SenChronoAge#

Index#

  1. Instantiate model class

  2. Define clock metadata

  3. Download clock dependencies

  4. Load features

  5. Load weights into base model

  6. Load reference values

  7. Load preprocess and postprocess objects

  8. Check all clock parameters

  9. Basic test

  10. Save torch model

  11. Clear directory

Let’s first import some packages:

[1]:

import os
import inspect
import shutil
import json
import torch
import pandas as pd
import pyaging as pya

Instantiate model class#

[2]:

def print_entire_class(cls):
    source = inspect.getsource(cls)
    print(source)

print_entire_class(pya.models.SenChronoAge)

class SenChronoAge(LinearReferenceClock):
    pass


[3]:

model = pya.models.SenChronoAge()

Define clock metadata#

[4]:

model.metadata["clock_name"] = 'senchronoage'
model.metadata["data_type"] = 'methylation'
model.metadata["species"] = 'Homo sapiens'
model.metadata["year"] = 2026
model.metadata["approved_by_author"] = '⌛'
model.metadata["citation"] = "Kasamoto, Kotaro, et al. \"DNA methylation clocks for estimating replicative senescence in human cells.\" Aging Cell (2026): e70430."
model.metadata["doi"] = "https://doi.org/10.1111/acel.70430"
model.metadata["research_only"] = None
model.metadata["notes"] = "Senescence-enriched DNA-methylation clock that estimates chronological age from a methylome subset prioritized for association with cellular senescence. It is one of a family of senescence-focused clocks whose age signal was not reversed by senolytic treatment in vitro, in mice, or in human trials."
model.metadata["tissue"] = 'whole blood (age-predictor training) with senescence/age/mortality-concordant CpGs selected using cultured human cell senescence datasets (fibroblasts, MSCs, epithelial cells)'
model.metadata["predicts"] = 'chronological age (senescence-enriched age predictor)'
model.metadata["unit"] = 'years'
model.metadata["model_type"] = 'Elastic net'
model.metadata["platform"] = 'Illumina 450K/EPIC'
model.metadata["population"] = 'adults'
model.metadata["journal"] = 'Aging Cell'
model.metadata["last_author"] = 'Albert T Higgins-Chen'
model.metadata["n_features"] = 187
model.metadata["citations"] = 0
model.metadata["citations_date"] = '2026-07-05'

Download clock dependencies#

[5]:

os.system(f"curl -sL -o SenChronoAge_CpGs.csv https://raw.githubusercontent.com/HigginsChenLab/methylCIPHER/19b12296b0d7eb7055a97d068064df635f44ce3e/data-raw/SenescenceAge/SenChronoAge_CpGs.csv")

[5]:

0

Load features#

[6]:

coef_df = pd.read_csv('SenChronoAge_CpGs.csv')
model.features = coef_df['CpG'].tolist()

Load weights into base model#

[7]:

weights = torch.tensor(coef_df['Coefficient'].tolist()).unsqueeze(0).float()
intercept = torch.tensor([-80.0532]).float()

[8]:

base_model = pya.models.LinearModel(input_dim=len(model.features))

base_model.linear.weight.data = weights.float()
base_model.linear.bias.data = intercept.float()

model.base_model = base_model

Load reference values#

[9]:

model.reference_values = None

Load preprocess and postprocess objects#

[10]:

model.preprocess_name = None
model.preprocess_dependencies = None

[11]:

model.postprocess_name = None
model.postprocess_dependencies = None

Check all clock parameters#

[12]:

pya.utils.print_model_details(model)


%==================================== Model Details ====================================%
Model Attributes:

training: True
metadata: {'approved_by_author': '⌛',
 'citation': 'Kasamoto, Kotaro, et al. "DNA methylation clocks for estimating '
             'replicative senescence in human cells." Aging Cell (2026): '
             'e70430.',
 'clock_name': 'senchronoage',
 'data_type': 'methylation',
 'doi': 'https://doi.org/10.1111/acel.70430',
 'notes': None,
 'research_only': None,
 'species': 'Homo sapiens',
 'version': None,
 'year': 2026}
reference_values: None
preprocess_name: None
preprocess_dependencies: None
postprocess_name: None
postprocess_dependencies: None
features: ['cg00210473', 'cg00254017', 'cg00296652', 'cg00602326', 'cg00922748', 'cg00964103', 'cg01013171', 'cg01079407', 'cg01141812', 'cg01196788', 'cg01249187', 'cg01263575', 'cg01302656', 'cg01654770', 'cg01675158', 'cg01769968', 'cg01987776', 'cg02716556', 'cg02796545', 'cg03649284', 'cg03660134', 'cg04094193', 'cg04270048', 'cg04432128', 'cg04503600', 'cg04597312', 'cg04840739', 'cg04912316', 'cg05530568', 'cg05818515']... [Total elements: 187]
base_model_features: None

%==================================== Model Details ====================================%
Model Structure:

base_model: LinearModel(
  (linear): Linear(in_features=187, out_features=1, bias=True)
)

%==================================== Model Details ====================================%
Model Parameters and Weights:

base_model.linear.weight: [9.502220153808594, -10.09235954284668, -7.13555383682251, 7.0440497398376465, 0.07385352998971939, 4.94988489151001, 3.2296602725982666, -0.23233868181705475, 13.087000846862793, 6.111741065979004, 3.240180492401123, -5.130921840667725, 5.639341354370117, 4.501803398132324, 0.6832999587059021, -0.25918036699295044, 4.322950839996338, 18.638635635375977, 3.3074159622192383, 5.428537845611572, -0.6449773907661438, 5.176876068115234, 1.967892050743103, 5.64846658706665, -0.2769940495491028, 3.7448530197143555, 7.980226039886475, 3.951530694961548, 12.726526260375977, -9.475204467773438]... [Tensor of shape torch.Size([1, 187])]
base_model.linear.bias: tensor([-80.0532])

%==================================== Model Details ====================================%

Basic test#

[13]:

torch.manual_seed(42)
input = torch.randn(10, len(model.features), dtype=float)
model.eval()
model.to(float)
pred = model(input)
pred

[13]:

tensor([[ -54.5464],
        [-218.2588],
        [ 143.5234],
        [-101.8496],
        [-296.5361],
        [-180.5059],
        [-193.5961],
        [-180.5310],
        [ -16.9680],
        [  65.8968]], dtype=torch.float64, grad_fn=<AddmmBackward0>)

Save torch model#

[14]:

torch.save(model, f"../weights/{model.metadata['clock_name']}.pt")

Clear directory#

[15]:

# Function to remove a folder and all its contents
def remove_folder(path):
    try:
        shutil.rmtree(path)
        print(f"Deleted folder: {path}")
    except Exception as e:
        print(f"Error deleting folder {path}: {e}")

# Get a list of all files and folders in the current directory
all_items = os.listdir('.')

# Loop through the items
for item in all_items:
    # Check if it's a file and does not end with .ipynb
    if os.path.isfile(item) and not item.endswith('.ipynb'):
        os.remove(item)
        print(f"Deleted file: {item}")
    # Check if it's a folder
    elif os.path.isdir(item):
        remove_folder(item)

Deleted file: SenChronoAge_CpGs.csv