MV-CVIB: a microbiome-based multi-view convolutional variational information bottleneck for predicting metastatic colorectal cancer
IntroductionImbalances in gut microbes have been implied in many human diseases, including colorectal cancer (CRC), inflammatory bowel disease, type 2 diabetes, obesity, autism, and Alzheimer's disease. Compared with other human diseases, CRC is a gastrointestinal malignancy with high mortality...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-08-01
|
| Series: | Frontiers in Microbiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmicb.2023.1238199/full |
| _version_ | 1797739493024858112 |
|---|---|
| author | Zhen Cui Yan Wu Qin-Hu Zhang Si-Guo Wang Ying He De-Shuang Huang |
| author_facet | Zhen Cui Yan Wu Qin-Hu Zhang Si-Guo Wang Ying He De-Shuang Huang |
| author_sort | Zhen Cui |
| collection | DOAJ |
| description | IntroductionImbalances in gut microbes have been implied in many human diseases, including colorectal cancer (CRC), inflammatory bowel disease, type 2 diabetes, obesity, autism, and Alzheimer's disease. Compared with other human diseases, CRC is a gastrointestinal malignancy with high mortality and a high probability of metastasis. However, current studies mainly focus on the prediction of colorectal cancer while neglecting the more serious malignancy of metastatic colorectal cancer (mCRC). In addition, high dimensionality and small samples lead to the complexity of gut microbial data, which increases the difficulty of traditional machine learning models.MethodsTo address these challenges, we collected and processed 16S rRNA data and calculated abundance data from patients with non-metastatic colorectal cancer (non-mCRC) and mCRC. Different from the traditional health-disease classification strategy, we adopted a novel disease-disease classification strategy and proposed a microbiome-based multi-view convolutional variational information bottleneck (MV-CVIB).ResultsThe experimental results show that MV-CVIB can effectively predict mCRC. This model can achieve AUC values above 0.9 compared to other state-of-the-art models. Not only that, MV-CVIB also achieved satisfactory predictive performance on multiple published CRC gut microbiome datasets.DiscussionFinally, multiple gut microbiota analyses were used to elucidate communities and differences between mCRC and non-mCRC, and the metastatic properties of CRC were assessed by patient age and microbiota expression. |
| first_indexed | 2024-03-12T13:58:54Z |
| format | Article |
| id | doaj.art-8ae09ff267174b02bdeea33a9f49df4e |
| institution | Directory Open Access Journal |
| issn | 1664-302X |
| language | English |
| last_indexed | 2024-03-12T13:58:54Z |
| publishDate | 2023-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Microbiology |
| spelling | doaj.art-8ae09ff267174b02bdeea33a9f49df4e2023-08-22T09:37:09ZengFrontiers Media S.A.Frontiers in Microbiology1664-302X2023-08-011410.3389/fmicb.2023.12381991238199MV-CVIB: a microbiome-based multi-view convolutional variational information bottleneck for predicting metastatic colorectal cancerZhen Cui0Yan Wu1Qin-Hu Zhang2Si-Guo Wang3Ying He4De-Shuang Huang5Institute of Machine Learning and Systems Biology, College of Electronics and Information Engineering, Tongji University, Shanghai, ChinaCollege of Electronics and Information Engineering, Tongji University, Shanghai, ChinaEIT Institute for Advanced Study, Ningbo, Zhejiang, ChinaInstitute of Machine Learning and Systems Biology, College of Electronics and Information Engineering, Tongji University, Shanghai, ChinaInstitute of Machine Learning and Systems Biology, College of Electronics and Information Engineering, Tongji University, Shanghai, ChinaEIT Institute for Advanced Study, Ningbo, Zhejiang, ChinaIntroductionImbalances in gut microbes have been implied in many human diseases, including colorectal cancer (CRC), inflammatory bowel disease, type 2 diabetes, obesity, autism, and Alzheimer's disease. Compared with other human diseases, CRC is a gastrointestinal malignancy with high mortality and a high probability of metastasis. However, current studies mainly focus on the prediction of colorectal cancer while neglecting the more serious malignancy of metastatic colorectal cancer (mCRC). In addition, high dimensionality and small samples lead to the complexity of gut microbial data, which increases the difficulty of traditional machine learning models.MethodsTo address these challenges, we collected and processed 16S rRNA data and calculated abundance data from patients with non-metastatic colorectal cancer (non-mCRC) and mCRC. Different from the traditional health-disease classification strategy, we adopted a novel disease-disease classification strategy and proposed a microbiome-based multi-view convolutional variational information bottleneck (MV-CVIB).ResultsThe experimental results show that MV-CVIB can effectively predict mCRC. This model can achieve AUC values above 0.9 compared to other state-of-the-art models. Not only that, MV-CVIB also achieved satisfactory predictive performance on multiple published CRC gut microbiome datasets.DiscussionFinally, multiple gut microbiota analyses were used to elucidate communities and differences between mCRC and non-mCRC, and the metastatic properties of CRC were assessed by patient age and microbiota expression.https://www.frontiersin.org/articles/10.3389/fmicb.2023.1238199/fullmicrobiomemulti-viewinformation bottleneckmetastatic colorectal cancerrisk assessment |
| spellingShingle | Zhen Cui Yan Wu Qin-Hu Zhang Si-Guo Wang Ying He De-Shuang Huang MV-CVIB: a microbiome-based multi-view convolutional variational information bottleneck for predicting metastatic colorectal cancer Frontiers in Microbiology microbiome multi-view information bottleneck metastatic colorectal cancer risk assessment |
| title | MV-CVIB: a microbiome-based multi-view convolutional variational information bottleneck for predicting metastatic colorectal cancer |
| title_full | MV-CVIB: a microbiome-based multi-view convolutional variational information bottleneck for predicting metastatic colorectal cancer |
| title_fullStr | MV-CVIB: a microbiome-based multi-view convolutional variational information bottleneck for predicting metastatic colorectal cancer |
| title_full_unstemmed | MV-CVIB: a microbiome-based multi-view convolutional variational information bottleneck for predicting metastatic colorectal cancer |
| title_short | MV-CVIB: a microbiome-based multi-view convolutional variational information bottleneck for predicting metastatic colorectal cancer |
| title_sort | mv cvib a microbiome based multi view convolutional variational information bottleneck for predicting metastatic colorectal cancer |
| topic | microbiome multi-view information bottleneck metastatic colorectal cancer risk assessment |
| url | https://www.frontiersin.org/articles/10.3389/fmicb.2023.1238199/full |
| work_keys_str_mv | AT zhencui mvcvibamicrobiomebasedmultiviewconvolutionalvariationalinformationbottleneckforpredictingmetastaticcolorectalcancer AT yanwu mvcvibamicrobiomebasedmultiviewconvolutionalvariationalinformationbottleneckforpredictingmetastaticcolorectalcancer AT qinhuzhang mvcvibamicrobiomebasedmultiviewconvolutionalvariationalinformationbottleneckforpredictingmetastaticcolorectalcancer AT siguowang mvcvibamicrobiomebasedmultiviewconvolutionalvariationalinformationbottleneckforpredictingmetastaticcolorectalcancer AT yinghe mvcvibamicrobiomebasedmultiviewconvolutionalvariationalinformationbottleneckforpredictingmetastaticcolorectalcancer AT deshuanghuang mvcvibamicrobiomebasedmultiviewconvolutionalvariationalinformationbottleneckforpredictingmetastaticcolorectalcancer |