ENCen100#

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.ENCen100)

class ENCen100(pyagingModel):
    def __init__(self):
        super().__init__()

    def preprocess(self, x):
        return x

    def postprocess(self, x):
        return x


[3]:

model = pya.models.ENCen100()

Define clock metadata#

[4]:

model.metadata["clock_name"] = "encen100"
model.metadata["data_type"] = "DNA methylation"  # Paper: DNA methylation clocks
model.metadata["species"] = "Homo sapiens"  # Paper: study individuals
model.metadata["year"] = 2023
model.metadata["approved_by_author"] = "⌛"
model.metadata["citation"] = "Dec, Eric, et al. \"Centenarian clocks: epigenetic clocks for validating claims of exceptional longevity.\" GeroScience 45 (2023): 1817–1835."
model.metadata["doi"] = "https://doi.org/10.1007/s11357-023-00731-7"
model.metadata["notes"] = "Elastic-net DNAm-age clock trained only in 184 centenarians aged 100–115; the authors advise against routine use but identify possible utility for evaluating supercentenarians."
model.metadata["research_only"] = None
model.metadata["tissue"] = ["whole blood", "saliva", "buccal epithelium"]  # Paper: blood, saliva, and buccals cells
model.metadata["predicts"] = ["chronological age"]  # Paper: DNAm age was defined as predicted age
model.metadata["training_target"] = ["chronological age"]  # Paper: regress chronological age on the CpG probes
model.metadata["unit"] = ["years"]  # Paper: individuals aged 40 years or older; predicted age
model.metadata["model_type"] = "elastic net regression"  # Paper: alpha parameter ... 0.5 (elastic net regression)
model.metadata["platform"] = ["Illumina 450K", "Illumina EPIC"]  # Paper: Infinium 450 K array and the Infinium methylation EPIC beadchip
model.metadata["population"] = "centenarians"  # Paper: trained only on centenarian samples; age group 100–115
model.metadata["journal"] = "GeroScience"
model.metadata["last_author"] = "Steve Horvath"
model.metadata["n_features"] = 198
model.metadata["citations"] = 45
model.metadata["citations_date"] = "2026-07-05"

Download clock dependencies#

Download GitHub repository#

[5]:

github_url = "https://github.com/victorychain/Centenarian-Clock.git"
github_folder_name = github_url.split('/')[-1].split('.')[0]
os.system(f"git clone {github_url}")

[5]:

0

Load features#

From CSV file#

[6]:

df = pd.read_csv('Centenarian-Clock/clocks/final_clocks.csv', index_col=0).T
df = df[df['ENCen100+'] != 0]
df = df.reset_index()

model.features = df['index'][1:].tolist()

Load weights into base model#

[7]:

weights = torch.tensor(df['ENCen100+'][1:].tolist()).unsqueeze(0).float()
intercept = torch.tensor([df['ENCen100+'][0]]).float()

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 = None

Load preprocess and postprocess objects#

[10]:

model.preprocess_name = None
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': 'Dec, Eric, et al. "Centenarian clocks: epigenetic clocks for '
             'validating claims of exceptional longevity." GeroScience (2023): '
             '1-19.',
 'clock_name': 'encen100',
 'data_type': 'methylation',
 'doi': 'https://doi.org/10.1007/s11357-023-00731-7',
 'notes': None,
 'research_only': None,
 'species': 'Homo sapiens',
 'version': None,
 'year': 2023}
reference_values: None
preprocess_name: None
preprocess_dependencies: None
postprocess_name: None
postprocess_dependencies: None
features: ['cg19923810', 'cg06727198', 'cg13587552', 'cg12278474', 'cg00944884', 'cg02309594', 'cg26131911', 'cg01918888', 'cg22748573', 'cg03557698', 'cg02008416', 'cg01909487', 'cg22215192', 'cg19490266', 'cg22041635', 'cg03265671', 'cg16054275', 'cg11908570', 'cg11314684', 'cg21825027', 'cg10881225', 'cg27072387', 'cg10198837', 'cg19910382', 'cg15903395', 'cg22854546', 'cg22774472', 'cg08147886', 'cg24938727', 'cg06613840']... [Total elements: 198]
base_model_features: None

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

base_model: LinearModel(
  (linear): Linear(in_features=198, out_features=1, bias=True)
)

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

base_model.linear.weight: [-0.09928683191537857, 0.49298134446144104, 0.4511302411556244, -0.7807422280311584, -1.8210344314575195, 0.5576984882354736, -7.65609884262085, -1.0797690153121948, -1.6125882863998413, -0.5077138543128967, 0.6321693062782288, 2.269329309463501, 0.48257339000701904, 2.2945704460144043, 17.37386703491211, 0.8210453987121582, -0.1428677886724472, 20.877824783325195, -0.7569608688354492, -4.292027950286865, 1.1173136234283447, 3.3253836631774902, 2.960419178009033, 0.7145973443984985, 1.6346321105957031, -20.96908950805664, 0.020137546584010124, -2.13246488571167, 0.9701406955718994, 3.8667945861816406]... [Tensor of shape torch.Size([1, 198])]
base_model.linear.bias: tensor([73.9947])

%==================================== 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([[ 38.4278],
        [126.9503],
        [180.1369],
        [153.0248],
        [-29.4523],
        [  8.3359],
        [-21.7442],
        [165.3959],
        [204.0825],
        [ 83.8679]], 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 folder: Centenarian-Clock