{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "e64c332b",
   "metadata": {},
   "source": [
    "# GliaSin"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "beac6e08",
   "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": "b253ebc7",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "de93ca98",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:20.364487Z",
     "iopub.status.busy": "2026-07-04T19:34:20.364369Z",
     "iopub.status.idle": "2026-07-04T19:34:22.461975Z",
     "shell.execute_reply": "2026-07-04T19:34:22.461400Z"
    }
   },
   "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": "6d2bccb5",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "087c7d05",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:22.463752Z",
     "iopub.status.busy": "2026-07-04T19:34:22.463539Z",
     "iopub.status.idle": "2026-07-04T19:34:22.467043Z",
     "shell.execute_reply": "2026-07-04T19:34:22.466550Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class GliaSin(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.GliaSin)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "31c87d84",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:22.468263Z",
     "iopub.status.busy": "2026-07-04T19:34:22.468180Z",
     "iopub.status.idle": "2026-07-04T19:34:22.470069Z",
     "shell.execute_reply": "2026-07-04T19:34:22.469651Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.GliaSin()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "75807bc8",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "2551a4be",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:22.471251Z",
     "iopub.status.busy": "2026-07-04T19:34:22.471162Z",
     "iopub.status.idle": "2026-07-04T19:34:22.473223Z",
     "shell.execute_reply": "2026-07-04T19:34:22.472759Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"gliasin\"\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\"] = \"Glia-Sin is a glia semi-intrinsic chronological-age clock: elastic-net regression was restricted to glia age-DMCTs but fitted to methylation values not adjusted for brain cell fractions.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"brain cortex\"]  # 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\"] = \"elastic net regression\"  # Paper: The clock was fitted using Elastic net.\n",
    "model.metadata[\"platform\"] = [\"Illumina 450K\"]  # Paper: Training/selection used Illumina 450K.\n",
    "model.metadata[\"population\"] = \"adults\"  # Paper: adults aged 18–97 years (Jaffe prefrontal-cortex training data)\n",
    "model.metadata[\"journal\"] = \"Aging\"\n",
    "model.metadata[\"last_author\"] = \"Andrew E. Teschendorff\"\n",
    "model.metadata[\"n_features\"] = 220\n",
    "model.metadata[\"citations\"] = 25\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "04625e1c",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "7234da5b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:22.475319Z",
     "iopub.status.busy": "2026-07-04T19:34:22.475208Z",
     "iopub.status.idle": "2026-07-04T19:34:22.614231Z",
     "shell.execute_reply": "2026-07-04T19:34:22.613731Z"
    }
   },
   "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/Glia-Sin.csv\"\n",
    "supplementary_file_name = \"coefficients.csv\"\n",
    "os.system(f\"curl -sL -o {supplementary_file_name} {supplementary_url}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "09c6f9e8",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "6e39b70a",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:22.615864Z",
     "iopub.status.busy": "2026-07-04T19:34:22.615738Z",
     "iopub.status.idle": "2026-07-04T19:34:22.621398Z",
     "shell.execute_reply": "2026-07-04T19:34:22.620887Z"
    }
   },
   "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": "1369e2ae",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "0436eee4",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:22.622936Z",
     "iopub.status.busy": "2026-07-04T19:34:22.622818Z",
     "iopub.status.idle": "2026-07-04T19:34:22.625269Z",
     "shell.execute_reply": "2026-07-04T19:34:22.624854Z"
    }
   },
   "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": "98b28904",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:22.626458Z",
     "iopub.status.busy": "2026-07-04T19:34:22.626366Z",
     "iopub.status.idle": "2026-07-04T19:34:22.628717Z",
     "shell.execute_reply": "2026-07-04T19:34:22.628281Z"
    }
   },
   "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": "2d247753",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "3a92e5b7",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:22.630113Z",
     "iopub.status.busy": "2026-07-04T19:34:22.630003Z",
     "iopub.status.idle": "2026-07-04T19:34:22.631616Z",
     "shell.execute_reply": "2026-07-04T19:34:22.631210Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e49be664",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "c5ee230c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:22.632592Z",
     "iopub.status.busy": "2026-07-04T19:34:22.632525Z",
     "iopub.status.idle": "2026-07-04T19:34:22.634291Z",
     "shell.execute_reply": "2026-07-04T19:34:22.633844Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "1ef7e07b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:22.635329Z",
     "iopub.status.busy": "2026-07-04T19:34:22.635264Z",
     "iopub.status.idle": "2026-07-04T19:34:22.636805Z",
     "shell.execute_reply": "2026-07-04T19:34:22.636528Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "174d5b47",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "f3037dd5",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:22.638168Z",
     "iopub.status.busy": "2026-07-04T19:34:22.638076Z",
     "iopub.status.idle": "2026-07-04T19:34:22.641516Z",
     "shell.execute_reply": "2026-07-04T19:34:22.641125Z"
    }
   },
   "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': 'gliasin',\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: ['cg10501210', 'cg13782884', 'cg14419975', 'cg16909962', 'cg16361302', 'cg21122225', 'cg23606718', 'cg04187185', 'cg18336674', 'cg02578944', 'cg04190475', 'cg11744777', 'cg14848772', 'cg16695576', 'cg18468088', 'cg20223728', 'cg01217984', 'cg12001630', 'cg26830108', 'cg05066959', 'cg15627457', 'cg13327545', 'cg14334161', 'cg17485681', 'cg01560972', 'cg08715791', 'cg26942121', 'cg10378521', 'cg10906284', 'cg24894584']... [Total elements: 220]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=220, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [-6.912019729614258, 19.981544494628906, 2.626999855041504, 13.658905029296875, 1.2430390119552612, 1.00424325466156, 12.733586311340332, 2.4791877269744873, -0.152785524725914, 1.1130852699279785, -2.2575085163116455, 11.418535232543945, 1.824793815612793, -1.495959758758545, 2.821787118911743, -7.900047302246094, 5.732859134674072, 2.7955639362335205, 1.5466865301132202, 0.026381725445389748, 2.8932950496673584, 5.647821426391602, 12.655052185058594, 0.6008855700492859, 0.8880432844161987, 3.119521141052246, -6.521735191345215, -2.816964626312256, 2.2651326656341553, 8.25953197479248]... [Tensor of shape torch.Size([1, 220])]\n",
      "base_model.linear.bias: tensor([0.9233])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d55e5719",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "3bee47d9",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:22.642730Z",
     "iopub.status.busy": "2026-07-04T19:34:22.642660Z",
     "iopub.status.idle": "2026-07-04T19:34:22.647348Z",
     "shell.execute_reply": "2026-07-04T19:34:22.646813Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[ -20.1317],\n",
       "        [ -18.5452],\n",
       "        [ -99.1609],\n",
       "        [ -98.8837],\n",
       "        [   9.2466],\n",
       "        [-205.0112],\n",
       "        [-147.6273],\n",
       "        [ 118.3328],\n",
       "        [-114.6954],\n",
       "        [-142.6733]], 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": "3aa8710e",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "3717ec3c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:22.648884Z",
     "iopub.status.busy": "2026-07-04T19:34:22.648771Z",
     "iopub.status.idle": "2026-07-04T19:34:22.653308Z",
     "shell.execute_reply": "2026-07-04T19:34:22.652881Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "68d5cd98",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "391af4d4",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:22.654647Z",
     "iopub.status.busy": "2026-07-04T19:34:22.654572Z",
     "iopub.status.idle": "2026-07-04T19:34:22.658049Z",
     "shell.execute_reply": "2026-07-04T19:34:22.657634Z"
    }
   },
   "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
}