SmokingMcCartney

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.McCartneySmoking)

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

    def preprocess(self, x):
        return x

    def postprocess(self, x):
        return x

model = pya.models.McCartneySmoking()

Define clock metadata

model.metadata["clock_name"] = 'mccartneysmoking'
model.metadata["data_type"] = 'methylation'
model.metadata["species"] = 'Homo sapiens'
model.metadata["year"] = 2018
model.metadata["approved_by_author"] = '⌛'
model.metadata["citation"] = "McCartney, Daniel L., et al. \"Epigenetic prediction of complex traits and death.\" Genome biology 19.1 (2018): 136."
model.metadata["doi"] = "https://doi.org/10.1186/s13059-018-1514-1"
model.metadata["research_only"] = None
model.metadata["notes"] = "Linear CpG score; higher values indicate smoking exposure."

Download clock dependencies

Download coefficient file

coeff_url = "https://raw.githubusercontent.com/bio-learn/biolearn/master/biolearn/data/Smoking.csv"
os.system(f"curl -L {coeff_url} -o Smoking.csv")

0

Load features

From CSV file

coeffs = pd.read_csv('Smoking.csv')
coeffs['feature'] = coeffs['CpGmarker']
coeffs['coefficient'] = coeffs['CoefficientTraining']

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

Load weights into base model

From CSV file

weights = torch.tensor(coeffs['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

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': 'McCartney, Daniel L., et al. "Epigenetic prediction of complex '
             'traits and death." Genome biology 19.1 (2018): 136.',
 'clock_name': 'mccartneysmoking',
 'data_type': 'methylation',
 'doi': 'https://doi.org/10.1186/s13059-018-1514-1',
 'notes': 'Linear CpG score; higher values indicate smoking exposure.',
 'research_only': None,
 'species': 'Homo sapiens',
 'version': None,
 'year': 2018}
reference_values: None
preprocess_name: None
preprocess_dependencies: None
postprocess_name: None
postprocess_dependencies: None
features: ['cg10573386', 'cg13560072', 'cg11084015', 'cg10321266', 'cg07597069', 'cg05218653', 'cg00077898', 'cg11207515', 'cg18392085', 'cg06088918', 'cg20077343', 'cg24169820', 'cg17833862', 'cg23079012', 'cg10696199', 'cg05442408', 'cg08038054', 'cg26775087', 'cg22371743', 'cg04136748', 'cg23288337', 'cg04561727', 'cg09648091', 'cg14142965', 'cg14708990', 'cg01558110', 'cg11704876', 'cg03616722', 'cg24714011', 'cg00231810']... [Total elements: 233]
base_model_features: None

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

base_model: LinearModel(
  (linear): Linear(in_features=233, out_features=1, bias=True)
)

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

base_model.linear.weight: [1.5160139799118042, 1.3958498239517212, 1.2834880352020264, 1.2621612548828125, 0.9191465377807617, 0.8301234841346741, 0.8246065378189087, 0.8208099007606506, 0.7282519936561584, 0.7219155430793762, 0.6905287504196167, 0.6882893443107605, 0.6189409494400024, 0.5594330430030823, 0.49723178148269653, 0.48923414945602417, 0.47508591413497925, 0.4401831328868866, 0.36066848039627075, 0.3536936938762665, 0.3378012776374817, 0.3341846168041229, 0.33264631032943726, 0.318849116563797, 0.31472083926200867, 0.308366596698761, 0.30539241433143616, 0.3030904531478882, 0.302953839302063, 0.28863614797592163]... [Tensor of shape torch.Size([1, 233])]
base_model.linear.bias: tensor([0.])

%==================================== 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([[ -1.4350],
        [ -4.1281],
        [-10.1821],
        [ -5.1272],
        [-11.3244],
        [ -3.2461],
        [  8.5989],
        [  3.6743],
        [  6.9403],
        [-17.4587]], 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: Smoking.csv