Machine Learning Unveils Sphingolipid Metabolism's Role in Tumour Microenvironment and Immunotherapy in Lung Cancer DOI Creative Commons
Lili Xu, Jianchun Wu, Jianhui Tian

et al.

Journal of Cellular and Molecular Medicine, Journal Year: 2025, Volume and Issue: 29(7)

Published: March 30, 2025

ABSTRACT TME is a core player in the development of cancerous lesion, immune evasive potential and its response to therapy. Sphingolipid metabolism, which governs number cellular processes, has been recognised as involved control heterogeneity within TME. metabolism‐related genes prevalent LUAD LUSC were identified using transcriptomic analysis clinical samples from TCGA GTEx databases. Lasso regression survival SVM Etra Application employed machine learning algorithms determine patient outcomes reveal key factors associated with gene expression chemotherapeutic response. Gene lung cancer cells was explored through scRNA‐seq data. Thereafter, mediation impact further performed explain defined relation between cell subsets sphingolipid metabolites their risk on cancers. Genes metabolism dysregulated cancer, correlating infiltration remodelling. ASAH1 SMPD1 strong prognostic markers. revealed higher T cells, macrophages fibroblasts. Sphingomyelin partially mediated link lymphocyte abundance risk. High‐risk phenotypes exhibited enhanced evasion via altered regulatory macrophage polarisation. This research highlights contribution shaping implications for immunotherapy.

Language: Английский

Machine Learning Unveils Sphingolipid Metabolism's Role in Tumour Microenvironment and Immunotherapy in Lung Cancer DOI Creative Commons
Lili Xu, Jianchun Wu, Jianhui Tian

et al.

Journal of Cellular and Molecular Medicine, Journal Year: 2025, Volume and Issue: 29(7)

Published: March 30, 2025

ABSTRACT TME is a core player in the development of cancerous lesion, immune evasive potential and its response to therapy. Sphingolipid metabolism, which governs number cellular processes, has been recognised as involved control heterogeneity within TME. metabolism‐related genes prevalent LUAD LUSC were identified using transcriptomic analysis clinical samples from TCGA GTEx databases. Lasso regression survival SVM Etra Application employed machine learning algorithms determine patient outcomes reveal key factors associated with gene expression chemotherapeutic response. Gene lung cancer cells was explored through scRNA‐seq data. Thereafter, mediation impact further performed explain defined relation between cell subsets sphingolipid metabolites their risk on cancers. Genes metabolism dysregulated cancer, correlating infiltration remodelling. ASAH1 SMPD1 strong prognostic markers. revealed higher T cells, macrophages fibroblasts. Sphingomyelin partially mediated link lymphocyte abundance risk. High‐risk phenotypes exhibited enhanced evasion via altered regulatory macrophage polarisation. This research highlights contribution shaping implications for immunotherapy.

Language: Английский

Citations

0