Identification and Validation of Cuproptosis-Related LncRNA Signatures in the Prognosis and Immunotherapy of Clear Cell Renal Cell Carcinoma Using Machine Learning
(1) Objective: We aimed to mine cuproptosis-related LncRNAs with prognostic value and construct a corresponding prognostic model using machine learning. External validation of the model was performed in the ICGC database and in multiple renal cancer cell lines via qPCR. <b>(2)</b> Method...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Biomolecules |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2218-273X/12/12/1890 |
| _version_ | 1827641529556008960 |
|---|---|
| author | Zhixun Bai Jing Lu Anjian Chen Xiang Zheng Mingsong Wu Zhouke Tan Jian Xie |
| author_facet | Zhixun Bai Jing Lu Anjian Chen Xiang Zheng Mingsong Wu Zhouke Tan Jian Xie |
| author_sort | Zhixun Bai |
| collection | DOAJ |
| description | (1) Objective: We aimed to mine cuproptosis-related LncRNAs with prognostic value and construct a corresponding prognostic model using machine learning. External validation of the model was performed in the ICGC database and in multiple renal cancer cell lines via qPCR. <b>(2)</b> Methods: TCGA and ICGC cohorts related to renal clear cell carcinoma were included. GO and KEGG analyses were conducted to determine the biological significance of differentially expressed cuproptosis-related LncRNAs (CRLRs). Machine learning (LASSO), Kaplan–Meier, and Cox analyses were conducted to determine the prognostic genes. The tumor microenvironment and tumor mutation load were further studied. TIDE and IC50 were used to evaluate the response to immunotherapy, a risk model of LncRNAs related to the cuproptosis genes was established, and the ability of this model was verified in an external independent ICGC cohort. LncRNAs were identified in normal HK-2 cells and verified in four renal cell lines via qPCR. (3) Results: We obtained 280 CRLRs and identified 66 LncRNAs included in the TCGA-KIRC cohort. Then, three hub LncRNAs (AC026401.3, FOXD2−AS1, and LASTR), which were over-expressed in the four ccRCC cell lines compared with the human renal cortex proximal tubule epithelial cell line HK-2, were identified. In the ICGC database, the expression of FOXD2-AS1 and LASTR was consistent with the qPCR and TCGA-KIRC. The results also indicated that patients with low-risk ccRCC—stratified by tumor-node metastasis stage, sex, and tumor grade—had significantly better overall survival than those with high-risk ccRCC. The predictive algorithm showed that, according to the three CRLR models, the low-risk group was more sensitive to nine target drugs (A.443654, A.770041, ABT.888, AG.014699, AMG.706, ATRA, AP.24534, axitinib, and AZ628), based on the estimated half-maximal inhibitory concentrations. In contrast, the high-risk group was more sensitive to ABT.263 and AKT inhibitors VIII and AS601245. Using the CRLR models, the correlation between the tumor immune microenvironment and cancer immunotherapy response revealed that high-risk patients are more likely to respond to immunotherapy than low-risk patients. In terms of immune marker levels, there were significant differences between the high- and low-risk groups. A high TMB score in the high-risk CRLR group was associated with worse survival, which could be a prognostic factor for KIRC. (4) Conclusions: This study elucidates the core cuproptosis-related LncRNAs, FOXD2−AS1, AC026401.3, and LASTR, in terms of potential predictive value, immunotherapeutic strategy, and outcome of ccRCC. |
| first_indexed | 2024-03-09T17:16:10Z |
| format | Article |
| id | doaj.art-5ea293793e304093a170b6fada6ff5f4 |
| institution | Directory Open Access Journal |
| issn | 2218-273X |
| language | English |
| last_indexed | 2024-03-09T17:16:10Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomolecules |
| spelling | doaj.art-5ea293793e304093a170b6fada6ff5f42023-11-24T13:35:10ZengMDPI AGBiomolecules2218-273X2022-12-011212189010.3390/biom12121890Identification and Validation of Cuproptosis-Related LncRNA Signatures in the Prognosis and Immunotherapy of Clear Cell Renal Cell Carcinoma Using Machine LearningZhixun Bai0Jing Lu1Anjian Chen2Xiang Zheng3Mingsong Wu4Zhouke Tan5Jian Xie6Organ Transplant Center, The Affiliated Hospital of Zunyi Medical University, Zunyi 563006, ChinaDepartment of Clinical, Zunyi Medical and Pharmaceutical College, Zunyi 563000, ChinaDepartment of Urology, The Affiliated Hospital of Zunyi Medical University, Zunyi 563006, ChinaDepartment of Medical Genetics, Zunyi Medical University, Zunyi 563006, ChinaDepartment of Medical Genetics, Zunyi Medical University, Zunyi 563006, ChinaOrgan Transplant Center, The Affiliated Hospital of Zunyi Medical University, Zunyi 563006, ChinaDepartment of Medical Genetics, Zunyi Medical University, Zunyi 563006, China(1) Objective: We aimed to mine cuproptosis-related LncRNAs with prognostic value and construct a corresponding prognostic model using machine learning. External validation of the model was performed in the ICGC database and in multiple renal cancer cell lines via