HepatoXu

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:

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

Instantiate model class

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

print_entire_class(pya.models.HepatoXu)

class HepatoXu(LinearReferenceClock):
    pass

model = pya.models.HepatoXu()

Define clock metadata

model.metadata["clock_name"] = 'hepatoxu'
model.metadata["data_type"] = 'methylation'
model.metadata["species"] = 'Homo sapiens'
model.metadata["year"] = 2017
model.metadata["approved_by_author"] = '⌛'
model.metadata["citation"] = "Xu, Ruo-Han, et al. \"Circulating tumour DNA methylation markers for diagnosis and prognosis of hepatocellular carcinoma.\" Nature Materials 16.11 (2017): 1155-1161."
model.metadata["doi"] = "https://doi.org/10.1038/nmat4997"
model.metadata["research_only"] = None
model.metadata["notes"] = "Blood plasma circulating tumour-DNA methylation marker panel that discriminates hepatocellular carcinoma from healthy controls and predicts tumour burden, stage, and prognosis, developed as a non-invasive liquid-biopsy diagnostic and prognostic model."
model.metadata["tissue"] = 'plasma cell-free DNA (ctDNA); methylation markers derived from HCC tumor tissue vs normal blood leukocytes'
model.metadata["predicts"] = 'hepatocellular carcinoma diagnosis (disease presence/status) and prognosis'
model.metadata["unit"] = 'probability (0-1)'
model.metadata["model_type"] = 'Logistic regression'
model.metadata["platform"] = 'Bisulfite sequencing'
model.metadata["population"] = 'adults (HCC patients, n=1,098, and normal/at-risk controls, n=835)'
model.metadata["journal"] = 'Nature Materials'
model.metadata["last_author"] = 'Kang Zhang'
model.metadata["n_features"] = 10
model.metadata["citations"] = 884
model.metadata["citations_date"] = '2026-07-05'

Download clock dependencies

os.system(f"curl -sL -o coefficients.csv https://raw.githubusercontent.com/bio-learn/biolearn/180852e2bab473303cb85da627178b1695ee9d86/biolearn/data/HepatoXu.csv")

0

Load features

df = pd.read_csv('coefficients.csv')
mask = df['CpGmarker'].astype(str).str.lower().isin(['intercept', '(intercept)'])
intercept_value = float(df.loc[mask, 'CoefficientTraining'].iloc[0]) if mask.any() else 0.0
coef_df = df.loc[~mask].reset_index(drop=True)
model.features = coef_df['CpGmarker'].tolist()

Load weights into base model

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

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

model.reference_values = None

Load preprocess and postprocess objects

model.preprocess_name = None
model.preprocess_dependencies = None

model.postprocess_name = None
model.postprocess_dependencies = None

Check all clock parameters

pya.utils.print_model_details(model)

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

training: True
metadata: {'approved_by_author': '⌛',
 'citation': 'Xu, Ruo-Han, et al. "Circulating tumour DNA methylation markers '
             'for diagnosis and prognosis of hepatocellular carcinoma." Nature '
             'Materials 16.11 (2017): 1155-1161.',
 'clock_name': 'hepatoxu',
 'data_type': 'methylation',
 'doi': 'https://doi.org/10.1038/nmat4997',
 'notes': None,
 'research_only': None,
 'species': 'Homo sapiens',
 'version': None,
 'year': 2017}
reference_values: None
preprocess_name: None
preprocess_dependencies: None
postprocess_name: None
postprocess_dependencies: None
features: ['cg10428836',
 'cg26668608',
 'cg25754195',
 'cg05205842',
 'cg11606215',
 'cg24067911',
 'cg18196829',
 'cg23211949',
 'cg17213048',
 'cg25459300']
base_model_features: None

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

base_model: LinearModel(
  (linear): Linear(in_features=10, out_features=1, bias=True)
)

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

base_model.linear.weight: tensor([[11.5430,  4.5570,  2.5190, -3.6120,  6.8650, -5.4390, -9.0780, -5.2090,
          6.6600,  1.9940]])
base_model.linear.bias: tensor([15.5950])

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

Basic test

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

tensor([[49.1148],
        [40.0752],
        [23.5150],
        [ 1.2405],
        [ 2.2419],
        [-6.4443],
        [ 1.1513],
        [33.1075],
        [61.1116],
        [22.9915]], dtype=torch.float64, grad_fn=<AddmmBackward0>)

Save torch model

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

Clear directory

# 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: coefficients.csv