Identification of a novel gene signature with regard to ferroptosis, prognosis prediction, and immune microenvironment in osteosarcoma

Ferroptosis is a novel form of non-apoptotic cell death that mainly results from the iron-dependent lethal accumulation of lipid peroxidation products. Here, we defined differentially expressed genes between control and RSL3-treated osteosarcoma cells as ferroptosis-associated genes (FAGs). These FAGs were then subjected to weighted gene correlation network analysis (WGCNA), and we found that the turquoise module, containing 71 FAGs, was markedly related to the patient's vital status. After that, FAGs in the turquoise module were utilized to construct a prognostic multigene (COL5A2, HOXB4, and UNC5B) signature for risk stratification in osteosarcoma. Validation in internal and external cohorts indicated the accuracy and clinical applicability of this signature in predicting the prognosis of patients with osteosarcoma. Univariate and multivariate Cox regression analyses suggested that the signature-derived risk score is an independent indicator of patient prognosis. Immunological analysis indicated that significant variations in stromal and ESTIMATE scores, as well as tumor purity, were found when the high- and low-risk groups were compared. Regarding immune cell infiltration, the proportion of activated CD4 memory T cells was significantly lower in the high-risk group than that in the low-risk group. The ssGSEA results suggested that CD8(+) T, Tfh, and Th1 cell scores were consistently lower in the high-risk group than those in the low-risk group. In terms of immune-related activities, the high-risk group had considerably lower scores for promoting inflammation, T-cell co-inhibition, and T-cell co-stimulation than the low-risk group, indicating the differential immunological state of the high- and low-risk groups. Of the three FAGs included in the signature, the expression of COL5A2, HOXB4, and UNC5B was higher in the high-risk groups, and the expression of COL5A2 and UNC5B was negatively associated with patient prognosis. Additionally, the mRNA levels of COL5A2 and HOXB4 were lower and those of UNC5B were higher in RSL3-treated cells than in control cells. In all, we systematically analyzed the transcriptional changes of osteosarcoma cells induced by RSL3 and constructed a novel three-gene signature with regard to ferroptosis, prognosis prediction, and immune microenvironment. We also identified COL5A2, HOXB4, and UNC5B as potential therapeutic targets and important regulators of ferroptosis in osteosarcoma.