TwelveCellDeconvoluteBloodEPIC

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.TwelveCellDeconvoluteBloodEPIC)

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

model = pya.models.TwelveCellDeconvoluteBloodEPIC()

Define clock metadata

model.metadata["clock_name"] = "twelvecelldeconvolutebloodepicbmem"
model.metadata["data_type"] = "DNA methylation"  # Paper: The TwelveCell model is a DeconvolutionModel whose reference rows are CpG loci.
model.metadata["species"] = "Homo sapiens"  # Paper: The registry declares species Human for TwelveCellDeconvoluteBloodEPIC.
model.metadata["year"] = 2022
model.metadata["approved_by_author"] = "⌛"
model.metadata["citation"] = "Salas, L.A., Zhang, Z., Koestler, D.C. et al. Enhanced cell deconvolution of peripheral blood using DNA methylation for high-resolution immune profiling. Nature Communications 13, 761 (2022)."
model.metadata["doi"] = "https://doi.org/10.1038/s41467-021-27864-7"
model.metadata["notes"] = "Reference-based constrained deconvolution returning the memory B cell proportion from EPIC-array blood methylation. The published EPIC IDOL-Ext library used 1,200 CpGs selected to optimize recovery of known artificial-mixture cell-type proportions; pyaging instead inherits Biolearn’s undocumented 240-CpG replacement, whose rows reproducibly comprise 10 positive and 10 negative maximal cell-versus-other methylation contrasts per subtype and are not a subset of the published 1,200 probes."
model.metadata["research_only"] = None
model.metadata["tissue"] = ["purified blood leukocytes"]  # Paper: The reference-matrix columns are twelve leukocyte subtypes used to deconvolve peripheral blood.
model.metadata["predicts"] = ["memory B cell proportion"]  # Paper: The model output is Cell Proportions and Bmem is one of the twelve returned columns.
model.metadata["training_target"] = ["cell-type proportions"]  # Paper: IDOL used artificial-mixture ground truth with known, prespecified proportions of the 12 cell types and optimized libraries by comparing deconvolution estimates with those known proportions.
model.metadata["unit"] = ["proportion"]  # Paper: The solver constrains each estimated cell proportion to 0–1 and all proportions to sum to one.
model.metadata["model_type"] = "reference-based constrained deconvolution"  # Paper: The implementation minimizes reference-matrix reconstruction error by constrained quadratic programming.
model.metadata["platform"] = ["Illumina EPIC"]  # Paper: The TwelveCell model registry sets platform to EPIC.
model.metadata["population"] = "adults"  # Paper: Reference cells were isolated from 41 male and 15 female anonymous healthy donors with mean age 32.2 years and range 19–58 years, spanning multiple self-identified ancestries.
model.metadata["journal"] = "Nature Communications"
model.metadata["last_author"] = "Brock C. Christensen"
model.metadata["n_features"] = 240
model.metadata["citations"] = 13
model.metadata["citations_date"] = "2026-07-05"

Download clock dependencies

Download reference file

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

0

Load features

From CSV file

import numpy as np
import pandas as pd

ref = pd.read_csv('twelve_cell_deconv.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 = 1
model.reference_values = torch.nanmean(ref_matrix, dim=1)

Load weights into base model

From CSV file

# No linear base model; deconvolution logic in model forward

Linear model

model.base_model = None

Load reference values

# reference_values already set above

Load preprocess and postprocess objects

model.preprocess_name = "fill_with_reference_means"
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': 'Ying, Kejun, et al. "A unified framework for systematic curation '
             'and evaluation of aging biomarkers." Nature Aging (2025): 1-17.',
 'clock_name': 'twelvecelldeconvolutebloodepicbmem',
 'data_type': 'methylation',
 'doi': 'https://doi.org/10.1038/s43587-025-00987-y',
 'notes': 'Estimated proportion of Bmem from 12-cell EPIC reference.',
 'research_only': None,
 'species': 'Homo sapiens',
 'version': None,
 'year': 2024}
reference_values: [0.9106685833333333, 0.8335768333333333, 0.8720161666666666, 0.8286470833333333, 0.92628525, 0.9155413333333334, 0.8792788333333332, 0.9127326666666665, 0.9067565833333332, 0.84800775, 0.10073516666666667, 0.14440299999999998, 0.049399916666666675, 0.08766050000000002, 0.07896441666666666, 0.12878258333333334, 0.16374524999999998, 0.13815541666666667, 0.17540216666666666, 0.1698345, 0.9202164166666665, 0.8607305833333334, 0.9136148333333334, 0.9245049999999999, 0.8901303333333334, 0.9271245, 0.8883705833333333, 0.8855881666666668, 0.9244469166666666, 0.92171125]... [Tensor of shape torch.Size([240])]
preprocess_name: 'fill_with_reference_means'
preprocess_dependencies: None
postprocess_name: None
postprocess_dependencies: None
features: ['cg11778706', 'cg13745692', 'cg15163862', 'cg15667493', 'cg09590647', 'cg24160371', 'cg04200580', 'cg02177087', 'cg02690807', 'cg08486432', 'cg08674813', 'cg17565444', 'cg20208538', 'cg08747761', 'cg16576285', 'cg08269714', 'cg10931172', 'cg18421366', 'cg06805218', 'cg21268578', 'cg23635663', 'cg10712263', 'cg03984633', 'cg27576286', 'cg00789615', 'cg20591136', 'cg08012294', 'cg19811231', 'cg13335048', 'cg27109907']... [Total elements: 240]
base_model_features: None
base_model: None
pseudo_inv: [0.0062597217235298664, 0.01539477951995796, 0.003836934604777173, 0.005564101437478809, 0.002277140363479023, 0.006073633184626901, 0.008477183290511526, -0.0001975656527457585, 0.005601139656499912, 0.007094362071883866, -0.006240708820602573, -0.009260375574434002, -0.0010103501546960773, -2.0931822748843616e-05, -0.003443105142629081, -0.006973754074381415, -0.014081560765767536, -0.01165024465832652, -0.017254358157385866, -0.018101141218108914, 0.016011891819700665, 0.007716146910953028, 0.01145146135203884, 0.007735843885753704, 0.014959580407076114, 0.011932867918461359, 0.014137094238940516, 0.016570818459337337, 0.006383014308174419, 0.007057464604785132]... [Tensor of shape torch.Size([12, 240])]
cell_index: 1

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


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


%==================================== 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([[0.0979],
        [0.0000],
        [0.0000],
        [0.0000],
        [0.0000],
        [0.0000],
        [0.0000],
        [0.0620],
        [0.0000],
        [0.0000]], dtype=torch.float64)

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: twelve_cell_deconv.csv