{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "a7bdb3d1",
   "metadata": {},
   "source": [
    "# CTSLiver"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ebf0a716",
   "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": "e45a86f6",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "63bed9f9",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:29.239268Z",
     "iopub.status.busy": "2026-07-04T19:34:29.239147Z",
     "iopub.status.idle": "2026-07-04T19:34:31.361432Z",
     "shell.execute_reply": "2026-07-04T19:34:31.360924Z"
    }
   },
   "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": "4efcc0da",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "196224ce",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:31.363098Z",
     "iopub.status.busy": "2026-07-04T19:34:31.362913Z",
     "iopub.status.idle": "2026-07-04T19:34:31.365661Z",
     "shell.execute_reply": "2026-07-04T19:34:31.365306Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class CTSLiver(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.CTSLiver)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "f9ac34fa",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:31.366972Z",
     "iopub.status.busy": "2026-07-04T19:34:31.366890Z",
     "iopub.status.idle": "2026-07-04T19:34:31.368669Z",
     "shell.execute_reply": "2026-07-04T19:34:31.368266Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.CTSLiver()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "467b5800",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "d9f4d92a",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:31.370082Z",
     "iopub.status.busy": "2026-07-04T19:34:31.369972Z",
     "iopub.status.idle": "2026-07-04T19:34:31.372236Z",
     "shell.execute_reply": "2026-07-04T19:34:31.371834Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"ctsliver\"\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\"] = \"LiverClock is a liver tissue-specific chronological-age clock trained by lasso on age-associated CpGs identified after adjustment for five estimated liver cell fractions; unlike HepClock, it is not hepatocyte-specific.\"\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\"] = 90\n",
    "model.metadata[\"citations\"] = 25\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "934e0cc9",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "aea5418c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:31.373566Z",
     "iopub.status.busy": "2026-07-04T19:34:31.373484Z",
     "iopub.status.idle": "2026-07-04T19:34:31.677657Z",
     "shell.execute_reply": "2026-07-04T19:34:31.677017Z"
    }
   },
   "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/Liver.csv\"\n",
    "supplementary_file_name = \"coefficients.csv\"\n",
    "os.system(f\"curl -sL -o {supplementary_file_name} {supplementary_url}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3aa5a0bc",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "112adec2",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:31.679896Z",
     "iopub.status.busy": "2026-07-04T19:34:31.679728Z",
     "iopub.status.idle": "2026-07-04T19:34:31.686351Z",
     "shell.execute_reply": "2026-07-04T19:34:31.685767Z"
    }
   },
   "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": "3f1902b3",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "c5b61450",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:31.688199Z",
     "iopub.status.busy": "2026-07-04T19:34:31.688071Z",
     "iopub.status.idle": "2026-07-04T19:34:31.690884Z",
     "shell.execute_reply": "2026-07-04T19:34:31.690311Z"
    }
   },
   "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": "1a213d37",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:31.692541Z",
     "iopub.status.busy": "2026-07-04T19:34:31.692414Z",
     "iopub.status.idle": "2026-07-04T19:34:31.695167Z",
     "shell.execute_reply": "2026-07-04T19:34:31.694699Z"
    }
   },
   "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": "8208c199",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "449d036b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:31.696883Z",
     "iopub.status.busy": "2026-07-04T19:34:31.696768Z",
     "iopub.status.idle": "2026-07-04T19:34:31.698774Z",
     "shell.execute_reply": "2026-07-04T19:34:31.698298Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "eeb6fbe6",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "0f0e241f",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:31.700387Z",
     "iopub.status.busy": "2026-07-04T19:34:31.700273Z",
     "iopub.status.idle": "2026-07-04T19:34:31.702368Z",
     "shell.execute_reply": "2026-07-04T19:34:31.701765Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "feaa129d",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:31.703759Z",
     "iopub.status.busy": "2026-07-04T19:34:31.703629Z",
     "iopub.status.idle": "2026-07-04T19:34:31.705412Z",
     "shell.execute_reply": "2026-07-04T19:34:31.704995Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "df4c3b96",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "70aee7b6",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:31.706999Z",
     "iopub.status.busy": "2026-07-04T19:34:31.706887Z",
     "iopub.status.idle": "2026-07-04T19:34:31.711163Z",
     "shell.execute_reply": "2026-07-04T19:34:31.710672Z"
    }
   },
   "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': 'ctsliver',\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: ['cg00147307', 'cg04055835', 'cg07014827', 'cg08639762', 'cg09085216', 'cg10501210', 'cg11037818', 'cg11837471', 'cg19861048', 'cg22793142', 'cg27553626', 'cg01139016', 'cg03602360', 'cg03957108', 'cg11797365', 'cg12477533', 'cg23059946', 'cg26469895', 'cg00481951', 'cg01633093', 'cg17631451', 'cg20669012', 'cg24572745', 'cg02650266', 'cg15848147', 'cg27652893', 'cg04671476', 'cg16049690', 'cg01017235', 'cg16867657']... [Total elements: 90]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=90, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [0.06677141785621643, -0.4691475033760071, 8.956233978271484, -7.425961494445801, -0.37923702597618103, -0.9674519896507263, -0.2163476198911667, -0.6666942834854126, -0.0633813887834549, -11.506742477416992, -4.447482585906982, -0.7794511914253235, 1.741921067237854, 3.4112987518310547, 1.951097846031189, 4.32723331451416, -7.400779724121094, -0.8474096059799194, 1.4585193395614624, -2.9431684017181396, -0.044251661747694016, -2.712244987487793, -3.016547918319702, 1.0454469919204712, 0.705701470375061, -5.014070510864258, 2.0638656616210938, 0.18794922530651093, 1.635787010192871, 51.198280334472656]... [Tensor of shape torch.Size([1, 90])]\n",
      "base_model.linear.bias: tensor([48.3286])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c9337e54",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "9b312d09",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:31.712546Z",
     "iopub.status.busy": "2026-07-04T19:34:31.712464Z",
     "iopub.status.idle": "2026-07-04T19:34:31.716977Z",
     "shell.execute_reply": "2026-07-04T19:34:31.716629Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[140.2069],\n",
       "        [ 45.0042],\n",
       "        [ -4.2454],\n",
       "        [-15.0873],\n",
       "        [-27.0882],\n",
       "        [150.2301],\n",
       "        [ 29.9997],\n",
       "        [257.3345],\n",
       "        [ 42.9376],\n",
       "        [-70.8377]], 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": "83e57549",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "d6d691ba",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:31.718563Z",
     "iopub.status.busy": "2026-07-04T19:34:31.718473Z",
     "iopub.status.idle": "2026-07-04T19:34:31.722639Z",
     "shell.execute_reply": "2026-07-04T19:34:31.722107Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "492ca0ea",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "34e2c2a5",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:31.724060Z",
     "iopub.status.busy": "2026-07-04T19:34:31.723971Z",
     "iopub.status.idle": "2026-07-04T19:34:31.727766Z",
     "shell.execute_reply": "2026-07-04T19:34:31.727381Z"
    }
   },
   "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
}