stemTOC

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.stemTOC)

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

    def preprocess(self, x):
        # Filter out -1 values per row and calculate the 0.95 quantile per row
        quantiles = []
        for row in x:
            filtered_row = row[row != -1]
            if len(filtered_row) > 0:
                quantile_95 = torch.quantile(filtered_row, 0.95)
            else:
                quantile_95 = torch.tensor(float('nan'))
            quantiles.append(quantile_95)
        return torch.vstack(quantiles)

    def postprocess(self, x):
        return x

model = pya.models.stemTOC()

Define clock metadata

model.metadata["clock_name"] = 'stemtoc'
model.metadata["data_type"] = 'methylation'
model.metadata["species"] = 'Homo sapiens'
model.metadata["year"] = 2024
model.metadata["approved_by_author"] = '✅'
model.metadata["citation"] = "Zhu, Tianyu, et al. \"An improved epigenetic counter to track mitotic age in normal and precancerous tissues.\" Nature Communications 15.1 (2024): 4211."
model.metadata["doi"] = "https://doi.org/10.1038/s41467-024-48649-8"
model.metadata["research_only"] = None
model.metadata["notes"] = "The reference values are simply -1 for the algorithm to ignore them."

Download clock dependencies

Download directly with curl

supplementary_url = "https://static-content.springer.com/esm/art%3A10.1038%2Fs41467-024-48649-8/MediaObjects/41467_2024_48649_MOESM4_ESM.xlsx"
supplementary_file_name = "coefficients.xlsx"
os.system(f"curl -o {supplementary_file_name} {supplementary_url}")

0

Load features

From Excel file

df = pd.read_excel('coefficients.xlsx', sheet_name='SuppData1', skiprows=1)
df['feature'] = df['ProbeID'].astype(str)

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

Load weights into base model

weights = torch.tensor([1.0]).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 = [-1]*len(model.features)

Load preprocess and postprocess objects

model.preprocess_name = "0.95 quantile"
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': 'Zhu, Tianyu, et al. "An improved epigenetic counter to track '
             'mitotic age in normal and precancerous tissues." Nature '
             'Communications 15.1 (2024): 4211.',
 'clock_name': 'stemtoc',
 'data_type': 'methylation',
 'doi': 'https://doi.org/10.1038/s41467-024-48649-8',
 'notes': 'The reference values are simply -1 for the algorithm to ignore '
          'them.',
 'research_only': None,
 'species': 'Homo sapiens',
 'version': None,
 'year': 2024}
reference_values: [-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1]... [Total elements: 371]
preprocess_name: '0.95 quantile'
preprocess_dependencies: None
postprocess_name: None
postprocess_dependencies: None
features: ['cg23062112', 'cg07365816', 'cg08659394', 'cg14575559', 'cg18560328', 'cg21229268', 'cg23091824', 'cg03865257', 'cg11250773', 'cg12892303', 'cg12781700', 'cg13583934', 'cg12065366', 'cg25203031', 'cg17404915', 'cg22299454', 'cg05404701', 'cg24010885', 'cg17712694', 'cg20707222', 'cg11297107', 'cg12799781', 'cg01718742', 'cg10263370', 'cg15774465', 'cg16491617', 'cg11832210', 'cg07686635', 'cg26510017', 'cg15745900']... [Total elements: 371]
base_model_features: None

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

base_model: LinearModel(
  (linear): Linear(in_features=371, out_features=1, bias=True)
)

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

base_model.linear.weight: tensor([[1.]])
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([[1.7652],
        [1.7920],
        [1.8101],
        [1.6322],
        [1.7383],
        [1.4275],
        [1.6186],
        [1.8202],
        [1.5886],
        [1.6065]], 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.xlsx