qPCR. <b>(2)</b> Methods: TCGA and ICGC cohorts related to renal clear cell carcinoma were included. GO and KEGG analyses were conducted to determine the biological significance of differentially expressed cuproptosis-related LncRNAs (CRLRs). Machine learning (LASSO), Kaplan–Meier, and Cox analyses were conducted to determine the prognostic genes. The tumor microenvironment and tumor mutation load were further studied. TIDE and IC50 were used to evaluate the response to immunotherapy, a risk model of LncRNAs related to the cuproptosis genes was established, and the ability of this model was verified in an external independent ICGC cohort. LncRNAs were identified in normal HK-2 cells and verified in four renal cell lines via qPCR. (3) Results: We obtained 280 CRLRs and identified 66 LncRNAs included in the TCGA-KIRC cohort. Then, three hub LncRNAs (AC026401.3, FOXD2−AS1, and LASTR), which were over-expressed in the four ccRCC cell lines compared with the human renal cortex proximal tubule epithelial cell line HK-2, were identified. In the ICGC database, the expression of FOXD2-AS1 and LASTR was consistent with the qPCR and TCGA-KIRC. The results also indicated that patients with low-risk ccRCC—stratified by tumor-node metastasis stage, sex, and tumor grade—had significantly better overall survival than those with high-risk ccRCC. The predictive algorithm showed that, according to the three CRLR models, the low-risk group was more sensitive to nine target drugs (A.443654, A.770041, ABT.888, AG.014699, AMG.706, ATRA, AP.24534, axitinib, and AZ628), based on the estimated half-maximal inhibitory concentrations. In contrast, the high-risk group was more sensitive to ABT.263 and AKT inhibitors VIII and AS601245. Using the CRLR models, the correlation between the tumor immune microenvironment and cancer immunotherapy response revealed that high-risk patients are more likely to respond to immunotherapy than low-risk patients. In terms of immune marker levels, there were significant differences between the high- and low-risk groups. A high TMB score in the high-risk CRLR group was associated with worse survival, which could be a prognostic factor for KIRC. (4) Conclusions: This study elucidates the core cuproptosis-related LncRNAs, FOXD2−AS1, AC026401.3, and LASTR, in terms of potential predictive value, immunotherapeutic strategy, and outcome of ccRCC.https://www.mdpi.com/2218-273X/12/12/1890ccRCClncRNAcuproptosisimmunotherapyTMB score |
| spellingShingle | Zhixun Bai Jing Lu Anjian Chen Xiang Zheng Mingsong Wu Zhouke Tan Jian Xie Identification and Validation of Cuproptosis-Related LncRNA Signatures in the Prognosis and Immunotherapy of Clear Cell Renal Cell Carcinoma Using Machine Learning Biomolecules ccRCC lncRNA cuproptosis immunotherapy TMB score |
| title | Identification and Validation of Cuproptosis-Related LncRNA Signatures in the Prognosis and Immunotherapy of Clear Cell Renal Cell Carcinoma Using Machine Learning |
| title_full | Identification and Validation of Cuproptosis-Related LncRNA Signatures in the Prognosis and Immunotherapy of Clear Cell Renal Cell Carcinoma Using Machine Learning |
| title_fullStr | Identification and Validation of Cuproptosis-Related LncRNA Signatures in the Prognosis and Immunotherapy of Clear Cell Renal Cell Carcinoma Using Machine Learning |
| title_full_unstemmed | Identification and Validation of Cuproptosis-Related LncRNA Signatures in the Prognosis and Immunotherapy of Clear Cell Renal Cell Carcinoma Using Machine Learning |
| title_short | Identification and Validation of Cuproptosis-Related LncRNA Signatures in the Prognosis and Immunotherapy of Clear Cell Renal Cell Carcinoma Using Machine Learning |
| title_sort | identification and validation of cuproptosis related lncrna signatures in the prognosis and immunotherapy of clear cell renal cell carcinoma using machine learning |
| topic | ccRCC lncRNA cuproptosis immunotherapy TMB score |
| url | https://www.mdpi.com/2218-273X/12/12/1890 |
| work_keys_str_mv | AT zhixunbai identificationandvalidationofcuproptosisrelatedlncrnasignaturesintheprognosisandimmunotherapyofclearcellrenalcellcarcinomausingmachinelearning AT jinglu identificationandvalidationofcuproptosisrelatedlncrnasignaturesintheprognosisandimmunotherapyofclearcellrenalcellcarcinomausingmachinelearning AT anjianchen identificationandvalidationofcuproptosisrelatedlncrnasignaturesintheprognosisandimmunotherapyofclearcellrenalcellcarcinomausingmachinelearning AT xiangzheng identificationandvalidationofcuproptosisrelatedlncrnasignaturesintheprognosisandimmunotherapyofclearcellrenalcellcarcinomausingmachinelearning AT mingsongwu identificationandvalidationofcuproptosisrelatedlncrnasignaturesintheprognosisandimmunotherapyofclearcellrenalcellcarcinomausingmachinelearning AT zhouketan identificationandvalidationofcuproptosisrelatedlncrnasignaturesintheprognosisandimmunotherapyofclearcellrenalcellcarcinomausingmachinelearning AT jianxie identificationandvalidationofcuproptosisrelatedlncrnasignaturesintheprognosisandimmunotherapyofclearcellrenalcellcarcinomausingmachinelearning |