{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "fc18810b",
   "metadata": {},
   "source": [
    "# Hep"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bcf9dcec",
   "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": "d3d7ef81",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "4689ddbd",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:24.666670Z",
     "iopub.status.busy": "2026-07-04T19:34:24.666492Z",
     "iopub.status.idle": "2026-07-04T19:34:26.832242Z",
     "shell.execute_reply": "2026-07-04T19:34:26.831704Z"
    }
   },
   "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": "b794a094",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "19d052eb",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:26.834058Z",
     "iopub.status.busy": "2026-07-04T19:34:26.833839Z",
     "iopub.status.idle": "2026-07-04T19:34:26.836908Z",
     "shell.execute_reply": "2026-07-04T19:34:26.836438Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class Hep(LinearReferenceClock):\n",
      "    pass\n",
      "\n"
     ]
    }
   ],
   "source": [
    "def print_entire_class(cls):\n",
    "    source = inspect.getsource(cls)\n",
    "    print(source)\n",
    "\n",
    "print_entire_class(pya.models.Hep)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "669a6c89",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:26.838145Z",
     "iopub.status.busy": "2026-07-04T19:34:26.838060Z",
     "iopub.status.idle": "2026-07-04T19:34:26.840052Z",
     "shell.execute_reply": "2026-07-04T19:34:26.839531Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.Hep()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "928c43e4",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "cbfd0448",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:26.841248Z",
     "iopub.status.busy": "2026-07-04T19:34:26.841173Z",
     "iopub.status.idle": "2026-07-04T19:34:26.843304Z",
     "shell.execute_reply": "2026-07-04T19:34:26.842938Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"hep\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: The model is based on DNA methylation measurements.\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: The study samples are Homo sapiens.\n",
    "model.metadata[\"year\"] = 2024\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Tong, Huige, et al. \\\"Cell-type specific epigenetic clocks to quantify biological age at cell-type resolution.\\\" Aging 16 (2024): 14204–14237.\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.18632/aging.206184\"\n",
    "model.metadata[\"notes\"] = \"HepClock is a hepatocyte-specific chronological-age clock trained by lasso on hepatocyte age-DMCTs identified with CellDMC after estimating five liver cell fractions.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"liver\"]  # Paper: The listed tissue is the model-development sample material.\n",
    "model.metadata[\"predicts\"] = [\"chronological age\"]  # Paper: The reported predictor output is chronological age.\n",
    "model.metadata[\"training_target\"] = [\"chronological age\"]  # Paper: The fitting outcome is chronological age.\n",
    "model.metadata[\"unit\"] = [\"years\"]  # Paper: The returned construct is expressed as years.\n",
    "model.metadata[\"model_type\"] = \"LASSO regression\"  # Paper: The clock was fitted using LASSO.\n",
    "model.metadata[\"platform\"] = [\"Illumina EPIC\"]  # Paper: Training/selection used Illumina EPIC.\n",
    "model.metadata[\"population\"] = \"adults\"  # Paper: adults aged 18–75 years (210 normal liver samples)\n",
    "model.metadata[\"journal\"] = \"Aging\"\n",
    "model.metadata[\"last_author\"] = \"Andrew E. Teschendorff\"\n",
    "model.metadata[\"n_features\"] = 70\n",
    "model.metadata[\"citations\"] = 25\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1c4e05d5",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "9f1e4bf0",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:26.844513Z",
     "iopub.status.busy": "2026-07-04T19:34:26.844448Z",
     "iopub.status.idle": "2026-07-04T19:34:27.149115Z",
     "shell.execute_reply": "2026-07-04T19:34:27.148384Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "supplementary_url = \"https://raw.githubusercontent.com/Duzhaozhen/OmniAge/c10fbe8cb92957520fbff1d55ae1def0691252e5/OmniAgePy/src/omniage/data/CTS/Hep.csv\"\n",
    "supplementary_file_name = \"coefficients.csv\"\n",
    "os.system(f\"curl -sL -o {supplementary_file_name} {supplementary_url}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d0d52a00",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "2b87ea26",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:27.150502Z",
     "iopub.status.busy": "2026-07-04T19:34:27.150388Z",
     "iopub.status.idle": "2026-07-04T19:34:27.155515Z",
     "shell.execute_reply": "2026-07-04T19:34:27.154921Z"
    }
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv('coefficients.csv')\n",
    "if str(df.columns[0]).startswith('Unnamed'):\n",
    "    df = df.iloc[:, 1:]\n",
    "mask = df['probe'].astype(str).str.lower().isin(['intercept', '(intercept)'])\n",
    "intercept_value = float(df.loc[mask, 'coef'].iloc[0]) if mask.any() else 0.0\n",
    "coef_df = df.loc[~mask].reset_index(drop=True)\n",
    "model.features = coef_df['probe'].tolist()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d47389c4",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "85236875",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:27.158514Z",
     "iopub.status.busy": "2026-07-04T19:34:27.158357Z",
