Identification of key serum biomarkers for the diagnosis and metastatic prediction of osteosarcoma by analysis of immune cell infiltration

Background The role of circular RNAs (circRNAs) and microRNAs (miRNAs) in osteosarcoma (OS) development has not been fully elucidated. Further, the contribution of the immune response to OS progression is not well defined. However, it is known that circRNAs and miRNAs can serve as biomarkers for the diagnosis, prognosis, and therapy of many cancers. Thus, the aim of this study was to identify novel key serum biomarkers for the diagnosis and metastatic prediction of OS by analysis of immune cell infiltration and associated RNA molecules. Methods Human OS differentially expressed circRNAs (DEcircRNAs), differentially expressed miRNAs (DEmiRNAs), and differentially expressed mRNAs (DEmRNAs) were identified by analysis of microarray data downloaded from Gene Expression Omnibus (GEO) datasets. Further, characteristic patterns of OS-infiltrating immune cells were analyzed. On this basis, we identified statistically significant transcription factors. Moreover we performed pathway enrichment analysis, constructed protein-protein interaction networks, and devised competitive endogenous RNA (ceRNA) networks. Biological targets of the ceRNA networks were evaluated and potential OS biomarkers confirmed by RT-qPCR analysis of the patients' serum. Results Seven differentially expressed circRNAs, 166 differentially expressed miRNAs, and 175 differentially expressed mRNAs were identified. An evaluation of cellular OS infiltration identified the highest level of infiltration by M0 macrophages, M2 macrophages, and CD8+ T cells, with M0 macrophages and CD8+ T cells as the most prominent. Significant patterns of tumor-infiltrating immune cells were identified by principal component analysis. Moreover, 185 statistically significant transcription factors were associated with OS. Further, in association with immune cell infiltration, hsa-circ-0010220, hsa-miR-326, hsa-miR-338-3p, and FAM98A were identified as potential novel biomarkers for OS diagnosis. Of these, FAM98A had the most promise as a diagnostic marker for OS and OS metastasis. Most importantly, a novel diagnostic model consisting of these four biomarkers (hsa-circ-0010220, hsa-miR-326, hsa-miR-338-3p, and FAM98A) was established with a 0.928 AUC value. Conclusions In summary, potential serum biomarkers for OS diagnosis and metastatic prediction were identified based on an analysis of immune cell infiltration. A novel diagnostic model consisting of these four promising serum biomarkers was established. Taken together, the results of this study provide a new perspective by which to understand immunotherapy of OS.