{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "8800a5a4",
   "metadata": {},
   "source": [
    "# CorticalClock"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6d82d0f5",
   "metadata": {},
   "source": [
    "## Index\n",
    "1. [Instantiate model class](#Instantiate-model-class)\n",
    "2. [Define clock metadata](#Define-clock-metadata)\n",
    "3. [Download clock dependencies](#Download-clock-dependencies)\n",
    "5. [Load features](#Load-features)\n",
    "6. [Load weights into base model](#Load-weights-into-base-model)\n",
    "7. [Load reference values](#Load-reference-values)\n",
    "8. [Load preprocess and postprocess objects](#Load-preprocess-and-postprocess-objects)\n",
    "10. [Check all clock parameters](#Check-all-clock-parameters)\n",
    "10. [Basic test](#Basic-test)\n",
    "11. [Save torch model](#Save-torch-model)\n",
    "12. [Clear directory](#Clear-directory)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6f2531fe",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "86a52380",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:05.843298Z",
     "iopub.status.busy": "2026-07-04T20:25:05.842864Z",
     "iopub.status.idle": "2026-07-04T20:25:07.923727Z",
     "shell.execute_reply": "2026-07-04T20:25:07.923249Z"
    }
   },
   "outputs": [],
   "source": [
    "import os\n",
    "import inspect\n",
    "import shutil\n",
    "import json\n",
    "import torch\n",
    "import pandas as pd\n",
    "import pyaging as pya"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1c0b75a7",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "a796decb",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:07.925506Z",
     "iopub.status.busy": "2026-07-04T20:25:07.925284Z",
     "iopub.status.idle": "2026-07-04T20:25:07.928315Z",
     "shell.execute_reply": "2026-07-04T20:25:07.927880Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class CorticalClock(LinearReferenceClock):\n",
      "    def postprocess(self, x):\n",
      "        \"\"\"Horvath anti-logarithmic linear transformation (adult age = 20).\"\"\"\n",
      "        adult_age = 20\n",
      "        mask_negative = x < 0\n",
      "        mask_non_negative = ~mask_negative\n",
      "        age = torch.empty_like(x)\n",
      "        age[mask_negative] = (1 + adult_age) * torch.exp(x[mask_negative]) - 1\n",
      "        age[mask_non_negative] = (1 + adult_age) * x[mask_non_negative] + adult_age\n",
      "        return age\n",
      "\n"
     ]
    }
   ],
   "source": [
    "def print_entire_class(cls):\n",
    "    source = inspect.getsource(cls)\n",
    "    print(source)\n",
    "\n",
    "print_entire_class(pya.models.CorticalClock)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "edb837f0",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:07.930866Z",
     "iopub.status.busy": "2026-07-04T20:25:07.930701Z",
     "iopub.status.idle": "2026-07-04T20:25:07.933416Z",
     "shell.execute_reply": "2026-07-04T20:25:07.932387Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.CorticalClock()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b7babd9c",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "577aad3e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:07.935376Z",
     "iopub.status.busy": "2026-07-04T20:25:07.935216Z",
     "iopub.status.idle": "2026-07-04T20:25:07.937499Z",
     "shell.execute_reply": "2026-07-04T20:25:07.937094Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"corticalclock\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: methylation\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: Homo sapiens\n",
    "model.metadata[\"year\"] = 2020\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Shireby, G. L., et al. \\\"Recalibrating the epigenetic clock: implications for assessing biological age in the human cortex.\\\" Brain 143.12 (2020): 3763-3775.\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1093/brain/awaa334\"\n",
    "model.metadata[\"notes\"] = \"Cortex-specific DNA-methylation chronological-age estimator trained by elastic net on 1,047 post-mortem cortical samples; its 347-CpG weighted score is back-transformed to years.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"brain cortex\"]  # Paper: brain cortex (post-mortem human cortical tissue)\n",
    "model.metadata[\"predicts\"] = [\"chronological age\"]  # Paper: chronological age\n",
    "model.metadata[\"training_target\"] = [\"chronological age\"]  # Paper: chronological age\n",
    "model.metadata[\"unit\"] = [\"years\"]  # Paper: years\n",
    "model.metadata[\"model_type\"] = \"elastic net regression\"  # Paper: Elastic net\n",
    "model.metadata[\"platform\"] = [\"Illumina 450K\"]  # Paper: Illumina 450K\n",
    "model.metadata[\"population\"] = \"human, age unspecified\"  # Paper: human cortex training set: 1,047 samples from 832 donors, ages 1–108 years\n",
    "model.metadata[\"journal\"] = \"Brain\"\n",
    "model.metadata[\"last_author\"] = \"Jonathan Mill\"\n",
    "model.metadata[\"n_features\"] = 347\n",
    "model.metadata[\"citations\"] = 206\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5084fb52",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "04065b6f",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:07.938792Z",
