A novel microRNA signature for pathological grading in lung adenocarcinoma based on TCGA and GEO data
- Zhiyu Yang
- Hongkun Yin
- Lei Shi
- Xiaohua Qian
Affiliations: SJTU‑Yitu Joint Laboratory of Artificial Intelligence in Healthcare, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200030, P.R. China, Shanghai Yitu Healthcare Technology Co. Ltd., Shanghai 200051, P.R. China, Hangzhou Yitu Healthcare Technology Co. Ltd., Hangzhou, Zhejiang 310012, P.R. China
- Published online on: March 4, 2020 https://doi.org/10.3892/ijmm.2020.4526
Copyright: © Yang
et al. This is an open access article distributed under the
terms of Creative
Commons Attribution License.
Views: 0 (Spandidos Publications: | PMC Statistics: )
Total PDF Downloads: 0 (Spandidos Publications: | PMC Statistics: )
This article is mentioned in:
Lung adenocarcinoma (LUAD) is one of the most common types of lung cancer and its poor prognosis largely depends on the tumor pathological stage. Critical roles of microRNAs (miRNAs) have been reported in the tumorigenesis and progression of lung cancer. However, whether the differential expression pattern of miRNAs could be used to distinguish early‑stage (stage I) from mid‑late‑stage (stages II‑IV) LUAD tumors is still unclear. In this study, clinical information and miRNA expression profiles of patients with LUAD were downloaded from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus databases. TCGA‑LUAD (n=470) dataset was used for model training and validation, and the GSE62182 (n=94) and GSE83527 (n=36) datasets were used as external independent test datasets. The diagnostic model was created through miRNA feature selection followed by SVM classifier and was confirmed by 5‑fold cross‑validation. A receiver operating characteristic curve was calculated to evaluate the accuracy and robustness of the model. Using the DX score and LIBSVM tool, a 16‑miRNA signature that could distinguish LUAD pathological stages was identified. The area under the curve rates were 0.62 [95% confidence interval (CI): 0.56‑0.67], 0.66 (95% CI: 0.54‑0.76) and 0.63 (95% CI: 0.43‑0.82) in TCGA‑LUAD internal validation dataset, the GSE62182 external validation dataset, and the GSE83527 external validation dataset, respectively. Kyoto Encyclopedia of Genes and Genomes and Gene Ontology enrichment analyses suggested that the target genes of the 16‑miRNA signature were mainly involved in metabolic pathways. The present findings demonstrate that a 16‑miRNA signature could serve as a promising diagnostic biomarker for pathological staging in LUAD.