Predicting the Lung Adenocarcinoma and Its Biomarkers by Integrating Gene Expression and DNA Methylation Data

Abstract

The early symptoms of lung adenocarcinoma patients are inapparent, and the clinical diagnosis of lung adenocarcinoma is primarily through X-ray examination and pathological section examination, whereas the discovery of biomarkers points out another direction for the diagnosis of lung adenocarcinoma with the development of bioinformatics technology. However, it is not accurate and trustworthy to diagnose lung adenocarcinoma due to omics data with high-dimension and low-sample size (HDLSS) features or biomarkers produced by utilizing only single omics data. To address the above problems, the feature selection methods of biological analysis are used to reduce the dimension of gene expression data (GSE19188) and DNA methylation data (GSE139032, GSE49996). In addition, the Cartesian product method is used to expand the sample set and integrate gene expression data and DNA methylation data. The classification is built by using a deep neural network and is evaluated on K-fold cross validation. Moreover, gene ontology analysis and literature retrieving are used to analyze the biological relevance of selected genes, TCGA database is used for survival analysis of these potential genes through Kaplan-Meier estimates to discover the detailed molecular mechanism of lung adenocarcinoma. Survival analysis shows that COL5A2 and SERPINB5 are significant for identifying lung adenocarcinoma and are considered biomarkers of lung adenocarcinoma.

From genetic correlations of Alzheimer’s disease to classification with artificial neural network models

“…Recent studies in bioinformatics have proposed the use of neural networks in molecular classification of diseases by gene expression and multi-omics data (Qiu et al 2022 ; Shao et al 2021 ). Many studies were focused on the comparison between artificial neuronal network and other machine learning methods, demonstrating that artificial neural networks are more flexible and work on different types of data (e.g., discrete or continuous data) (Esteva et al 2019 ; Biganzoli et al 1998 ; Zhu et al 2020b ).…”