Comprehensively analysis of immunophenotyping signature in triple-negative breast cancer patients based on machine learning
Immunotherapy is a promising strategy for triple-negative breast cancer (TNBC) patients, however, the overall survival (OS) of 5-years is still not satisfactory. Hence, developing more valuable prognostic signature is urgently needed for clinical practice. This study established and verified an effe...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-06-01
|
| Series: | Frontiers in Pharmacology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphar.2023.1195864/full |
| _version_ | 1827918128187703296 |
|---|---|
| author | Lijuan Tang Zhe Zhang Jun Fan Jing Xu Jiashen Xiong Lu Tang Yan Jiang Shu Zhang Gang Zhang Wentian Luo Yan Xu |
| author_facet | Lijuan Tang Zhe Zhang Jun Fan Jing Xu Jiashen Xiong Lu Tang Yan Jiang Shu Zhang Gang Zhang Wentian Luo Yan Xu |
| author_sort | Lijuan Tang |
| collection | DOAJ |
| description | Immunotherapy is a promising strategy for triple-negative breast cancer (TNBC) patients, however, the overall survival (OS) of 5-years is still not satisfactory. Hence, developing more valuable prognostic signature is urgently needed for clinical practice. This study established and verified an effective risk model based on machine learning methods through a series of publicly available datasets. Furthermore, the correlation between risk signature and chemotherapy drug sensitivity were also performed. The findings showed that comprehensive immune typing is highly effective and accurate in assessing prognosis of TNBC patients. Analysis showed that IL18R1, BTN3A1, CD160, CD226, IL12B, GNLY and PDCD1LG2 are key genes that may affect immune typing of TNBC patients. The risk signature plays a robust ability in prognosis prediction compared with other clinicopathological features in TNBC patients. In addition, the effect of our constructed risk model on immunotherapy response was superior to TIDE results. Finally, high-risk groups were more sensitive to MR-1220, GSK2110183 and temsirolimus, indicating that risk characteristics could predict drug sensitivity in TNBC patients to a certain extent. This study proposes an immunophenotype-based risk assessment model that provides a more accurate prognostic assessment tool for patients with TNBC and also predicts new potential compounds by performing machine learning algorithms. |
| first_indexed | 2024-03-13T03:38:22Z |
| format | Article |
| id | doaj.art-550a883a1c2040ab8cefb7733a65ac3e |
| institution | Directory Open Access Journal |
| issn | 1663-9812 |
| language | English |
| last_indexed | 2024-03-13T03:38:22Z |
| publishDate | 2023-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Pharmacology |
| spelling | doaj.art-550a883a1c2040ab8cefb7733a65ac3e2023-06-23T13:16:39ZengFrontiers Media S.A.Frontiers in Pharmacology1663-98122023-06-011410.3389/fphar.2023.11958641195864Comprehensively analysis of immunophenotyping signature in triple-negative breast cancer patients based on machine learningLijuan TangZhe ZhangJun FanJing XuJiashen XiongLu TangYan JiangShu ZhangGang ZhangWentian LuoYan XuImmunotherapy is a promising strategy for triple-negative breast cancer (TNBC) patients, however, the overall survival (OS) of 5-years is still not satisfactory. Hence, developing more valuable prognostic signature is urgently needed for clinical practice. This study established and verified an effective risk model based on machine learning methods through a series of publicly available datasets. Furthermore, the correlation between risk signature and chemotherapy drug sensitivity were also performed. The findings showed that comprehensive immune typing is highly effective and accurate in assessing prognosis of TNBC patients. Analysis showed that IL18R1, BTN3A1, CD160, CD226, IL12B, GNLY and PDCD1LG2 are key genes that may affect immune typing of TNBC patients. The risk signature plays a robust ability in prognosis prediction compared with other clinicopathological features in TNBC patients. In addition, the effect of our constructed risk model on immunotherapy response was superior to TIDE results. Finally, high-risk groups were more sensitive to MR-1220, GSK2110183 and temsirolimus, indicating that risk characteristics could predict drug sensitivity in TNBC patients to a certain extent. This study proposes an immunophenotype-based risk assessment model that provides a more accurate prognostic assessment tool for patients with TNBC and also predicts new potential compounds by performing machine learning algorithms.https://www.frontiersin.org/articles/10.3389/fphar.2023.1195864/fulltriple-negative breast cancerimmunotherapyimmunophenotypeprognosischemotherapy |
| spellingShingle | Lijuan Tang Zhe Zhang Jun Fan Jing Xu Jiashen Xiong Lu Tang Yan Jiang Shu Zhang Gang Zhang Wentian Luo Yan Xu Comprehensively analysis of immunophenotyping signature in triple-negative breast cancer patients based on machine learning Frontiers in Pharmacology triple-negative breast cancer immunotherapy immunophenotype prognosis chemotherapy |
| title | Comprehensively analysis of immunophenotyping signature in triple-negative breast cancer patients based on machine learning |
| title_full | Comprehensively analysis of immunophenotyping signature in triple-negative breast cancer patients based on machine learning |
| title_fullStr | Comprehensively analysis of immunophenotyping signature in triple-negative breast cancer patients based on machine learning |
| title_full_unstemmed | Comprehensively analysis of immunophenotyping signature in triple-negative breast cancer patients based on machine learning |
| title_short | Comprehensively analysis of immunophenotyping signature in triple-negative breast cancer patients based on machine learning |
| title_sort | comprehensively analysis of immunophenotyping signature in triple negative breast cancer patients based on machine learning |
| topic | triple-negative breast cancer immunotherapy immunophenotype prognosis chemotherapy |
| url | https://www.frontiersin.org/articles/10.3389/fphar.2023.1195864/full |
| work_keys_str_mv | AT lijuantang comprehensivelyanalysisofimmunophenotypingsignatureintriplenegativebreastcancerpatientsbasedonmachinelearning AT zhezhang comprehensivelyanalysisofimmunophenotypingsignatureintriplenegativebreastcancerpatientsbasedonmachinelearning AT junfan comprehensivelyanalysisofimmunophenotypingsignatureintriplenegativebreastcancerpatientsbasedonmachinelearning AT jingxu comprehensivelyanalysisofimmunophenotypingsignatureintriplenegativebreastcancerpatientsbasedonmachinelearning AT jiashenxiong comprehensivelyanalysisofimmunophenotypingsignatureintriplenegativebreastcancerpatientsbasedonmachinelearning AT lutang comprehensivelyanalysisofimmunophenotypingsignatureintriplenegativebreastcancerpatientsbasedonmachinelearning AT yanjiang comprehensivelyanalysisofimmunophenotypingsignatureintriplenegativebreastcancerpatientsbasedonmachinelearning AT shuzhang comprehensivelyanalysisofimmunophenotypingsignatureintriplenegativebreastcancerpatientsbasedonmachinelearning AT gangzhang comprehensivelyanalysisofimmunophenotypingsignatureintriplenegativebreastcancerpatientsbasedonmachinelearning AT wentianluo comprehensivelyanalysisofimmunophenotypingsignatureintriplenegativebreastcancerpatientsbasedonmachinelearning AT yanxu comprehensivelyanalysisofimmunophenotypingsignatureintriplenegativebreastcancerpatientsbasedonmachinelearning |