MoGCN: A Multi-Omics Integration Method Based on Graph Convolutional Network for Cancer Subtype Analysis
In light of the rapid accumulation of large-scale omics datasets, numerous studies have attempted to characterize the molecular and clinical features of cancers from a multi-omics perspective. However, there are great challenges in integrating multi-omics using machine learning methods for cancer su...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-02-01
|
| Series: | Frontiers in Genetics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fgene.2022.806842/full |
| _version_ | 1798031134619074560 |
|---|---|
| author | Xiao Li Jie Ma Ling Leng Mingfei Han Mansheng Li Fuchu He Yunping Zhu |
| author_facet | Xiao Li Jie Ma Ling Leng Mingfei Han Mansheng Li Fuchu He Yunping Zhu |
| author_sort | Xiao Li |
| collection | DOAJ |
| description | In light of the rapid accumulation of large-scale omics datasets, numerous studies have attempted to characterize the molecular and clinical features of cancers from a multi-omics perspective. However, there are great challenges in integrating multi-omics using machine learning methods for cancer subtype classification. In this study, MoGCN, a multi-omics integration model based on graph convolutional network (GCN) was developed for cancer subtype classification and analysis. Genomics, transcriptomics and proteomics datasets for 511 breast invasive carcinoma (BRCA) samples were downloaded from the Cancer Genome Atlas (TCGA). The autoencoder (AE) and the similarity network fusion (SNF) methods were used to reduce dimensionality and construct the patient similarity network (PSN), respectively. Then the vector features and the PSN were input into the GCN for training and testing. Feature extraction and network visualization were used for further biological knowledge discovery and subtype classification. In the analysis of multi-dimensional omics data of the BRCA samples in TCGA, MoGCN achieved the highest accuracy in cancer subtype classification compared with several popular algorithms. Moreover, MoGCN can extract the most significant features of each omics layer and provide candidate functional molecules for further analysis of their biological effects. And network visualization showed that MoGCN could make clinically intuitive diagnosis. The generality of MoGCN was proven on the TCGA pan-kidney cancer datasets. MoGCN and datasets are public available at https://github.com/Lifoof/MoGCN. Our study shows that MoGCN performs well for heterogeneous data integration and the interpretability of classification results, which confers great potential for applications in biomarker identification and clinical diagnosis. |
| first_indexed | 2024-04-11T19:51:17Z |
| format | Article |
| id | doaj.art-5f940d5b0e5144278a3bb7593ba32d50 |
| institution | Directory Open Access Journal |
| issn | 1664-8021 |
| language | English |
| last_indexed | 2024-04-11T19:51:17Z |
| publishDate | 2022-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Genetics |
| spelling | doaj.art-5f940d5b0e5144278a3bb7593ba32d502022-12-22T04:06:17ZengFrontiers Media S.A.Frontiers in Genetics1664-80212022-02-011310.3389/fgene.2022.806842806842MoGCN: A Multi-Omics Integration Method Based on Graph Convolutional Network for Cancer Subtype AnalysisXiao Li0Jie Ma1Ling Leng2Mingfei Han3Mansheng Li4Fuchu He5Yunping Zhu6State Key Laboratory of Proteomics, Beijing Proteome Research Center, National Center for Protein Sciences (Beijing), Beijing Institute of Life Omics, Beijing, ChinaState Key Laboratory of Proteomics, Beijing Proteome Research Center, National Center for Protein Sciences (Beijing), Beijing Institute of Life Omics, Beijing, ChinaStem Cell and Regenerative Medicine Lab, Department of Medical Science Research Center, State Key Laboratory of Complex Severe and Rare Diseases, Translational Medicine Center, Peking Union Medical College Hospital, Peking Union Medical College and Chinese Academy of Medical Sciences, Beijing, ChinaState Key Laboratory of Proteomics, Beijing Proteome Research Center, National Center for Protein Sciences (Beijing), Beijing Institute of Life Omics, Beijing, ChinaState Key Laboratory of Proteomics, Beijing Proteome Research Center, National Center for Protein Sciences (Beijing), Beijing Institute of Life Omics, Beijing, ChinaState Key Laboratory