IntrinClock#
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.IntrinClock)
class IntrinClock(pyagingModel):
def __init__(self):
super().__init__()
def preprocess(self, x):
return x
def postprocess(self, x):
"""
Applies an anti-logarithmic linear transformation to a PyTorch tensor.
"""
adult_age = 20
# Create a mask for negative and non-negative values
mask_negative = x < 0
mask_non_negative = ~mask_negative
# Initialize the result tensor
age_tensor = torch.empty_like(x)
# Exponential transformation for negative values
age_tensor[mask_negative] = (1 + adult_age) * torch.exp(x[mask_negative]) - 1
# Linear transformation for non-negative values
age_tensor[mask_non_negative] = (1 + adult_age) * x[mask_non_negative] + adult_age
return age_tensor
[3]:
model = pya.models.IntrinClock()
Define clock metadata#
[4]:
model.metadata["clock_name"] = "intrinclock"
model.metadata["data_type"] = "DNA methylation" # Paper: IntrinClock uses CpG DNA methylation beta values.
model.metadata["species"] = "Homo sapiens" # Paper: The clock database and sorted immune-cell experiments used human samples.
model.metadata["year"] = 2024
model.metadata["approved_by_author"] = "⌛"
model.metadata["citation"] = "Tomusiak, A., et al. “Development of an epigenetic clock resistant to changes in immune cell composition.” Communications Biology 7, 934 (2024)."
model.metadata["doi"] = "https://doi.org/10.1038/s42003-024-06609-4"
model.metadata["notes"] = "Multi-tissue chronological-age clock designed by excluding CpGs associated with CD8+ T-cell differentiation, then fitting two sequential elastic-net models so predictions remain stable across immune-cell composition. The article reports 381 CpGs; the official lambda.min model and this implementation both use the same 380 non-zero CpG inputs."
model.metadata["research_only"] = None
model.metadata["tissue"] = ["multi-tissue"] # Paper: Training used samples from many tissues, with the majority from blood.
model.metadata["predicts"] = ["chronological age"] # Paper: IntrinClock was developed as an epigenetic age predictor and evaluated against chronological age.
model.metadata["training_target"] = ["chronological age"] # Paper: Ages were transformed using Horvath's original clock formula before training.
model.metadata["unit"] = ["years"] # Paper: pyaging inverse-transforms the linear score with the Horvath anti-log/linear function and returns years.
model.metadata["model_type"] = "two-stage elastic net regression" # Paper: Two elastic-net glmnet models were fit with alpha 0.5 and tenfold cross-validation.
model.metadata["platform"] = ["Illumina 450K", "Illumina EPIC"] # Paper: The fitting database contained samples measured on 450K or EPIC arrays.
model.metadata["population"] = "all ages" # Paper: After quality control and a 75:25 split, 9,104 samples trained the model and 2,994 validated it.
model.metadata["journal"] = "Communications Biology"
model.metadata["last_author"] = "Eric Verdin"
model.metadata["n_features"] = 380 # Paper: At lambda.min, the official serialized cv.glmnet model contains 380 non-zero CpG coefficients, and pyaging contains the identical 380-probe set.
