The accumulation of senescent cells is increasingly recognized as a hallmark of biological aging, contributing to various chronic medical conditions. This study introduces a novel biomarker, the senescence-associated secretory phenotype (SASP) Score, developed through a deep-learning framework. The SASP Score aims to quantify the burden of cellular senescence and predict health outcomes.
What this study does not show
While the study presents a strong association between the SASP Score and health outcomes, it does not establish direct causation or clinical utility in a real-world setting.
The researchers utilized a comprehensive analytical workflow, beginning with the selection of biologically relevant SASP proteins. They employed a Guided autoencoder with Transformer (GAET) model, leveraging data from the UK Biobank Pharma Proteomics Project (UKB-PPP). This model was internally validated and assessed for associations within the UK Biobank dataset.
Furthermore, the SASP Score underwent external validation and longitudinal assessment in an independent randomized clinical trial cohort. The findings indicated that the deep learning-derived SASP Score was a robust, independent predictor of mortality risk and the onset of serious chronic medical conditions, including dementia, chronic obstructive pulmonary disease (COPD), myocardial infarction, and stroke.
Notably, the study also observed that multimodal exercise significantly altered the trajectory of the SASP Score over an 18-month period in an independent cohort, suggesting potential avenues for intervention.
This research highlights the potential of the SASP Score as a biomarker for systemic cellular senescence burden, offering insights into aging research and the evaluation of geroscience-guided interventions. The statistical methods employed provide enhanced interpretability and cross-platform utility, suggesting that the SASP Score could serve as a valuable tool in future studies.
Evidence scorecard
- Analytic validity: established
- Clinical validity: partial
- Clinical utility: not established
The evidence is based on primary research involving human participants.