epiTOC1

epiTOC1#

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:

[1]:

import os
import inspect
import shutil
import json
import torch
import pandas as pd
import pyaging as pya

Instantiate model class#

[2]:

def print_entire_class(cls):
    source = inspect.getsource(cls)
    print(source)

print_entire_class(pya.models.epiTOC1)

class epiTOC1(pyagingModel):
    def __init__(self):
        super().__init__()

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

    def postprocess(self, x):
        return x


[3]:

model = pya.models.epiTOC1()

Define clock metadata#

[4]:

model.metadata["clock_name"] = 'epitoc1'
model.metadata["data_type"] = 'methylation'
model.metadata["species"] = 'Homo sapiens'
model.metadata["year"] = 2016
model.metadata["approved_by_author"] = '✅'
model.metadata["citation"] = "Yang, Zhen, et al. \"Correlation of an epigenetic mitotic clock with cancer risk.\" Genome biology 17 (2016): 1-18."
model.metadata["doi"] = "https://doi.org/10.1186/s13059-016-1064-3"
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#

[5]:

supplementary_url = "https://static-content.springer.com/esm/art%3A10.1186%2Fs13059-016-1064-3/MediaObjects/13059_2016_1064_MOESM2_ESM.xls"
supplementary_file_name = "coefficients.xlsx"
os.system(f"curl -o {supplementary_file_name} {supplementary_url}")

[5]:

0

Load features#

From Excel file#

[6]:

df = pd.read_excel('coefficients.xlsx', sheet_name='agehyperPCGT-tableS1', skiprows=1)
df['feature'] = df['CpG'].astype(str)

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

Load weights into base model#

[7]:

weights = torch.tensor([1.0]).unsqueeze(0)
intercept = torch.tensor([0.0])

Linear model#

[8]:

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#

[9]:

model.reference_values = [-1]*len(model.features)

Load preprocess and postprocess objects#

[10]:

model.preprocess_name = "mean"
model.preprocess_dependencies = None

[11]:

model.postprocess_name = None
model.postprocess_dependencies = None

Check all clock parameters#

[12]:

pya.utils.print_model_details(model)


%==================================== Model Details ====================================%
Model Attributes:

training: True
metadata: {'approved_by_author': '⌛',
 'citation': 'Yang, Zhen, et al. "Correlation of an epigenetic mitotic clock '
             'with cancer risk." Genome biology 17 (2016): 1-18.',
 'clock_name': 'epitoc1',
 'data_type': 'methylation',
 'doi': 'https://doi.org/10.1186/s13059-016-1064-3',
 'notes': 'The reference values are simply -1 for the algorithm to ignore '
          'them.',
 'research_only': None,
 'species': 'Homo sapiens',
 'version': None,
 'year': 2016}
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: 385]
preprocess_name: 'mean'
preprocess_dependencies: None
postprocess_name: None
postprocess_dependencies: None
features: ['cg00043095', 'cg00060320', 'cg00181968', 'cg00329270', 'cg00347369', 'cg00397986', 'cg00466268', 'cg00665492', 'cg00884606', 'cg00916884', 'cg00930628', 'cg00962913', 'cg01050423', 'cg01185626', 'cg01435574', 'cg01537995', 'cg01587896', 'cg01670677', 'cg01699217', 'cg01783070', 'cg01830294', 'cg02004418', 'cg02056682', 'cg02071825', 'cg02150988', 'cg02160530', 'cg02186542', 'cg02266732', 'cg02315940', 'cg02554246']... [Total elements: 385]
base_model_features: None

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

base_model: LinearModel(
  (linear): Linear(in_features=385, 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#

[13]:

torch.manual_seed(42)
input = torch.randn(10, len(model.features), dtype=float)
model.eval()
model.to(float)
pred = model(input)
pred

[13]:

tensor([[ 0.0669],
        [-0.0019],
        [ 0.0772],
        [ 0.0336],
        [-0.1134],
        [-0.0825],
        [-0.0375],
        [-0.0160],
        [-0.0543],
        [-0.0141]], dtype=torch.float64, grad_fn=<AddmmBackward0>)

Save torch model#

[14]:

torch.save(model, f"../weights/{model.metadata['clock_name']}.pt")

Clear directory#

[15]:

# 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
Deleted folder: .ipynb_checkpoints
Contents