model.metadata["citations"] = 53
model.metadata["citations_date"] = "2026-07-05"
Download clock dependencies#
[5]:
coefficient_dict = {
'cg00054496': 0.629765,
'cg00055555': 0.000478,
'cg00088042': 0.542504,
'cg00107606': -0.602358,
'cg00359604': -0.207408,
'cg00448707': 0.101321,
'cg00454305': 0.214177,
'cg00480331': 0.279553,
'cg00491255': 0.235923,
'cg00579423': -0.023261,
'cg00583733': -0.187858,
'cg00588393': 0.306040,
'cg00590036': 0.946985,
'cg00593462': 0.339070,
'cg00716277': -0.117843,
'cg00734800': -0.282424,
'cg00751156': 0.895214,
'cg00753885': -0.463940,
'cg00790928': -0.333871,
'cg00792123': -0.455670,
'cg00796360': -0.040682,
'cg01028142': 0.248537,
'cg01080924': -0.063070,
'cg01131866': -0.143417,
'cg01153342': -0.434237,
'cg01176694': -0.164361,
'cg01260146': -0.685730,
'cg01410876': 0.000990,
'cg01426818': 0.090433,
'cg01447660': -0.377915,
'cg01483824': 0.001925,
'cg01632288': 0.020347,
'cg01676322': -0.008812,
'cg01723606': 0.150160,
'cg01747664': -0.195955,
'cg01748892': 0.291528,
'cg01773685': 0.108342,
'cg01945641': 0.077529,
'cg01948062': -0.243899,
'cg02018277': -0.101781,
'cg02071825': 0.663272,
'cg02118627': -0.015532,
'cg02273647': 0.098363,
'cg02315513': 0.163021,
'cg02372745': 0.844674,
'cg02605776': 0.102264,
'cg02632185': 0.219644,
'cg02677192': 0.075650,
'cg02695349': 0.014691,
'cg02741548': -0.230018,
'cg02773698': 0.154705,
'cg02798181': -0.012452,
'cg02813298': -0.021371,
'cg02821342': -0.835542,
'cg02869559': -0.178805,
'cg02905830': -0.065400,
'cg03039990': -0.112718,
'cg03065311': 0.144953,
'cg03080043': 0.027251,
'cg03260211': 0.219926,
'cg03292213': -0.095841,
'cg03331387': 0.009966,
'cg03404662': 0.240773,
'cg04035728': -0.020864,
'cg04193160': 0.189600,
'cg04232649': -0.303726,
'cg04425110': 0.039951,
'cg04435719': -0.424840,
'cg04461859': 0.035512,
'cg04508804': 0.017993,
'cg04568797': -0.162114,
'cg04596060': -0.480476,
'cg04768459': -0.195784,
'cg04847146': -0.088714,
'cg04875128': 0.333810,
'cg04897804': 0.095390,
'cg04946721': 0.132790,
'cg04982874': 0.030834,
'cg05147654': -0.012265,
'cg05324516': -0.243302,
'cg05396044': 1.052750,
'cg05442902': -0.380687,
'cg05473871': -0.195023,
'cg05502081': -0.317073,
'cg05527430': 0.228954,
'cg05638500': 0.404251,
'cg05675373': 0.052474,
'cg05714496': -0.140482,
'cg05760722': -0.169668,
'cg05782445': 0.243627,
'cg05790551': 0.689393,
'cg05823563': -0.221066,
'cg05826458': 0.063505,
'cg05896926': 0.111656,
'cg05915866': -0.233932,
'cg06208270': -0.161155,
'cg06279276': 0.001596,
'cg06339542': -0.105458,
'cg06375761': -0.013404,
'cg06385324': 1.149900,
'cg06460983': 0.242894,
'cg06462666': -0.092600,
'cg06526721': -0.016389,
'cg06568490': 0.250606,
'cg06685111': -0.449694,
'cg06739520': 0.608522,
'cg06766273': -0.442990,
'cg06785746': 0.062742,
'cg06836406': 0.176486,
'cg06889422': -0.063114,
'cg06943141': 0.077398,
'cg06965409': -0.448577,
'cg06975196': -0.177409,
'cg07077115': -0.095823,
'cg07082267': -0.237335,
'cg07158339': -0.076210,
'cg07292235': 0.012162,
'cg07337598': 0.059696,
'cg07477282': 1.446001,
