cABEC

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.cABEC)

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

    def preprocess(self, x):
        return x

    def postprocess(self, x):
        return x

model = pya.models.cABEC()

Define clock metadata

model.metadata["clock_name"] = 'cabec'
model.metadata["data_type"] = 'methylation'
model.metadata["species"] = 'Homo sapiens'
model.metadata["year"] = 2020
model.metadata["approved_by_author"] = '⌛'
model.metadata["citation"] = "Lee, Yunsung, et al. \"Blood-based epigenetic estimators of chronological age in human adults using DNA methylation data from the Illumina MethylationEPIC array.\" BMC genomics 21 (2020): 1-13."
model.metadata["doi"] = "https://doi.org/10.1186/s12864-020-07168-8"
model.metadata["research_only"] = None
model.metadata["notes"] = None

Download clock dependencies

Download directly with curl

supplementary_url = "https://static-content.springer.com/esm/art%3A10.1186%2Fs12864-020-07168-8/MediaObjects/12864_2020_7168_MOESM1_ESM.csv"
supplementary_file_name = "coefficients.csv"
os.system(f"curl -o {supplementary_file_name} {supplementary_url}")

0

Load features

From CSV file

df = pd.read_csv('coefficients.csv', index_col=0)
df = df[~df['cABEC_coefficient'].isna()]
df['feature'] = df.index.tolist()
df['coefficient'] = df['cABEC_coefficient']
model.features = df['feature'][1:].tolist()

Load weights into base model

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

<ipython-input-7-232b7c74dbf3>:2: FutureWarning: Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`
  intercept = torch.tensor([df['coefficient'][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

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': 'Lee, Yunsung, et al. "Blood-based epigenetic estimators of '
             'chronological age in human adults using DNA methylation data '
             'from the Illumina MethylationEPIC array." BMC genomics 21 '
             '(2020): 1-13.',
 'clock_name': 'cabec',
 'data_type': 'methylation',
 'doi': 'https://doi.org/10.1186/s12864-020-07168-8',
 'notes': None,
 'research_only': None,
 'species': 'Homo sapiens',
 'version': None,
 'year': 2020}
reference_values: None
preprocess_name: None
preprocess_dependencies: None
postprocess_name: None
postprocess_dependencies: None
features: ['cg00000165', 'cg00001687', 'cg00004257', 'cg00012238', 'cg00015770', 'cg00018181', 'cg00039864', 'cg00053073', 'cg00071360', 'cg00074086', 'cg00112685', 'cg00116092', 'cg00156551', 'cg00172812', 'cg00193490', 'cg00199846', 'cg00231483', 'cg00260883', 'cg00262681', 'cg00265788', 'cg00290373', 'cg00314660', 'cg00347882', 'cg00370293', 'cg00381684', 'cg00387658', 'cg00397859', 'cg00406023', 'cg00448707', 'cg00456672']... [Total elements: 1892]
base_model_features: None

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

base_model: LinearModel(
  (linear): Linear(in_features=1892, out_features=1, bias=True)
)

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

base_model.linear.weight: [-0.5071440935134888, 3.8805794715881348, -0.004386255983263254, -0.3082602918148041, 0.7501303553581238, -0.07783860713243484, -0.03706755116581917, -3.0622639656066895, -0.27626731991767883, -0.4478277266025543, 0.7638550400733948, 1.4799879789352417, -0.9727926254272461, -0.08195030689239502, -2.9534730911254883, 1.5299639701843262, -0.09737197309732437, 0.12180330604314804, -0.06913822144269943, -0.36189907789230347, -0.07744547724723816, -0.7775667309761047, -1.5537751913070679, -0.0737200528383255, 0.02495921030640602, -0.2793864905834198, 0.4901841878890991, 0.8282898664474487, 1.9143801927566528, -0.2619211971759796]... [Tensor of shape torch.Size([1, 1892])]
base_model.linear.bias: tensor([42.8285])

%==================================== 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([[ 35.7819],
        [ 48.6824],
        [-73.2872],
        [141.0891],
        [ 49.2925],
        [-72.9852],
        [213.5275],
        [ 64.9323],
        [ 80.0819],
        [-44.4303]], 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