Research Paper Volume 16, Issue 2 pp 1860—1878
The integration of multi-omics analysis and machine learning for the identification of prognostic assessment and immunotherapy efficacy through aging-associated genes in lung cancer
- 1 Department of Respiratory, General Hospital of Northern Theater Command, Shenyang, China
- 2 Department of Respiratory, Wuhu Hospital, East China Normal University, The Second People’s Hospital of Wuhu, Wuhu, Anhui, China
Received: August 29, 2023 Accepted: December 4, 2023 Published: January 22, 2024
https://doi.org/10.18632/aging.205464How to Cite
Copyright: © 2024 Lu et al. This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Abstract
Background: Recent years revealed key molecules in lung cancer research, yet their exact roles in disease onset and progression remain uncertain. Lung cancer’s heterogeneity complicates prognosis prediction. This study integrates pivotal molecules to evaluate patient prognosis and immunotherapy efficacy.
Methods: The WGCNA algorithm identified module genes linked to immunity. The Lasso-Cox method built a prognostic model for outcome prediction. GO and KEGG analyses explored gene pathways. ssGSEA quantified immune cell types and functions. The riskScore predicts the effectiveness of immunotherapy based on its correlation with DNA repair and immune checkpoint genes. Single-cell sequencing examined key gene expression across cell types.
Results: Using WGCNA, we identified the MEbrown module related to immunity. Lasso-Cox selected “BLK,” “ITGB4,” “PRKCH,” and “SNAI1” for the prognostic model. MF analysis revealed enriched functions including antigen binding, GTPase regulator activity. In terms of BP, processes like immune signaling and mitotic division were enriched. CC enrichment included immunoglobulin complexes and chromosomal regions. Enriched pathways encompassed Cell cycle, Focal adhesion, Cellular senescence, and p53 signaling. ssGSEA evaluated immune cell abundance. RiskScore correlated with CTLA4 and PD1 through MMR and immune checkpoint analysis. Single-cell analysis indicated gene expression across cell types for BLK, ITGB4, PRKCH, and SNAI1.
Conclusion: In summary, our developed prognostic model utilizing age-related genes effectively predicts lung cancer prognosis and the efficacy of immune therapy.