LncRNA Expression Signature in Prediction of the Prognosis of Lung Adenocarcinoma.

OBJECTIVE: To determine if lncRNA expression can be used for the prognoses of patients diagnosed with lung adenocarcinoma (LUAD) patients.

METHODS: The Cancer Genome Atlas database was used to identify 409 LUAD patients for whom there were both, gene expression data and relevant clinical information available. LncRNAs were then selected from the expression data through record linkage between the National Center for Biotechnology Information (NCBI) and Ensemble databases. lncRNAs with significantly different expression levels between normal and tumor tissues were screened, and those whose levels correlated with a positive LUAD prognosis were identified. Based on the expression of the selected lncRNAs, an unsupervised learning method was used to cluster these patients into two groups, and survival analyses were performed to assess the overall survival (OS) between the two groups. Receiver operating characteristic curves were used to calculate the specificity and sensitivity of the models based on the presence of these lncRNAs, and the model was tested with another dataset from the Gene Expression Omnibus.

RESULTS: A total of 151 lncRNAs were found to be differentially expressed between tumor and normal tissues (permutation p-values <0.05) based on the Cancer Genome Atlas dataset, and 20 lncRNAs were associated with OS. Two lncRNAs (DKFZP434 L187 and LOC285548) were correlated with LUAD. All patients with high expression of these two lncRNAs from the two datasets exhibited poor OS compared with those with low expression (p < 0.05).

CONCLUSIONS: The expression of DKFZP434 L187 and LOC285548 may have prognostic value for the OS of LUAD patients.