Sync celldrift
Browse files- README.md +39 -0
- celldrift.provenance.json +16 -0
- celldrift.pt +3 -0
- config.json +36 -0
README.md
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: pyaging
|
| 3 |
+
tags:
|
| 4 |
+
- pyaging
|
| 5 |
+
- aging-clock
|
| 6 |
+
- biology
|
| 7 |
+
- dna-methylation
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# celldrift
|
| 11 |
+
|
| 12 |
+
Replication signature trained on 31 serially passaged hTERT-immortalized human astrocyte samples. The released 62-PC elastic-net predictor over 2,322 CpGs is folded algebraically into a single linear score. Output is calibrated to cumulative population doublings, not years. Original-author missingness is preserved: supplied NaNs become zero, whereas absent CpGs use module means. GitHub commit 066b3e816795f3c0b372ff8d33f59185a490bd8b; DOI 10.5281/zenodo.7693699. Upstream software license is unspecified (Zenodo: Other (Open)).
|
| 13 |
+
|
| 14 |
+
Model weights retain the original authors' terms; the pyaging software license does not relicense them.
|
| 15 |
+
|
| 16 |
+
| | |
|
| 17 |
+
|---|---|
|
| 18 |
+
| **Predicts** | mitotic age |
|
| 19 |
+
| **Species** | Homo sapiens |
|
| 20 |
+
| **Tissue** | cultured human cells |
|
| 21 |
+
| **Data type** | DNA methylation |
|
| 22 |
+
| **Model type** | PCA + elastic net regression |
|
| 23 |
+
| **Year** | 2023 |
|
| 24 |
+
|
| 25 |
+
## Use with pyaging
|
| 26 |
+
|
| 27 |
+
```python
|
| 28 |
+
import pyaging as pya
|
| 29 |
+
|
| 30 |
+
pya.pred.predict_age(adata, ["celldrift"])
|
| 31 |
+
```
|
| 32 |
+
|
| 33 |
+
Browse every clock in the [pyaging Clock Catalogue](https://pyaging.readthedocs.io).
|
| 34 |
+
|
| 35 |
+
## Citation
|
| 36 |
+
|
| 37 |
+
Minteer, C. J., et al. (2023). More than bad luck: Cancer and aging are linked to replication-driven changes to the epigenome. Science Advances, 9(29), eadf4163.
|
| 38 |
+
|
| 39 |
+
https://doi.org/10.1126/sciadv.adf4163
|
celldrift.provenance.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"url": "https://github.com/MorganLevineLab/CellDRIFT",
|
| 3 |
+
"commit": "066b3e816795f3c0b372ff8d33f59185a490bd8b",
|
| 4 |
+
"sha256": {
|
| 5 |
+
"R/CellDRIFT.R": "6ee6af7dae221428823419cf7b78219cbf301a92f941adeda08bb6895c74bbaa",
|
| 6 |
+
"data/CV.CellDRIFT.rda": "4965aef078d809f5ea9ac6b43078e95422ed246bb867f2cf3e5101c24c3009e0",
|
| 7 |
+
"data/Fit.CellDRIFT.rda": "cabb4ffabbbb21ef61365a2c80fef0241c885ccb7dd9d91c5b0f94c0c9ea99a3",
|
| 8 |
+
"data/PCA_tan.rda": "70ec2fa10a536862372fc257d901ca8ea298d0bfd93ec9ed8e14a859348f676b",
|
| 9 |
+
"data/PCA_yellow.rda": "dc48b27642595d43a3d652ea452b02e1ce079ce724160370439da152d85d4448",
|
| 10 |
+
"data/exampleDNAm.rda": "a3651b09ea232a73aac771a65d6350f7d430eb1b3f9f891135c66682cfa404aa",
|
| 11 |
+
"data/tan_module_means.rda": "a85cacd677a377798412682a020a73f55f12133e7c33fbd8b730469682ebb173",
|
| 12 |
+
"data/yellow_module_means.rda": "5796b864adbea94dc5ffe85be388d3761d13243c2995b99a9d7052c6ecc748e2"
|
| 13 |
+
},
|
| 14 |
+
"lambda_min": 0.9280867766247382,
|
| 15 |
+
"license": "Unspecified in GitHub DESCRIPTION; Zenodo 7693699 lists Other (Open)."
|
| 16 |
+
}
|
celldrift.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1864639a5cee8ad78d5d5ae6b4ac614c75d50d1cf5420bc362548d9380d76ecb
|
| 3 |
+
size 103733
|
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"approved_by_author": "\u231b",
|
| 3 |
+
"citation": "Minteer, C. J., et al. (2023). More than bad luck: Cancer and aging are linked to replication-driven changes to the epigenome. Science Advances, 9(29), eadf4163.",
|
| 4 |
+
"citations": 29,
|
| 5 |
+
"citations_date": "2026-10-02",
|
| 6 |
+
"clock_name": "celldrift",
|
| 7 |
+
"data_type": "DNA methylation",
|
| 8 |
+
"doi": "https://doi.org/10.1126/sciadv.adf4163",
|
| 9 |
+
"journal": "Science Advances",
|
| 10 |
+
"last_author": "Morgan E. Levine",
|
| 11 |
+
"model_type": "PCA + elastic net regression",
|
| 12 |
+
"n_features": 2322,
|
| 13 |
+
"notes": "Replication signature trained on 31 serially passaged hTERT-immortalized human astrocyte samples. The released 62-PC elastic-net predictor over 2,322 CpGs is folded algebraically into a single linear score. Output is calibrated to cumulative population doublings, not years. Original-author missingness is preserved: supplied NaNs become zero, whereas absent CpGs use module means. GitHub commit 066b3e816795f3c0b372ff8d33f59185a490bd8b; DOI 10.5281/zenodo.7693699. Upstream software license is unspecified (Zenodo: Other (Open)).",
|
| 14 |
+
"platform": [
|
| 15 |
+
"Illumina EPIC"
|
| 16 |
+
],
|
| 17 |
+
"population": "human cell cultures",
|
| 18 |
+
"predicts": [
|
| 19 |
+
"mitotic age"
|
| 20 |
+
],
|
| 21 |
+
"preprocess": "supplied NaNs to zero; absent CpGs to module means",
|
| 22 |
+
"reference_values": true,
|
| 23 |
+
"research_only": null,
|
| 24 |
+
"species": "Homo sapiens",
|
| 25 |
+
"tissue": [
|
| 26 |
+
"cultured human cells"
|
| 27 |
+
],
|
| 28 |
+
"training_target": [
|
| 29 |
+
"population doublings"
|
| 30 |
+
],
|
| 31 |
+
"unit": [
|
| 32 |
+
"population doublings"
|
| 33 |
+
],
|
| 34 |
+
"version": "0.5.4",
|
| 35 |
+
"year": 2023
|
| 36 |
+
}
|