GrimAge2LogCRP

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.GrimAge2LogCRP)

class GrimAge2LogCRP(pyagingModel):
    def __init__(self):
        super().__init__()

    def preprocess(self, x):
        return x

    def postprocess(self, x):
        return x

model = pya.models.GrimAge2LogCRP()

Define clock metadata

model.metadata["clock_name"] = 'grimage2logcrp'
model.metadata["data_type"] = 'methylation'
model.metadata["species"] = 'Homo sapiens'
model.metadata["year"] = 2022
model.metadata["approved_by_author"] = '⌛'
model.metadata["citation"] = "Lu, Ake T., et al. \"DNA methylation GrimAge version 2.\" Aging (Albany NY) 14.23 (2022): 9484."
model.metadata["doi"] = "https://doi.org/10.18632/aging.204434"
model.metadata["research_only"] = True
model.metadata["notes"] = None

Download clock dependencies

logger = pya.logger.Logger()
urls = [
    "https://pyaging.s3.amazonaws.com/supporting_files/grimage2_subcomponents.csv",
    "https://pyaging.s3.amazonaws.com/supporting_files/grimage2.csv",
    "https://pyaging.s3.amazonaws.com/supporting_files/datMiniAnnotation3_Gold.csv",
]
dir = "."
for url in urls:
    pya.utils.download(url, dir, logger, indent_level=1)

|-----------> Downloading data to ./grimage2_subcomponents.csv
|-----------> in progress: 100.0000%
|-----------> Downloading data to ./grimage2.csv
|-----------> in progress: 100.0000%%
|-----------> Downloading data to ./datMiniAnnotation3_Gold.csv
|-----------> in progress: 100.0000%

Load features

From CSV

df = pd.read_csv('grimage2_subcomponents.csv', index_col=0)
df['Y.pred'].unique()

array(['DNAmGDF_15', 'DNAmB2M', 'DNAmCystatin_C', 'DNAmTIMP_1', 'DNAmadm',
       'DNAmpai_1', 'DNAmleptin', 'DNAmPACKYRS', 'DNAmlog.CRP',
       'DNAmlog.A1C'], dtype=object)

df = df[df['Y.pred'] == 'DNAmlog.CRP']
df['feature'] = df['var']
df['coefficient'] = df['beta']
model.features = df['feature'][1:].tolist()

df.head()

	Y.pred	var	beta	feature	coefficient
1796	DNAmlog.CRP	Intercept	-0.231448	Intercept	-0.231448
1797	DNAmlog.CRP	cg01391867	-0.238114	cg01391867	-0.238114
1798	DNAmlog.CRP	cg06298190	0.137911	cg06298190	0.137911
1799	DNAmlog.CRP	cg03110633	0.397843	cg03110633	0.397843
1800	DNAmlog.CRP	cg05303999	0.445975	cg05303999	0.445975

Load weights into base model

Linear model

weights = torch.tensor(df['coefficient'][1:].tolist()).unsqueeze(0)
intercept = torch.tensor([df['coefficient'].iloc[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

reference_df = pd.read_csv('datMiniAnnotation3_Gold.csv', index_col=0)
model.reference_values = reference_df.loc[model.features[0:]]['gold'].tolist()

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': 'Lu, Ake T., et al. "DNA methylation GrimAge version 2." Aging '
             '(Albany NY) 14.23 (2022): 9484.',
 'clock_name': 'grimage2logcrp',
 'data_type': 'methylation',
 'doi': 'https://doi.org/10.18632/aging.204434',
 'notes': None,
 'research_only': True,
 'species': 'Homo sapiens',
 'version': None,
 'year': 2022}
reference_values: [0.0229199108411034, 0.18157609704669, 0.0145712286188007, 0.913922509481157, 0.809605421222521, 0.703858551128724, 0.828079343471397, 0.8354705752375, 0.945562513470214, 0.219544227570287, 0.628295804305801, 0.0556920557050531, 0.883510168741842, 0.80868027489568, 0.942843729694158, 0.175324342316158, 0.873109700042845, 0.0947894779919567, 0.733082005089516, 0.883065598559295, 0.127222466210419, 0.846006900277736, 0.323099124395025, 0.0672194476736834, 0.919339370837926, 0.0989639070730932, 0.932356263376567, 0.0528287534203248, 0.219316986390691, 0.92697340543759]... [Total elements: 132]
preprocess_name: None
preprocess_dependencies: None
postprocess_name: 'cox_to_years'
postprocess_dependencies: None
features: ['cg01391867', 'cg06298190', 'cg03110633', 'cg05303999', 'cg01130991', 'cg13316619', 'cg20747455', 'cg26471058', 'cg02135821', 'cg18376497', 'cg12035880', 'cg02713068', 'cg02495445', 'cg03788610', 'cg08055490', 'cg06975311', 'cg22163406', 'cg22455450', 'cg03574306', 'cg13155421', 'cg22902266', 'cg09566331', 'cg26403843', 'cg06560379', 'cg13565994', 'cg07989867', 'cg21658515', 'cg05313771', 'cg12363682', 'cg19647685']... [Total elements: 132]
base_model_features: None

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

base_model: LinearModel(
  (linear): Linear(in_features=132, out_features=1, bias=True)
)

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

base_model.linear.weight: [-0.2381139099597931, 0.13791120052337646, 0.3978428244590759, 0.44597509503364563, 0.06502892822027206, -0.11037616431713104, 0.0026236912235617638, 0.13811077177524567, -1.9391815662384033, 0.02908332832157612, 0.28280875086784363, 0.9672318696975708, -0.09226538240909576, -0.20673252642154694, -0.8090327382087708, 3.308124303817749, 0.3115508258342743, 0.24958042800426483, 0.009494591504335403, -0.5394561886787415, 0.852174699306488, 0.03074250929057598, 0.02842751331627369, -1.275362491607666, 2.463428497314453, 0.08571851998567581, -0.8256807923316956, -1.2374017238616943, 0.29840514063835144, -0.22478485107421875]... [Tensor of shape torch.Size([1, 132])]
base_model.linear.bias: tensor([-0.2314])

%==================================== 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([[ -1.5050],
        [ -5.0319],
        [  1.0132],
        [-24.1760],
        [ -8.6024],
        [ -5.2143],
        [ 13.2554],
        [ -3.3618],
        [-10.8422],
        [ -6.0286]], 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: grimage2_subcomponents.csv
Deleted file: datMiniAnnotation3_Gold.csv
Deleted file: grimage2.csv