Small non-coding RNAs are potential diagnostic biomarkers for lung cancer. Mitochondria-derived small RNA (mtRNA) is a novel regulatory small non-coding RNA that only recently has been identified and cataloged. Currently, there are no reports of studies of mtRNA in human lung cancer. Currently, normalization methods are unstable, and they often fail to identify differentially expressed small non-coding RNAs (sncRNAs). In order to identify reliable biomarkers for lung cancer screening, we used a ratio-based method using mtRNAs newly discovered in human peripheral blood mononuclear cells. In the discovery cohort (AUC = 0.981) and independent validation cohort (AUC = 0.916) the prediction model of eight mtRNA ratios distinguished lung cancer patients from controls. The prediction model will provide reliable biomarkers that will allow blood-based screening to become more feasible and will help make lung cancer diagnosis more accurate in clinical practice.

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.