NeuSin#
Index#
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.NeuSin)
class NeuSin(LinearReferenceClock):
pass
[3]:
model = pya.models.NeuSin()
Define clock metadata#
[4]:
model.metadata["clock_name"] = "neusin"
model.metadata["data_type"] = "DNA methylation" # Paper: The model is based on DNA methylation measurements.
model.metadata["species"] = "Homo sapiens" # Paper: The study samples are Homo sapiens.
model.metadata["year"] = 2024
model.metadata["approved_by_author"] = "⌛"
model.metadata["citation"] = "Tong, Huige, et al. \"Cell-type specific epigenetic clocks to quantify biological age at cell-type resolution.\" Aging 16 (2024): 13452–13504."
model.metadata["doi"] = "https://doi.org/10.18632/aging.206184"
model.metadata["notes"] = "Neu-Sin is a neuron semi-intrinsic chronological-age clock: elastic-net regression was restricted to neuron age-DMCTs but fitted to methylation values not adjusted for brain cell fractions."
model.metadata["research_only"] = None
model.metadata["tissue"] = ["brain cortex"] # Paper: For training the clocks, we used one of the largest collections of prefrontal cortex (PFC) samples profiled with Illumina 450k technology, encompassing 416 samples with a wide age range (18–97 years).
model.metadata["predicts"] = ["chronological age"] # Paper: Finally, elastic net predictors of chronological age are trained from the Neu-DMCTs parameterized by a penalty parameter.
model.metadata["training_target"] = ["chronological age"] # Paper: Having identified the significant neuron-DMCTs, we next trained Elastic Net regression (glmnet R package) models (alpha = 0.5) for age, each parameterized by a different penalty parameter (lambda) value.
model.metadata["unit"] = ["years"] # Paper: For training the clocks, we used one of the largest collections of prefrontal cortex (PFC) samples profiled with Illumina 450k technology, encompassing 416 samples with a wide age range (18–97 years).
model.metadata["model_type"] = "elastic net regression" # Paper: Having identified the significant neuron-DMCTs, we next trained Elastic Net regression (glmnet R package) models (alpha = 0.5) for age, each parameterized by a different penalty parameter (lambda) value.
model.metadata["platform"] = ["Illumina 450K"] # Paper: For training the clocks, we used one of the largest collections of prefrontal cortex (PFC) samples profiled with Illumina 450k technology, encompassing 416 samples with a wide age range (18–97 years).
model.metadata["population"] = "adults" # Paper: For training the clocks, we used one of the largest collections of prefrontal cortex (PFC) samples profiled with Illumina 450k technology, encompassing 416 samples with a wide age range (18–97 years).
model.metadata["journal"] = "Aging"
model.metadata["last_author"] = "Andrew E. Teschendorff"
model.metadata["n_features"] = 672 # Paper: The official Neu-SinCoef.rda object contains 673 rows: one (Intercept) row and 672 non-intercept CpG coefficient rows.
model.metadata["citations"] = 25
model.metadata["citations_date"] = "2026-07-05"
Download clock dependencies#
[5]:
supplementary_url = "https://raw.githubusercontent.com/Duzhaozhen/OmniAge/c10fbe8cb92957520fbff1d55ae1def0691252e5/OmniAgePy/src/omniage/data/CTS/Neu-Sin.csv"
supplementary_file_name = "coefficients.csv"
os.system(f"curl -sL -o {supplementary_file_name} {supplementary_url}")
[5]:
0
Load features#
[6]:
df = pd.read_csv('coefficients.csv')
if str(df.columns[0]).startswith('Unnamed'):
df = df.iloc[:, 1:]
mask = df['probe'].astype(str).str.lower().isin(['intercept', '(intercept)'])
intercept_value = float(df.loc[mask, 'coef'].iloc[0]) if mask.any() else 0.0
coef_df = df.loc[~mask].reset_index(drop=True)
model.features = coef_df['probe'].tolist()
Load weights into base model#
[7]:
weights = torch.tensor(coef_df['coef'].tolist()).unsqueeze(0).float()
intercept = torch.tensor([intercept_value]).float()
[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': 'Tong, Huige, et al. "Cell-type-specific and '
'cell-type-independent DNA methylation clocks." Aging 16 (2024).',
'clock_name': 'neusin',
'data_type': 'methylation',
'doi': 'https://doi.org/10.18632/aging.206184',
'notes': None,
'research_only': None,
'species': 'Homo sapiens',
'version': None,
'year': 2024}
reference_values: None
preprocess_name: None
preprocess_dependencies: None
postprocess_name: None
postprocess_dependencies: None
features: ['cg10626816', 'cg13571388', 'cg17826530', 'cg06711298', 'cg08193650', 'cg10442729', 'cg17343483', 'cg20361600', 'cg21185289', 'cg16369288', 'cg22702772', 'cg26856080', 'cg06385118', 'cg18171715', 'cg18586891', 'cg05477834', 'cg15690342', 'cg18635552', 'cg18745317', 'cg25108022', 'cg00537387', 'cg08692175', 'cg25739875', 'cg18048071', 'cg19421584', 'cg22493372', 'cg02324367', 'cg05492433', 'cg16241714', 'cg26003909']... [Total elements: 672]
base_model_features: None
%==================================== Model Details ====================================%
Model Structure:
base_model: LinearModel(
(linear): Linear(in_features=672, out_features=1, bias=True)
)
%==================================== Model Details ====================================%
Model Parameters and Weights:
base_model.linear.weight: [0.6255767941474915, 0.00018867039761971682, 1.4650660753250122, -4.989912986755371, 2.8106305599212646, 3.3365237712860107, -8.365673065185547, -7.561515808105469, -2.2176127433776855, 2.238844394683838, 5.353684425354004, 18.882240295410156, -1.537793755531311, 18.469179153442383, 0.3016071319580078, -0.4679134786128998, 0.7296689748764038, -9.179381370544434, 0.04645940288901329, 7.833886623382568, -2.897672414779663, -21.346012115478516, 9.050196647644043, 0.5711203813552856, 0.47357064485549927, 0.11948469281196594, 0.0023688615765422583, -1.3019375801086426, 57.94570541381836, -2.4218344688415527]... [Tensor of shape torch.Size([1, 672])]
base_model.linear.bias: tensor([20.1315])
%==================================== 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([[ -26.3359],
[ 213.3675],
[-104.1039],
[-339.0749],
[ -66.5274],
[ 113.9317],
[ 141.6260],
[ -65.5180],
[ -2.5413],
[-400.5478]], 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.csv