     "iopub.status.busy": "2026-07-04T20:25:07.938688Z",
     "iopub.status.idle": "2026-07-04T20:25:09.598296Z",
     "shell.execute_reply": "2026-07-04T20:25:09.597617Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "os.system(f\"curl -sL -o CorticalClockCoefs.txt https://raw.githubusercontent.com/gemmashireby/CorticalClock/80c3df19c01d9aac25c9fd5aecd5bbc42aba0939/PredCorticalAge/CorticalClockCoefs.txt\")\n",
    "os.system(f\"curl -sL -o Ref_DNAm_brain_values.rdat https://raw.githubusercontent.com/gemmashireby/CorticalClock/80c3df19c01d9aac25c9fd5aecd5bbc42aba0939/PredCorticalAge/Ref_DNAm_brain_values.rdat\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "8cd791b7",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:09.600118Z",
     "iopub.status.busy": "2026-07-04T20:25:09.600003Z",
     "iopub.status.idle": "2026-07-04T20:25:09.602806Z",
     "shell.execute_reply": "2026-07-04T20:25:09.602375Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Writing download.r\n"
     ]
    }
   ],
   "source": [
    "%%writefile download.r\n",
    "\n",
    "library(jsonlite)\n",
    "coefs <- read.table(\"CorticalClockCoefs.txt\", header = TRUE, stringsAsFactors = FALSE)\n",
    "coefs <- coefs[tolower(coefs$probe) != \"intercept\" & tolower(coefs$probe) != \"(intercept)\", ]\n",
    "load(\"Ref_DNAm_brain_values.rdat\")\n",
    "refvals <- as.numeric(ref[coefs$probe])\n",
    "write_json(list(probe = coefs$probe, coef = coefs$coef, ref = refvals), \"cortical.json\", digits = 10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "fdc45fac",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:09.604027Z",
     "iopub.status.busy": "2026-07-04T20:25:09.603944Z",
     "iopub.status.idle": "2026-07-04T20:25:11.832575Z",
     "shell.execute_reply": "2026-07-04T20:25:11.832004Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "os.system(\"Rscript download.r\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "46be35b3",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "200eb498",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:11.834376Z",
     "iopub.status.busy": "2026-07-04T20:25:11.834247Z",
     "iopub.status.idle": "2026-07-04T20:25:11.836609Z",
     "shell.execute_reply": "2026-07-04T20:25:11.836198Z"
    }
   },
   "outputs": [],
   "source": [
    "d = json.load(open('cortical.json'))\n",
    "model.features = list(d['probe'])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0a57b01c",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "9f02ed0d",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:11.838022Z",
     "iopub.status.busy": "2026-07-04T20:25:11.837917Z",
     "iopub.status.idle": "2026-07-04T20:25:11.840143Z",
     "shell.execute_reply": "2026-07-04T20:25:11.839781Z"
    }
   },
   "outputs": [],
   "source": [
    "# Intercept 0.577682570446177 hard-coded in the CorticalClock reference script\n",
    "weights = torch.tensor(d['coef']).unsqueeze(0).float()\n",
    "intercept = torch.tensor([0.577682570446177]).float()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "fed7deeb",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:11.841490Z",
     "iopub.status.busy": "2026-07-04T20:25:11.841392Z",
     "iopub.status.idle": "2026-07-04T20:25:11.843603Z",
     "shell.execute_reply": "2026-07-04T20:25:11.843217Z"
    }
   },
   "outputs": [],
   "source": [
    "base_model = pya.models.LinearModel(input_dim=len(model.features))\n",
    "\n",
    "base_model.linear.weight.data = weights.float()\n",
    "base_model.linear.bias.data = intercept.float()\n",
    "\n",
    "model.base_model = base_model"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2bdbd5f2",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "64dda625",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:11.845025Z",
     "iopub.status.busy": "2026-07-04T20:25:11.844927Z",
     "iopub.status.idle": "2026-07-04T20:25:11.848252Z",
     "shell.execute_reply": "2026-07-04T20:25:11.846206Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = d['ref']"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "87094355",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "f8117483",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:11.849950Z",
     "iopub.status.busy": "2026-07-04T20:25:11.849839Z",
     "iopub.status.idle": "2026-07-04T20:25:11.851716Z",
     "shell.execute_reply": "2026-07-04T20:25:11.851295Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "5842cecc",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:11.853193Z",
     "iopub.status.busy": "2026-07-04T20:25:11.853113Z",
     "iopub.status.idle": "2026-07-04T20:25:11.854837Z",
     "shell.execute_reply": "2026-07-04T20:25:11.854394Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = 'anti_log_linear'\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "45f7dc20",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "7e0cfa19",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:11.856253Z",
     "iopub.status.busy": "2026-07-04T20:25:11.856160Z",
     "iopub.status.idle": "2026-07-04T20:25:11.859956Z",
     "shell.execute_reply": "2026-07-04T20:25:11.859432Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Shireby, Gemma L., et al. \"Recalibrating the epigenetic clock: '\n",
