DNAmFILi#

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.DNAmFILi)

class DNAmFILi(LinearReferenceClock):
    pass


[3]:

model = pya.models.DNAmFILi()

Define clock metadata#

[4]:

model.metadata["clock_name"] = "dnamfili"
model.metadata["data_type"] = "DNA methylation"  # Paper: A DNA methylation-based score was derived to predict frailty.
model.metadata["species"] = "Homo sapiens"  # Paper: A DNA methylation-based score was derived to predict frailty.
model.metadata["year"] = 2022
model.metadata["approved_by_author"] = "⌛"
model.metadata["citation"] = "Li, X. et al. Derivation and validation of an epigenetic frailty risk score in population-based cohorts of older adults. Nature Communications 13, 5269 (2022)."
model.metadata["doi"] = "https://doi.org/10.1038/s41467-022-32893-x"
model.metadata["notes"] = "Epigenetic frailty risk score (eFRS), a weighted 20-CpG whole-blood DNA-methylation score selected by LASSO from replicated frailty-associated loci."
model.metadata["research_only"] = None
model.metadata["tissue"] = ["whole blood"]  # Paper: A DNA methylation-based score was derived to predict frailty.
model.metadata["predicts"] = ["frailty risk"]  # Paper: A DNA methylation-based score was derived to predict frailty.
model.metadata["training_target"] = ["frailty"]  # Paper: Frailty was defined by a deficit-accumulation frailty index.
model.metadata["unit"] = ["unitless"]  # Paper: The eFRS was constructed as a weighted CpG score.
model.metadata["model_type"] = "LASSO regression"  # Paper: LASSO regression selected candidates and constructed eFRS.
model.metadata["platform"] = ["Illumina EPIC", "Illumina 450K"]  # Paper: EPIC was used in subsets I/II; 450K in subset III.
model.metadata["population"] = "older adults"  # Paper: ESTHER recruited adults aged 50-75; KORA-Age enrolled adults aged at least 65.
model.metadata["journal"] = "Nature Communications"
model.metadata["last_author"] = "Hermann Brenner"
model.metadata["n_features"] = 20
model.metadata["citations"] = 22
model.metadata["citations_date"] = "2026-07-05"

Download clock dependencies#

[5]:

os.system(f"curl -sL -o DNAmFI_Li_CpGs.rda https://raw.githubusercontent.com/HigginsChenLab/methylCIPHER/19b12296b0d7eb7055a97d068064df635f44ce3e/data/DNAmFI_Li_CpGs.rda")

[5]:

0

[6]:

%%writefile download.r

library(jsonlite)
load("DNAmFI_Li_CpGs.rda")
write_json(DNAmFI_Li_CpGs, "coefficients.json", digits = 10)

Writing download.r

[7]:

os.system("Rscript download.r")

[7]:

0

Load features#

[8]:

coef_df = pd.DataFrame(json.load(open('coefficients.json')))
model.features = coef_df['CpG'].tolist()

Load weights into base model#

[9]:

weights = torch.tensor(coef_df['Beta'].tolist()).unsqueeze(0).float()
intercept = torch.tensor([0.204]).float()

[10]:

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#

[11]:

model.reference_values = None

Load preprocess and postprocess objects#

[12]:

model.preprocess_name = None
model.preprocess_dependencies = None

[13]:

model.postprocess_name = None
model.postprocess_dependencies = None

Check all clock parameters#

[14]:

pya.utils.print_model_details(model)


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

training: True
metadata: {'approved_by_author': '⌛',
 'citation': 'Li, Xiaoyu, et al. "A DNA methylation-based epigenetic frailty '
             'score in older adults." Nature Communications 13.1 (2022): 5269.',
 'clock_name': 'dnamfili',
 'data_type': 'methylation',
 'doi': 'https://doi.org/10.1038/s41467-022-32893-x',
 'notes': None,
 'research_only': None,
 'species': 'Homo sapiens',
 'version': None,
 'year': 2022}
reference_values: None
preprocess_name: None
preprocess_dependencies: None
postprocess_name: None
postprocess_dependencies: None
features: ['cg00921350',
 'cg01234420',
 'cg02867102',
 'cg03725309',
 'cg04955914',
 'cg07312601',
 'cg07349348',
 'cg08463758',
 'cg10408430',
 'cg11700584',
 'cg12510708',
 'cg13570972',
 'cg15058210',
 'cg15380836',
 'cg17860366',
 'cg17971578',
 'cg18791730',
 'cg19267254',
 'cg21656937',
 'cg23458887']
base_model_features: None

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

base_model: LinearModel(
  (linear): Linear(in_features=20, out_features=1, bias=True)
)

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

base_model.linear.weight: tensor([[-0.2090, -0.1000, -0.0160, -0.2930, -0.1460, -0.0840,  0.1580,  0.1370,
          0.2480, -0.1010, -0.0490,  0.0640, -0.0570, -0.1800, -0.1440,  0.3150,
         -0.0750, -0.1760, -0.0250, -0.0770]])
base_model.linear.bias: tensor([0.2040])

%==================================== Model Details ====================================%

Basic test#

[15]:

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

[15]:

tensor([[-1.3837],
        [-0.2305],
        [-0.8730],
        [ 0.7649],
        [ 0.6257],
        [ 0.3401],
        [ 0.5390],
        [-1.0176],
        [ 0.3744],
        [ 0.9479]], dtype=torch.float64, grad_fn=<AddmmBackward0>)

Save torch model#

[16]:

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

Clear directory#

[17]:

# 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 file: DNAmFI_Li_CpGs.rda
Deleted file: coefficients.json