Dataset Information

Development and validation of RNA binding protein-applied prediction model for gastric cancer.

ABSTRACT: RNA-binding proteins (RBPs) have been reported to be associated with the occurrence and progression of multiple cancers, but the role in gastric adenocarcinoma remains poorly understood. The present study aims to uncover potential RBPs associated with the survival of gastric adenocarcinoma, as well as corresponding biologic properties and signaling pathways of these RBPs. RNA sequencing and clinical data of GC were obtained from The Cancer Genome Atlas (n=373) and the Gene Expression Omnibus (GSE84437, n=433) database. Tumor samples in TCGA were randomly divided into the training and internal testing group by R software. A total of 238 DERBPs were selected for univariate and multivariate Cox regression analyses. Five pivotal RBP genes (RNASE2, METTL1, ANG, YBX2 and LARP6) were screened out and were used to construct a new prognostic model. Survival relevance and prediction accuracy of model were tested via Kaplan-Meier (K-M) curves and receiver operating characteristic (ROC) curves in internal and external testing groups. Further analysis has also showed that this model could serve as an independent prognosis-related parameter. A prognostic nomogram has been eventually developed, and presents a good performance of prediction.

SUBMITTER: Dai S

PROVIDER: S-EPMC7950299 | biostudies-literature | 2021 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Development and validation of RNA binding protein-applied prediction model for gastric cancer.

Dai Shuang S Huang Yan Y Liu Ting T Xu Zi-Han ZH Liu Tao T Chen Lan L Wang Zhi-Wu ZW Luo Feng F

Aging 20210211 4

RNA-binding proteins (RBPs) have been reported to be associated with the occurrence and progression of multiple cancers, but the role in gastric adenocarcinoma remains poorly understood. The present study aims to uncover potential RBPs associated with the survival of gastric adenocarcinoma, as well as corresponding biologic properties and signaling pathways of these RBPs. RNA sequencing and clinical data of GC were obtained from The Cancer Genome Atlas (n=373) and the Gene Expression Omnibus (GS ...[more]

PMID: 33589575

Similar Datasets

Project description:ObjectiveThis study focuses on the risk of venous thromboembolism (VTE) in patients with gastric or esophageal cancer (GC/EC), investigating the risk factors for VTE in this population. Utilizing machine learning techniques, the research aims to develop an interpretable VTE risk prediction model. The goal is to identify patients with gastric or esophageal cancer who are at high risk of VTE at an early stage in clinical practice, thereby enabling precise anticoagulant prophylaxis and thrombus management.MethodsThis study is a real-world investigation aimed at predicting VTE in patients with GC/EC. Data were collected from inpatients diagnosed with GC/EC at Sichuan Provincial People's Hospital between 1 January 2018, and 31 June 2023. Using nine supervised learning algorithms, 576 prediction models were developed based on 56 available variables. Subsequently, a simplified modeling approach was employed using the top 12 feature variables from the best-performing model. The primary metric for assessing the predictive performance of the models was the area under the ROC curve (AUC). Additionally, the training data used to construct the best model in this study were employed to externally validate several existing assessment models, including the Padua, Caprini, Khorana, and COMPASS-CAT scores.ResultsA total of 3,742 cases of GC/EC patients were collected after excluding duplicate visit information. The study included 861 (23.0%) patients, of which 124 (14.4%) developed VTE. The top five models based on AUC for full-variable modeling are as follows: GBoost (0.9646), Logic Regression (0.9443), AdaBoost (0.9382), CatBoost (0.9354), XGBoost (0.8097). For simplified modeling, the models are: Simp-CatBoost (0.8811), Simp-GBoost (0.8771), Simp-Random Forest (0.8736), Simp-AdaBoost (0.8263), Simp-Logistic Regression (0.8090). After evaluating predictive performance and practicality, the Simp-GBoost model was determined as the best model for this study. External validation of the Padua score, Caprini score, Khorana score, and COMPASS-CAT score based on the training set of the Simp-GBoost model yielded AUCs of 0.4367, 0.2900, 0.5000, and 0.3633, respectively.ConclusionIn this study, we analyzed the risk factors of VTE in GC/EC patients, and constructed a well-performing VTE risk prediction model capable of accurately identifying the extent of VTE risk in patients. Four VTE prediction scoring systems were introduced to externally validate the dataset of this study. The results demonstrated that the VTE risk prediction model established in this study held greater clinical utility for patients with GC/EC. The Simp-GB model can provide intelligent assistance in the early clinical assessment of VTE risk in these patients.

Project description:BackgroundEvidence from prevailing studies show that hepatocellular carcinoma (HCC) is among the top cancers with high mortality globally. Gene regulation at post-transcriptional level orchestrated by RNA-binding proteins (RBPs) is an important mechanism that modifies various biological behaviors of HCC. Currently, it is not fully understood how RBPs affects the prognosis of HCC. In this study, we aimed to construct and validate an RBP-related model to predict the prognosis of HCC patients.MethodsDifferently expressed RBPs were identified in HCC patients based on the GSE54236 dataset from the Gene Expression Omnibus (GEO) database. Integrative bioinformatics analyses were performed to select hub genes. Gene expression patterns were validated in The Cancer Genome Atlas (TCGA) database, after which univariate and multivariate Cox regression analyses, as well as Kaplan-Meier analysis were performed to develop a prognostic model. Then, the performance of the prognostic model was assessed using receiver operating characteristic (ROC) curves and clinicopathological correlation analysis. Moreover, data from the International Cancer Genome Consortium (ICGC) database were used for external validation. Finally, a nomogram combining clinicopathological parameters and prognostic model was established for the individual prediction of survival probability.ResultsThe prognostic risk model was finally constructed based on two RBPs (BOP1 and EZH2), facilitating risk-stratification of HCC patients. Survival was markedly higher in the low-risk group relative to the high-risk group. Moreover, higher risk score was associated with advanced pathological grade and late clinical stage. Besides, the risk score was found to be an independent prognosis factor based on multivariate analysis. Nomogram including the risk score and clinical stage proved to perform better in predicting patient prognosis.ConclusionsThe RBP-related prognostic model established in this study may function as a prognostic indicator for HCC, which could provide evidence for clinical decision making.

Dataset Information

Development and validation of RNA binding protein-applied prediction model for gastric cancer.

Publications

Development and validation of RNA binding protein-applied prediction model for gastric cancer.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets