Deep learning algorithm reveals two prognostic subtypes in patients with gliomas
Abstract Background Gliomas are highly complex and heterogeneous tumors, rendering prognosis prediction challenging. The advent of deep learning algorithms and the accessibility of multi-omic data represent a new approach for the identification of survival-sensitive subtypes. Herein, an autoencoder-...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-10-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12859-022-04970-x |
| _version_ | 1828343035810807808 |
|---|---|
| author | Jing Tian Mingzhen Zhu Zijing Ren Qiang Zhao Puqing Wang Colin K. He Min Zhang Xiaochun Peng Beilei Wu Rujia Feng Minglong Fu |
| author_facet | Jing Tian Mingzhen Zhu Zijing Ren Qiang Zhao Puqing Wang Colin K. He Min Zhang Xiaochun Peng Beilei Wu Rujia Feng Minglong Fu |
| author_sort | Jing Tian |
| collection | DOAJ |
| description | Abstract Background Gliomas are highly complex and heterogeneous tumors, rendering prognosis prediction challenging. The advent of deep learning algorithms and the accessibility of multi-omic data represent a new approach for the identification of survival-sensitive subtypes. Herein, an autoencoder-based approach was used to identify two survival-sensitive subtypes using RNA sequencing (RNA-seq) and DNA methylation (DNAm) data from The Cancer Genome Atlas (TCGA) dataset. The subtypes were used as labels to build a support vector machine model with cross-validation. We validated the robustness of the model on Chinese Glioma Genome Atlas (CGGA) dataset. DNAm-driven genes were identified by integrating DNAm and gene expression profiling analyses using the R MethylMix package and carried out for further enrichment analysis. Results For TCGA dataset, the model produced a high C-index (0.92 ± 0.02), low brier score (0.16 ± 0.02), and significant log-rank p value (p < 0.0001). The model also had a decent performance for CGGA dataset (CGGA DNAm: C-index of 0.70, brier score of 0.21; CGGA RNA-seq: C-index of 0.79, brier score of 0.18). Moreover, we identified 389 DNAm-driven genes of survival-sensitive subtypes, which were significantly enriched in the glutathione metabolism pathway. Conclusions Our study identified two survival-sensitive subtypes of glioma and provided insights into the molecular mechanisms underlying glioma development; thus, potentially providing a new target for the prognostic prediction of gliomas and supporting personalized treatment strategies. |
| first_indexed | 2024-04-13T23:36:58Z |
| format | Article |
| id | doaj.art-49b23ee70f074fb9a1665e8d14c8887a |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-04-13T23:36:58Z |
| publishDate | 2022-10-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-49b23ee70f074fb9a1665e8d14c8887a2022-12-22T02:24:40ZengBMCBMC Bioinformatics1471-21052022-10-0123111010.1186/s12859-022-04970-xDeep learning algorithm reveals two prognostic subtypes in patients with gliomasJing Tian0Mingzhen Zhu1Zijing Ren2Qiang Zhao3Puqing Wang4Colin K. He5Min Zhang6Xiaochun Peng7Beilei Wu8Rujia Feng9Minglong Fu10Hubei Clinical Research Center of Parkinson’s Disease, Xiangyang Key Laboratory of Movement Disorders, Xiangyang No.1 People’s Hospital, Hubei University of MedicineHubei Clinical Research Center of Parkinson’s Disease, Xiangyang Key Laboratory of Movement Disorders, Xiangyang No.1 People’s Hospital, Hubei University of MedicineHubei Clinical Research Center of Parkinson’s Disease, Xiangyang Key Laboratory of Movement Disorders, Xiangyang No.1 People’s Hospital, Hubei University of MedicineHubei Clinical Research Center of Parkinson’s Disease, Xiangyang Key Laboratory of Movement Disorders, Xiangyang No.1 People’s Hospital, Hubei University of MedicineHubei Clinical Research Center of Parkinson’s Disease, Xiangyang Key Laboratory of Movement Disorders, Xiangyang No.1 People’s Hospital, Hubei University of MedicineData Science and Statistics, Stego Tech LLCHubei Clinical Research Center of Parkinson’s Disease, Xiangyang Key Laboratory of Movement Disorders, Xiangyang No.1 People’s Hospital, Hubei University of MedicineHubei Clinical Research Center of Parkinson’s Disease, Xiangyang Key Laboratory of Movement Disorders, Xiangyang No.1 People’s Hospital, Hubei University of MedicineHubei Clinical Research Center