CpGPTGrimAge3

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
import numpy as np

Instantiate model class

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

print_entire_class(pya.models.CpGPTGrimAge3)

class CpGPTGrimAge3(pyagingModel):
    def __init__(self):
        super().__init__()

    def preprocess(self, x):
        """
        Scales an array based on the median and standard deviation.
        """
        median = torch.tensor(self.preprocess_dependencies[0], device=x.device, dtype=x.dtype)
        std = torch.tensor(self.preprocess_dependencies[1], device=x.device, dtype=x.dtype)
        x = (x - median) / std
        return x

    def postprocess(self, x):
        """
        Converts from a Cox parameter to age in units of years.
        """
        cox_mean = self.postprocess_dependencies[0]
        cox_std = self.postprocess_dependencies[1]
        age_mean = self.postprocess_dependencies[2]
        age_std = self.postprocess_dependencies[3]

        # Normalize
        x = (x - cox_mean) / cox_std

        # Scale
        x = (x * age_std) + age_mean

        return x

model = pya.models.CpGPTGrimAge3()

Define clock metadata

model.metadata["clock_name"] = 'cpgptgrimage3'
model.metadata["data_type"] = 'methylation'
model.metadata["species"] = 'Homo sapiens'
model.metadata["year"] = 2025
model.metadata["approved_by_author"] = '✅'
model.metadata["citation"] = "de Lima Camillo, Lucas Paulo, et al. \"CpGPT: a foundation model for DNA methylation.\" bioRxiv (2024): 2024-10."
model.metadata["doi"] = "https://doi.org/10.1101/2024.10.24.619766"
model.metadata["research_only"] = True
model.metadata["notes"] = None

Download clock dependencies

logger = pya.logger.Logger()
urls = [
    "https://pyaging.s3.us-east-1.amazonaws.com/supporting_files/cpgpt_grimage3_dependencies/reliable/cpgpt_grimage3_weights_all_datasets_reliable.csv",
    "https://pyaging.s3.us-east-1.amazonaws.com/supporting_files/cpgpt_grimage3_dependencies/reliable/input_scaler_mean_all_datasets_reliable.npy",
    "https://pyaging.s3.us-east-1.amazonaws.com/supporting_files/cpgpt_grimage3_dependencies/reliable/input_scaler_scale_all_datasets_reliable.npy"
]
dir = "."
for url in urls:
    pya.utils.download(url, dir, logger, indent_level=1)

|-----------> Data found in ./cpgpt_grimage3_weights_all_datasets_reliable.csv
|-----------> Data found in ./input_scaler_mean_all_datasets_reliable.npy
|-----------> Data found in ./input_scaler_scale_all_datasets_reliable.npy

Load features

From CSV

df = pd.read_csv('cpgpt_grimage3_weights_all_datasets_reliable.csv')
model.features = df['feature'].tolist()

df.head()

	feature	coefficient
0	age	0.845167
1	grimage2timp1	0.318954
2	grimage2packyrs	0.385882
3	grimage2logcrp	0.404675
4	grimage2adm	0.180551

Load weights into base model

Linear model

weights = torch.tensor(df['coefficient'].tolist()).unsqueeze(0)
intercept = torch.tensor([0.0])

Linear model

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

scale_mean = np.load('input_scaler_mean_all_datasets_reliable.npy')
scale_std = np.load('input_scaler_scale_all_datasets_reliable.npy')

model.reference_values = None

Load preprocess and postprocess objects

model.preprocess_name = 'scale'
model.preprocess_dependencies = [scale_mean, scale_std]

model.postprocess_name = 'cox_to_years'
model.postprocess_dependencies = [
    0.54372919,
    1.52036698,
    64.94560376271838,
    11.920838151170104
]

Check all clock parameters

pya.utils.print_model_details(model)

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

training: True
metadata: {'approved_by_author': '✅',
 'citation': 'de Lima Camillo, Lucas Paulo, et al. "CpGPT: a foundation model '
             'for DNA methylation." bioRxiv (2024): 2024-10.',
 'clock_name': 'cpgptgrimage3',
 'data_type': 'methylation',
 'doi': 'https://doi.org/10.1101/2024.10.24.619766',
 'notes': None,
 'research_only': True,
 'species': 'Homo sapiens',
 'version': None,
 'year': 2025}
reference_values: None
preprocess_name: 'scale'
preprocess_dependencies: [array([ 6.50000000e+01,  3.49212152e+04,  1.21734902e+01,  2.73993813e-01,
        3.51222301e+02,  8.51761217e+03,  8.85501049e+02, -5.21484375e-01,
       -2.49755859e-01, -2.58056641e-01, -7.65991211e-02, -1.37939453e-01,
        2.53173828e-01,  1.33399963e-02, -4.01245117e-01,  1.90368652e-01,
       -3.27301025e-02,  1.29127502e-02, -2.78564453e-01,  1.92277772e+04,
        2.87399292e-02, -3.61083984e-01, -1.25961304e-02, -2.21801758e-01]),
 array([1.52000000e+01, 2.39220372e+03, 1.43614564e+01, 7.58010775e-01,
       3.24518463e+01, 5.54305012e+03, 2.81677880e+02, 1.54296875e-01,
       1.58935547e-01, 3.54949951e-01, 1.87866211e-01, 4.43069458e-01,
       2.97714233e-01, 3.31024170e-01, 3.81805420e-01, 1.43981934e-01,
       1.65519714e-01, 2.10388184e-01, 1.30737305e-01, 3.97488350e+03,
       3.68286133e-01, 7.37304688e-02, 3.28125000e-01, 4.43408966e-01])]
postprocess_name: 'cox_to_years'
postprocess_dependencies: [0.54372919, 1.52036698, 64.94560376271838, 11.920838151170104]
features: ['age',
 'grimage2timp1',
 'grimage2packyrs',
 'grimage2logcrp',
 'grimage2adm',
 'grimage2leptin',
 'grimage2gdf15',
 'cpgpt_s100a9',
 'cpgpt_tnfrsf13c',
 'cpgpt_tgfb1',
 'cpgpt_tek',
 'cpgpt_ccl14',
 'cpgpt_tnfsf15',
 'cpgpt_lilrb2',
 'cpgpt_tnf',
 'cpgpt_chit1',
 'cpgpt_postn',
 'cpgpt_il34',
 'cpgpt_pdcd1',
 'grimage2pai1',
 'cpgpt_cst3',
 'cpgpt_cxcl2',
 'cpgpt_gzma',
 'cpgpt_il5']
base_model_features: None

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

base_model: LinearModel(
  (linear): Linear(in_features=24, out_features=1, bias=True)
)

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

base_model.linear.weight: tensor([[ 0.8452,  0.3190,  0.3859,  0.4047,  0.1806, -0.2435,  0.0367, -0.0855,
          2.0569, -3.9567,  1.8897, -2.3948, -3.8697,  4.5260,  0.0498,  1.4570,
         -1.7014, -1.5117, -1.5438,  0.1255,  5.3232, -0.4491,  0.6656,  0.7276]])
base_model.linear.bias: tensor([0.])

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

Basic test

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

tensor([[-425.9024],
        [-312.5518],
        [-563.8393],
        [-260.0897],
        [ -69.1534],
        [  30.5343],
        [-252.0608],
        [-445.2048],
        [ -64.2164],
        [ 103.0451]], dtype=torch.float64, grad_fn=<AddBackward0>)

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: cpgpt_grimage3_weights_all_datasets_reliable.csv
Deleted file: input_scaler_mean_all_datasets_reliable.npy
Deleted file: input_scaler_scale_all_datasets_reliable.npy