Cancer molecular subtyping using limited multi-omics data with missingness.
Diagnosing cancer subtypes is a prerequisite for precise treatment. Existing multi-omics data fusion-based diagnostic solutions build on the requisite of sufficient samples with complete multi-omics data, which is challenging to obtain in clinical applications. To address the bottleneck of collectin...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2024-12-01
|
| Series: | PLoS Computational Biology |
| Online Access: | https://doi.org/10.1371/journal.pcbi.1012710 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841533259858575360 |
|---|---|
| author | Yongqi Bu Jiaxuan Liang Zhen Li Jianbo Wang Jun Wang Guoxian Yu |
| author_facet | Yongqi Bu Jiaxuan Liang Zhen Li Jianbo Wang Jun Wang Guoxian Yu |
| author_sort | Yongqi Bu |
| collection | DOAJ |
| description | Diagnosing cancer subtypes is a prerequisite for precise treatment. Existing multi-omics data fusion-based diagnostic solutions build on the requisite of sufficient samples with complete multi-omics data, which is challenging to obtain in clinical applications. To address the bottleneck of collecting sufficient samples with complete data in clinical applications, we proposed a flexible integrative model (CancerSD) to diagnose cancer subtype using limited samples with incomplete multi-omics data. CancerSD designs contrastive learning tasks and masking-and-reconstruction tasks to reliably impute missing omics, and fuses available omics data with the imputed ones to accurately diagnose cancer subtypes. To address the issue of limited clinical samples, it introduces a category-level contrastive loss to extend the meta-learning framework, effectively transferring knowledge from external datasets to pretrain the diagnostic model. Experiments on benchmark datasets show that CancerSD not only gives accurate diagnosis, but also maintains a high authenticity and good interpretability. In addition, CancerSD identifies important molecular characteristics associated with cancer subtypes, and it defines the Integrated CancerSD Score that can serve as an independent predictive factor for patient prognosis. |
| format | Article |
| id | doaj-art-bbd786cca9484892ae2db8d7603b5bf2 |
| institution | Kabale University |
| issn | 1553-734X 1553-7358 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS Computational Biology |
| spelling | doaj-art-bbd786cca9484892ae2db8d7603b5bf22025-01-17T05:30:55ZengPublic Library of Science (PLoS)PLoS Computational Biology1553-734X1553-73582024-12-012012e101271010.1371/journal.pcbi.1012710Cancer molecular subtyping using limited multi-omics data with missingness.Yongqi BuJiaxuan LiangZhen LiJianbo WangJun WangGuoxian YuDiagnosing cancer subtypes is a prerequisite for precise treatment. Existing multi-omics data fusion-based diagnostic solutions build on the requisite of sufficient samples with complete multi-omics data, which is challenging to obtain in clinical applications. To address the bottleneck of collecting sufficient samples with complete data in clinical applications, we proposed a flexible integrative model (CancerSD) to diagnose cancer subtype using limited samples with incomplete multi-omics data. CancerSD designs contrastive learning tasks and masking-and-reconstruction tasks to reliably impute missing omics, and fuses available omics data with the imputed ones to accurately diagnose cancer subtypes. To address the issue of limited clinical samples, it introduces a category-level contrastive loss to extend the meta-learning framework, effectively transferring knowledge from external datasets to pretrain the diagnostic model. Experiments on benchmark datasets show that CancerSD not only gives accurate diagnosis, but also maintains a high authenticity and good interpretability. In addition, CancerSD identifies important molecular characteristics associated with cancer subtypes, and it defines the Integrated CancerSD Score that can serve as an independent predictive factor for patient prognosis.https://doi.org/10.1371/journal.pcbi.1012710 |
| spellingShingle | Yongqi Bu Jiaxuan Liang Zhen Li Jianbo Wang Jun Wang Guoxian Yu Cancer molecular subtyping using limited multi-omics data with missingness. PLoS Computational Biology |
| title | Cancer molecular subtyping using limited multi-omics data with missingness. |
| title_full | Cancer molecular subtyping using limited multi-omics data with missingness. |
| title_fullStr | Cancer molecular subtyping using limited multi-omics data with missingness. |
| title_full_unstemmed | Cancer molecular subtyping using limited multi-omics data with missingness. |
| title_short | Cancer molecular subtyping using limited multi-omics data with missingness. |
| title_sort | cancer molecular subtyping using limited multi omics data with missingness |
| url | https://doi.org/10.1371/journal.pcbi.1012710 |
| work_keys_str_mv | AT yongqibu cancermolecularsubtypingusinglimitedmultiomicsdatawithmissingness AT jiaxuanliang cancermolecularsubtypingusinglimitedmultiomicsdatawithmissingness AT zhenli cancermolecularsubtypingusinglimitedmultiomicsdatawithmissingness AT jianbowang cancermolecularsubtypingusinglimitedmultiomicsdatawithmissingness AT junwang cancermolecularsubtypingusinglimitedmultiomicsdatawithmissingness AT guoxianyu cancermolecularsubtypingusinglimitedmultiomicsdatawithmissingness |