Evaluation of the screening and diagnosis model for the lung adenocarcinoma protein function module based on WGCNA and machine learning

Abstract

This paper aims to identify lung adenocarcinoma biomarkers through WGCNA and machine learning and construct a clinical diagnosis model for lung adenocarcinoma. We used the lung cancer protein expression data from the CPTAC database to conduct differentiation analysis, built a WGCNA network of lung adenocarcinoma samples and a WGCNA network of lung tumor samples and normal samples, and assessed the overlapped module of these two networks using machine learning. GO and KEGG abundance analysis was conducted to find proteins related to lung tumor, a correlation network for proteins in the overlapped module was created to mine the target protein biomarkers, and machine learning was used to create and analyze a screening model. Therewere2317 differentially expressed proteins obtained from 213 lung tumor samples from the CPTAC database; the lung tumor network and the lung tumor para-carcinoma tissue joint network had two overlapping modules; through PPI network optimization, we mined 11 protein biomarkers related to lung adenocarcinoma. Through verification based on data outside TCGA, we found that the lung adenocarcinoma diagnosis model constructed based on the 11 protein biomarkers had high accuracy and stability, showing clinical and biological significance.