HRSInCHPhenoAge#

Index#

Instantiate model class
Define clock metadata
Download clock dependencies
Load features
Load weights into base model
Load reference values
Load preprocess and postprocess objects
Check all clock parameters
Basic test
Save torch model
Clear directory

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.HRSInCHPhenoAge)

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

    def preprocess(self, x):
        return x

    def postprocess(self, x):
        return x

[3]:

model = pya.models.HRSInCHPhenoAge()

Define clock metadata#

[4]:

model.metadata["clock_name"] = "hrsinchphenoage"
model.metadata["data_type"] = "DNA methylation"  # Paper: The study constructs clocks from DNA methylation measurements.
model.metadata["species"] = "Homo sapiens"  # Paper: The analyzed samples and clock are human.
model.metadata["year"] = 2022
model.metadata["approved_by_author"] = "⌛"
model.metadata["citation"] = "Higgins-Chen, Albert T., et al. \"A computational solution for bolstering reliability of epigenetic clocks: implications for clinical trials and longitudinal tracking.\" Nature Aging 2 (2022): 644–661."
model.metadata["doi"] = "https://doi.org/10.1038/s43587-022-00248-2"
model.metadata["notes"] = "CpG-weighted HRS/InCHIANTI retraining of DNAm PhenoAge produced during the PC-clocks work; this implementation is not a principal-component clock."
model.metadata["research_only"] = None
model.metadata["tissue"] = ["whole blood"]  # Paper: The HRS and InCHIANTI methylation training samples were blood samples.
model.metadata["predicts"] = ["phenotypic age"]  # Paper: The function returns HRSInChPhenoAge.
model.metadata["training_target"] = ["phenotypic age"]  # Paper: The retrained model is explicitly identified as PhenoAge.
model.metadata["unit"] = ["years"]  # Paper: The returned PhenoAge estimate is on an age scale.
model.metadata["model_type"] = "weighted linear score"  # Paper: The function multiplies beta values by fitted CpG weights and adds an intercept.
model.metadata["platform"] = ["Illumina 450K", "Illumina EPIC"]  # Paper: HRS and InCHIANTI training data span EPIC and 450K methylation arrays.
model.metadata["population"] = "adults"  # Paper: The function identifies HRS and InCHIANTI as the retraining data.
model.metadata["journal"] = "Nature Aging"
model.metadata["last_author"] = "Morgan E. Levine"
model.metadata["n_features"] = 959
model.metadata["citations"] = 497
model.metadata["citations_date"] = "2026-07-05"

Download clock dependencies#

Download GitHub repository#

[5]:

github_url = "https://github.com/MorganLevineLab/methylCIPHER.git"
github_folder_name = github_url.split('/')[-1].split('.')[0]
os.system(f"git clone {github_url}")

[5]:

Load features#

From CSV file#

[6]:

df = pd.read_csv('methylCIPHER/data-raw/HRSInChPhenoAge_CpG.csv')
df['feature'] = df['CpG']
df['coefficient'] = df['Weight']

model.features = df['feature'].tolist()

Load weights into base model#

[7]:

weights = torch.tensor(df['coefficient'].tolist()).unsqueeze(0)
intercept = torch.tensor([52.8334080])

Linear model#

[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 = None

Load preprocess and postprocess objects#

[10]:

model.preprocess_name = None
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': 'Higgins-Chen, Albert T., et al. "A computational solution for '
             'bolstering reliability of epigenetic clocks: Implications for '
             'clinical trials and longitudinal tracking." Nature aging 2.7 '
             '(2022): 644-661.',
 'clock_name': 'hrsinchphenoage',
 'data_type': 'methylation',
 'doi': 'https://doi.org/10.1038/s43587-022-00248-2',
 'notes': None,
 'research_only': None,
 'species': 'Homo sapiens',
 'version': None,
 'year': 2022}
reference_values: None
preprocess_name: None
preprocess_dependencies: None
postprocess_name: None
postprocess_dependencies: None
features: ['cg00025138', 'cg00036347', 'cg00043599', 'cg00049440', 'cg00056497', 'cg00059225', 'cg00066239', 'cg00067518', 'cg00101154', 'cg00135293', 'cg00137209', 'cg00211115', 'cg00238295', 'cg00276799', 'cg00282953', 'cg00312921', 'cg00376639', 'cg00401091', 'cg00417823', 'cg00448560', 'cg00481159', 'cg00495693', 'cg00503840', 'cg00509996', 'cg00551910', 'cg00574958', 'cg00593462', 'cg00602811', 'cg00615241', 'cg00618626']... [Total elements: 959]
base_model_features: None

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

base_model: LinearModel(
  (linear): Linear(in_features=959, out_features=1, bias=True)
)

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

base_model.linear.weight: [-12.598388671875, 2.0095407962799072, 3.08774995803833, 1.5167790651321411, 0.20355011522769928, 1.68230140209198, -1.249173879623413, -0.8185797333717346, 0.4907846450805664, 0.5390154123306274, 15.449186325073242, -1.285083293914795, -0.7427912354469299, 1.5232256650924683, 0.5885316729545593, 2.078218936920166, 3.4780304431915283, -10.69495964050293, 2.9323976039886475, -5.428037166595459, 0.2791459858417511, -0.285178542137146, 0.9086608290672302, -0.1606019139289856, 1.7213571071624756, -5.501366138458252, 0.08092798292636871, -2.233879566192627, -1.4966527223587036, -4.973464488983154]... [Tensor of shape torch.Size([1, 959])]
base_model.linear.bias: tensor([52.8334])

%==================================== 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([[ 319.0174],
        [ -70.3330],
        [  49.5369],
        [ -66.2511],
        [ -99.2095],
        [-165.9214],
        [ 160.0792],
        [ 293.2276],
        [ 181.4062],
        [-175.9353]], 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 folder: methylCIPHER