Integrated single-cell and spatial mapping coupled with machine learning unveils core stemness landscapes and regulatory drivers in triple-negative breast cancer - PubMed
4 hours ago
- #Machine learning
- #Triple-negative breast cancer
- #Cancer stem cells
- Integrated single-cell RNA sequencing (scRNA-seq), spatial transcriptomics, and bulk transcriptomic data to study triple-negative breast cancer (TNBC).
- Identified high-stemness cell populations using inferCNV and CytoTRACE algorithms.
- Constructed an XGBoost-based risk prediction model with five core stemness-related genes (CALD1, ANP32B, FIS1, CD82, APLP2).
- High-stemness score group showed poorer prognosis and enhanced immune evasion.
- Trajectory analysis revealed high-stemness subpopulation at the initiation stage of differentiation.
- Notch signaling was highly active in enrichment analyses.
- Virtual knockdown of hub genes suppressed stemness markers like NOTCH1.
- Drug sensitivity analysis identified BI.2536 and related compounds as effective for high-risk group.
- Core genes serve as potential molecular targets for personalized TNBC therapies.