The accumulation of senescent cells is increasingly recognized as a hallmark of biological aging, correlating with the onset of various chronic medical conditions. These senescent cells exhibit a unique secretory profile known as the senescence-associated secretory phenotype (SASP), which can influence neighboring and distant tissues. This study, published in Aging Cell, investigates a deep-learning based biomarker, termed the SASP Score, that aims to quantify systemic cellular senescence burden and its association with health outcomes.
What this study does not show
While the study identifies the SASP Score as a predictor of mortality and chronic conditions, it does not establish direct causal relationships or the effectiveness of interventions based on the score.
The researchers developed and validated the SASP Score by integrating large-scale population proteomics data with a semi-supervised deep learning framework. The analytical workflow involved several key steps:
- Selection of biologically curated SASP proteins.
- Development of a Guided autoencoder with Transformer (GAET) model using data from the UK Biobank Pharma Proteomics Project (UKB-PPP).
- Internal evaluation and association analyses within the UK Biobank.
- External validation and longitudinal assessment in an independent randomized clinical trial cohort.
The findings indicate that the deep learning-derived SASP Score serves as a strong, independent predictor of mortality risk and the incidence of serious chronic medical conditions, including dementia, chronic obstructive pulmonary disease (COPD), myocardial infarction, and stroke. Furthermore, in an independent cohort, multimodal exercise was shown to significantly alter the trajectory of the SASP Score over an 18-month period.
This research highlights the potential of the SASP Score as a biomarker for systemic cellular senescence burden, suggesting that it could be a valuable tool for aging research and the evaluation of geroscience-guided interventions. The study’s statistical approach offers enhanced interpretability and cross-platform utility, which may facilitate future research in this area.
Evidence scorecard
- Analytic validity: established
- Clinical validity: partial
- Clinical utility: partial
The evidence is based on primary research involving human subjects.