Background: Lung cancer is one of the dominant causes of cancer-related deaths worldwide. Ferroptosis, an iron-dependent regulated cell death, plays an important role in the cancer immunotherapy. However, the role of immunity- and ferroptosis-related gene signature in non-small cell lung cancer (NSCLC) remains unknown.Method: The RNA sequencing (RNA-seq) expression data and clinical information of NSCLC were downloaded from The Cancer Genome Atlas (TCGA) database and performed differential analysis. Univariate and multivariate cox regressions were used to identify the ferroptosis-related gene, and receiver operating characteristic (ROC) model was established using the independent risk factors. GO and KEGG enrichment analyses were performed to investigate the biological functions of differential genes.Results: A 5-gene signature was constructed to stratify patients into high- and low-risk groups. Compared with patients in the low-risk group, patients in the high-risk group showed significantly poor overall survival (P < 0.001 in the TCGA cohort and P = 0.001 in the GSE13213 cohort). The risk score was an independent predictor for overall survival in multivariate Cox regression analyses (HR > 1, P < 0.01). The 1 year-, 2 year- and 3 year-ROCs were 0.792, 0.644 and 0.641 in TCGA and 0.623, 0.636 and 0.631 in GSE13213, respectively. Functional analysis revealed that immune-related pathways were enriched, and immune status were different between two risk groups. Conclusions: We identified differently expressed immunity- and ferroptosis-related genes that may involve in NSCLC. These genes may predict the overall survival in NSCLC and targeting ferroptosis may be an alternative for clinical therapy.