Abstract
Lung cancer is one of the world's most common and deadly cancers. The two main types of lung cancer are non-small cell lung cancer (NSCLC) and small cell lung cancer (SCLC). More than 85% of lung cancers are NSCLC. Genetic factors play a significant role in the risk of NSCLC. Growing studies focus on studying risk factors at the molecular level. The aim of the study is to build a pipeline to integrate Genome-wide association analysis (GWAS) and transcriptomics data with machine learning to effectively identify genetic risk factors of NSCLC. GWAS datasets and GWAS summary data were downloaded from GWAS catalog, which include lung carcinoma genetic variants among the European population. Then, with the GWAS summary, data functional analysis of significant SNPs was performed using a webserver called FUMAGWAS. The transcriptomics data of NSCLC and non-NSCLC people were used to build a machine learning model to identify the key genes that help predict the NSCLC. The top up-regulation and down-regulation genes were identified by the BART cancer webserver, and the mechanistic roles of the genes were validated by literature review. By performing integrative analysis of GWAS and transcriptomics analysis using machine learning, we identified multiple SNPs and genes that related to NSCLC. The computational pipeline may facilitate the biomarker discovery for NSCLC and other diseases.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have