of Parkinson’s Disease, Xiangyang Key Laboratory of Movement Disorders, Xiangyang No.1 People’s Hospital, Hubei University of MedicineHubei Clinical Research Center of Parkinson’s Disease, Xiangyang Key Laboratory of Movement Disorders, Xiangyang No.1 People’s Hospital, Hubei University of MedicineHubei Clinical Research Center of Parkinson’s Disease, Xiangyang Key Laboratory of Movement Disorders, Xiangyang No.1 People’s Hospital, Hubei University of MedicineAbstract Background Gliomas are highly complex and heterogeneous tumors, rendering prognosis prediction challenging. The advent of deep learning algorithms and the accessibility of multi-omic data represent a new approach for the identification of survival-sensitive subtypes. Herein, an autoencoder-based approach was used to identify two survival-sensitive subtypes using RNA sequencing (RNA-seq) and DNA methylation (DNAm) data from The Cancer Genome Atlas (TCGA) dataset. The subtypes were used as labels to build a support vector machine model with cross-validation. We validated the robustness of the model on Chinese Glioma Genome Atlas (CGGA) dataset. DNAm-driven genes were identified by integrating DNAm and gene expression profiling analyses using the R MethylMix package and carried out for further enrichment analysis. Results For TCGA dataset, the model produced a high C-index (0.92 ± 0.02), low brier score (0.16 ± 0.02), and significant log-rank p value (p < 0.0001). The model also had a decent performance for CGGA dataset (CGGA DNAm: C-index of 0.70, brier score of 0.21; CGGA RNA-seq: C-index of 0.79, brier score of 0.18). Moreover, we identified 389 DNAm-driven genes of survival-sensitive subtypes, which were significantly enriched in the glutathione metabolism pathway. Conclusions Our study identified two survival-sensitive subtypes of glioma and provided insights into the molecular mechanisms underlying glioma development; thus, potentially providing a new target for the prognostic prediction of gliomas and supporting personalized treatment strategies.https://doi.org/10.1186/s12859-022-04970-xAutoencoder-based approachSupport vector machineSurvival-sensitive subtypesMulti-omics dataGlutathione metabolism pathway |
| spellingShingle | Jing Tian Mingzhen Zhu Zijing Ren Qiang Zhao Puqing Wang Colin K. He Min Zhang Xiaochun Peng Beilei Wu Rujia Feng Minglong Fu Deep learning algorithm reveals two prognostic subtypes in patients with gliomas BMC Bioinformatics Autoencoder-based approach Support vector machine Survival-sensitive subtypes Multi-omics data Glutathione metabolism pathway |
| title | Deep learning algorithm reveals two prognostic subtypes in patients with gliomas |
| title_full | Deep learning algorithm reveals two prognostic subtypes in patients with gliomas |
| title_fullStr | Deep learning algorithm reveals two prognostic subtypes in patients with gliomas |
| title_full_unstemmed | Deep learning algorithm reveals two prognostic subtypes in patients with gliomas |
| title_short | Deep learning algorithm reveals two prognostic subtypes in patients with gliomas |
| title_sort | deep learning algorithm reveals two prognostic subtypes in patients with gliomas |
| topic | Autoencoder-based approach Support vector machine Survival-sensitive subtypes Multi-omics data Glutathione metabolism pathway |
| url | https://doi.org/10.1186/s12859-022-04970-x |
| work_keys_str_mv | AT jingtian deeplearningalgorithmrevealstwoprognosticsubtypesinpatientswithgliomas AT mingzhenzhu deeplearningalgorithmrevealstwoprognosticsubtypesinpatientswithgliomas AT zijingren deeplearningalgorithmrevealstwoprognosticsubtypesinpatientswithgliomas AT qiangzhao deeplearningalgorithmrevealstwoprognosticsubtypesinpatientswithgliomas AT puqingwang deeplearningalgorithmrevealstwoprognosticsubtypesinpatientswithgliomas AT colinkhe deeplearningalgorithmrevealstwoprognosticsubtypesinpatientswithgliomas AT minzhang deeplearningalgorithmrevealstwoprognosticsubtypesinpatientswithgliomas AT xiaochunpeng deeplearningalgorithmrevealstwoprognosticsubtypesinpatientswithgliomas AT beileiwu deeplearningalgorithmrevealstwoprognosticsubtypesinpatientswithgliomas AT rujiafeng deeplearningalgorithmrevealstwoprognosticsubtypesinpatientswithgliomas AT minglongfu deeplearningalgorithmrevealstwoprognosticsubtypesinpatientswithgliomas |