EpiCMITHypo#
Index#
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.EpiCMITHypo)
class EpiCMITHypo(epiTOC1):
pass
[3]:
model = pya.models.EpiCMITHypo()
Define clock metadata#
[4]:
model.metadata["clock_name"] = 'epicmithypo'
model.metadata["data_type"] = 'methylation'
model.metadata["species"] = 'Homo sapiens'
model.metadata["year"] = 2020
model.metadata["approved_by_author"] = '⌛'
model.metadata["citation"] = "Duran-Ferrer, Marti, et al. \"The proliferative history shapes the DNA methylome of B-cell tumors and predicts clinical outcome.\" Nature Cancer 1.11 (2020): 1066-1081."
model.metadata["doi"] = "https://doi.org/10.1038/s43018-020-00131-2"
model.metadata["research_only"] = None
model.metadata["notes"] = "Hypomethylation-based component of the epiCMIT mitotic clock, tracking the cumulative mitotic history of B cells from progressive loss of DNA methylation in heterochromatin and serving as an independent prognostic marker in B-cell malignancies."
model.metadata["tissue"] = 'B cells / B-cell tumors (normal B-cell subpopulations and neoplasms: ALL, MCL, DLBCL, CLL, MM)'
model.metadata["predicts"] = 'mitotic age / cumulative proliferative history (hypomethylation component)'
model.metadata["unit"] = 'score (arbitrary)'
model.metadata["model_type"] = 'Mitotic model'
model.metadata["platform"] = 'Illumina 450K/EPIC'
model.metadata["population"] = 'B-cell tumor patients and normal B cells (human)'
model.metadata["journal"] = 'Nature Cancer'
model.metadata["last_author"] = 'José I. Martı́n-Subero'
model.metadata["n_features"] = 1164
model.metadata["citations"] = 104
model.metadata["citations_date"] = '2026-07-05'
Download clock dependencies#
[5]:
supplementary_url = "https://static-content.springer.com/esm/art%3A10.1038%2Fs43018-020-00131-2/MediaObjects/43018_2020_131_MOESM3_ESM.xlsx"
supplementary_file_name = "epicmit.xlsx"
os.system(f"curl -sL -o {supplementary_file_name} {supplementary_url}")
[5]:
0
Load features#
[6]:
df = pd.read_excel('epicmit.xlsx', sheet_name='Table 23')
df = df[df['epiCMIT.class'].astype(str).str.contains('hypo', case=False)]
model.features = df['Name'].tolist()
Load weights into base model#
[7]:
weights = torch.tensor([-1.0]).unsqueeze(0)
intercept = torch.tensor([1.0])
[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 = [-1]*len(model.features)
Load preprocess and postprocess objects#
[10]:
model.preprocess_name = "mean"
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': 'Duran-Ferrer, Marti, et al. "The proliferative history shapes '
'the DNA methylome of B-cell tumors and predicts clinical '
'outcome." Nature Cancer 1.11 (2020): 1066-1081.',
'clock_name': 'epicmithypo',
'data_type': 'methylation',
'doi': 'https://doi.org/10.1038/s43018-020-00131-2',
'notes': None,
'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: 1164]
preprocess_name: 'mean'
preprocess_dependencies: None
postprocess_name: None
postprocess_dependencies: None
features: ['cg21870274', 'cg17810211', 'cg08263140', 'cg05663262', 'cg00055603', 'cg05042706', 'cg25469314', 'cg16515477', 'cg07910726', 'cg22037030', 'cg00954256', 'cg13047196', 'cg04910179', 'cg08123701', 'cg14777634', 'cg11795488', 'cg21679730', 'cg11228758', 'cg13784017', 'cg17987458', 'cg12302119', 'cg05928873', 'cg17041296', 'cg16926302', 'cg11338128', 'cg05948962', 'cg01952027', 'cg17175521', 'cg17011453', 'cg26032419']... [Total elements: 1164]
base_model_features: None
%==================================== Model Details ====================================%
Model Structure:
base_model: LinearModel(
(linear): Linear(in_features=1164, out_features=1, bias=True)
)
%==================================== Model Details ====================================%
Model Parameters and Weights:
base_model.linear.weight: tensor([[-1.]])
base_model.linear.bias: tensor([1.])
%==================================== 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([[0.9526],
[1.0553],
[1.0356],
[0.9706],
[1.0003],
[0.9377],
[1.0229],
[1.0117],
[1.0650],
[0.9722]], 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: epicmit.xlsx