Bocklandt

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.Bocklandt)

class Bocklandt(LinearReferenceClock):
    pass

model = pya.models.Bocklandt()

Define clock metadata

model.metadata["clock_name"] = "bocklandt"
model.metadata["data_type"] = "DNA methylation"  # Paper: The predictor uses CpG methylation percentages.
model.metadata["species"] = "Homo sapiens"  # Paper: The study analyzed human saliva.
model.metadata["year"] = 2011
model.metadata["approved_by_author"] = "⌛"
model.metadata["citation"] = "Bocklandt, S., Lin, W., Sehl, M.E. et al. Epigenetic predictor of age. PLoS ONE 6, e14821 (2011)."
model.metadata["doi"] = "https://doi.org/10.1371/journal.pone.0014821"
model.metadata["notes"] = "Package-facing one-CpG identity score: pyaging returns raw cg09809672 methylation with coefficient 1 and zero intercept. The published saliva age regression instead uses EDARADD and NPTX2, including an EDARADD-squared basis term; that published age model is not implemented."
model.metadata["research_only"] = None
model.metadata["tissue"] = ["saliva"]  # Paper: Both discovery and validation samples were saliva.
model.metadata["predicts"] = ["EDARADD methylation"]  # Paper: The packaged object contains only cg09809672 with coefficient 1.
model.metadata["training_target"] = ["chronological age"]  # Paper: Chronological age was the regression outcome.
model.metadata["unit"] = ["beta value"]  # Paper: The packaged single-CpG output is raw cg09809672/EDARADD methylation on the beta-value scale.
model.metadata["model_type"] = "single-CpG score"  # Paper: The packaged object contains only cg09809672 with coefficient 1.
model.metadata["platform"] = ["Illumina 27K"]  # Paper: Feature discovery used the Illumina HumanMethylation27 array.
model.metadata["population"] = "adults"  # Paper: Discovery used 34 male monozygotic twin pairs aged 21–55; validation included unrelated adults aged 18–70.
model.metadata["journal"] = "PLoS ONE"
model.metadata["last_author"] = "Éric Vilain"
model.metadata["n_features"] = 1
model.metadata["citations"] = 1057
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/Bocklandt.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': 'Bocklandt, Sven, et al. "Epigenetic predictor of age." PloS one '
             '6.6 (2011): e14821.',
 'clock_name': 'bocklandt',
 'data_type': 'methylation',
 'doi': 'https://doi.org/10.1371/journal.pone.0014821',
 'notes': None,
 'research_only': None,
 'species': 'Homo sapiens',
 'version': None,
 'year': 2011}
reference_values: None
preprocess_name: None
preprocess_dependencies: None
postprocess_name: None
postprocess_dependencies: None
features: ['cg09809672']
base_model_features: None

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

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

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

base_model.linear.weight: tensor([[1.]])
base_model.linear.bias: tensor([0.])

%==================================== 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([[ 0.3367],
        [ 0.1288],
        [ 0.2345],
        [ 0.2303],
        [-1.1229],
        [-0.1863],
        [ 2.2082],
        [-0.6380],
        [ 0.4617],
        [ 0.2674]], 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