Integrating WGCNA and machine learning algorithm to identify ACSM5 as a prognostic biomarker and therapeutic target for predicting immunotherapy efficacy in non-small cell lung cancer

Background: Lung cancer has a high incidence rate, and immunotherapy is only effective for a subset of patients. This study aimed to develop a signature associated with immunotherapy response to accurately predict the prognosis of non-small cell lung cancer (NSCLC) patients and assess immunotherapy efficacy. Such efforts are crucial to address the therapeutic challenges faced by patients with advanced lung cancer. Methods: Using weighted gene co-expression network analysis (WGCNA), we identified genes correlated with immunotherapy response. These genes were subsequently integrated with the data from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) to formulate prognostic signatures. A total of 101 machine learning algorithms were employed to construct these prognostic signatures. Following this, we conducted an in-depth analysis of the prognostic signatures and investigated their associations with patient prognosis, tumor microenvironment (TME), and the efficacy of chemotherapeutic agents, targeted therapies, and immunotherapy. Results: The constructed signature demonstrated a significant disparity in prognosis between high-risk and low-risk NSCLC patient groups. The prognostic capability of this signature was rigorously validated across various clinical subgroups and TCGA cohorts, and it emerged as an independent prognostic factor through multivariable analysis. To augment the precision of prognostic predictions, we developed a nomogram. Notably, the immune checkpoint inhibitor response prediction scores (IPS) were elevated in the low-risk group, indicating a potential benefit of immunotherapy for these patients. Quantitative reverse transcription polymerase chain reaction (qRT-PCR) was used to determine the expression levels of key risk-associated genes in the tissue samples, leading to the identification of Acyl-CoA synthetase medium chain family member 5 (ACSM5) as a promising therapeutic target in NSCLC. Conclusions: Our signature, which is linked to immunotherapy response, aids in predicting the prognosis and immunotherapy outcomes of NSCLC patients, thereby offering valuable insights for their clinical management.