Dataset Information

Integrating Genomic Data with Transcriptomic Data for Improved Survival Prediction for Adult Diffuse Glioma.

ABSTRACT: Background: Glioma is the most common type of primary central nervous system tumors. However, the relationship between gene mutations and transcriptome is unclear in diffuse glioma, and there are no systemic analyses with regard to the genotype-phenotype association currently. Methods: We performed the multi-omics analysis in large glioblastoma multiforme (GBM, n=126) and low-grade glioma (LGG, n=481) cohorts obtained from The Cancer Genome Atlas (TCGA) database. We used multivariate linear models to evaluate associations between driver gene mutations and global gene expression. We developed generalized linear models to evaluate associations between genetic/expression factors with clinicopathologic features. Multivariate Cox proportional hazards models were used to predict the overall survival. Results: The potential relationship between genotype and genetics, clinical as well as pathologic features, on diffused glioma was observed. At least one driver mutation correlated with expression changes of about 10% of genes in GBMs while about 80% of genes in LGGs. The strongest association between mutations and expression changes was observed for DRG2 and LRCC41 gene in GBMs and LGGs, respectively. Additionally, the association between genomics features and clinicopathologic features suggested the different underlying molecular mechanisms in molecular subtypes or histology subtypes. For predicting survival, among genetics, transcriptome and clinical variables, transcriptome features made the largest contribution. By combining all the available data, the accuracy in predicting the prognosis of diffuse glioma in patients was also improved. Conclusion: Our study results revealed the influences of driver gene mutations on global gene expression in diffuse glioma patients. A more accurate model in predicting the prognosis of patients was achieved when combining with all the available data than just transcriptomic data.

SUBMITTER: Yang Q

PROVIDER: S-EPMC7171505 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Integrating Genomic Data with Transcriptomic Data for Improved Survival Prediction for Adult Diffuse Glioma.

Yang Qi Q Xiong Yi Y Jiang Nian N Zeng Fanyuan F Huang Chunhai C Li Xuejun X

Journal of Cancer 20200406 13

<b>Background</b>: Glioma is the most common type of primary central nervous system tumors. However, the relationship between gene mutations and transcriptome is unclear in diffuse glioma, and there are no systemic analyses with regard to the genotype-phenotype association currently. <b>Methods</b>: We performed the multi-omics analysis in large glioblastoma multiforme (GBM, n=126) and low-grade glioma (LGG, n=481) cohorts obtained from The Cancer Genome Atlas (TCGA) database. We used multivaria ...[more]

PMID: 32328184

Similar Datasets

Project description:BackgroundThe prognosis of diffuse midline glioma (DMG) patients with H3K27M (H3K27M-DMG) alterations is poor; however, a model that encourages accurate prediction of prognosis for such lesions on an individual basis remains elusive. We aimed to construct an H3K27M-DMG survival model based on DeepSurv to predict patient prognosis.MethodsPatients recruited from a single center were used for model training, and patients recruited from another center were used for external validation. Univariate and multivariate Cox regression analyses were used to select features. Four machine learning models were constructed, and the consistency index (C-index) and integrated Brier score (IBS) were calculated. We used the receiver operating characteristic curve (ROC) and area under the receiver operating characteristic (AUC) curve to assess the accuracy of predicting 6-month, 12-month, 18-month and 24-month survival rates. A heatmap of feature importance was used to explain the results of the four models.ResultsWe recruited 113 patients in the training set and 23 patients in the test set. We included tumor size, tumor location, Karnofsky Performance Scale (KPS) score, enhancement, radiotherapy, and chemotherapy for model training. The accuracy of DeepSurv prediction is highest among the four models, with C-indexes of 0.862 and 0.811 in the training and external test sets, respectively. The DeepSurv model had the highest AUC values at 6 months, 12 months, 18 months and 24 months, which were 0.970 (0.919-1), 0.950 (0.877-1), 0.939 (0.845-1), and 0.875 (0.690-1), respectively. We designed an interactive interface to more intuitively display the survival probability prediction results provided by the DeepSurv model.ConclusionThe DeepSurv model outperforms traditional machine learning models in terms of prediction accuracy and robustness, and it can also provide personalized treatment recommendations for patients. The DeepSurv model may provide decision-making assistance for patients in formulating treatment plans in the future.

Dataset Information

Integrating Genomic Data with Transcriptomic Data for Improved Survival Prediction for Adult Diffuse Glioma.

Publications

Integrating Genomic Data with Transcriptomic Data for Improved Survival Prediction for Adult Diffuse Glioma.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets