Identification of an early diagnostic biomarker of lung adenocarcinoma based on co-expression similarity and construction of a diagnostic model

Abstract

BackgroundThe purpose of this study was to achieve early and accurate diagnosis of lung cancer and long-term monitoring of the therapeutic response.MethodsWe downloaded GSE20189 from GEO database as analysis data. We also downloaded human lung adenocarcinoma RNA-seq transcriptome expression data from the TCGA database as validation data. Finally, the expression of all of the genes underwent z test normalization. We used ANOVA to identify differentially expressed genes specific to each stage, as well as the intersection between them. Two methods, correlation analysis and co-expression network analysis, were used to compare the expression patterns and topological properties of each stage. Using the functional quantification algorithm, we evaluated the functional level of each significantly enriched biological function under different stages. A machine-learning algorithm was used to screen out significant functions as features and to establish an early diagnosis model. Finally, survival analysis was used to verify the correlation between the outcome and the biomarkers that we found.ResultsWe screened 12 significant biomarkers that could distinguish lung cancer patients with diverse risks. Patients carrying variations in these 12 genes also presented a poor outcome in terms of survival status compared with patients without variations.ConclusionsWe propose a new molecular-based noninvasive detection method. According to the expression of the stage-specific gene set in the peripheral blood of patients with lung cancer, the difference in the functional level is quantified to realize the early diagnosis and prediction of lung cancer.

Comparing biological information contained in mRNA and non-coding RNAs for classification of lung cancer patients

“…Specifically, in [69] a SVM was used to classify 445 adenocarcinoma (AC) and 19 normal (N) samples from RNA-seq data using 44 gene features. Also in [70] a SVM was used. In their case, 73 adenocarcinoma (AC) and 80 normal (N) samples from RNA-seq data were classified using 12 gene features.…”

TSPAN1, TMPRSS4, SDR16C5, and CTSE as Novel Panel for Pancreatic Cancer: A Bioinformatics Analysis and Experiments Validation

“…However, most studies only used DEGs or the first 25% variation genes to construct a weighted gene co-expression network, which may result in a loss of genetic diversity. Moreover, some studies only used the feature selection method to select biomarkers ( 17 , 43 , 48 ). Although this method can reduce the dimensionality of data, these genes that play important roles in the cancer process may be lost.…”

“…Currently, WGCNA was widely applied to screen hub genes in various cancers (9). This approach can identify critical cancer driver genes that may be a significant therapeutic target or diagnostic marker (43). In recent years, several biomarkers have been identified in the field of cancer research using WGCNA (44)(45)(46)(47).…”

Identification and validation of smoking-related genes in lung adenocarcinoma using an in vitro carcinogenesis model and bioinformatics analysis

“…For example, SPP1 has been identified as a prognostic biomarker in four LUAD datasets in the GEO database, which was also validated by the TCGA database [ 13 ]. Fan et al suggested 12 significant biomarkers that could distinguish lung cancer patients with different risks from the GEO database [ 14 ]. Gan et al identified the aberrantly expressed miR-375 gene involved in LUAD through the comparison of miRNA expression profiles in cancerous tissues based on the analysis and validation from TCGA and GEO datasets and published studies[ 15 ].…”