Objective：This study investigated the expression of mitochondrial autophagy - related genes（MRG）in asthma to establish a novel model for disease prediction，and also identified asthma subtypes based on the MRG to figure out the potential molecular targeted drugs. Methods：The data of asthmatic airway samples were obtained from gene expression omnibus data base. Differentially expressed MRGs were screened and validated in asthmatic mice or primary airway epithelial cells challenged by interleukin（IL）- 13 with immunohistochemistry so as to build a model for disease prediction using machine learning algorithms. According to the different MRG expression pattern，two subtypes of asthma were defined，and biological functions and signaling pathways were investigated by gene ontology（GO）and kyoto encyclopedia of genes and genomes（KEGG）analysis to find out the potential agents through a connectivity map database. Results：MRG expression in asthma patients was significantly increased compared with those in healthy subjects. Among these genes，translocase of outer mitochondrial membrane 5（TOMM5）was found to be the top differentially expressed MRG，which were up-regulated both in the airway epithelium of asthma patients or asthmatic mice and the primary airway epithelial cells stimulated by IL-13. In 22 MRGs，seven genes[TOMM5，FUN14 domain containing 1，translocase of outer mitochondrial membrane 22，sequestosome 1，phosphoglycerate mutase 5，mitofusin-2，ribosomal protein S27a]were screened to establish a model for disease prediction for its good performance exhibited by a receiver operating characteristic curve assessment in asthma. Through a consensus cluster analysis，two subtypes of asthma were classified considering the differences of gene expression and pathway enrichment. The predicted small molecule agents targeting these two subtypes were XMD8 - 92 and Verrucarin - A，respectively. Conclusion：Seven MRGs were confirmed to be the effective molecular markers for asthma prediction，and our findings may provide valuable evidences and open a new insight for the development of individualized approaches for asthma management.