Abstract
BACKGROUND: Lung adenocarcinoma (LUAD) is a highly heterogeneous cancer type with a poor prognosis. Accurate subtype identification can help guide its treatment. The traditional subtype identification methods using a single-omics approach make it difficult to comprehensively characterize the molecular features of LUAD. Identification of subtypes through multi-omics association strategies can effectively supplement the shortcomings of single-omics information. METHODS: In this study, we used the Generative Adversarial Network (GAN) to mine transcriptomic, proteomic, and epigenomic information and generate an integrated data set. The newly integrated data were then used to identify LUAD immune subtypes. In the improved GAN (MOGAN) method, we not only integrated multiple omics datasets but also included the interactions between proteins and genes and between methylation and genes. Thus, we achieved effective complementarity of multi-omics information. RESULTS: Two subtypes, MOGANTPM_S1 and MOGANTPM_S2, were identified using immune cell infiltration analysis and the integrated multi-omics data. MOGANTPM_S1 patients displayed higher immune cell infiltration, better prognosis, and sensitivity to immune checkpoint inhibitors (ICIs), while MOGANTPM_S2 had lower immune cell infiltration, poorer prognosis, and were insensitive to ICIs. Therefore, immunotherapy was more suitable for MOGANTPM_S1 patients in clinical practice. In addition, this study developed a LUAD subtype diagnostic model using the transcriptomic and proteomic features of five genes, which can be used to guide clinical subtype diagnosis. CONCLUSIONS: In summary, the MOGAN method was applied to integrate three omics data types and successfully identify two LUAD immune subtypes with significant survival differences. This classification method may be useful for LUAD treatment decisions.