Mayne

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.Mayne)

class Mayne(LinearReferenceClock):
    def postprocess(self, x):
        """Gestational age in weeks (as published)."""
        return x

model = pya.models.Mayne()

Define clock metadata

model.metadata["clock_name"] = "mayne"
model.metadata["data_type"] = "DNA methylation"  # Paper: The model is based on DNA methylation measurements.
model.metadata["species"] = "Homo sapiens"  # Paper: The study samples are Homo sapiens.
model.metadata["year"] = 2017
model.metadata["approved_by_author"] = "⌛"
model.metadata["citation"] = "Mayne, Benjamin T., et al. \"Accelerated placental aging in early onset preeclampsia pregnancies identified by DNA methylation.\" Epigenomics 9 (2017): 279–289."
model.metadata["doi"] = "https://doi.org/10.2217/epi-2016-0103"
model.metadata["notes"] = "Placental elastic-net clock trained on pooled healthy human placenta methylation datasets; 62 selected CpGs predict gestational age and were used to test age acceleration in early-onset preeclampsia."
model.metadata["research_only"] = None
model.metadata["tissue"] = ["placenta"]  # Paper: The listed tissue is the model-development sample material.
model.metadata["predicts"] = ["gestational age"]  # Paper: The reported predictor output is gestational age.
model.metadata["training_target"] = ["gestational age"]  # Paper: The fitting outcome is gestational age.
model.metadata["unit"] = ["weeks"]  # Paper: The returned construct is expressed as weeks.
model.metadata["model_type"] = "elastic net regression"  # Paper: The clock was fitted using Elastic net.
model.metadata["platform"] = ["Illumina 27K", "Illumina 450K"]  # Paper: Training/selection used Illumina 27K/450K.
model.metadata["population"] = "pregnancies"  # Paper: healthy human placentas sampled across gestation
model.metadata["journal"] = "Epigenomics"
model.metadata["last_author"] = "Tina Bianco‐Miotto"
model.metadata["n_features"] = 62
model.metadata["citations"] = 150
model.metadata["citations_date"] = "2026-07-05"

Download clock dependencies

os.system(f"curl -sL -o coefficients.csv https://raw.githubusercontent.com/Duzhaozhen/OmniAge/c10fbe8cb92957520fbff1d55ae1def0691252e5/OmniAgePy/src/omniage/data/Mayne_GA.csv")

0

Load features

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

Load weights into base model

weights = torch.tensor(coef_df['coef'].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': 'Mayne, Benjamin T., et al. "Accelerated placental aging in early '
             'onset preeclampsia pregnancies identified by DNA methylation." '
             'Epigenomics 9.3 (2017): 279-289.',
 'clock_name': 'mayne',
 'data_type': 'methylation',
 'doi': 'https://doi.org/10.2217/epi-2016-0103',
 '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: ['cg12146151', 'cg16127845', 'cg17133388', 'cg13997435', 'cg12360736', 'cg07300408', 'cg11739626', 'cg00828602', 'cg21624359', 'cg22639768', 'cg11388238', 'cg06958211', 'cg19317715', 'cg20291222', 'cg03490200', 'cg26353877', 'cg22957381', 'cg19742789', 'cg02976574', 'cg16356956', 'cg26143719', 'cg09990086', 'cg16746631', 'cg10245048', 'cg00047050', 'cg25623459', 'cg25374854', 'cg02589695', 'cg19289461', 'cg16816226']... [Total elements: 62]
base_model_features: None

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

base_model: LinearModel(
  (linear): Linear(in_features=62, out_features=1, bias=True)
)

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

base_model.linear.weight: [-1.9282536506652832, -26.4451904296875, -17.35150718688965, -0.9527280330657959, -5.665579319000244, -2.0989339351654053, -0.7110825181007385, -0.03753948584198952, -2.35093355178833, -2.3877365589141846, -4.450428009033203, -0.32594966888427734, -2.3679003715515137, -3.580242156982422, -4.025350570678711, -0.034084122627973557, -5.023456573486328, -10.068197250366211, -6.389592170715332, -0.3280542492866516, -0.40900924801826477, -5.404386043548584, -6.043520927429199, -0.026322754099965096, -1.531197428703308, -2.4376535415649414, -0.4204040467739105, -7.178297996520996, -3.049933433532715, -1.4748220443725586]... [Tensor of shape torch.Size([1, 62])]
base_model.linear.bias: tensor([24.9903])

%==================================== 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([[ -39.5419],
        [  25.7659],
        [  44.2797],
        [  -0.9077],
        [  92.4899],
        [  86.2686],
        [-106.0699],
        [  76.7959],
        [  20.1038],
        [  21.3373]], 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