A risk prediction model of gene signatures in ovarian cancer through bagging of GA-XGBoost models
Introduction: Ovarian cancer (OC) is one of the most frequent gynecologic cancers among women, and high-accuracy risk prediction techniques are essential to effectively select the best intervention strategies and clinical management for OC patients at different risk levels. Current risk prediction m...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-05-01
|
| Series: | Journal of Advanced Research |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2090123220302320 |
| _version_ | 1819067572633468928 |
|---|---|
| author | Yi-Wen Hsiao Chun-Liang Tao Eric Y. Chuang Tzu-Pin Lu |
| author_facet | Yi-Wen Hsiao Chun-Liang Tao Eric Y. Chuang Tzu-Pin Lu |
| author_sort | Yi-Wen Hsiao |
| collection | DOAJ |
| description | Introduction: Ovarian cancer (OC) is one of the most frequent gynecologic cancers among women, and high-accuracy risk prediction techniques are essential to effectively select the best intervention strategies and clinical management for OC patients at different risk levels. Current risk prediction models used in OC have low sensitivity, and few of them are able to identify OC patients at high risk of mortality, which would both optimize the treatment of high-risk patients and prevent unnecessary medical intervention in those at low risk. Objectives: To this end, we have developed a bagging-based algorithm with GA-XGBoost models that predicts the risk of death from OC using gene expression profiles. Methods: Four gene expression datasets from public sources were used as training (n = 1) or validation (n = 3) sets. The performance of our proposed algorithm was compared with fine-tuning and other existing methods. Moreover, the biological function of selected genetic features was further interpreted, and the response to a panel of approved drugs was predicted for different risk levels. Results: The proposed algorithm showed good sensitivity (74–100%) in the validation sets, compared with two simple models whose sensitivity only reached 47% and 60%. The prognostic gene signature used in this study was highly connected to AKT, a key component of the PI3K/AKT/mTOR signaling pathway, which influences the tumorigenesis, proliferation, and progression of OC. Conclusion: These findings demonstrated an improvement in the sensitivity of risk classification of OC patients with our risk prediction models compared with other methods. Ongoing effort is needed to validate the outcomes of this approach for precise clinical treatment. |
| first_indexed | 2024-12-21T16:20:23Z |
| format | Article |
| id | doaj.art-aa749b211af64a999c62ba00e32f3e6e |
| institution | Directory Open Access Journal |
| issn | 2090-1232 |
| language | English |
| last_indexed | 2024-12-21T16:20:23Z |
| publishDate | 2021-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Advanced Research |
| spelling | doaj.art-aa749b211af64a999c62ba00e32f3e6e2022-12-21T18:57:36ZengElsevierJournal of Advanced Research2090-12322021-05-0130113122A risk prediction model of gene signatures in ovarian cancer through bagging of GA-XGBoost modelsYi-Wen Hsiao0Chun-Liang Tao1Eric Y. Chuang2Tzu-Pin Lu3Department of Public Health, Institute of Epidemiology and Preventive Medicine, College of Public Health, National Taiwan University, Taipei, TaiwanDepartment of Public Health, Institute of Epidemiology and Preventive Medicine, College of Public Health, National Taiwan University, Taipei, TaiwanBioinformatics and Biostatistics Core, Center of Genomic and Precision Medicine, National Taiwan University, Taipei, Taiwan; Graduate Institute of Biomedical Electronics and Bioinformatics, Department of Electrical Engineering, National Taiwan University, TaiwanDepartment of Public Health, Institute of Epidemiology and Preventive Medicine, College of Public Health, National Taiwan University, Taipei, Taiwan; Bioinformatics and Biostatistics Core, Center of Genomic and Precision Medicine, National Taiwan University, Taipei, Taiwan; Corresponding author at: Department of Public Health, Institute of Epidemiology and Preventive Medicine, College of Public Health, National Taiwan University, Taipei, Taiwan.Introduction: Ovarian cancer (OC) is one of the most frequent gynecologic cancers among women, and high-accuracy risk prediction techniques are essential to effectively select the best intervention strategies and clinical management for OC patients at different risk levels. Current risk prediction models used in OC have low sensitivity, and few of them are able to identify OC patients at high risk of mortality, which would both optimize the treatment of high-risk patients and prevent unnecessary medical intervention in those at low risk. Objectives: To this end, we have developed a bagging-based algorithm with GA-XGBoost models that predicts the risk of death from OC using gene expression profiles. Methods: Four gene expression datasets from public sources were used as training (n = 1) or validation (n = 3) sets. The performance of our proposed algorithm was compared with fine-tuning and other existing methods. Moreover, the biological function of selected genetic features was further interpreted, and the response to a panel of approved drugs was predicted for different risk levels. Results: The proposed algorithm showed good sensitivity (74–100%) in the validation sets, compared with two simple models whose sensitivity only reached 47% and 60%. The prognostic gene signature used in this study was highly connected to AKT, a key component of the PI3K/AKT/mTOR signaling pathway, which influences the tumorigenesis, proliferation, and progression of OC. Conclusion: These findings demonstrated an improvement in the sensitivity of risk classification of OC patients with our risk prediction models compared with other methods. Ongoing effort is needed to validate the outcomes of this approach for precise clinical treatment.http://www.sciencedirect.com/science/article/pii/S2090123220302320Ovarian cancerRisk predictionGene expressionMachine learningGA-XGBoostBagging algorithm |
| spellingShingle | Yi-Wen Hsiao Chun-Liang Tao Eric Y. Chuang Tzu-Pin Lu A risk prediction model of gene signatures in ovarian cancer through bagging of GA-XGBoost models Journal of Advanced Research Ovarian cancer Risk prediction Gene expression Machine learning GA-XGBoost Bagging algorithm |
| title | A risk prediction model of gene signatures in ovarian cancer through bagging of GA-XGBoost models |
| title_full | A risk prediction model of gene signatures in ovarian cancer through bagging of GA-XGBoost models |
| title_fullStr | A risk prediction model of gene signatures in ovarian cancer through bagging of GA-XGBoost models |
| title_full_unstemmed | A risk prediction model of gene signatures in ovarian cancer through bagging of GA-XGBoost models |
| title_short | A risk prediction model of gene signatures in ovarian cancer through bagging of GA-XGBoost models |
| title_sort | risk prediction model of gene signatures in ovarian cancer through bagging of ga xgboost models |
| topic | Ovarian cancer Risk prediction Gene expression Machine learning GA-XGBoost Bagging algorithm |
| url | http://www.sciencedirect.com/science/article/pii/S2090123220302320 |
| work_keys_str_mv | AT yiwenhsiao ariskpredictionmodelofgenesignaturesinovariancancerthroughbaggingofgaxgboostmodels AT chunliangtao ariskpredictionmodelofgenesignaturesinovariancancerthroughbaggingofgaxgboostmodels AT ericychuang ariskpredictionmodelofgenesignaturesinovariancancerthroughbaggingofgaxgboostmodels AT tzupinlu ariskpredictionmodelofgenesignaturesinovariancancerthroughbaggingofgaxgboostmodels AT yiwenhsiao riskpredictionmodelofgenesignaturesinovariancancerthroughbaggingofgaxgboostmodels AT chunliangtao riskpredictionmodelofgenesignaturesinovariancancerthroughbaggingofgaxgboostmodels AT ericychuang riskpredictionmodelofgenesignaturesinovariancancerthroughbaggingofgaxgboostmodels AT tzupinlu riskpredictionmodelofgenesignaturesinovariancancerthroughbaggingofgaxgboostmodels |