Lung cancer is the leading cause of cancer worldwide. Despite recent advances in the management of resected lung cancer tumors (i.e., the use of adjuvant therapy) and more effective treatments in the metastatic setting (i.e., molecular targeted agents), the cure rate of lung cancer remains low. Successful molecular testing of lung cancer requires the identification and understanding of events that take place during the multistep tumorigenic process of lung cancer. As with other solid tumors, lung cancer is the result of the accumulation of genetic and epigenetic alterations over a long course of exposure to a carcinogen, such as tobacco smoke. Discovering new prognostic or predictive biomarkers or developing new detection tools for lung cancer is one of the major areas of translational cancer research. However, given our current understanding of the multifactorial process of lung carcinogenesis and the heterogeneous nature of the disease, monitoring of one or a few genes is limited. A pangenomic analysis seems more efficient for deciphering the complexity of lung cancer. The prospect of identifying specific events in lung carcinogenesis is significantly brightened by the recent development of high-throughput gene expression analysis. Since 2000, several studies have reported on the molecular classification of human lung carcinomas on the basis of gene expression and have described numerous putative biological markers of cancer. At this time, improving the biological significance of microarray data appears to be an important challenge. The most recent studies propose refining molecular classification of non-small-cell lung cancer on the basis of mRNA expression profiles. Other studies described new prognostic biomarkers that will be useful for the therapeutic management of patient's bearing lung cancer (non-small-cell lung cancer). The present review summarizes the main recent advances associated with gene expression analysis in the field of lung cancer and, notably, non-small-cell lung tumors.