Integrating machine learning and multi-omics analysis to develop an asparagine metabolism immunity index for improving clinical outcome and drug sensitivity in lung adenocarcinoma.

Abstract

Lung adenocarcinoma (LUAD) is a malignancy affecting the respiratory system. Most patients are diagnosed with advanced or metastatic lung cancer due to the fact that most of their clinical symptoms are insidious, resulting in a bleak prognosis. Given that abnormal reprogramming of asparagine metabolism (AM) has emerged as an emerging therapeutic target for anti-tumor therapy. However, the clinical significance of abnormal reprogramming of AM in LUAD patients is unclear. In this study, we collected 864 asparagine metabolism-related genes (AMGs) and used a machine-learning computational framework to develop an asparagine metabolism immunity index (AMII) for LUAD patients. Through the utilization of median AMII scores, LUAD patients were segregated into either a low-AMII group or a high-AMII group. We observed outstanding performance of AMII in predicting survival prognosis in LUAD patients in the TCGA-LUAD cohort and in three externally independently validated GEO cohorts (GSE72094, GSE37745, and GSE30219), and poorer prognosis for LUAD patients in the high-AMII group. The results of univariate and multivariate analyses showed that AMII can be used as an independent risk factor for LUAD patients. In addition, the results of C-index analysis and decision analysis showed that AMII-based nomograms had a robust performance in terms of accuracy of prognostic prediction and net clinical benefit in patients with LUAD. Excitingly, LUAD patients in the low-AMII group were more sensitive to commonly used chemotherapeutic drugs. Consequently, AMII is expected to be a novel diagnostic tool for clinical classification, providing valuable insights for clinical decision-making and personalized management of LUAD patients.