Dataset Information

Machine learning constructs a T cell-related signature for predicting prognosis and drug sensitivity in ovarian cancer.

ABSTRACT:

Background

The leading cause of death related to gynecologic cancer is ovarian cancer, which typically has a poor prognosis. T cells are referred to as key mediators of immunosurveillance and tumor eradication, and unbalanced regulation or lack of T cells in tumors result in immunotherapy resistance.

Methods

The identification of T cell related markers depended on single-cell RNA-seq analysis. Using data from multiple datasets, including TCGA, GSE14764, GSE26193, GSE26712, and GSE140082, we constructed a prognostic signature called TRS (T cell-related signature) using 10 different machine learning algorithms. The correlation between TRS and drug sensitivity were analyzed using the data from GSE91061 and IMvigor210 dataset.

Results

PlsRcox method based TRS was as a risk factor for the clinical outcome of ovarian cancer patients. In comparison with stage, grade and many prognostic signatures, the performance of our TRS in evaluating the clinical outcome was better in ovarian cancer. TRS-based risk score showed distinct association with the level of ESTIMATE score, immune-related function score and immune cells. Moreover, TRS could be used to predict the immunotherapy response and chemotherapy response in ovarian cancer.

Conclusion

In conclusion, we constructed a powerful TRS in ovarian cancer, which could accurately predict the clinical outcome of patients and be used to predict the immunotherapy response and chemotherapy response.

SUBMITTER: Zhang Y

PROVIDER: S-EPMC10929824 | biostudies-literature | 2024 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning constructs a T cell-related signature for predicting prognosis and drug sensitivity in ovarian cancer.

Zhang Yunzheng Y Pei Lipeng L

Aging 20240209 4

<h4>Background</h4>The leading cause of death related to gynecologic cancer is ovarian cancer, which typically has a poor prognosis. T cells are referred to as key mediators of immunosurveillance and tumor eradication, and unbalanced regulation or lack of T cells in tumors result in immunotherapy resistance.<h4>Methods</h4>The identification of T cell related markers depended on single-cell RNA-seq analysis. Using data from multiple datasets, including TCGA, GSE14764, GSE26193, GSE26712, and GSE ...[more]

PMID: 38345575

Similar Datasets

Project description:BackgroundHepatocellular carcinoma (HCC) remains a growing threat to global health. Necroptosis is a newly discovered form of cell necrosis that plays a vital role in cancer development. Thus, we conducted this study to identify a predictive signature of HCC based on necroptosis-related genes.MethodsThe tumor samples in the liver hepatocellular carcinoma (LIHC) cohort from The Cancer Genome Atlas (TCGA) database were subtyped using the consensus clustering algorithm. Univariate Cox regression and LASSO-Cox analysis were performed to identify a gene signature from genes differentially expressed between tumor clusters. Then, we integrated the TNM stage and the prognostic model to build a nomogram. The gene signature and the nomogram were externally validated in the GSE14520 cohort from the Gene Expression Omnibus (GEO) and the LIRP-JP cohort from the International Cancer Genome Consortium (ICGC). Evaluations of predictive performance evaluations were conducted using Kaplan-Meier plots, time-dependent receiver operating characteristic curves, principal component analyses, concordance indices, and decision curve analyses. The tumor microenvironment was estimated using eight published methods. Finally, we forecasted the sensitivity of HCC patients to immunotherapy and chemotherapy based on this gene signature.ResultsWe identified two necroptosis-related clusters and a 10-gene signature (MTMR2, CDCA8, S100A9, ANXA10, G6PD, SLC1A5, SLC2A1, SPP1, PLOD2, and MMP1). The gene signature and the nomogram had good predictive ability in the TCGA, ICGC, and GEO cohorts. The risk score was positively associated with the levels of necroptosis and immune cell infiltrations (especially of immunosuppressive cells). The high-risk group could benefit more from immunotherapy and some chemotherapeutics than the low-risk group.ConclusionThe necroptosis-related gene signature provides a new method for the risk stratification and treatment optimization of HCC. The nomogram can further improve predictive accuracy.

Project description:BackgroundPlatelets can dynamically regulate tumor development and progression. Nevertheless, research on the predictive value and specific roles of platelets in gastric cancer (GC) is limited. This research aims to establish a predictive platelets-related gene signature in GC with prognostic and therapeutic implications.MethodsWe downloaded the transcriptome data and clinical materials of GC patients (n=378) from The Cancer Genome Atlas (TCGA) database. Prognostic platelets-related genes screened by univariate Cox regression were included in Least Absolute Shrinkage and Selection Operator (LASSO) analysis to construct a risk model. Kaplan-Meier curves and receiver operating characteristic curves (ROCs) were performed in the TCGA cohort and three independent validation cohorts. A nomogram integrating the risk score and clinicopathological features was constructed. Functional enrichment and tumor microenvironment (TME) analyses were performed. Drug sensitivity prediction was conducted through The Cancer Therapeutics Response Portal (CTRP) database. Finally, the expression of ten signature genes was validated by quantitative real-time PCR (qRT-PCR).ResultsA ten-gene (SERPINE1, ANXA5, DGKQ, PTPN6, F5, DGKB, PCDH7, GNG11, APOA1, and TF) predictive risk model was finally constructed. Patients were categorized as high- or low-risk using median risk score as the threshold. The area under the ROC curve (AUC) values for the 1-, 2-, and 3-year overall survival (OS) in the training cohort were 0.670, 0.695, and 0.707, respectively. Survival analysis showed a better OS in low-risk patients in the training and validation cohorts. The AUCs of the nomogram for predicting 1-, 2-, and 3-year OS were 0.708, 0.763, and 0.742, respectively. TME analyses revealed a higher M2 macrophage infiltration and an immunosuppressive TME in the high-risk group. Furthermore, High-risk patients tended to be more sensitive to thalidomide, MK-0752, and BRD-K17060750.ConclusionThe novel platelets-related genes signature we identified could be used for prognosis and treatment prediction in GC.

Dataset Information

Machine learning constructs a T cell-related signature for predicting prognosis and drug sensitivity in ovarian cancer.

Background

Methods

Results

Conclusion

Publications

Machine learning constructs a T cell-related signature for predicting prognosis and drug sensitivity in ovarian cancer.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets