Development and validation of an interpretable machine learning model identify the lactylation-related protein SUSD3 as a prognostic and therapeutic biomarker for breast cancer - PubMed
3 months ago
- #breast cancer
- #lactylation
- #machine learning
- Development of an interpretable machine learning model to identify lactylation-related protein SUSD3 as a biomarker for breast cancer.
- Lactylation, a post-translational modification, is linked to cancer progression and immune modulation, but its exact role in tumorigenesis is unclear.
- Study utilized genomic datasets including single-cell RNA sequencing, bulk transcriptomic data, and spatial transcriptomics from public databases.
- A lactylation-related signature was developed using machine learning, correlating with immune cell infiltration, chemokine expression, and tumor mutation burden.
- The signature helps identify breast cancer patients likely to respond to immunotherapy.
- Experimental validation confirmed the role of SUSD3 in human breast samples.
- The lactylation risk model predicts malignant progression and immune evasion in breast cancer, offering potential as a therapeutic target and diagnostic marker.
- The model provides a framework for gene screening applicable to other diseases and pathogenic mechanisms.