     "iopub.status.idle": "2026-07-04T19:34:27.160978Z",
     "shell.execute_reply": "2026-07-04T19:34:27.160492Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor(coef_df['coef'].tolist()).unsqueeze(0).float()\n",
    "intercept = torch.tensor([intercept_value]).float()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "5379658c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:27.162229Z",
     "iopub.status.busy": "2026-07-04T19:34:27.162119Z",
     "iopub.status.idle": "2026-07-04T19:34:27.164327Z",
     "shell.execute_reply": "2026-07-04T19:34:27.163895Z"
    }
   },
   "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": "c4316823",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "459b363b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:27.165762Z",
     "iopub.status.busy": "2026-07-04T19:34:27.165650Z",
     "iopub.status.idle": "2026-07-04T19:34:27.167307Z",
     "shell.execute_reply": "2026-07-04T19:34:27.166948Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "290ec07c",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "653b9034",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:27.168593Z",
     "iopub.status.busy": "2026-07-04T19:34:27.168507Z",
     "iopub.status.idle": "2026-07-04T19:34:27.170761Z",
     "shell.execute_reply": "2026-07-04T19:34:27.170194Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "cb727c9c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:27.172041Z",
     "iopub.status.busy": "2026-07-04T19:34:27.171935Z",
     "iopub.status.idle": "2026-07-04T19:34:27.173792Z",
     "shell.execute_reply": "2026-07-04T19:34:27.173419Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b64b0919",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "c012f5d9",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:27.175219Z",
     "iopub.status.busy": "2026-07-04T19:34:27.175099Z",
     "iopub.status.idle": "2026-07-04T19:34:27.178806Z",
     "shell.execute_reply": "2026-07-04T19:34:27.178350Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Tong, Huige, et al. \"Cell-type-specific and '\n",
      "             'cell-type-independent DNA methylation clocks.\" Aging 16 (2024).',\n",
      " 'clock_name': 'hep',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.18632/aging.206184',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'Homo sapiens',\n",
      " 'version': None,\n",
      " 'year': 2024}\n",
      "reference_values: None\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: None\n",
      "postprocess_dependencies: None\n",
      "features: ['cg02928345', 'cg05694089', 'cg06095777', 'cg06852461', 'cg10501210', 'cg15491247', 'cg26885220', 'cg21245277', 'cg25004441', 'cg03553786', 'cg04472001', 'cg10727673', 'cg11320499', 'cg14317285', 'cg17078152', 'cg11970349', 'cg04671476', 'cg08272151', 'cg09458096', 'cg11830096', 'cg14314729', 'cg16049690', 'cg26921969', 'cg05460965', 'cg13719443', 'cg14119792', 'cg09832613', 'cg10548492', 'cg10774647', 'cg14668632']... [Total elements: 70]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=70, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [-6.017436981201172, -5.4592413902282715, -2.176126003265381, -1.1635955572128296, -11.279679298400879, -2.4325146675109863, 0.5495437979698181, 34.79977798461914, 0.5566549301147461, 5.5801191329956055, -7.796560287475586, -7.169039249420166, 1.542575716972351, 15.734872817993164, 0.35905373096466064, 6.515843868255615, 19.468814849853516, 1.418412446975708, 0.03253895044326782, 3.5211238861083984, -0.3575636148452759, 3.376959800720215, 21.540037155151367, -7.9151692390441895, -2.348267078399658, -1.2504611015319824, -3.796130418777466, 13.8594388961792, 4.52095365524292, 0.2238227277994156]... [Tensor of shape torch.Size([1, 70])]\n",
      "base_model.linear.bias: tensor([16.7101])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "feeaa7e7",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "24319b56",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:27.180479Z",
     "iopub.status.busy": "2026-07-04T19:34:27.180367Z",
     "iopub.status.idle": "2026-07-04T19:34:27.185941Z",
     "shell.execute_reply": "2026-07-04T19:34:27.185482Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[103.2090],\n",
       "        [ 59.8991],\n",
       "        [  7.7645],\n",
       "        [-52.8674],\n",
       "        [115.0976],\n",
       "        [-25.3601],\n",
       "        [148.0905],\n",
       "        [ 40.7066],\n",
       "        [104.7873],\n",
       "        [-31.2725]], dtype=torch.float64, grad_fn=<AddmmBackward0>)"
      ]
     },
     "execution_count": 13,
     "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": "4cc6e5f5",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "e99ad0a7",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:27.187214Z",
     "iopub.status.busy": "2026-07-04T19:34:27.187127Z",
     "iopub.status.idle": "2026-07-04T19:34:27.191580Z",
     "shell.execute_reply": "2026-07-04T19:34:27.190922Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "115afba3",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "8af87b0e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:27.192862Z",
     "iopub.status.busy": "2026-07-04T19:34:27.192771Z",
     "iopub.status.idle": "2026-07-04T19:34:27.196390Z",
     "shell.execute_reply": "2026-07-04T19:34:27.195986Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted file: coefficients.csv\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
}