |
| description | Abstract Background Accurately classifying complex diseases is crucial for diagnosis and personalized treatment. Integrating multi-omics data has been demonstrated to enhance the accuracy of analyzing and classifying complex diseases. This can be attributed to the highly correlated nature of the data with various diseases, as well as the comprehensive and complementary information it provides. However, integrating multi-omics data for complex diseases is challenged by data characteristics such as high imbalance, scale variation, heterogeneity, and noise interference. These challenges further emphasize the importance of developing effective methods for multi-omics data integration. Results We proposed a novel multi-omics data learning model called MODILM, which integrates multiple omics data to improve the classification accuracy of complex diseases by obtaining more significant and complementary information from different single-omics data. Our approach includes four key steps: 1) constructing a similarity network for each omics data using the cosine similarity measure, 2) leveraging Graph Attention Networks to learn sample-specific and intra-association features from similarity networks for single-omics data, 3) using Multilayer Perceptron networks to map learned features to a new feature space, thereby strengthening and extracting high-level omics-specific features, and 4) fusing these high-level features using a View Correlation Discovery Network to learn cross-omics features in the label space, which results in unique class-level distinctiveness for complex diseases. To demonstrate the effectiveness of MODILM, we conducted experiments on six benchmark datasets consisting of miRNA expression, mRNA, and DNA methylation data. Our results show that MODILM outperforms state-of-the-art methods, effectively improving the accuracy of complex disease classification. Conclusions Our MODILM provides a more competitive way to extract and integrate important and complementary information from multiple omics data, providing a very promising tool for supporting decision-making for clinical diagnosis. |
| first_indexed | 2024-04-09T14:02:33Z |
| format | Article |
| id | doaj.art-c07a97178f874f368261e391116117fd |
| institution | Directory Open Access Journal |
| issn | 1472-6947 |
| language | English |
| last_indexed | 2024-04-09T14:02:33Z |
| publishDate | 2023-05-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Informatics and Decision Making |
| spelling | doaj.art-c07a97178f874f368261e391116117fd2023-05-07T11:15:07ZengBMCBMC Medical Informatics and Decision Making1472-69472023-05-0123111810.1186/s12911-023-02173-9MODILM: towards better complex diseases classification using a novel multi-omics data integration learning modelYating Zhong0Yuzhong Peng1Yanmei Lin2Dingjia Chen3Hao Zhang4Wen Zheng5Yuanyuan Chen6Changliang Wu7Guangxi Key Lab of Human-Machine Interaction and Intelligent Decision, Nanning Normal UniversityGuangxi Key Lab of Human-Machine Interaction and Intelligent Decision, Nanning Normal UniversitySchool of Environment and Life Science, Nanning Normal UniversityGuangxi Key Lab of Human-Machine Interaction and Intelligent Decision, Nanning Normal UniversitySchool of Computer Science, Fudan UniversityGuangxi Key Lab of Human-Machine Interaction and Intelligent Decision, Nanning Normal UniversityGuangxi Key Lab of Human-Machine Interaction and Intelligent Decision, Nanning Normal UniversityDepartment of Spleen, Stomach and Liver Diseases, Guangxi International Zhuang Medical HospitalAbstract Background Accurately classifying complex diseases is crucial for diagnosis and personalized treatment. Integrating multi-omics data has been demonstrated to enhance the accuracy of analyzing and classifying complex diseases. This can be attributed to the highly correlated nature of the data with various diseases, as well as the comprehensive and complementary information it provides. However, integrating multi-omics data for complex diseases is challenged by data characteristics such as high imbalance, scale variation, heterogeneity, and noise interference. These challenges further emphasize the importance of developing effective methods for multi-omics data integration. Results We proposed a novel multi-omics data learning model called MODILM, which integrates multiple omics data to improve the classification accuracy of complex diseases by obtaining more significant and complementary information from different single-omics data. Our approach includes four key steps: 1) constructing a similarity network for each omics data using the cosine similarity measure, 2) leveraging Graph Attention Networks to learn sample-specific and intra-association features from similarity networks for single-omics data, 3) using Multilayer Perceptron networks to map learned features to a new feature space, thereby strengthening and extracting high-level omics-specific features, and 4) fusing these high-level features using a View Correlation Discovery Network to learn cross-omics features in the label space, which results in unique class-level distinctiveness for complex diseases. To demonstrate the effectiveness of MODILM, we conducted experiments on six benchmark datasets consisting of miRNA expression, mRNA, and DNA methylation data. Our results show that MODILM outperforms state-of-the-art methods, effectively improving the accuracy of complex disease classification. Conclusions Our MODILM provides a more competitive way to extract and integrate important and complementary information from multiple omics data, providing a very promising tool for supporting decision-making for clinical diagnosis.https://doi.org/10.1186/s12911-023-02173-9Complex disease classificationMulti-omics data integrationGraph Attention NetworksDeep learning |
| spellingShingle | Yating Zhong Yuzhong Peng Yanmei Lin Dingjia Chen Hao Zhang Wen Zheng Yuanyuan Chen Changliang Wu MODILM: towards better complex diseases classification using a novel multi-omics data integration learning model BMC Medical Informatics and Decision Making Complex disease classification Multi-omics data integration Graph Attention Networks Deep learning |
| title | MODILM: towards better complex diseases classification using a novel multi-omics data integration learning model |
| title_full | MODILM: towards better complex diseases classification using a novel multi-omics data integration learning model |
| title_fullStr | MODILM: towards better complex diseases classification using a novel multi-omics data integration learning model |
| title_full_unstemmed | MODILM: towards better complex diseases classification using a novel multi-omics data integration learning model |
| title_short | MODILM: towards better complex diseases classification using a novel multi-omics data integration learning model |
| title_sort | modilm towards better complex diseases classification using a novel multi omics data integration learning model |
| topic | Complex disease classification Multi-omics data integration Graph Attention Networks Deep learning |
| url | https://doi.org/10.1186/s12911-023-02173-9 |
| work_keys_str_mv | AT yatingzhong modilmtowardsbettercomplexdiseasesclassificationusinganovelmultiomicsdataintegrationlearningmodel AT yuzhongpeng modilmtowardsbettercomplexdiseasesclassificationusinganovelmultiomicsdataintegrationlearningmodel AT yanmeilin modilmtowardsbettercomplexdiseasesclassificationusinganovelmultiomicsdataintegrationlearningmodel AT dingjiachen modilmtowardsbettercomplexdiseasesclassificationusinganovelmultiomicsdataintegrationlearningmodel AT haozhang modilmtowardsbettercomplexdiseasesclassificationusinganovelmultiomicsdataintegrationlearningmodel AT wenzheng modilmtowardsbettercomplexdiseasesclassificationusinganovelmultiomicsdataintegrationlearningmodel AT yuanyuanchen modilmtowardsbettercomplexdiseasesclassificationusinganovelmultiomicsdataintegrationlearningmodel AT changliangwu modilmtowardsbettercomplexdiseasesclassificationusinganovelmultiomicsdataintegrationlearningmodel |