---
library_name: pyaging
tags:
- pyaging
- aging-clock
- biology
- dna-methylation
---

# cpgptpcgrimage3

Principal-component CpGPTGrimAge3 implementation combining chronological age, GrimAge2 DNAm proxies, and CpGPT-predicted plasma-protein proxies; 30 proxy inputs are projected to 29 PCs, entered with age into a Cox linear predictor, and calibrated to years. Supply derived methylation protein/lifestyle proxies and age, not a raw CpG matrix or measured proteomics. CpGPT protein proxies come from the proteins checkpoint on its trained standardized scale; required proxies must be present.

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, mortality risk |
| **Species** | Homo sapiens |
| **Tissue** | whole blood |
| **Data type** | DNA methylation |
| **Model type** | PCA + Cox regression |
| **Year** | 2024 |

## Use with pyaging

```python
import pyaging as pya

pya.pred.predict_age(adata, ["cpgptpcgrimage3"])
```

Browse every clock in the [pyaging Clock Catalogue](https://pyaging.readthedocs.io).

## Citation

de Lima Camillo, L. P., Sehgal, R., Armstrong, J., et al. CpGPT: a foundation model for DNA methylation. bioRxiv 2024.10.24.619766 (2024).

https://doi.org/10.1101/2024.10.24.619766