ZhangBLUP

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.ZhangBLUP)

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

    def preprocess(self, x):
        """
        Scales the input PyTorch tensor per row with mean 0 and std 1.
        """
        row_means = torch.mean(x, dim=1, keepdim=True)
        row_stds = torch.std(x, dim=1, keepdim=True)

        # Avoid division by zero in case of a row with constant value
        row_stds = torch.where(row_stds == 0, torch.ones_like(row_stds), row_stds)

        x_scaled = (x - row_means) / row_stds
        return x_scaled

    def postprocess(self, x):
        return x

model = pya.models.ZhangBLUP()

Define clock metadata

model.metadata["clock_name"] = 'zhangblup'
model.metadata["data_type"] = 'methylation'
model.metadata["species"] = 'Homo sapiens'
model.metadata["year"] = 2019
model.metadata["approved_by_author"] = '⌛'
model.metadata["citation"] = "Zhang, Qian, et al. \"Improved precision of epigenetic clock estimates across tissues and its implication for biological ageing.\" Genome medicine 11 (2019): 1-11."
model.metadata["doi"] = 'https://doi.org/10.1186/s13073-019-0667-1'
model.metadata["research_only"] = None
model.metadata["notes"] = None

Download clock dependencies

Download GitHub repository

github_url = "https://github.com/qzhang314/DNAm-based-age-predictor.git"
github_folder_name = github_url.split('/')[-1].split('.')[0]
os.system(f"git clone {github_url}")

0

Download from R package

%%writefile download.r

data = readRDS("DNAm-based-age-predictor/data.rds")

write.csv(data, "example_data.csv")

Writing download.r

os.system("Rscript download.r")

0

Load features

From CSV file

df = pd.read_table('DNAm-based-age-predictor/blup.coef', sep=' ')
df['feature'] = df['probe']
df['coefficient'] = df['coef']

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]])

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

From CSV file

reference_feature_values_df = pd.read_csv('example_data.csv', index_col=0)
reference_feature_values_df = reference_feature_values_df.loc[:, model.features]
model.reference_values = reference_feature_values_df.mean().tolist()

Load preprocess and postprocess objects

model.preprocess_name = 'scale_row'
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': 'Zhang, Qian, et al. "Improved precision of epigenetic clock '
             'estimates across tissues and its implication for biological '
             'ageing." Genome medicine 11 (2019): 1-11.',
 'clock_name': 'zhangblup',
 'data_type': 'methylation',
 'doi': 'https://doi.org/10.1186/s13073-019-0667-1',
 'notes': None,
 'research_only': None,
 'species': 'Homo sapiens',
 'version': None,
 'year': 2019}
reference_values: [0.05946290980445651, 0.9016779859564634, 0.8511621554128406, 0.07497523935546724, 0.08079601941558237, 0.13789119095690058, 0.959990162673912, 0.054840405638908254, 0.11271586156940745, 0.06867464793155438, 0.04092332774669377, 0.03122014881875939, 0.12091171597794977, 0.8626077673429406, 0.02002095456899887, 0.037161243530447204, 0.5228131230887364, 0.025038065219011623, 0.03411737762225109, 0.023966201717807785, 0.13213191286915785, 0.03613520841142101, 0.11053625925027737, 0.09303164766153527, 0.07697707482010466, 0.040677518106921974, 0.016422537053260692, 0.01646509240082735, 0.9634930275356334, 0.8664078943468241]... [Total elements: 319607]
preprocess_name: 'scale_row'
preprocess_dependencies: None
postprocess_name: None
postprocess_dependencies: None
features: ['cg18478105', 'cg14361672', 'cg01763666', 'cg02115394', 'cg13417420', 'cg12480843', 'cg26724186', 'cg24133276', 'cg19607165', 'cg11073926', 'cg08770523', 'cg24040570', 'cg15998406', 'cg11947782', 'cg11945228', 'cg14361409', 'cg00376553', 'cg12898275', 'cg21650422', 'cg24176744', 'cg08360726', 'cg07469408', 'cg08730728', 'cg22782271', 'cg26846647', 'cg24568647', 'cg01415275', 'cg00172270', 'cg27548741', 'cg09659208']... [Total elements: 319607]
base_model_features: None

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

base_model: LinearModel(
  (linear): Linear(in_features=319607, out_features=1, bias=True)
)

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

base_model.linear.weight: [-0.011127361096441746, 0.0005570068024098873, -0.01769556663930416, 0.009089098311960697, -0.016315005719661713, -0.012607994489371777, -0.006776333786547184, 0.005497894249856472, -0.031007202342152596, 0.007024446967989206, 0.0072049410082399845, 0.006631432566791773, -0.028644423931837082, -0.0067995828576385975, -0.003207291942089796, -0.010230086743831635, 0.002228884259238839, -0.0012665422400459647, 0.010415713302791119, -0.0016215209616348147, 0.015202521346509457, -0.0019047950627282262, -0.01444777101278305, 0.01679779589176178, -0.0016255266964435577, -0.0027738267090171576, -0.0028552687726914883, 0.0026693870313465595, 0.0018644158262759447, 0.004981260746717453]... [Tensor of shape torch.Size([1, 319607])]
base_model.linear.bias: tensor([91.1540])

%==================================== 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([[107.0536],
        [ 90.5363],
        [ 81.2531],
        [ 97.2001],
        [ 91.7565],
        [ 95.9860],
        [ 97.9471],
        [ 97.2143],
        [107.3615],
        [ 90.4772]], 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: download.r
Deleted folder: DNAm-based-age-predictor
Deleted file: example_data.csv