ProstateCancerKirby#
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.ProstateCancerKirby)
class ProstateCancerKirby(LinearReferenceClock):
pass
[3]:
model = pya.models.ProstateCancerKirby()
Define clock metadata#
[4]:
model.metadata["clock_name"] = 'prostatecancerkirby'
model.metadata["data_type"] = 'methylation'
model.metadata["species"] = 'Homo sapiens'
model.metadata["year"] = 2017
model.metadata["approved_by_author"] = '⌛'
model.metadata["citation"] = "Kirby, Michael K., et al. \"Genome-wide DNA methylation measurements in prostate tissues uncovers novel prostate cancer diagnostic biomarkers and predictors of progression.\" BMC Cancer 17.1 (2017): 273."
model.metadata["doi"] = "https://doi.org/10.1186/s12885-017-3252-2"
model.metadata["research_only"] = None
model.metadata["notes"] = "Prostate-tissue DNA-methylation diagnostic classifier that distinguishes malignant prostate cancer from benign-adjacent tissue, built by logistic regression on genome-wide Illumina 450K methylation from 73 tumor and 63 benign-adjacent prostate samples. The differentially methylated signature was also examined as a predictor of disease progression."
model.metadata["tissue"] = 'prostate tissue (fresh-frozen malignant and benign-adjacent)'
model.metadata["predicts"] = 'prostate cancer diagnosis (malignant vs benign tissue)'
model.metadata["unit"] = 'probability (0-1)'
model.metadata["model_type"] = 'Logistic regression'
model.metadata["platform"] = 'Illumina 450K'
model.metadata["population"] = 'adult men (prostate cancer patients)'
model.metadata["journal"] = 'BMC Cancer'
model.metadata["last_author"] = 'R Myers'
model.metadata["n_features"] = 3
model.metadata["citations"] = 61
model.metadata["citations_date"] = '2026-07-05'
Download clock dependencies#
[5]:
os.system(f"curl -sL -o prostatecancerkirby.xlsx https://static-content.springer.com/esm/art%3A10.1186%2Fs12885-017-3252-2/MediaObjects/12885_2017_3252_MOESM4_ESM.xlsx")
[5]:
0
Load features#
[6]:
raw = pd.read_excel('prostatecancerkirby.xlsx', sheet_name=0, header=None)
hdr_cell = val_cell = None
for i in range(len(raw)):
for j in range(raw.shape[1]):
c = str(raw.iloc[i, j])
if '(Intercept)' in c and 'cg' in c:
hdr_cell = c
val_cell = str(raw.iloc[i + 1, j])
break
if hdr_cell:
break
names = hdr_cell.split()
nums = [float(x) for x in val_cell.split()]
intercept_value = 0.0
feats, coefs = [], []
for name, num in zip(names, nums):
if 'Intercept' in name:
intercept_value = num
else:
feats.append(name)
coefs.append(num)
model.features = feats
/Users/lucascamillo/pyaging/.venv/lib/python3.13/site-packages/openpyxl/worksheet/_reader.py:329: UserWarning: Unknown extension is not supported and will be removed
warn(msg)
Load weights into base model#
[7]:
weights = torch.tensor(coefs).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': 'Kirby, Michael K., et al. "Genome-wide DNA methylation '
'measurements in prostate tissues uncovers novel prostate cancer '
'diagnostic biomarkers and predictors of progression." BMC Cancer '
'17.1 (2017): 273.',
'clock_name': 'prostatecancerkirby',
'data_type': 'methylation',
'doi': 'https://doi.org/10.1186/s12885-017-3252-2',
'notes': None,
'research_only': None,
'species': 'Homo sapiens',
'version': None,
'year': 2017}
reference_values: None
preprocess_name: None
preprocess_dependencies: None
postprocess_name: None
postprocess_dependencies: None
features: ['cg00054525', 'cg16794576', 'cg24581650']
base_model_features: None
%==================================== Model Details ====================================%
Model Structure:
base_model: LinearModel(
(linear): Linear(in_features=3, out_features=1, bias=True)
)
%==================================== Model Details ====================================%
Model Parameters and Weights:
base_model.linear.weight: tensor([[-17.0370, 24.1830, -13.8250]])
base_model.linear.bias: tensor([6.5240])
%==================================== 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([[ 3.3665],
[ 15.9152],
[ -7.6545],
[ 9.1350],
[ 7.7513],
[ 24.9928],
[ -6.7956],
[ 17.0494],
[ 17.7305],
[-18.3624]], 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: prostatecancerkirby.xlsx