Objective To identify disulfidptosis-related gene(DRG)in acute myocardial infarction(AMI)by bioinformatics,analyze the molecular pattern of DRGs in AMI,and construct a DRGs-related prediction model.Methods AMI-related datasets were downloaded from the Gene Expression Omnibus database,and DRGs with differential expression were screened in AMI.CIBERSORT method was used to analyze the immune infiltration.Based on the differentially expressed DRGs,the AMI patients were classified into distinct subtypes via consensus clustering,followed by immune infiltration analysis,differential expression analysis,gene ontology and Kyoto encyclopedia of genes and genomes enrichment analysis,and gene set variation analysis.Weighted gene co-expression network analysis(WGCNA)was then performed to construct subtype-associated modules and identify hub genes.Finally,least absolute shrinkage and selection operator,random forest,and support vector machine-recursive feature elimination were used to screen feature genes to construct a DRGs-related prediction model.The model’s diagnostic efficacy was evaluated by nomogram and receiver operating characteristic(ROC)curve analysis,followed by external validation.Results Nine differentially expressed DRGs were identified between AMI patients and controls.Based on the expression levels of these nine DRGs,AMI patients were divided into two DRGs subtypes,C1 and C2.Increased infiltration of monocytes,M0 macrophages,and neutrophils was observed in AMI patients and C1 subtype(all P<0.05),indicating a close correlation between DRGs and immune cells.There were 257 differentially expressed genes between the C1 and C2 subtypes,which were related to biological processes such as myeloid leukocyte activation and positive regulation of cytokines.Fcγ receptor-mediated phagocytosis and NOD-like receptor signaling pathway activity were enhanced in C1 subtype.WGCNA analysis suggested that the brown module exhibited the strongest correlation with DRG subtypes(r=0.67),from which 23 differentially expressed genes were identified.The feature genes screened by three machine learning methods were interpolated to obtain a DRGs-related prediction model consisting of three genes(AQP9,F5 and PYGL).Nomogram and ROC curves(AUC_train=0.891,AUC_test=0.840)showed good diagnostic efficacy.Conclusions DRGs were closely related to the occurrence and progression of AMI.The DRGs-related prediction model consisting of AQP9,F5 and PYGL may provide targets for the diagnosis and personalized treatment of AMI.