MO-GCN: A multi-omics graph convolutional network for discriminative analysis of schizophrenia
The methodology of machine learning with multi-omics data has been widely adopted in the discriminative analyses of schizophrenia, but most of these studies ignored the cooperative interactions and topological attributes of multi-omics networks. In this study, we constructed three types of brain gra...
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-02-01
|
| Series: | Brain Research Bulletin |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0361923025000115 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825206952107442176 |
|---|---|
| author | Haiyuan Wang Runlin Peng Yuanyuan Huang Liqin Liang Wei Wang Baoyuan Zhu Chenyang Gao Minxin Guo Jing Zhou Hehua Li Xiaobo Li Yuping Ning Fengchun Wu Kai Wu |
| author_facet | Haiyuan Wang Runlin Peng Yuanyuan Huang Liqin Liang Wei Wang Baoyuan Zhu Chenyang Gao Minxin Guo Jing Zhou Hehua Li Xiaobo Li Yuping Ning Fengchun Wu Kai Wu |
| author_sort | Haiyuan Wang |
| collection | DOAJ |
| description | The methodology of machine learning with multi-omics data has been widely adopted in the discriminative analyses of schizophrenia, but most of these studies ignored the cooperative interactions and topological attributes of multi-omics networks. In this study, we constructed three types of brain graphs (BGs), three types of gut graphs (GGs), and nine types of brain-gut combined graphs (BGCGs) for each individual. We proposed a novel methodology of multi-omics graph convolutional network (MO-GCN) with an attention mechanism to construct a classification model by integrating all BGCGs. We also identified important brain and gut features using the Topk pooling layer and analyzed their correlations with the Positive and Negative Syndrome Scale (PANSS) and MATRICS Consensus Cognitive Battery (MCCB) scores. The results showed that the novel MO-GCN model using BGCGs outperformed the GCN models using either BGs or GGs. In particular, the accuracy of the best model by 5-fold cross-validation reached 84.0 %. Interpretability analysis revealed that the top 10 important brain features were primarily from the hippocampus, olfactory, fusiform and pallidum, which were involved in the brain systems of memory, learning and emotion. The top 10 important gut features were primarily from Dorea, Ruminococcus, Subdoligranulum and Clostridium, etc. Moreover, the important brain and gut features were significantly correlated with the PANSS and MCCB scores, respectively. In conclusion, the MO-GCN can effectively improve the classification performance and provide a potential gut microbiota-brain perspective for the understanding of schizophrenia. |
| format | Article |
| id | doaj-art-688c984816984b629627ea522949d03c |
| institution | Kabale University |
| issn | 1873-2747 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Brain Research Bulletin |
| spelling | doaj-art-688c984816984b629627ea522949d03c2025-02-07T04:46:41ZengElsevierBrain Research Bulletin1873-27472025-02-01221111199MO-GCN: A multi-omics graph convolutional network for discriminative analysis of schizophreniaHaiyuan Wang0Runlin Peng1Yuanyuan Huang2Liqin Liang3Wei Wang4Baoyuan Zhu5Chenyang Gao6Minxin Guo7Jing Zhou8Hehua Li9Xiaobo Li10Yuping Ning11Fengchun Wu12Kai Wu13School of Biomedical Sciences and Engineering, South China University of Technology, Guangzhou International Campus, Guangzhou 511442, ChinaSchool of Biomedical Sciences and Engineering, South China University of Technology, Guangzhou International Campus, Guangzhou 511442, ChinaDepartment of Psychiatry, The Affiliated Brain Hospital of Guangzhou Medical University, Guangzhou 510370, China; Guangdong Engineering Technology Research Center for Translational Medicine of Mental Disorders, Guangzhou 510370, ChinaSchool of Biomedical Sciences and Engineering, South China University of Technology, Guangzhou International Campus, Guangzhou 511442, ChinaSchool of Biomedical Sciences and Engineering, South China University of Technology, Guangzhou International Campus, Guangzhou 511442, ChinaSchool of Material Science and Engineering, South China University of Technology, Guangzhou 510006, ChinaSchool of Biomedical Sciences and Engineering, South China University of Technology, Guangzhou International Campus, Guangzhou 511442, ChinaSchool of Biomedical Sciences and Engineering, South China University of Technology, Guangzhou International Campus, Guangzhou 511442, ChinaSchool of Material Science and Engineering, South China University of Technology, Guangzhou 510006, China; Guangdong Engineering Technology Research Center for Translational Medicine of Mental Disorders, Guangzhou 510370, China; Guangdong Engineering Technology Research Center for Diagnosis and Rehabilitation of Dementia, Guangzhou 510500, China; National Engineering Research Center for Tissue Restoration and Reconstruction, South China University of Technology, Guangzhou 510006, ChinaDepartment of Psychiatry, The Affiliated Brain Hospital of Guangzhou Medical University, Guangzhou 510370, China; Guangdong Engineering Technology Research Center for Translational Medicine of Mental Disorders, Guangzhou 510370, ChinaDepartment of Biomedical Engineering, New Jersey Institute of Technology, Newark, NJ, USADepartment of Psychiatry, The Affiliated Brain Hospital of Guangzhou Medical University, Guangzhou 510370, China; Guangdong Engineering Technology Research Center for Translational Medicine of Mental Disorders, Guangzhou 