CellPopAge#

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.CellPopAge)

class CellPopAge(LinearReferenceClock):
    pass


[3]:

model = pya.models.CellPopAge()

Define clock metadata#

[4]:

model.metadata["clock_name"] = "cellpopage"
model.metadata["data_type"] = "DNA methylation"  # Paper: The model is based on DNA methylation measurements.
model.metadata["species"] = "Homo sapiens"  # Paper: The study samples are Homo sapiens.
model.metadata["year"] = 2024
model.metadata["approved_by_author"] = "⌛"
model.metadata["citation"] = "Lujan, Celia, et al. \"An expedited screening platform for the discovery of anti-ageing compounds in vitro and in vivo.\" Genome Medicine 16 (2024): 85."
model.metadata["doi"] = "https://doi.org/10.1186/s13073-024-01349-w"
model.metadata["notes"] = "CellPopAge is an elastic-net DNA-methylation clock using 42 selected CpGs to predict passage-based age of serially cultured adult primary human fibroblast populations and screen compounds that decelerate this measure."
model.metadata["research_only"] = None
model.metadata["tissue"] = ["cultured fibroblasts"]  # Paper: The listed tissue is the model-development sample material.
model.metadata["predicts"] = ["cell-population passage age"]  # Paper: The reported predictor output is cell-population passage age.
model.metadata["training_target"] = ["cell passage number"]  # Paper: The fitting outcome is cell passage number.
model.metadata["unit"] = ["passages"]  # Paper: The returned construct is expressed as cell passage number.
model.metadata["model_type"] = "elastic net regression"  # Paper: The clock was fitted using Elastic net.
model.metadata["platform"] = ["Illumina EPIC"]  # Paper: Training/selection used Illumina EPIC.
model.metadata["population"] = "human cell cultures"  # Paper: adult primary human fibroblast cultures (39 training samples, passages 10–20)
model.metadata["journal"] = "Genome Medicine"
model.metadata["last_author"] = "Ivana Bjedov"
model.metadata["n_features"] = 42
model.metadata["citations"] = 6
model.metadata["citations_date"] = "2026-07-05"

Download clock dependencies#

[5]:

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

[5]:

0

[6]:

%%writefile download.r

library(jsonlite)
load("CellPopAge_ref.rda")
write_json(CellPopAge_ref$all_CpGs, "coefficients.json", digits = 10)
write_json(CellPopAge_ref$intercept, "intercept.json", digits = 10)

Writing download.r

[7]:

os.system("Rscript download.r")

[7]:

0

Load features#

[8]:

coef_df = pd.DataFrame(json.load(open('coefficients.json')))
model.features = coef_df['CpG'].tolist()
iv = json.load(open('intercept.json'))
intercept_value = iv[0] if isinstance(iv, list) else iv

Load weights into base model#

[9]:

weights = torch.tensor(coef_df['coefficient'].tolist()).unsqueeze(0).float()
intercept = torch.tensor([intercept_value]).float()

[10]:

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#

[11]:

model.reference_values = None

Load preprocess and postprocess objects#

[12]:

model.preprocess_name = None
model.preprocess_dependencies = None

[13]:

model.postprocess_name = None
model.postprocess_dependencies = None

Check all clock parameters#

[14]:

pya.utils.print_model_details(model)


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

training: True
metadata: {'approved_by_author': '⌛',
 'citation': 'Lujan, Gabriel M., et al. "A DNA methylation clock to measure '
             'the epigenetic age of cell populations." Genome Medicine 16 '
             '(2024).',
 'clock_name': 'cellpopage',
 'data_type': 'methylation',
 'doi': 'https://doi.org/10.1186/s13073-024-01349-w',
 'notes': None,
 'research_only': None,
 'species': 'Homo sapiens',
 'version': None,
 'year': 2024}
reference_values: None
preprocess_name: None
preprocess_dependencies: None
postprocess_name: None
postprocess_dependencies: None
features: ['cg03662648', 'cg07230471', 'cg09689790', 'cg00283934', 'cg27617964', 'cg21734265', 'cg21184340', 'cg17342766', 'cg00312508', 'cg08907118', 'cg12071423', 'cg16622870', 'cg08126590', 'cg04121501', 'cg18571156', 'cg22900075', 'cg26475539', 'cg27500194', 'cg09992376', 'cg26450896', 'cg06863239', 'cg25651783', 'cg08461941', 'cg11738198', 'cg23407476', 'cg01159380', 'cg05369308', 'cg27537795', 'cg15563081', 'cg19920898']... [Total elements: 2543]
base_model_features: None

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

base_model: LinearModel(
  (linear): Linear(in_features=2543, out_features=1, bias=True)
)

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

base_model.linear.weight: [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.5474669337272644, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]... [Tensor of shape torch.Size([1, 2543])]
base_model.linear.bias: tensor([11.5268])

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

Basic test#

[15]:

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

[15]:

tensor([[ 8.1066],
        [21.9362],
        [13.3644],
        [31.7122],
        [30.1219],
        [-3.8962],
        [ 9.8756],
        [-2.5270],
        [ 2.6161],
        [ 9.8903]], dtype=torch.float64, grad_fn=<AddmmBackward0>)

Save torch model#

[16]:

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

Clear directory#

[17]:

# 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: intercept.json
Deleted file: download.r
Deleted file: coefficients.json
Deleted file: CellPopAge_ref.rda