Development and pan-cancer validation of an epigenetics-based random survival forest model for prognosis prediction and drug response in OS
BackgroundOsteosarcoma (OS) exhibits significant epigenetic heterogeneity, yet its systematic characterization and clinical implications remain largely unexplored.MethodsWe analyzed single-cell transcriptomes of five primary OS samples, identifying cell type-specific epigenetic features and their ev...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Pharmacology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphar.2025.1529525/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589786351665152 |
|---|---|
| author | Chaoyi Yin Kede Chi Zhiqing Chen Shabin Zhuang Yongsheng Ye Binshan Zhang Cailiang Cai |
| author_facet | Chaoyi Yin Kede Chi Zhiqing Chen Shabin Zhuang Yongsheng Ye Binshan Zhang Cailiang Cai |
| author_sort | Chaoyi Yin |
| collection | DOAJ |
| description | BackgroundOsteosarcoma (OS) exhibits significant epigenetic heterogeneity, yet its systematic characterization and clinical implications remain largely unexplored.MethodsWe analyzed single-cell transcriptomes of five primary OS samples, identifying cell type-specific epigenetic features and their evolutionary trajectories. An epigenetics-based Random Survival Forest (RSF) model was constructed using 801 curated epigenetic factors and validated in multiple independent cohorts.ResultsOur analysis revealed distinct epigenetic states in the OS microenvironment, with particular activity in OS cells and osteoclasts. The RSF model identified key predictive genes including OLFML2B, ACTB, and C1QB, and demonstrated broad applicability across multiple cancer types. Risk stratification analysis revealed distinct therapeutic response patterns, with low-risk groups showing enhanced sensitivity to traditional chemotherapy drugs while high-risk groups responded better to targeted therapies.ConclusionOur epigenetics-based model demonstrates excellent prognostic accuracy (AUC>0.997 in internal validation, 0.832–0.929 in external cohorts) and provides a practical tool for treatment stratification. These findings establish a clinically applicable framework for personalized therapy selection in OS patients. |
| format | Article |
| id | doaj-art-a714443330ab489ab00ea8e545fb8c28 |
| institution | Kabale University |
| issn | 1663-9812 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Pharmacology |
| spelling | doaj-art-a714443330ab489ab00ea8e545fb8c282025-01-24T08:43:08ZengFrontiers Media S.A.Frontiers in Pharmacology1663-98122025-01-011610.3389/fphar.2025.15295251529525Development and pan-cancer validation of an epigenetics-based random survival forest model for prognosis prediction and drug response in OSChaoyi Yin0Kede Chi1Zhiqing Chen2Shabin Zhuang3Yongsheng Ye4Binshan Zhang5Cailiang Cai6Department of Orthopaedics, Dongguan Hospital of Guangzhou University of Chinese Medicine, Dongguan, ChinaDepartment One of Spine Surgery, Zhongshan Hospital of Traditional Chinese Medicine, Zhongshan, ChinaDepartment of Orthopaedics, Dongguan Hospital of Guangzhou University of Chinese Medicine, Dongguan, ChinaDepartment of Orthopaedics, Dongguan Hospital of Guangzhou University of Chinese Medicine, Dongguan, ChinaDepartment of Orthopaedics, Dongguan Hospital of Guangzhou University of Chinese Medicine, Dongguan, ChinaDepartment of Orthopaedics, Dongguan Hospital of Guangzhou University of Chinese Medicine, Dongguan, ChinaDepartment of Orthopaedics, Dongguan Hospital of Guangzhou University of Chinese Medicine, Dongguan, ChinaBackgroundOsteosarcoma (OS) exhibits significant epigenetic heterogeneity, yet its systematic characterization and clinical implications remain largely unexplored.MethodsWe analyzed single-cell transcriptomes of five primary OS samples, identifying cell type-specific epigenetic features and their evolutionary trajectories. An epigenetics-based Random Survival Forest (RSF) model was constructed using 801 curated epigenetic factors and validated in multiple independent cohorts.ResultsOur analysis revealed distinct epigenetic states in the OS microenvironment, with particular activity in OS cells and osteoclasts. The RSF model identified key predictive genes including OLFML2B, ACTB, and C1QB, and demonstrated broad applicability across multiple cancer types. Risk stratification analysis revealed distinct therapeutic response patterns, with low-risk groups showing enhanced sensitivity to traditional chemotherapy drugs while high-risk groups responded better to targeted therapies.ConclusionOur epigenetics-based model demonstrates excellent prognostic accuracy (AUC>0.997 in internal validation, 0.832–0.929 in external cohorts) and provides a practical tool for treatment stratification. These findings establish a clinically applicable framework for personalized therapy selection in OS patients.https://www.frontiersin.org/articles/10.3389/fphar.2025.1529525/fullosteosarcomaepigenetic heterogeneitysingle-cell RNA sequencingrandom survival forestprognostic modeldrug sensitivity |
| spellingShingle | Chaoyi Yin Kede Chi Zhiqing Chen Shabin Zhuang Yongsheng Ye Binshan Zhang Cailiang Cai Development and pan-cancer validation of an epigenetics-based random survival forest model for prognosis prediction and drug response in OS Frontiers in Pharmacology osteosarcoma epigenetic heterogeneity single-cell RNA sequencing random survival forest prognostic model drug sensitivity |
| title | Development and pan-cancer validation of an epigenetics-based random survival forest model for prognosis prediction and drug response in OS |
| title_full | Development and pan-cancer validation of an epigenetics-based random survival forest model for prognosis prediction and drug response in OS |
| title_fullStr | Development and pan-cancer validation of an epigenetics-based random survival forest model for prognosis prediction and drug response in OS |
| title_full_unstemmed | Development and pan-cancer validation of an epigenetics-based random survival forest model for prognosis prediction and drug response in OS |
| title_short | Development and pan-cancer validation of an epigenetics-based random survival forest model for prognosis prediction and drug response in OS |
| title_sort | development and pan cancer validation of an epigenetics based random survival forest model for prognosis prediction and drug response in os |
| topic | osteosarcoma epigenetic heterogeneity single-cell RNA sequencing random survival forest prognostic model drug sensitivity |
| url | https://www.frontiersin.org/articles/10.3389/fphar.2025.1529525/full |
| work_keys_str_mv | AT chaoyiyin developmentandpancancervalidationofanepigeneticsbasedrandomsurvivalforestmodelforprognosispredictionanddrugresponseinos AT kedechi developmentandpancancervalidationofanepigeneticsbasedrandomsurvivalforestmodelforprognosispredictionanddrugresponseinos AT zhiqingchen developmentandpancancervalidationofanepigeneticsbasedrandomsurvivalforestmodelforprognosispredictionanddrugresponseinos AT shabinzhuang developmentandpancancervalidationofanepigeneticsbasedrandomsurvivalforestmodelforprognosispredictionanddrugresponseinos AT yongshengye developmentandpancancervalidationofanepigeneticsbasedrandomsurvivalforestmodelforprognosispredictionanddrugresponseinos AT binshanzhang developmentandpancancervalidationofanepigeneticsbasedrandomsurvivalforestmodelforprognosispredictionanddrugresponseinos AT cailiangcai developmentandpancancervalidationofanepigeneticsbasedrandomsurvivalforestmodelforprognosispredictionanddrugresponseinos |