510370, ChinaDepartment of Psychiatry, The Affiliated Brain Hospital of Guangzhou Medical University, Guangzhou 510370, China; Guangdong Engineering Technology Research Center for Translational Medicine of Mental Disorders, Guangzhou 510370, China; Key Laboratory of Neurogenetics and Channelopathies of Guangdong Province and the Ministry of Education of China, Guangzhou Medical University, Guangzhou 510370, China; Corresponding author at: Department of Psychiatry, The Affiliated Brain Hospital of Guangzhou Medical University, Guangzhou 510370, ChinaSchool of Biomedical Sciences and Engineering, South China University of Technology, Guangzhou International Campus, Guangzhou 511442, China; Guangdong Province Key Laboratory of Biomedical Engineering, South China University of Technology, Guangzhou 510006, China; Department of Aging Research and Geriatric Medicine, Institute of Development, Aging and Cancer, Tohoku University, Sendai 980-8575, Japan; Corresponding author at: School of Biomedical Sciences and Engineering, South China University of Technology, Guangzhou International Campus, Guangzhou 511442, ChinaThe methodology of machine learning with multi-omics data has been widely adopted in the discriminative analyses of schizophrenia, but most of these studies ignored the cooperative interactions and topological attributes of multi-omics networks. In this study, we constructed three types of brain graphs (BGs), three types of gut graphs (GGs), and nine types of brain-gut combined graphs (BGCGs) for each individual. We proposed a novel methodology of multi-omics graph convolutional network (MO-GCN) with an attention mechanism to construct a classification model by integrating all BGCGs. We also identified important brain and gut features using the Topk pooling layer and analyzed their correlations with the Positive and Negative Syndrome Scale (PANSS) and MATRICS Consensus Cognitive Battery (MCCB) scores. The results showed that the novel MO-GCN model using BGCGs outperformed the GCN models using either BGs or GGs. In particular, the accuracy of the best model by 5-fold cross-validation reached 84.0 %. Interpretability analysis revealed that the top 10 important brain features were primarily from the hippocampus, olfactory, fusiform and pallidum, which were involved in the brain systems of memory, learning and emotion. The top 10 important gut features were primarily from Dorea, Ruminococcus, Subdoligranulum and Clostridium, etc. Moreover, the important brain and gut features were significantly correlated with the PANSS and MCCB scores, respectively. In conclusion, the MO-GCN can effectively improve the classification performance and provide a potential gut microbiota-brain perspective for the understanding of schizophrenia.http://www.sciencedirect.com/science/article/pii/S0361923025000115SchizophreniaMulti-omicsBrain networkGut networkClassificationGraph convolutional network |
| spellingShingle | Haiyuan Wang Runlin Peng Yuanyuan Huang Liqin Liang Wei Wang Baoyuan Zhu Chenyang Gao Minxin Guo Jing Zhou Hehua Li Xiaobo Li Yuping Ning Fengchun Wu Kai Wu MO-GCN: A multi-omics graph convolutional network for discriminative analysis of schizophrenia Brain Research Bulletin Schizophrenia Multi-omics Brain network Gut network Classification Graph convolutional network |
| title | MO-GCN: A multi-omics graph convolutional network for discriminative analysis of schizophrenia |
| title_full | MO-GCN: A multi-omics graph convolutional network for discriminative analysis of schizophrenia |
| title_fullStr | MO-GCN: A multi-omics graph convolutional network for discriminative analysis of schizophrenia |
| title_full_unstemmed | MO-GCN: A multi-omics graph convolutional network for discriminative analysis of schizophrenia |
| title_short | MO-GCN: A multi-omics graph convolutional network for discriminative analysis of schizophrenia |
| title_sort | mo gcn a multi omics graph convolutional network for discriminative analysis of schizophrenia |
| topic | Schizophrenia Multi-omics Brain network Gut network Classification Graph convolutional network |
| url | http://www.sciencedirect.com/science/article/pii/S0361923025000115 |
| work_keys_str_mv | AT haiyuanwang mogcnamultiomicsgraphconvolutionalnetworkfordiscriminativeanalysisofschizophrenia AT runlinpeng mogcnamultiomicsgraphconvolutionalnetworkfordiscriminativeanalysisofschizophrenia AT yuanyuanhuang mogcnamultiomicsgraphconvolutionalnetworkfordiscriminativeanalysisofschizophrenia AT liqinliang mogcnamultiomicsgraphconvolutionalnetworkfordiscriminativeanalysisofschizophrenia AT weiwang mogcnamultiomicsgraphconvolutionalnetworkfordiscriminativeanalysisofschizophrenia AT baoyuanzhu mogcnamultiomicsgraphconvolutionalnetworkfordiscriminativeanalysisofschizophrenia AT chenyanggao mogcnamultiomicsgraphconvolutionalnetworkfordiscriminativeanalysisofschizophrenia AT minxinguo mogcnamultiomicsgraphconvolutionalnetworkfordiscriminativeanalysisofschizophrenia AT jingzhou mogcnamultiomicsgraphconvolutionalnetworkfordiscriminativeanalysisofschizophrenia AT hehuali mogcnamultiomicsgraphconvolutionalnetworkfordiscriminativeanalysisofschizophrenia AT xiaoboli mogcnamultiomicsgraphconvolutionalnetworkfordiscriminativeanalysisofschizophrenia AT yupingning mogcnamultiomicsgraphconvolutionalnetworkfordiscriminativeanalysisofschizophrenia AT fengchunwu mogcnamultiomicsgraphconvolutionalnetworkfordiscriminativeanalysisofschizophrenia AT kaiwu mogcnamultiomicsgraphconvolutionalnetworkfordiscriminativeanalysisofschizophrenia |