DeconvoluteBloodEPIC

DeconvoluteBloodEPIC#

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:

[9]:

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

Instantiate model class#

[10]:

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

print_entire_class(pya.models.DeconvoluteBloodEPIC)

class DeconvoluteBloodEPIC(DeconvolutionSingleCell):
    def __init__(self):
        super().__init__()


[11]:

model = pya.models.DeconvoluteBloodEPIC()

Define clock metadata#

[12]:

model.metadata["clock_name"] = 'deconvolutebloodepiccd4tcell'
model.metadata["data_type"] = 'methylation'
model.metadata["species"] = 'Homo sapiens'
model.metadata["year"] = 2024
model.metadata["approved_by_author"] = '⌛'
model.metadata["citation"] = "Ying, Kejun, et al. \"A unified framework for systematic curation and evaluation of aging biomarkers.\" Nature Aging (2025): 1-17."
model.metadata["doi"] = "https://doi.org/10.1038/s43587-025-00987-y"
model.metadata["research_only"] = None
model.metadata["notes"] = "Estimated proportion of cd4_t_cell from EPIC reference."

Download clock dependencies#

Download reference file#

[13]:

coeff_url = "https://raw.githubusercontent.com/bio-learn/biolearn/master/biolearn/data/EPIC_salas_18_reference.csv"
os.system(f"curl -L {coeff_url} -o EPIC_salas_18_reference.csv")

[13]:

0

Load features#

From CSV file#

[14]:

import numpy as np
import pandas as pd

ref = pd.read_csv('EPIC_salas_18_reference.csv', index_col=0)
model.features = ref.index.astype(str).tolist()

ref_matrix = torch.tensor(ref.values, dtype=torch.float64)
pseudo_inv = torch.linalg.pinv(ref_matrix)

model.pseudo_inv = pseudo_inv
model.cell_index = 3
model.reference_values = torch.nanmean(ref_matrix, dim=1)

Load weights into base model#

From CSV file#

[15]:

# No linear base model; deconvolution logic in model forward

Linear model#

[16]:

model.base_model = None

Load reference values#

[17]:

# reference_values already set above

Load preprocess and postprocess objects#

[18]:

model.preprocess_name = "fill_with_reference_means"
model.preprocess_dependencies = None

[19]:

model.postprocess_name = None
model.postprocess_dependencies = None

Check all clock parameters#

[20]:

pya.utils.print_model_details(model)


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

training: True
metadata: {'approved_by_author': '⌛',
 'citation': 'Ying, Kejun, et al. "A unified framework for systematic curation '
             'and evaluation of aging biomarkers." Nature Aging (2025): 1-17.',
 'clock_name': 'deconvolutebloodepiccd4tcell',
 'data_type': 'methylation',
 'doi': 'https://doi.org/10.1038/s43587-025-00987-y',
 'notes': 'Estimated proportion of cd4_t_cell from EPIC reference.',
 'research_only': None,
 'species': 'Homo sapiens',
 'version': None,
 'year': 2024}
reference_values: [0.20518415451984126, 0.19970558314682532, 0.1024157725119047, 0.2008561107023811, 0.14881559691666668, 0.18691947926984118, 0.09904868163095237, 0.11866279766269845, 0.11413279887698413, 0.07614163463888889, 0.11287183193253969, 0.09002383478571424, 0.15332935412698398, 0.10906152481746033, 0.12821537873412694, 0.11714246567063487, 0.1349594052698413, 0.21058724882142854, 0.23903708456349196, 0.09275976726984132, 0.08500618109523812, 0.17428245038095244, 0.24038344935714295, 0.24988523996428577, 0.1389251376904763, 0.11076903522222221, 0.10888998828968255, 0.09822708860317463, 0.09986797370634924, 0.11328396424206344]... [Tensor of shape torch.Size([600])]
preprocess_name: 'fill_with_reference_means'
preprocess_dependencies: None
postprocess_name: None
postprocess_dependencies: None
features: ['cg02091275', 'cg10613215', 'cg04738410', 'cg23954655', 'cg10825315', 'cg12093275', 'cg05915362', 'cg15472145', 'cg14781394', 'cg03753191', 'cg04554131', 'cg08708961', 'cg05366453', 'cg23889684', 'cg09936080', 'cg11612354', 'cg13525276', 'cg21264165', 'cg24197536', 'cg19935718', 'cg24756631', 'cg14637146', 'cg11311865', 'cg04449166', 'cg08311647', 'cg21870144', 'cg06516865', 'cg03172796', 'cg25446602', 'cg24102319']... [Total elements: 600]
base_model_features: None
base_model: None
pseudo_inv: [0.018423516597868533, 0.02076496108902344, 0.006246045739563567, 0.017322627415437906, 0.012596462279237032, 0.014680027443715469, 0.005387403052654981, 0.00826322984364358, 0.006720451696782447, 0.003520144956793594, 0.007097605150112215, 0.006828305361872053, 0.009242538044463792, 0.005067549321932598, 0.00998902642967594, 0.009749104467339021, 0.010083925381389934, 0.01566659748873227, 0.017857728483860698, 0.005648755947299582, 0.003880839808950153, 0.010944187408221806, 0.014789742065456597, 0.01823321395305361, 0.009616296123845524, 0.005330229811626641, 0.007168874993235975, 0.003581639488212511, 0.004981727200100809, 0.006052278008950252]... [Tensor of shape torch.Size([6, 600])]
cell_index: 3

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


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


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

Basic Test#

[21]:

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

[21]:

tensor([[0.0430],
        [0.7736],
        [0.3586],
        [0.0814],
        [0.3474],
        [0.2807],
        [0.8061],
        [0.5854],
        [0.1188],
        [0.5425]], dtype=torch.float64)

Save torch model#

[22]:

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

Clear directory#

[23]:

# 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: EPIC_salas_18_reference.csv
Contents