206
Views
3
Downloads
12
Crossref
12
WoS
11
Scopus
0
CSCD
Liver cancer presents divergent clinical behaviors. There remain opportunities for molecular markers to improve liver cancer diagnosis and prognosis, especially since tRNA-derived small RNAs (tsRNA) have rarely been studied. In this study, a random forests (RF) diagnostic model was built based upon tsRNA profiling of paired tumor and adjacent normal samples and validated by independent validation (IV). A LASSO model was used to developed a seven-tsRNA-based risk score signature for liver cancer prognosis. Model performance was evaluated by a receiver operating characteristic curve (ROC curve) and Precision-Recall curve (PR curve). The five-tsRNA-based RF diagnosis model had area under the receiver operating characteristic curve (AUROC) 88% and area under the precision–recall curve (AUPR) 87% in the discovery cohort and 87% and 86% in IV-AUROC and IV-AUPR, respectively. The seven-tsRNA-based prognostic model predicts the overall survival of liver cancer patients (Hazard Ratio 2.02, 95% CI 1.36–3.00, P < 0.001), independent of standard clinicopathological prognostic factors. Moreover, the model successfully categorizes patients into high-low risk groups. Diagnostic and prognostic modeling can be reliably utilized in the diagnosis of liver cancer and high-low risk classification of patients based upon tsRNA characterization.
The results here are in part based upon data generated by the TCGA Research Network:
This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).