of Proteomics, Beijing Proteome Research Center, National Center for Protein Sciences (Beijing), Beijing Institute of Life Omics, Beijing, ChinaState Key Laboratory of Proteomics, Beijing Proteome Research Center, National Center for Protein Sciences (Beijing), Beijing Institute of Life Omics, Beijing, ChinaIn light of the rapid accumulation of large-scale omics datasets, numerous studies have attempted to characterize the molecular and clinical features of cancers from a multi-omics perspective. However, there are great challenges in integrating multi-omics using machine learning methods for cancer subtype classification. In this study, MoGCN, a multi-omics integration model based on graph convolutional network (GCN) was developed for cancer subtype classification and analysis. Genomics, transcriptomics and proteomics datasets for 511 breast invasive carcinoma (BRCA) samples were downloaded from the Cancer Genome Atlas (TCGA). The autoencoder (AE) and the similarity network fusion (SNF) methods were used to reduce dimensionality and construct the patient similarity network (PSN), respectively. Then the vector features and the PSN were input into the GCN for training and testing. Feature extraction and network visualization were used for further biological knowledge discovery and subtype classification. In the analysis of multi-dimensional omics data of the BRCA samples in TCGA, MoGCN achieved the highest accuracy in cancer subtype classification compared with several popular algorithms. Moreover, MoGCN can extract the most significant features of each omics layer and provide candidate functional molecules for further analysis of their biological effects. And network visualization showed that MoGCN could make clinically intuitive diagnosis. The generality of MoGCN was proven on the TCGA pan-kidney cancer datasets. MoGCN and datasets are public available at https://github.com/Lifoof/MoGCN. Our study shows that MoGCN performs well for heterogeneous data integration and the interpretability of classification results, which confers great potential for applications in biomarker identification and clinical diagnosis.https://www.frontiersin.org/articles/10.3389/fgene.2022.806842/fullmulti-omics integrationgraph convolutional networkautoencodersimilarity network fusioncancer subtype classification |
| spellingShingle | Xiao Li Jie Ma Ling Leng Mingfei Han Mansheng Li Fuchu He Yunping Zhu MoGCN: A Multi-Omics Integration Method Based on Graph Convolutional Network for Cancer Subtype Analysis Frontiers in Genetics multi-omics integration graph convolutional network autoencoder similarity network fusion cancer subtype classification |
| title | MoGCN: A Multi-Omics Integration Method Based on Graph Convolutional Network for Cancer Subtype Analysis |
| title_full | MoGCN: A Multi-Omics Integration Method Based on Graph Convolutional Network for Cancer Subtype Analysis |
| title_fullStr | MoGCN: A Multi-Omics Integration Method Based on Graph Convolutional Network for Cancer Subtype Analysis |
| title_full_unstemmed | MoGCN: A Multi-Omics Integration Method Based on Graph Convolutional Network for Cancer Subtype Analysis |
| title_short | MoGCN: A Multi-Omics Integration Method Based on Graph Convolutional Network for Cancer Subtype Analysis |
| title_sort | mogcn a multi omics integration method based on graph convolutional network for cancer subtype analysis |
| topic | multi-omics integration graph convolutional network autoencoder similarity network fusion cancer subtype classification |
| url | https://www.frontiersin.org/articles/10.3389/fgene.2022.806842/full |
| work_keys_str_mv | AT xiaoli mogcnamultiomicsintegrationmethodbasedongraphconvolutionalnetworkforcancersubtypeanalysis AT jiema mogcnamultiomicsintegrationmethodbasedongraphconvolutionalnetworkforcancersubtypeanalysis AT lingleng mogcnamultiomicsintegrationmethodbasedongraphconvolutionalnetworkforcancersubtypeanalysis AT mingfeihan mogcnamultiomicsintegrationmethodbasedongraphconvolutionalnetworkforcancersubtypeanalysis AT manshengli mogcnamultiomicsintegrationmethodbasedongraphconvolutionalnetworkforcancersubtypeanalysis AT fuchuhe mogcnamultiomicsintegrationmethodbasedongraphconvolutionalnetworkforcancersubtypeanalysis AT yunpingzhu mogcnamultiomicsintegrationmethodbasedongraphconvolutionalnetworkforcancersubtypeanalysis |