pac
Mortality-equivalent proteomic age from the original Kuo et al. R release, using all 128 Olink Explore 3072 plasma protein NPX values plus chronological age in years. Supply original lowercase identifiers, including fut3_fut5 and ntprobnp; there is no sex covariate. NPX is assay-normalized log2 relative abundance, not raw counts, concentrations, linear abundances or z-scores. NPX labeling alone does not establish comparability across panels, batches, plasma and serum. No cohort scaling, normalization, or imputation is applied during scoring. Every predictor column is required; supplied NaNs propagate. The paper used k-nearest-neighbor imputation (k=10) before model fitting; any upstream imputation is a separate caller decision. The full-precision original Gompertz constants are retained, without the later Insilico wrapper's rounding or optional distribution matching. Output is mortality-equivalent age in years, not a clinical diagnosis or an age-acceleration residual. Development cohort: UK Biobank adults aged 39-70. The original repository specifies no code license; the publication is CC BY 4.0. No author approval of this conversion is claimed.
Model weights retain the original authors' terms; the pyaging software license does not relicense them. These weights are restricted to research use under the authors' terms.
| Predicts | biological age |
| Species | Homo sapiens |
| Tissue | plasma |
| Data type | proteomics |
| Model type | Gompertz proportional hazards model |
| Year | 2024 |
Use with pyaging
import pyaging as pya
pya.pred.predict_age(adata, ["pac"])
Browse every clock in the pyaging Clock Catalogue.
Citation
Kuo, C.-L., et al. "Proteomic aging clock (PAC) predicts age-related outcomes in middle-aged and older adults." Aging Cell 23, e14195 (2024).
- Downloads last month
- 26