Machine learning models reveal ARHGAP11A's impact on lymph node metastasis and stemness in NSCLC

Abstract

Most patients with non-small cell lung cancer (NSCLC) are diagnosed at an advanced stage of the disease, which complicates treatment due to a heightened risk of metastasis. Consequently, the timely identification of biomarkers associated with lymph node metastasis is essential for improving the clinical management of NSCLC patients. In this research, the WGCNA algorithm was utilized to pinpoint genes linked to lymph node metastasis in NSCLC. A cluster analysis was carried out to investigate how these genes correlate with the prognosis and the outcomes of immunotherapy for NSCLC patients. Following this, diagnostic and prognostic models were created and validated through various machine learning methodologies. The random forest technique highlighted the importance of ARHGAP11A, leading to an in-depth examination of its role in NSCLC. By analyzing 78 tissue chip samples from NSCLC patients, the study confirmed the association between ARHGAP11A expression, patient prognosis, and lymph node metastasis. Finally, the influence of ARHGAP11A on NSCLC cells was assessed through cell function experiments. This research utilized the WGCNA technique to identify 25 genes that are related to lymph node metastasis, clarifying their connections with tumor invasion, growth, and the activation of stemness pathways. Cluster analysis revealed significant associations between these genes and lymph node metastasis in NSCLC, especially concerning immunotherapy and targeted treatments. A diagnostic system that combines various machine learning approaches demonstrated strong efficacy in forecasting both the diagnosis and prognosis of NSCLC. Importantly, ARHGAP11A was identified as a key prognostic gene associated with lymph node metastasis in NSCLC. Molecular docking analyses suggested that ARHGAP11A has a strong affinity for targeted therapies within NSCLC. Additionally, immunohistochemical assessments confirmed that higher levels of ARHGAP11A expression correlate with unfavorable outcomes for NSCLC patients. Experiments on cells showed that reducing ARHGAP11A expression can hinder the proliferation, metastasis, and stemness traits of NSCLC cells. This investigation reveals the novel insight that ARHGAP11A may function as a potential biomarker connected to lymph node metastasis in NSCLC. Moreover, reducing the expression of ARHGAP11A has demonstrated the ability to diminish tumor stemness characteristics, presenting a promising opportunity for improving treatment strategies for this condition.

Keywords: NSCLC; immunotherapy; lymph node metastasis; machine learning; stemness.