Dataset Information

Identification of Signatures of Prognosis Prediction for Melanoma Using a Hypoxia Score.

ABSTRACT: Melanoma is one of the most aggressive cancers. Hypoxic microenvironment affects multiple cellular pathways and contributes to tumor progression. The purpose of the research was to investigate the association between hypoxia and melanoma, and identify the prognostic value of hypoxia-related genes. Based on the GSVA algorithm, gene expression profile collected from The Cancer Genome Atlas (TCGA) was used for calculating the hypoxia score. The Kaplan-Meier plot suggested that a high hypoxia score was correlated with the inferior survival of melanoma patients. Using differential gene expression analysis and WGCNA, a total of 337 overlapping genes associated with hypoxia were determined. Protein-protein interaction network and functional enrichment analysis were conducted, and Lasso Cox regression was performed to establish the prognostic gene signature. Lasso regression showed that seven genes displayed the best features. A novel seven-gene signature (including ABCA12, PTK6, FERMT1, GSDMC, KRT2, CSTA, and SPRR2F) was constructed for prognosis prediction. The ROC curve inferred good performance in both the TCGA cohort and validation cohorts. Therefore, our study determined the prognostic implication of the hypoxia score in melanoma and showed a novel seven-gene signature to predict prognosis, which may provide insights into the prognosis evaluation and clinical decision making.

SUBMITTER: Shou Y

PROVIDER: S-EPMC7550673 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Identification of Signatures of Prognosis Prediction for Melanoma Using a Hypoxia Score.

Shou Yanhong Y Yang Lu L Yang Yongsheng Y Zhu Xiaohua X Li Feng F Xu Jinhua J

Frontiers in genetics 20200929

Melanoma is one of the most aggressive cancers. Hypoxic microenvironment affects multiple cellular pathways and contributes to tumor progression. The purpose of the research was to investigate the association between hypoxia and melanoma, and identify the prognostic value of hypoxia-related genes. Based on the GSVA algorithm, gene expression profile collected from The Cancer Genome Atlas (TCGA) was used for calculating the hypoxia score. The Kaplan-Meier plot suggested that a high hypoxia score ...[more]

PMID: 33133157

Similar Datasets

Project description:Background: Adrenocortical carcinoma (ACC) is a rare malignant endocrine tumor derived from the adrenal cortex. Because of its highly aggressive nature, the prognosis of patients with adrenocortical carcinoma is not impressive. Hypoxia exists in the vast majority of solid tumors and contributes to invasion, metastasis, and drug resistance. This study aimed to reveal the role of hypoxia in Adrenocortical carcinoma and develop a hypoxia risk score (HRS) for Adrenocortical carcinoma prognostic prediction. Methods: Hypoxia-related genes were obtained from the Molecular Signatures Database. The training cohorts of patients with adrenocortical carcinoma were downloaded from The Cancer Genome Atlas, while another three validation cohorts with comprehensive survival data were collected from the Gene Expression Omnibus. In addition, we constructed a hypoxia classifier using a random survival forest model. Moreover, we explored the relationship between the hypoxia risk score and immunophenotype in adrenocortical carcinoma to evaluate the efficacy of immune check inhibitors (ICI) therapy and prognosis of patients. Results: HRS and tumor stage were identified as independent prognostic factors. HRS was negatively correlated with immune cycle activity, immune cell infiltration, and the T cell inflammatory score. Therefore, we considered the low hypoxia risk score group as the inflammatory immunophenotype, whereas the high HRS group was a non-inflammatory immunophenotype. In addition, the HRS was negatively related to the expression of common immune checkpoint molecules such as PD-L1, CD200, CTLA-4, and TIGIT, suggesting that patients with a lower hypoxia risk score respond better to immunotherapy. Conclusion: We developed and validated a novel hypoxia risk score to predict the immunophenotype and response of patients with adrenocortical carcinoma to immune check inhibitors therapy. These findings not only provide fresh prognostic indicators for adrenocortical carcinoma but also offer several promising treatment targets for this disease.

Project description:BackgroundBiomarkers are a key component of precision medicine. However, full clinical integration of biomarkers has been met with challenges, partly attributed to analytical difficulties. It has been shown that biomarker reproducibility is susceptible to data preprocessing approaches. Here, we systematically evaluated machine-learning ensembles of preprocessing methods as a general strategy to improve biomarker performance for prediction of survival from early breast cancer.ResultsWe risk stratified breast cancer patients into either low-risk or high-risk groups based on four published hypoxia signatures (Buffa, Winter, Hu, and Sorensen), using 24 different preprocessing approaches for microarray normalization. The 24 binary risk profiles determined for each hypoxia signature were combined using a random forest to evaluate the efficacy of a preprocessing ensemble classifier. We demonstrate that the best way of merging preprocessing methods varies from signature to signature, and that there is likely no 'best' preprocessing pipeline that is universal across datasets, highlighting the need to evaluate ensembles of preprocessing algorithms. Further, we developed novel signatures for each preprocessing method and the risk classifications from each were incorporated in a meta-random forest model. Interestingly, the classification of these biomarkers and its ensemble show striking consistency, demonstrating that similar intrinsic biological information are being faithfully represented. As such, these classification patterns further confirm that there is a subset of patients whose prognosis is consistently challenging to predict.ConclusionsPerformance of different prognostic signatures varies with pre-processing method. A simple classifier by unanimous voting of classifications is a reliable way of improving on single preprocessing methods. Future signatures will likely require integration of intrinsic and extrinsic clinico-pathological variables to better predict disease-related outcomes.

