{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "ef375ab3",
   "metadata": {},
   "source": [
    "# Wu"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "37ab0032",
   "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": "837f458e",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "36c174fc",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:14.023480Z",
     "iopub.status.busy": "2026-07-04T20:25:14.023303Z",
     "iopub.status.idle": "2026-07-04T20:25:16.159946Z",
     "shell.execute_reply": "2026-07-04T20:25:16.159488Z"
    }
   },
   "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": "2f093b20",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "7194c9c3",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:16.161621Z",
     "iopub.status.busy": "2026-07-04T20:25:16.161446Z",
     "iopub.status.idle": "2026-07-04T20:25:16.164487Z",
     "shell.execute_reply": "2026-07-04T20:25:16.163945Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class Wu(LinearReferenceClock):\n",
      "    def postprocess(self, x):\n",
      "        \"\"\"Horvath anti-log (adult age = 48) giving months, then months to years.\"\"\"\n",
      "        adult_age = 48\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 / 12.0\n",
      "\n"
     ]
    }
   ],
   "source": [
    "def print_entire_class(cls):\n",
    "    source = inspect.getsource(cls)\n",
    "    print(source)\n",
    "\n",
    "print_entire_class(pya.models.Wu)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "b29cdb41",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:16.165955Z",
     "iopub.status.busy": "2026-07-04T20:25:16.165842Z",
     "iopub.status.idle": "2026-07-04T20:25:16.167651Z",
     "shell.execute_reply": "2026-07-04T20:25:16.167264Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.Wu()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1d9ed58a",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "c6f00388",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:16.169167Z",
     "iopub.status.busy": "2026-07-04T20:25:16.169042Z",
     "iopub.status.idle": "2026-07-04T20:25:16.170964Z",
     "shell.execute_reply": "2026-07-04T20:25:16.170647Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"wu\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: The model predicts child age from blood DNA methylation.\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: The model was built from healthy children's blood samples.\n",
    "model.metadata[\"year\"] = 2019\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Wu, X., et al. “DNA methylation profile is a quantitative measure of biological aging in children.” Aging 11(22): 10031–10051 (2019).\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.18632/aging.102399\"\n",
    "model.metadata[\"notes\"] = \"Child-specific 111-CpG blood age predictor built by sure independence screening followed by elastic net; pyaging converts the published month-scale output to years.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"whole blood\"]  # Paper: Healthy children's peripheral blood datasets were used to build the model.\n",
    "model.metadata[\"predicts\"] = [\"chronological age\"]  # Paper: The model's DNA methylation age closely predicted chronological age.\n",
    "model.metadata[\"training_target\"] = [\"chronological age\"]  # Paper: Age was converted to months and transformed by function F before elastic-net fitting.\n",
    "model.metadata[\"unit\"] = [\"years\"]  # Paper: The packaged postprocess applies the published inverse age transform in months and divides by 12.\n",
    "model.metadata[\"model_type\"] = \"screened elastic net regression\"  # Paper: Sure independence screening reduced dimensionality before glmnet elastic-net regression.\n",
    "model.metadata[\"platform\"] = [\"Illumina 27K\", \"Illumina 450K\"]  # Paper: Five training datasets used 27K and six used 450K; fitting used shared probes.\n",
    "model.metadata[\"population\"] = \"children\"  # Paper: The model used 716 child blood samples aged 9–212 months.\n",
    "model.metadata[\"journal\"] = \"Aging\"\n",
    "model.metadata[\"last_author\"] = \"Huiying Liang\"\n",
    "model.metadata[\"n_features\"] = 111\n",
    "model.metadata[\"citations\"] = 82\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "577d6c30",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "4b0f6969",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:16.172316Z",
     "iopub.status.busy": "2026-07-04T20:25:16.172226Z",
     "iopub.status.idle": "2026-07-04T20:25:16.502433Z",
     "shell.execute_reply": "2026-07-04T20:25:16.501259Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "os.system(f\"curl -sL -o wu.xlsx https://cdn.aging-us.com/article/102399/supplementary/SD3/0/aging-v11i22-102399-supplementary-material-SD3.xlsx\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5eeae20d",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "89167494",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:16.506344Z",
     "iopub.status.busy": "2026-07-04T20:25:16.506003Z",
     "iopub.status.idle": "2026-07-04T20:25:16.643268Z",
     "shell.execute_reply": "2026-07-04T20:25:16.642753Z"
    }
   },
   "outputs": [],
   "source": [
    "df = pd.read_excel('wu.xlsx', sheet_name='CpGs_information')\n",
    "mask = df['CpGs'].astype(str).str.lower().isin(['intercept', '(intercept)'])\n",
    "intercept_value = float(df.loc[mask, 'Active.coefficients'].iloc[0]) if mask.any() else 0.0\n",
    "coef_df = df.loc[~mask].reset_index(drop=True)\n",
    "model.features = coef_df['CpGs'].tolist()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6849edd5",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "71d7fcc0",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:16.644695Z",
