{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["16"],"submitter":["Zhang H"],"pubmed_abstract":["<h4>Background</h4>Lumbar disc degeneration, a primary cause of chronic low back pain, is closely linked to inflammatory responses and the immune microenvironment; however, its underlying mechanisms remain poorly understood.<h4>Methods</h4>This study integrated scRNA-seq and bulk RNA-seq data to identify macrophage subpopulations in degenerative tissues and constructed co-expression modules using hdWGCNA. Functional enrichment was explored through GO, KEGG, and GSEA analyses. A panel of 101 machine learning algorithms was employed to screen diagnostic genes, with ROC curves used for validation. A combined diagnostic model for LDD risk was developed based on the expression profiles of the diagnostic genes. Additionally, immune infiltration was assessed via CIBERSORT, potential therapeutic c"],"journal":["Frontiers in immunology"],"pagination":["1671961"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12705385"],"repository":["biostudies-literature"],"pubmed_title":["Integration of single-cell sequencing and machine learning identifies key macrophage-associated genetic signatures in lumbar disc degeneration."],"pmcid":["PMC12705385"],"pubmed_authors":["Gao M","Zhu J","Dai B","Li D","Zhang H","Xiang X","Peng J"],"additional_accession":[]},"is_claimable":false,"name":"Integration of single-cell sequencing and machine learning identifies key macrophage-associated genetic signatures in lumbar disc degeneration.","description":"<h4>Background</h4>Lumbar disc degeneration, a primary cause of chronic low back pain, is closely linked to inflammatory responses and the immune microenvironment; however, its underlying mechanisms remain poorly understood.<h4>Methods</h4>This study integrated scRNA-seq and bulk RNA-seq data to identify macrophage subpopulations in degenerative tissues and constructed co-expression modules using hdWGCNA. Functional enrichment was explored through GO, KEGG, and GSEA analyses. A panel of 101 machine learning algorithms was employed to screen diagnostic genes, with ROC curves used for validation. A combined diagnostic model for LDD risk was developed based on the expression profiles of the diagnostic genes. Additionally, immune infiltration was assessed via CIBERSORT, potential therapeutic c","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025","modification":"2026-06-06T04:02:53.666Z","creation":"2026-05-25T03:12:11.81Z"},"accession":"S-EPMC12705385","cross_references":{"pubmed":["41409278"],"doi":["10.3389/fimmu.2025.1671961"]}}