      "             'implications for assessing biological age in the human cortex.\" '\n",
      "             'Brain 143.12 (2020): 3763-3775.',\n",
      " 'clock_name': 'corticalclock',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1093/brain/awaa334',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'Homo sapiens',\n",
      " 'version': None,\n",
      " 'year': 2020}\n",
      "reference_values: [0.21611617687, 0.15740657645, 0.7341710846, 0.060822631032, 0.10575749654, 0.62440019335, 0.13956151931, 0.93910437046, 0.67922573527, 0.41269620156, 0.18058134103, 0.30387161589, 0.72916401957, 0.16249365613, 0.10514838761, 0.32006057604, 0.41533755409, 0.76224987996, 0.1012865392, 0.068627506888, 0.62711858238, 0.067610974155, 0.73657937789, 0.085680987307, 0.16091221649, 0.5857097145, 0.65691321067, 0.5219473048, 0.14838958913, 0.46603381304]... [Total elements: 347]\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: 'anti_log_linear'\n",
      "postprocess_dependencies: None\n",
      "features: ['cg00059225', 'cg00088042', 'cg00252534', 'cg00297950', 'cg00384539', 'cg00491255', 'cg00521255', 'cg00648582', 'cg00771642', 'cg00924265', 'cg00935119', 'cg00940577', 'cg01091514', 'cg01122755', 'cg01162920', 'cg01194538', 'cg01264729', 'cg01311102', 'cg01529637', 'cg01532168', 'cg01616394', 'cg01639032', 'cg01641432', 'cg01655150', 'cg01745370', 'cg01899542', 'cg02046143', 'cg02047661', 'cg02357838', 'cg02361903']... [Total elements: 347]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=347, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [0.24595920741558075, 0.18271556496620178, 0.16822335124015808, 0.14175772666931152, 0.17820188403129578, 0.14450779557228088, -0.2443627119064331, -0.03914619982242584, 0.1277257353067398, -0.06851626932621002, -0.038119036704301834, -0.061217304319143295, -0.03222978115081787, 0.06571090221405029, -0.1973567008972168, -0.151609405875206, -0.15242373943328857, -0.10921627283096313, 0.026809634640812874, 0.3346559405326843, -0.01871008612215519, 0.5150526762008667, -0.0013768351636826992, -0.32761350274086, -0.00586429750546813, -0.050962597131729126, -0.007779109291732311, -0.017116934061050415, 0.2379734218120575, -0.5452234148979187]... [Tensor of shape torch.Size([1, 347])]\n",
      "base_model.linear.bias: tensor([0.5777])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "30266c3a",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "692fecc2",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:11.861718Z",
     "iopub.status.busy": "2026-07-04T20:25:11.861597Z",
     "iopub.status.idle": "2026-07-04T20:25:11.869668Z",
     "shell.execute_reply": "2026-07-04T20:25:11.869207Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[ 2.8786e+01],\n",
       "        [-9.7972e-01],\n",
       "        [ 1.7019e+01],\n",
       "        [-9.1772e-01],\n",
       "        [ 8.8761e+00],\n",
       "        [ 1.7652e+01],\n",
       "        [ 1.6345e+02],\n",
       "        [-2.4936e-03],\n",
       "        [-9.7389e-01],\n",
       "        [-9.8054e-01]], dtype=torch.float64, grad_fn=<IndexPutBackward0>)"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "torch.manual_seed(42)\n",
    "input = torch.randn(10, len(model.features), dtype=float)\n",
    "model.eval()\n",
    "model.to(float)\n",
    "pred = model(input)\n",
    "pred"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "14e69f9f",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "7d8665ca",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:11.870971Z",
     "iopub.status.busy": "2026-07-04T20:25:11.870893Z",
     "iopub.status.idle": "2026-07-04T20:25:11.874624Z",
     "shell.execute_reply": "2026-07-04T20:25:11.874209Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ce2c1c1c",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "e802cfb6",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:11.875875Z",
     "iopub.status.busy": "2026-07-04T20:25:11.875802Z",
     "iopub.status.idle": "2026-07-04T20:25:11.880225Z",
     "shell.execute_reply": "2026-07-04T20:25:11.879838Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted file: CorticalClockCoefs.txt\n",
      "Deleted file: Ref_DNAm_brain_values.rdat\n",
      "Deleted file: download.r\n",
      "Deleted file: cortical.json\n"
     ]
    }
   ],
   "source": [
    "# Function to remove a folder and all its contents\n",
    "def remove_folder(path):\n",
    "    try:\n",
    "        shutil.rmtree(path)\n",
    "        print(f\"Deleted folder: {path}\")\n",
    "    except Exception as e:\n",
    "        print(f\"Error deleting folder {path}: {e}\")\n",
    "\n",
    "# Get a list of all files and folders in the current directory\n",
    "all_items = os.listdir('.')\n",
    "\n",
    "# Loop through the items\n",
    "for item in all_items:\n",
    "    # Check if it's a file and does not end with .ipynb\n",
    "    if os.path.isfile(item) and not item.endswith('.ipynb'):\n",
    "        os.remove(item)\n",
    "        print(f\"Deleted file: {item}\")\n",
    "    # Check if it's a folder\n",
    "    elif os.path.isdir(item):\n",
    "        remove_folder(item)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.13.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}