     "iopub.status.busy": "2026-07-04T20:25:16.644619Z",
     "iopub.status.idle": "2026-07-04T20:25:16.646808Z",
     "shell.execute_reply": "2026-07-04T20:25:16.646247Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor(coef_df['Active.coefficients'].tolist()).unsqueeze(0).float()\n",
    "intercept = torch.tensor([intercept_value]).float()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "57ba4354",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:16.648075Z",
     "iopub.status.busy": "2026-07-04T20:25:16.647990Z",
     "iopub.status.idle": "2026-07-04T20:25:16.650460Z",
     "shell.execute_reply": "2026-07-04T20:25:16.649968Z"
    }
   },
   "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": "1ea86ce2",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "91bd25eb",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:16.651805Z",
     "iopub.status.busy": "2026-07-04T20:25:16.651724Z",
     "iopub.status.idle": "2026-07-04T20:25:16.653446Z",
     "shell.execute_reply": "2026-07-04T20:25:16.653113Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "55812aeb",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "548f9777",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:16.654632Z",
     "iopub.status.busy": "2026-07-04T20:25:16.654562Z",
     "iopub.status.idle": "2026-07-04T20:25:16.656059Z",
     "shell.execute_reply": "2026-07-04T20:25:16.655708Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "9a949fec",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:16.657128Z",
     "iopub.status.busy": "2026-07-04T20:25:16.657047Z",
     "iopub.status.idle": "2026-07-04T20:25:16.658605Z",
     "shell.execute_reply": "2026-07-04T20:25:16.658275Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = 'anti_log_linear'\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "36bc88a6",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "e71c82bd",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:16.659875Z",
     "iopub.status.busy": "2026-07-04T20:25:16.659791Z",
     "iopub.status.idle": "2026-07-04T20:25:16.662811Z",
     "shell.execute_reply": "2026-07-04T20:25:16.662415Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Wu, Xiaohui, et al. \"DNA methylation profile is a quantitative '\n",
      "             'measure of biological aging in children.\" Aging 11.22 (2019): '\n",
      "             '10031-10051.',\n",
      " 'clock_name': 'wu',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.18632/aging.102399',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'Homo sapiens',\n",
      " 'version': None,\n",
      " 'year': 2019}\n",
      "reference_values: None\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: 'anti_log_linear'\n",
      "postprocess_dependencies: None\n",
      "features: ['cg00343092', 'cg00563932', 'cg00571634', 'cg00629217', 'cg01511567', 'cg01515426', 'cg01756060', 'cg01899253', 'cg02385474', 'cg02489552', 'cg02626929', 'cg02789485', 'cg03224418', 'cg03340261', 'cg03970609', 'cg04458548', 'cg04460372', 'cg04474832', 'cg04527989', 'cg04784672', 'cg05073035', 'cg05228408', 'cg05294455', 'cg05352668', 'cg05921699', 'cg05995267', 'cg06204948', 'cg06495803', 'cg07408456', 'cg08032971']... [Total elements: 111]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=111, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [-1.1359976530075073, -2.2549679279327393, 1.2051302194595337, -1.4431147575378418, 0.5572546720504761, -4.753889083862305, -2.9755256175994873, -0.8770837783813477, -1.1014573574066162, 0.5342934727668762, 0.128916397690773, 0.35315999388694763, -0.16534864902496338, -6.689713954925537, 0.563336193561554, -0.28343427181243896, -0.9679408669471741, -1.2036683559417725, 0.6776095032691956, 1.7862359285354614, 1.216035008430481, -0.6090858578681946, 0.9103692173957825, -1.5713691711425781, 1.8002407550811768, 0.6004332900047302, 0.6391267776489258, 0.3963273763656616, -2.025444269180298, 0.6885870695114136]... [Tensor of shape torch.Size([1, 111])]\n",
      "base_model.linear.bias: tensor([2.3769])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cd69350f",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "58893a28",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:16.664243Z",
     "iopub.status.busy": "2026-07-04T20:25:16.664152Z",
     "iopub.status.idle": "2026-07-04T20:25:16.668877Z",
     "shell.execute_reply": "2026-07-04T20:25:16.668505Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[ 7.1793e+01],\n",
       "        [ 3.4194e+00],\n",
       "        [-8.3333e-02],\n",
       "        [ 2.7208e-01],\n",
       "        [-8.3328e-02],\n",
       "        [ 4.4315e+01],\n",
       "        [ 1.1845e+02],\n",
       "        [-8.2270e-02],\n",
       "        [-8.3325e-02],\n",
       "        [ 2.5722e+01]], dtype=torch.float64, grad_fn=<DivBackward0>)"
      ]
     },
     "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": "c6056a6d",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "6ef6fad9",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:16.670245Z",
     "iopub.status.busy": "2026-07-04T20:25:16.670166Z",
     "iopub.status.idle": "2026-07-04T20:25:16.673302Z",
     "shell.execute_reply": "2026-07-04T20:25:16.672898Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "844dc2b1",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "b01cfca1",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:16.674654Z",
     "iopub.status.busy": "2026-07-04T20:25:16.674579Z",
     "iopub.status.idle": "2026-07-04T20:25:16.677995Z",
     "shell.execute_reply": "2026-07-04T20:25:16.677656Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted file: wu.xlsx\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
}