epiTOC2#
Index#
Let’s first import some packages:
[30]:
import os
import inspect
import shutil
import json
import torch
import pandas as pd
import pyaging as pya
Instantiate model class#
[31]:
def print_entire_class(cls):
source = inspect.getsource(cls)
print(source)
print_entire_class(pya.models.epiTOC2)
class epiTOC2(pyagingModel):
def __init__(self):
super().__init__()
self.delta = None
self.beta0 = None
def preprocess(self, x):
"""
Replace NaNs with zero; missing features should already be imputed via reference_values.
"""
return torch.nan_to_num(x, nan=0.0)
def forward(self, x):
x = self.preprocess(x)
device = x.device
dtype = x.dtype
delta = self.delta.to(device=device, dtype=dtype)
beta0 = self.beta0.to(device=device, dtype=dtype)
denom = delta * (1 - beta0)
denom = torch.where(denom == 0, torch.ones_like(denom), denom)
contrib = (x - beta0) / denom
k = contrib.size(1)
vals = 2.0 * torch.sum(contrib, dim=1) / k
return self.postprocess(vals.unsqueeze(1))
def postprocess(self, x):
return x
[32]:
model = pya.models.epiTOC2()
Define clock metadata#
[33]:
model.metadata["clock_name"] = "epitoc2"
model.metadata["data_type"] = "DNA methylation" # Paper: The study constructs clocks from DNA methylation measurements.
model.metadata["species"] = "Homo sapiens" # Paper: The analyzed samples and clock are human.
model.metadata["year"] = 2020
model.metadata["approved_by_author"] = "⌛"
model.metadata["citation"] = "Teschendorff, Andrew E. \"A comparison of epigenetic mitotic-like clocks for cancer risk prediction.\" Genome Medicine 12 (2020): 56."
model.metadata["doi"] = "https://doi.org/10.1186/s13073-020-00752-3"
model.metadata["notes"] = "Dynamic methylation-transmission model returning total cumulative stem-cell divisions per stem cell; an intrinsic rate additionally requires chronological age but is not this implementation's returned value."
model.metadata["research_only"] = None
model.metadata["tissue"] = ["whole blood"] # Paper: Parameters were fitted in the Hannum whole-blood cohort.
model.metadata["predicts"] = ["mitotic age"] # Paper: The epiTOC2 estimate is total stem-cell divisions per stem cell.
model.metadata["training_target"] = ["chronological age"] # Paper: CpG dynamic-model parameters were fitted against age-associated methylation trajectories.
model.metadata["unit"] = ["cell divisions per stem cell"] # Paper: The model output is total stem-cell divisions per stem cell.
model.metadata["model_type"] = "dynamic methylation transmission model" # Paper: A dynamic model of methylation transmission with stem-cell divisions defines epiTOC2.
model.metadata["platform"] = ["Illumina 450K"] # Paper: The Hannum training cohort was measured on the Illumina 450K array.
model.metadata["population"] = "adults" # Paper: Model fitting used Hannum whole blood spanning ages 19 to 101.
