GrimAge2Leptin

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.GrimAge2Leptin)

class GrimAge2Leptin(pyagingModel):
    def __init__(self):
        super().__init__()

    def preprocess(self, x):
        return x

    def postprocess(self, x):
        return x

model = pya.models.GrimAge2Leptin()

Define clock metadata

model.metadata["clock_name"] = 'grimage2leptin'
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'] == 'DNAmleptin']
df['feature'] = df['var']
df['coefficient'] = df['beta']
model.features = df['feature'][1:].tolist()

df.head()

	Y.pred	var	beta	feature	coefficient
1434	DNAmleptin	Intercept	7210.062555	Intercept	7210.062555
1435	DNAmleptin	cg11781622	399.815717	cg11781622	399.815717
1436	DNAmleptin	cg13947317	3861.580695	cg13947317	3861.580695
1437	DNAmleptin	cg24145109	4281.873546	cg24145109	4281.873546
1438	DNAmleptin	cg19694465	1714.111981	cg19694465	1714.111981

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': 'grimage2leptin',
 '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: [0.920486032494228, 0.945983138574711, 0.175327347008541, 0.802335112177663, 0.0247552231850483, 0.0173798986148957, 0.0384209480708605, 0.935580510727358, 0.0753967785264462, 0.846802534526148, 0.023407474895155, 0.0258010644664732, 0.580486573508762, 0.134591579250635, 0.248811991314463, 0.0203892784279929, 0.780951039316296, 0.0136097188128507, 0.0428553986489399, 0.930023723262686, 0.9386474887599, 0.0199869326993668, 0.103705423432714, 0.0165397606025236, 0.895587696379722, 0.0420611676843711, 0.838280676738539, 0.0214771540238072, 0.0980339573006406, 0.0239307537419646]... [Total elements: 187]
preprocess_name: None
preprocess_dependencies: None
postprocess_name: 'cox_to_years'
postprocess_dependencies: None
features: ['cg11781622', 'cg13947317', 'cg24145109', 'cg19694465', 'cg15211499', 'cg10511249', 'cg16383389', 'cg04607246', 'cg08926056', 'cg14652203', 'cg20248954', 'cg23814988', 'cg05971102', 'cg07520608', 'cg01412762', 'cg09920725', 'cg12977946', 'cg20150163', 'cg04946715', 'cg08645207', 'cg14716323', 'cg01956624', 'cg00497251', 'cg27114661', 'cg17025841', 'cg06841024', 'cg27326062', 'cg10747042', 'cg18098839', 'cg13457961']... [Total elements: 187]
base_model_features: None

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

base_model: LinearModel(
  (linear): Linear(in_features=187, out_features=1, bias=True)
)

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

base_model.linear.weight: [399.8157043457031, 3861.580810546875, 4281.87353515625, 1714.1119384765625, -25588.5390625, 25643.771484375, -3710.89697265625, 1028.21484375, 4559.81591796875, -9729.9609375, 28351.38671875, 60980.60546875, 894.3289184570312, 2256.300537109375, -997.83447265625, 16759.64453125, 637.7293090820312, -14579.912109375, -7351.828125, 37.74680709838867, 5151.525390625, -38035.12890625, -3955.989990234375, -2736.428466796875, 154.31683349609375, -5049.8408203125, 4.860612869262695, -59299.390625, -594.4842529296875, 3549.596435546875]... [Tensor of shape torch.Size([1, 187])]
base_model.linear.bias: tensor([7210.0625])

%==================================== 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([[-120362.4131],
        [-333415.5971],
        [ 129251.7214],
        [  63121.7818],
        [-306690.5105],
        [-118785.7437],
        [  80334.4922],
        [  45302.3369],
        [-291923.9350],
        [ 357345.7592]], 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