A tumor-infiltrating B lymphocytes -related index based on machine-learning predicts prognosis and immunotherapy response in lung adenocarcinoma.

Introduction: Tumor-infiltrating B lymphocytes (TILBs) play a pivotal role in shaping the immune microenvironment of tumors (TIME) and in the progression of lung adenocarcinoma (LUAD). However, there remains a scarcity of research that has thoroughly and systematically delineated the characteristics of TILBs in LUAD. Method: The research employed single-cell RNA sequencing from the GSE117570 dataset to identify markers linked to TILBs. A comprehensive machine learning approach, utilizing ten distinct algorithms, facilitated the creation of a TILB-related index (BRI) across the TCGA, GSE31210, and GSE72094 datasets. We used multiple algorithms to evaluate the relationships between BRI and TIME, as well as immune therapy-related biomarkers. Additionally, we assessed the role of BRI in predicting immune therapy response in two datasets, GSE91061 and GSE126044. Result: BRI functioned as an independent risk determinant in LUAD, demonstrating a robust and reliable capacity to predict overall survival rates. We observed significant differences in the scores of B cells, M2 macrophages, NK cells, and regulatory T cells between the high and low BRI score groups. Notably, BRI was found to inversely correlate with cytotoxic CD8+ T-cell infiltration (r = -0.43, p < 0.001) and positively correlate with regulatory T cells (r = 0.31, p = 0.008). We also found that patients with lower BRI were more likely to respond to immunotherapy and were associated with reduced IC50 values for standard chemotherapy and targeted therapy drugs, in contrast to higher BRI. Additionally, the BRI-based survival prediction nomogram demonstrated significant promise for clinical application in predicting the 1-, 3-, and 5-year overall survival rates among LUAD patients. Discussion: Our study developed a BRI model using ten different algorithms and 101 algorithm combinations. The BRI could be a valuable tool for risk stratification, prognosis, and selection of treatment approaches.