Machine learning unveils immune-related signature in multicenter glioma studies

• DOI: 10.1016/j.isci.2024.109317
• Publication Date: 2024-02-23T18:05:22Z
• Authors: Sha Yang; Xiang Wang; Renzheng Huan; Mei Deng; Zhuo Kong; Yunbiao Xiong; Tao Luo; Zheng Jin; Jian Liu; Liangzhao Chu; Guoqiang Han; Jiqin Zhang; Ying Tan
• Keywords: Subtyping; Clinical Significance; Gene signature; Signature (topology)

In glioma molecular subtyping, existing biomarkers are limited, prompting the development of new ones. We present a multicenter study-derived consensus immune-related and prognostic gene signature (CIPS) using an optimal risk score model 101 algorithms. CIPS, independent factor, showed stable powerful predictive performance for overall progression-free survival, surpassing traditional clinical variables. The correlated significantly with immune microenvironment, indicating potential sensitivity to immunotherapy. High-risk groups exhibited distinct chemotherapy drug sensitivity. Seven genes, including IGFBP2 TNFRSF12A, were validated by qRT-PCR, higher expression in tumors relevance. upregulated GBM, demonstrated inhibitory effects on cell proliferation, migration, invasion. CIPS emerges as robust tool enhancing individual patient outcomes, while TNFRSF12A pose promising tumor markers therapeutic targets.