Abstract
BACKGROUND: Renal transplantation can significantly improve the survival rate and quality of life of patients with end-stage renal disease, but the probability of acute rejection (AR) in adult renal transplant recipients is still approximately 12.2%. Machine learning (ML) is superior to traditional statistical methods in various clinical scenarios. However, the current AR model is constructed only through simple difference analysis or a single queue, which cannot guarantee the accuracy of prediction. Therefore, this study identified and validated new gene sets that contribute to the early prediction of AR and the prognosis prediction of patients after renal transplantation by constructing a more accurate AR gene signature through ML technology. METHODS: Based on the Gene Expression Omnibus (GEO) database and multiple bioinformatic analyses, we identified differentially expressed genes (DEGs) and built a gene signature via LASSO regression and SVM analysis. Immune cell infiltration and immunocyte association analyses were also conducted. Furthermore, we investigated the relationship between AR genes and graft survival status. RESULTS: Twenty-four DEGs were identified. A 5 gene signature (CPA6, EFNA1, HBM, THEM5, and ZNF683) were obtained by LASSO analysis and SVM analysis, which had a satisfied ability to differentiate AR and NAR in the training cohort, internal validation cohort and external validation cohort. Additionally, ZNF683 was associated with graft survival. CONCLUSION: A 5 gene signature, particularly ZNF683, provided insight into a precise therapeutic schedule and clinical applications for AR patients.