'cg07589899': 0.563002,
'cg07739179': 0.034575,
'cg07759394': -0.350554,
'cg07955995': 0.287813,
'cg08033031': -0.210983,
'cg08046044': 0.234338,
'cg08074084': 0.270753,
'cg08097417': 2.583904,
'cg08169949': 0.730853,
'cg08279008': -0.334302,
'cg08296037': -0.057226,
'cg08356445': 0.145932,
'cg08357125': -0.177629,
'cg08482080': -0.361281,
'cg08521677': -0.385882,
'cg08857478': -0.231122,
'cg08993878': -0.083171,
'cg09036297': 0.219183,
'cg09105193': 0.594248,
'cg09214983': -0.150207,
'cg09278098': -0.081549,
'cg09281539': -0.130365,
'cg09338875': -0.653133,
'cg09406384': -0.873546,
'cg09553982': 0.029792,
'cg09624130': -0.162465,
'cg09661809': 0.320360,
'cg09692396': -0.493154,
'cg09693106': -0.027079,
'cg09809672': -0.153914,
'cg09841001': -0.081456,
'cg09846458': -0.189517,
'cg09910998': -0.109396,
'cg09962925': 0.512151,
'cg09971754': -0.199292,
'cg10064339': -0.140178,
'cg10070101': -0.089134,
'cg10118784': 0.281102,
'cg10163222': -0.034615,
'cg10192736': -0.270267,
'cg10307580': -0.143452,
'cg10315903': 0.051591,
'cg10373645': -0.153072,
'cg10381888': 0.196570,
'cg10523019': 0.159604,
'cg10552698': -0.376593,
'cg10561067': -0.158230,
'cg10596537': -0.055959,
'cg10788210': 2.527910,
'cg10838157': -0.176249,
'cg10858686': -0.077274,
'cg10933003': 0.163029,
'cg10951117': 0.025426,
'cg11051055': 0.201423,
'cg11059561': 0.318553,
'cg11098525': 0.337549,
'cg11109027': -0.805256,
'cg11126313': 0.209309,
'cg11176990': 0.359544,
'cg11401866': 0.105506,
'cg11431402': 0.017453,
'cg11527930': 0.085740,
'cg11539664': 0.242090,
'cg11539674': 0.085122,
'cg11582617': -0.079856,
'cg11789185': 0.337167,
'cg11791577': -0.114446,
'cg11825926': -0.271932,
'cg11989576': 0.111367,
'cg12309479': -0.205215,
'cg12340166': 0.071403,
'cg12366582': -0.686739,
'cg12397924': -0.112834,
'cg12497786': -0.103957,
'cg12497883': 0.062538,
'cg12709970': -0.600442,
'cg12791555': 0.126912,
'cg12810523': -0.133198,
'cg12848614': -0.199842,
'cg12850242': 0.042669,
'cg12924510': -0.014322,
'cg12948621': 0.167489,
'cg12981137': 0.088587,
'cg13085980': -0.065387,
'cg13136596': -0.148944,
'cg13204699': -0.071927,
'cg13246426': 0.252035,
'cg13251484': -0.454989,
'cg13365340': -0.184025,
'cg13443627': 0.059344,
'cg13494498': 0.244286,
'cg13575298': 0.291580,
'cg13683374': -0.104213,
'cg13697378': 0.083463,
'cg13706079': 0.108472,
'cg13720865': 0.041302,
'cg13730743': -0.641688,
'cg13785883': 0.945837,
'cg13844899': -0.193918,
'cg13854874': 0.079520,
'cg13935689': 0.246708,
'cg13983063': -0.192778,
'cg14003022': -0.005578,
'cg14034476': -0.103989,
'cg14074174': -0.427476,
'cg14140060': 0.032882,
'cg14291650': -0.102791,
'cg14295611': -0.297499,
'cg14305711': -0.015526,
'cg14331163': -0.149986,
'cg14362004': 0.415994,
'cg14424579': 1.327706,
'cg14627089': 0.180821,
'cg14782206': 0.119040,
'cg14815005': -0.513939,
'cg14829814': -0.064138,
'cg14884160': -0.384053,
'cg15118606': 0.170109,
'cg15128510': 0.073551,
'cg15159987': 0.321430,
'cg15178202': -0.194715,
'cg15208197': 0.132881,
'cg15363134': -0.074360,
'cg15548613': 0.082398,