Project description:Simple Summary The increase in adjuvant treatment of melanoma patients makes it necessary to provide the most accurate prognostic assessment possible, even at early stages of the disease. Although conventional risk stratification correctly identifies most patients in need of adjuvant treatment, there are some patients who, despite having a low tumor stage, have poor prognosis and could therefore benefit from early therapy. To close this gap in prognosis estimation, deep learning-based image analyses of histological sections could play a central role in the future. The aim of this study was to investigate whether such an analysis is possible only using basic image analysis of 831 H&E-stained melanoma sections using Google’s Teachable Machine. Although the classification obtained does not provide an additional prognostic estimate to conventional melanoma classification, this study shows that prognostic prediction is possible at the mere cellular image level. Abstract Background: The increasing number of melanoma patients makes it necessary to establish new strategies for prognosis assessment to ensure follow-up care. Deep-learning-based image analysis of primary melanoma could be a future component of risk stratification. Objectives: To develop a risk score for overall survival based on image analysis through artificial intelligence (AI) and validate it in a test cohort. Methods: Hematoxylin and eosin (H&E) stained sections of 831 melanomas, diagnosed from 2012–2015 were photographed and used to perform deep-learning-based group classification. For this purpose, the freely available software of Google’s teachable machine was used. Five hundred patient sections were used as the training cohort, and 331 sections served as the test cohort. Results: Using Google’s Teachable Machine, a prognosis score for overall survival could be developed that achieved a statistically significant prognosis estimate with an AUC of 0.694 in a ROC analysis based solely on image sections of approximately 250 × 250 µm. The prognosis group “low-risk” (n = 230) showed an overall survival rate of 93%, whereas the prognosis group “high-risk” (n = 101) showed an overall survival rate of 77.2%. Conclusions: The study supports the possibility of using deep learning-based classification systems for risk stratification in melanoma. The AI assessment used in this study provides a significant risk estimate in melanoma, but it does not considerably improve the existing risk classification based on the TNM classification.

Project description:BackgroundOne of the most diverse tumors is pancreatic cancer (PC), which makes predicting the prognosis challenging. PC development is directly related to hypoxia, angiogenesis, and immunotherapy. It is still unclear how the three features are related.MethodsThe Genotype-Tissue Expression (GTEx) and the Cancer Genome Atlas (TCGA) database were employed to obtain sequencing data for healthy pancreatic tissues and PC tissues, respectively. According to the constructed hypoxic prognostic model (HPM) and angiogenic prognostic model (APM), 4 subtypes of PC were identified. Hypoxia and angiogenesis prognostic model (HAPM) was established based on differentially expressed genes (DEGs) between high-angiogenesis/high-hypoxia (HH) and low-angiogenesis/low-hypoxia (LL) subgroups. Base on the median risk score, PC patients were separated into high-risk and low-risk groups, and clinical traits, prognosis, percentage of immune cell infiltration, PD-1 expression, and the fraction of T-cell depletion were compared between the groups. Finally, the predictive accuracy of the tumor immune dysfunction and rejection (TIDE) and tumor inflammatory signature (TIS) models, as well as HAPM, was compared.ResultWe analyzed the mRNA sequencing data from 178 PC tissues and 171 normal pancreatic tissues to obtain 9527 DEGs. We discovered 200 genes linked with hypoxia and 36 genes involved with angiogenesis through the literature. We found the core genes related with hypoxia and angiogenesis in PC by intersecting the DEGs of the HH and LL subgroups with those of PC via WGCNA. IL-17 signaling pathway, ECM-receptor interactions, cytokine receptor interactions, etc. were all enriched in the Kyoto Encyclopedia of Genes and Genomes (KEGG) results of core genes. HAPM has good predictive efficiency, according to an evaluation of KM survival curves and ROC curves. The external dataset also validated the model's ability to anticipate outcomes. Patients in the high- and low-risk groups were compared for PD1 expression and T-cell exclusion scores, which suggested that the model might be used to forecast which PC patients might benefit from immunotherapy.ConclusionsThe probable molecular processes connecting hypoxia and angiogenesis are described in this work, and a model is developed that may be utilized to forecast the prognosis for PC patients and the benefits of immunotherapy.

Dataset Information

Identification of Signatures of Prognosis Prediction for Melanoma Using a Hypoxia Score.

Publications

Identification of Signatures of Prognosis Prediction for Melanoma Using a Hypoxia Score.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets