Background <p>Intervertebral disc degeneration (IVDD) has risen to become a global health problem, and its mechanisms are not well understood. The aim of this study was to use machine learning methods to identify key medullary senescence genes associated with IVDD and to further screen for potential biomarkers, as well as to explore the pathways by which these genes can be analyzed in both IVDD and normal states.</p> Methods <p>Gene expression profiles (GSE70362) of IVDD were analyzed from the extensive Gene Expression Omnibus database, and senescence-related genes (SRGs) were obtained from the cell age database. We utilized the Kyoto Encyclopedia of Genes (KEGG) and Gene Ontology (GO) databases for comprehensive functional enrichment analysis. To identify Hub SRDEGs with highly correlated IVDD features (Hub IVDD-SRDEGs), Weighted Gene Co-expression Network Analysis (WGCNA) and two machine learning methods (random forest, and support vector machine recursive feature elimination) were used. Finally, external validation was performed using quantitative polymerase chain reaction (qPCR) and Western blot experiment, and clinic samples validation was also performed using quantitative polymerase chain reaction (qPCR) experiment.</p> Results <p>We discovered 470 DEGs in normal and IVDD nucleus pulposus samples. According to functional enrichment, DEGs are primarily associated with positive regulation of transcription from RNA polymerase II promoter, canonical Wnt signaling pathway, mitotic spindle assembly, response to organic cyclic compound, and cardiac muscle cell apoptotic process. In vivo experiments (qPCR and WB) verified the expression of TAF13 protein. Subsequent qPCR of human nucleus pulposus tissue also showed the same trend of TAF13 gene expression. Hub IVDD-SRDEGs with excellent IVDD diagnostic ability were identified as TAF13.</p> Conclusions <p>Nucleus pulposus aging may promote the progression of IVDD. TAF13 can be used as a novel diagnostic biomolecular marker and for IVDD.</p>