'cg15586420': -0.088739,
'cg15820033': -0.028047,
'cg15829826': -0.696270,
'cg15851799': -0.076108,
'cg15951188': 0.114012,
'cg16026522': 0.182903,
'cg16136840': -0.072940,
'cg16241714': 0.901287,
'cg16331674': 0.483335,
'cg16370875': 0.391429,
'cg16478145': 0.075640,
'cg16485682': 0.127591,
'cg16639637': -0.052944,
'cg16703882': 0.525210,
'cg16742481': -0.272142,
'cg16750275': -0.189936,
'cg16837441': -0.029999,
'cg16932827': -0.223159,
'cg17121412': -0.100472,
'cg17152981': 0.168534,
'cg17317023': 0.116863,
'cg17713912': 0.124633,
'cg17758721': 0.738194,
'cg17796960': 0.037607,
'cg17802633': -0.145015,
'cg17804348': 0.157616,
'cg17892169': -0.090332,
'cg18087943': -0.122351,
'cg18113084': -0.643732,
'cg18147606': -0.241852,
'cg18153869': 0.132170,
'cg18336453': 0.275552,
'cg18382305': -0.146864,
'cg18400181': -0.476893,
'cg18417423': 0.132226,
'cg18424208': 0.104091,
'cg18575740': 0.060317,
'cg18601714': 0.110121,
'cg18635432': 0.028141,
'cg18644787': -0.756996,
'cg18781966': -0.193718,
'cg18832152': -0.596254,
'cg18847227': 0.028334,
'cg18881501': -0.089093,
'cg18933331': -0.388073,
'cg19021197': 0.229413,
'cg19065177': 0.101292,
'cg19216851': 0.131758,
'cg19283196': 0.175860,
'cg19283806': -0.281685,
'cg19590421': -0.065829,
'cg19635712': 0.162209,
'cg19668234': -0.040411,
'cg19711783': -0.113758,
'cg19761273': -0.108853,
'cg19801705': 0.051839,
'cg20011402': -0.257504,
'cg20149168': 0.149040,
'cg20222376': -0.106672,
'cg20234855': 0.244570,
'cg20386580': 0.094042,
'cg20422417': 0.122609,
'cg20434178': 0.341773,
'cg20515136': -0.334444,
'cg20559403': 0.249909,
'cg20631204': -0.115376,
'cg20665157': 0.099555,
'cg20686554': 0.041199,
'cg20744625': 0.520346,
'cg20761322': 0.066527,
'cg20912517': -0.185820,
'cg21038957': -0.103066,
'cg21159778': 0.090493,
'cg21165519': -0.205365,
'cg21186299': 2.029120,
'cg21200656': 0.246572,
'cg21213853': 0.222802,
'cg21281007': 0.224273,
'cg21495653': 0.222406,
'cg21610904': -0.027103,
'cg21824162': -0.665451,
'cg21828345': 0.070299,
'cg21988244': 0.031230,
'cg22158769': 0.107564,
'cg22266749': -0.100535,
'cg22268271': -0.453787,
'cg22517995': 0.354932,
'cg22527345': 0.231810,
'cg22639325': -0.072690,
'cg22682373': 0.267342,
'cg22697239': 0.176375,
'cg22796704': -0.280375,
'cg22849665': -0.217533,
'cg22943590': -0.239895,
'cg22947322': -0.052930,
'cg23078123': -0.242301,
'cg23104823': -0.613725,
'cg23125200': -0.033819,
'cg23347399': 0.013117,
'cg23684204': 0.104843,
'cg23715237': -0.231238,
'cg23744638': -0.129161,
'cg23956238': 0.533778,
'cg24174665': 0.187453,
'cg24350475': -0.101080,
'cg24398933': -0.054795,
'cg24408436': 0.156341,
'cg24429836': -0.100258,
'cg24489983': -0.115641,
'cg24510518': -0.035831,
'cg24515575': 0.267510,
'cg24524451': -0.054761,
'cg24667575': 0.242073,
'cg24672014': 0.054554,
'cg24686644': -0.508029,
'cg24707573': 0.045543,
'cg24871743': -0.002360,
'cg24893035': 0.047359,
'cg25052374': -0.015616,
'cg25067162': 0.029022,
'cg25108022': 0.341638,
'cg25129541': -0.152400,
'cg25267487': 0.047397,
'cg25698236': -0.122299,
