VidalBralo

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.VidalBralo)

class VidalBralo(pyagingModel):
    def __init__(self):
        super().__init__()

    def preprocess(self, x):
        if self.reference_values is None:
            return x
        if isinstance(self.reference_values, torch.Tensor):
            reference = self.reference_values.to(device=x.device, dtype=x.dtype)
        else:
            reference = torch.tensor(self.reference_values, device=x.device, dtype=x.dtype)
        return torch.where(torch.isnan(x), reference, x)

    def postprocess(self, x):
        return x

model = pya.models.VidalBralo()

Define clock metadata

model.metadata["clock_name"] = "vidalbralo"
model.metadata["data_type"] = "DNA methylation"  # Paper: DNA methylation age measures
model.metadata["species"] = "Homo sapiens"  # Paper: 390 healthy Caucasian donors
model.metadata["year"] = 2016
model.metadata["approved_by_author"] = "⌛"
model.metadata["citation"] = "Vidal-Bralo, Laura, Yolanda Lopez-Golan, and Antonio Gonzalez. \"Simplified assay for epigenetic age estimation in whole blood of adults.\" Frontiers in Genetics 7 (2016): 126."
model.metadata["doi"] = "https://doi.org/10.3389/fgene.2016.00126"
model.metadata["notes"] = "Eight-CpG whole-blood chronological-age estimator selected by forward stepwise regression in 390 adults and calibrated by multiple linear regression; CpGs were chosen for compatibility with a single multiplex MS-SNuPE assay."
model.metadata["research_only"] = None
model.metadata["tissue"] = ["whole blood"]  # Paper: whole blood (WB)
model.metadata["predicts"] = ["chronological age"]  # Paper: estimate age from blood DNA
model.metadata["training_target"] = ["chronological age"]  # Paper: forward stepwise linear regression with age
model.metadata["unit"] = ["years"]  # Paper: Age range; MAD ... years
model.metadata["model_type"] = "linear regression"  # Paper: multiple linear regression parameters of the 8 CpG DmAM
model.metadata["platform"] = ["Illumina 27K"]  # Paper: training ... obtained with the Illumina Human Methylation 27K BeadChip
model.metadata["population"] = "adults"  # Paper: 390 healthy subjects older than 20 years
model.metadata["journal"] = "Frontiers in Genetics"
model.metadata["last_author"] = "Antonio Gonzalez"
model.metadata["n_features"] = 8
model.metadata["citations"] = 145
model.metadata["citations_date"] = "2026-07-05"

Download clock dependencies

# The 8-CpG DmAM coefficients are given directly in Table 2 of
# Vidal-Bralo et al. 2016 (Front. Genet. 7:126); they are defined inline below,
# so no external download is required.

Load features

# Multiple linear regression parameters of the 8 CpG DmAM (Vidal-Bralo et al. 2016, Table 2)
coef_df = pd.DataFrame({
    'CpG': ['cg16386080', 'cg24768561', 'cg19761273', 'cg25809905',
            'cg09809672', 'cg02228185', 'cg17471102', 'cg10917602'],
    'coefficient': [59.5, 33.9, -44.0, -19.7, -22.8, -16.8, -17.7, -11.4],
})
model.features = coef_df['CpG'].tolist()

Load weights into base model

weights = torch.tensor(coef_df['coefficient'].tolist()).unsqueeze(0).float()
intercept = torch.tensor([84.7]).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': 'Vidal-Bralo, Laura, Yolanda Lopez-Golan, and Antonio Gonzalez. '
             '"Simplified assay for epigenetic age estimation in whole blood '
             'of adults." Frontiers in genetics 7 (2016): 126.',
 'clock_name': 'vidalbralo',
 'data_type': 'methylation',
 'doi': 'https://doi.org/10.3389/fgene.2016.00126',
 'notes': None,
 'research_only': None,
 'species': 'Homo sapiens',
 'version': None,
 'year': 2016}
reference_values: None
preprocess_name: None
preprocess_dependencies: None
postprocess_name: None
postprocess_dependencies: None
features: ['cg16386080',
 'cg24768561',
 'cg19761273',
 'cg25809905',
 'cg09809672',
 'cg02228185',
 'cg17471102',
 'cg10917602']
base_model_features: None

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

base_model: LinearModel(
  (linear): Linear(in_features=8, out_features=1, bias=True)
)

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

base_model.linear.weight: tensor([[ 59.5000,  33.9000, -44.0000, -19.7000, -22.8000, -16.8000, -17.7000,
         -11.4000]])
base_model.linear.bias: tensor([84.7000])

%==================================== 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([[126.0523],
        [104.1466],
        [ 75.2432],
        [ 58.5473],
        [160.9427],
        [ 27.2660],
        [137.7398],
        [262.1763],
        [125.6747],
        [171.3440]], 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)