model.metadata["journal"] = "Genome Medicine"
model.metadata["last_author"] = "Andrew E. Teschendorff"
model.metadata["n_features"] = 163
model.metadata["citations"] = 155
model.metadata["citations_date"] = "2026-07-05"
Download clock dependencies#
Download coefficient file#
[34]:
coeff_url = "https://raw.githubusercontent.com/bio-learn/biolearn/master/biolearn/data/EpiTOC2.csv"
os.system(f"curl -L {coeff_url} -o EpiTOC2.csv")
[34]:
0
Load features#
From Excel file#
[35]:
df = pd.read_csv('EpiTOC2.csv', index_col=0)
df['feature'] = df.index.astype(str)
model.features = df['feature'].tolist()
Load weights into base model#
[36]:
#### From CSV file
[37]:
model.delta = torch.tensor(df['delta'].values, dtype=torch.float32).unsqueeze(0)
model.beta0 = torch.tensor(df['beta0'].values, dtype=torch.float32).unsqueeze(0)
model.base_model = None
[38]:
#### Linear model
Not used; computation happens in the model forward#
[39]:
model.reference_values = [-1]*len(model.features)
model.reference_values = [0.0] * len(model.features)
[40]:
model.preprocess_name = "mean"
model.preprocess_dependencies = None
[41]:
model.preprocess_name = "nan_to_zero"
model.preprocess_dependencies = None
model.postprocess_name = None model.postprocess_dependencies = None
[42]:
pya.utils.print_model_details(model)
%==================================== Model Details ====================================%
Model Attributes:
training: True
metadata: {'approved_by_author': '⌛',
'citation': 'Teschendorff, Andrew E. "A comparison of epigenetic mitotic-like '
'clocks for cancer risk prediction." Genome Medicine 12.1 (2020): '
'56.',
'clock_name': 'epitoc2',
'data_type': 'methylation',
'doi': 'https://doi.org/10.1186/s13073-020-00752-3',
'notes': 'Stem cell division rate estimate using EpiTOC2.',
'research_only': None,
'species': 'Homo sapiens',
'version': None,
'year': 2020}
reference_values: [-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1]... [Total elements: 163]
preprocess_name: 'nan_to_zero'
preprocess_dependencies: None
postprocess_name: None
postprocess_dependencies: None
features: ['cg00043095', 'cg00347369', 'cg00397986', 'cg00466268', 'cg00884606', 'cg00916884', 'cg01435574', 'cg01537995', 'cg01587896', 'cg01699217', 'cg01783070', 'cg01830294', 'cg02150988', 'cg02186542', 'cg02266732', 'cg02631468', 'cg02726121', 'cg02796545', 'cg02964724', 'cg03045635', 'cg03111498', 'cg03140968', 'cg03181582', 'cg03430846', 'cg03450948', 'cg03603951', 'cg03874199', 'cg04188273', 'cg04408488', 'cg04431946']... [Total elements: 163]
base_model_features: None
base_model: None
delta: [4.999999873689376e-05, 4.999999873689376e-05, 4.999999873689376e-05, 9.999999747378752e-05, 9.999999747378752e-05, 4.999999873689376e-05, 4.999999873689376e-05, 4.999999873689376e-05, 9.999999747378752e-05, 4.999999873689376e-05, 4.999999873689376e-05, 0.0002500000118743628, 9.999999747378752e-05, 4.999999873689376e-05, 4.999999873689376e-05, 4.999999873689376e-05, 4.999999873689376e-05, 9.999999747378752e-05, 4.999999873689376e-05, 0.0002500000118743628, 9.999999747378752e-05, 4.999999873689376e-05, 4.999999873689376e-05, 4.999999873689376e-05, 9.999999747378752e-05, 4.999999873689376e-05, 4.999999873689376e-05, 9.999999747378752e-06, 4.999999873689376e-05, 4.999999873689376e-05]... [Tensor of shape torch.Size([1, 163])]
beta0: [0.019999999552965164, 0.05000000074505806, 0.05000000074505806, 0.05000000074505806, 0.009999999776482582, 0.05000000074505806, 0.05000000074505806, 0.05000000074505806, 0.029999999329447746, 0.05000000074505806, 0.03999999910593033, 0.0, 0.029999999329447746, 0.05000000074505806, 0.019999999552965164, 0.05000000074505806, 0.029999999329447746, 0.019999999552965164, 0.05000000074505806, 0.029999999329447746, 0.029999999329447746, 0.03999999910593033, 0.05000000074505806, 0.05000000074505806, 0.029999999329447746, 0.009999999776482582, 0.029999999329447746, 0.019999999552965164, 0.019999999552965164, 0.03999999910593033]... [Tensor of shape torch.Size([1, 163])]
%==================================== Model Details ====================================%
Model Structure:
%==================================== Model Details ====================================%
Model Parameters and Weights:
%==================================== Model Details ====================================%
Basic test#
[43]:
torch.manual_seed(42)
input = torch.randn(10, len(model.features), dtype=float)
model.eval()
model.to(float)
pred = model(input)
pred
[43]:
tensor([[ 1562.6673],
[-3824.6137],
[ 645.1144],
[-1810.9748],
[ -142.2699],
[ 1630.9714],
[ 9229.4758],
[ 4666.7934],
[ 5489.9210],
[ 1256.8648]], dtype=torch.float64)
Save torch model#
[44]:
torch.save(model, f"../weights/{model.metadata['clock_name']}.pt")
Clear directory#
[45]:
# 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: EpiTOC2.csv