'cg25711358': -0.106817,
'cg25771195': 0.164269,
'cg25909396': -0.275267,
'cg26002713': -0.164871,
'cg26116103': -0.265104,
'cg26256771': -0.302967,
'cg26311208': -0.022138,
'cg26748578': -0.069656,
'cg26765295': 0.048243,
'cg26962778': 0.083161,
'cg27239168': 0.270015,
'cg27361964': -0.054397,
'cg27651143': 0.235585,
}
intercept = -2.349778
Load features#
[6]:
model.features = list(coefficient_dict.keys())
Load weights into base model#
[7]:
weights = torch.tensor(list(coefficient_dict.values())).unsqueeze(0)
intercept = torch.tensor([intercept])
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 = 'anti_log_linear'
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': 'Tomusiak, Alan, et al. "Development of an epigenetic clock '
'resistant to changes in immune cell composition." Communications '
'Biology 7.1 (2024): 934.',
'clock_name': 'intrinclock',
'data_type': 'methylation',
'doi': 'https://doi.org/10.1038/s42003-024-06609-4',
'notes': None,
'research_only': None,
'species': 'Homo sapiens',
'version': None,
'year': 2024}
reference_values: None
preprocess_name: None
preprocess_dependencies: None
postprocess_name: 'anti_log_linear'
postprocess_dependencies: None
features: ['cg00054496', 'cg00055555', 'cg00088042', 'cg00107606', 'cg00359604', 'cg00448707', 'cg00454305', 'cg00480331', 'cg00491255', 'cg00579423', 'cg00583733', 'cg00588393', 'cg00590036', 'cg00593462', 'cg00716277', 'cg00734800', 'cg00751156', 'cg00753885', 'cg00790928', 'cg00792123', 'cg00796360', 'cg01028142', 'cg01080924', 'cg01131866', 'cg01153342', 'cg01176694', 'cg01260146', 'cg01410876', 'cg01426818', 'cg01447660']... [Total elements: 380]
base_model_features: None
%==================================== Model Details ====================================%
Model Structure:
base_model: LinearModel(
(linear): Linear(in_features=380, out_features=1, bias=True)
)
%==================================== Model Details ====================================%
Model Parameters and Weights:
base_model.linear.weight: [0.629764974117279, 0.0004780000017490238, 0.5425040125846863, -0.6023579835891724, -0.20740799605846405, 0.10132099688053131, 0.2141769975423813, 0.27955299615859985, 0.23592300713062286, -0.023260999470949173, -0.1878580003976822, 0.3060399889945984, 0.9469850063323975, 0.33906999230384827, -0.11784300208091736, -0.2824240028858185, 0.8952140212059021, -0.46393999457359314, -0.3338710069656372, -0.45566999912261963, -0.040681999176740646, 0.24853700399398804, -0.06306999921798706, -0.14341700077056885, -0.434237003326416, -0.16436100006103516, -0.68572998046875, 0.0009899999713525176, 0.09043300151824951, -0.37791499495506287]... [Tensor of shape torch.Size([1, 380])]
base_model.linear.bias: tensor([-2.3498])
%==================================== 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([[ -0.9125],
[ 11.0212],
[ 29.7538],
[ 18.8043],
[ -1.0000],
[118.1667],
[ -0.9992],
[172.2491],
[ -0.9376],
[ 55.5021]], dtype=torch.float64, grad_fn=<IndexPutBackward0>)
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)