An Integrated Deep Network for Cancer Survival Prediction Using Omics Data
As a highly sophisticated disease that humanity faces, cancer is known to be associated with dysregulation of cellular mechanisms in different levels, which demands novel paradigms to capture informative features from different omics modalities in an integrated way. Successful stratification of pati...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-07-01
|
| Series: | Frontiers in Big Data |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fdata.2021.568352/full |
| _version_ | 1818624085486206976 |
|---|---|
| author | Hamid Reza Hassanzadeh May D. Wang |
| author_facet | Hamid Reza Hassanzadeh May D. Wang |
| author_sort | Hamid Reza Hassanzadeh |
| collection | DOAJ |
| description | As a highly sophisticated disease that humanity faces, cancer is known to be associated with dysregulation of cellular mechanisms in different levels, which demands novel paradigms to capture informative features from different omics modalities in an integrated way. Successful stratification of patients with respect to their molecular profiles is a key step in precision medicine and in tailoring personalized treatment for critically ill patients. In this article, we use an integrated deep belief network to differentiate high-risk cancer patients from the low-risk ones in terms of the overall survival. Our study analyzes RNA, miRNA, and methylation molecular data modalities from both labeled and unlabeled samples to predict cancer survival and subsequently to provide risk stratification. To assess the robustness of our novel integrative analytics, we utilize datasets of three cancer types with 836 patients and show that our approach outperforms the most successful supervised and semi-supervised classification techniques applied to the same cancer prediction problems. In addition, despite the preconception that deep learning techniques require large size datasets for proper training, we have illustrated that our model can achieve better results for moderately sized cancer datasets. |
| first_indexed | 2024-12-16T18:51:21Z |
| format | Article |
| id | doaj.art-e93b7474c90e457fbcb2319436fa3b12 |
| institution | Directory Open Access Journal |
| issn | 2624-909X |
| language | English |
| last_indexed | 2024-12-16T18:51:21Z |
| publishDate | 2021-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Big Data |
| spelling | doaj.art-e93b7474c90e457fbcb2319436fa3b122022-12-21T22:20:42ZengFrontiers Media S.A.Frontiers in Big Data2624-909X2021-07-01410.3389/fdata.2021.568352568352An Integrated Deep Network for Cancer Survival Prediction Using Omics DataHamid Reza Hassanzadeh0May D. Wang1School of Interactive Computing, Georgia Institute of Technology, Atlanta, GA, United StatesDepartment of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA, United StatesAs a highly sophisticated disease that humanity faces, cancer is known to be associated with dysregulation of cellular mechanisms in different levels, which demands novel paradigms to capture informative features from different omics modalities in an integrated way. Successful stratification of patients with respect to their molecular profiles is a key step in precision medicine and in tailoring personalized treatment for critically ill patients. In this article, we use an integrated deep belief network to differentiate high-risk cancer patients from the low-risk ones in terms of the overall survival. Our study analyzes RNA, miRNA, and methylation molecular data modalities from both labeled and unlabeled samples to predict cancer survival and subsequently to provide risk stratification. To assess the robustness of our novel integrative analytics, we utilize datasets of three cancer types with 836 patients and show that our approach outperforms the most successful supervised and semi-supervised classification techniques applied to the same cancer prediction problems. In addition, despite the preconception that deep learning techniques require large size datasets for proper training, we have illustrated that our model can achieve better results for moderately sized cancer datasets.https://www.frontiersin.org/articles/10.3389/fdata.2021.568352/fulldeep belief networksintegrated cancer survival analysisRNA-seqprecision medicinedeep learningmulti-omics |
| spellingShingle | Hamid Reza Hassanzadeh May D. Wang An Integrated Deep Network for Cancer Survival Prediction Using Omics Data Frontiers in Big Data deep belief networks integrated cancer survival analysis RNA-seq precision medicine deep learning multi-omics |
| title | An Integrated Deep Network for Cancer Survival Prediction Using Omics Data |
| title_full | An Integrated Deep Network for Cancer Survival Prediction Using Omics Data |
| title_fullStr | An Integrated Deep Network for Cancer Survival Prediction Using Omics Data |
| title_full_unstemmed | An Integrated Deep Network for Cancer Survival Prediction Using Omics Data |
| title_short | An Integrated Deep Network for Cancer Survival Prediction Using Omics Data |
| title_sort | integrated deep network for cancer survival prediction using omics data |
| topic | deep belief networks integrated cancer survival analysis RNA-seq precision medicine deep learning multi-omics |
| url | https://www.frontiersin.org/articles/10.3389/fdata.2021.568352/full |
| work_keys_str_mv | AT hamidrezahassanzadeh anintegrateddeepnetworkforcancersurvivalpredictionusingomicsdata AT maydwang anintegrateddeepnetworkforcancersurvivalpredictionusingomicsdata AT hamidrezahassanzadeh integrateddeepnetworkforcancersurvivalpredictionusingomicsdata AT maydwang integrateddeepnetworkforcancersurvivalpredictionusingomicsdata |