{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "136553c7",
   "metadata": {},
   "source": [
    "# Weidner"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "13408b5f",
   "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": "d3a9aaea",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "1f91650f",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:14:50.757904Z",
     "iopub.status.busy": "2026-07-04T19:14:50.757632Z",
     "iopub.status.idle": "2026-07-04T19:14:53.618509Z",
     "shell.execute_reply": "2026-07-04T19:14:53.617898Z"
    }
   },
   "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": "a636e6cd",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "df72b135",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:14:53.620223Z",
     "iopub.status.busy": "2026-07-04T19:14:53.620026Z",
     "iopub.status.idle": "2026-07-04T19:14:53.622809Z",
     "shell.execute_reply": "2026-07-04T19:14:53.622444Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class Weidner(pyagingModel):\n",
      "    def __init__(self):\n",
      "        super().__init__()\n",
      "\n",
      "    def preprocess(self, x):\n",
      "        if self.reference_values is None:\n",
      "            return x\n",
      "        if isinstance(self.reference_values, torch.Tensor):\n",
      "            reference = self.reference_values.to(device=x.device, dtype=x.dtype)\n",
      "        else:\n",
      "            reference = torch.tensor(self.reference_values, device=x.device, dtype=x.dtype)\n",
      "        return torch.where(torch.isnan(x), reference, x)\n",
      "\n",
      "    def postprocess(self, x):\n",
      "        return x\n",
      "\n"
     ]
    }
   ],
   "source": [
    "def print_entire_class(cls):\n",
    "    source = inspect.getsource(cls)\n",
    "    print(source)\n",
    "\n",
    "print_entire_class(pya.models.Weidner)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "07f61977",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:14:53.624076Z",
     "iopub.status.busy": "2026-07-04T19:14:53.623984Z",
     "iopub.status.idle": "2026-07-04T19:14:53.625725Z",
     "shell.execute_reply": "2026-07-04T19:14:53.625282Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.Weidner()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "06626889",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "a9aca4a3",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:14:53.626915Z",
     "iopub.status.busy": "2026-07-04T19:14:53.626845Z",
     "iopub.status.idle": "2026-07-04T19:14:53.628900Z",
     "shell.execute_reply": "2026-07-04T19:14:53.628504Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"weidner\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: DNA methylation changes at just three CpG sites\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: blood samples from healthy human donors\n",
    "model.metadata[\"year\"] = 2014\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Weidner, C. I., Lin, Q., Koch, C. M., et al. (2014). Aging of blood can be tracked by DNA methylation changes at just three CpG sites. Genome Biology, 15, R24.\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1186/gb-2014-15-2-r24\"\n",
    "model.metadata[\"notes\"] = \"Three-site whole-blood epigenetic-age estimator. The sites were selected from Illumina 27K blood profiles, and the final multivariate linear equation was fitted on targeted bisulfite-pyrosequencing beta values from 82 blood samples and validated in 69 independent samples.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"whole blood\"]  # Paper: DNAm profiles derived from blood samples; model fitted on blood samples\n",
    "model.metadata[\"predicts\"] = [\"biological age\"]  # Paper: signature provides a simple biomarker to estimate the state of aging in blood\n",
    "model.metadata[\"training_target\"] = [\"chronological age\"]  # Paper: multivariate linear model to predict donor age\n",
    "model.metadata[\"unit\"] = [\"years\"]  # Paper: Predicted age (in years)\n",
    "model.metadata[\"model_type\"] = \"linear regression\"  # Paper: multivariate linear regression model\n",
    "model.metadata[\"platform\"] = [\"Illumina 27K\", \"bisulfite sequencing\"]  # Paper: HumanMethylation27 BeadChip feature selection followed by pyrosequencing after bisulfite conversion\n",
    "model.metadata[\"population\"] = \"adults\"  # Paper: 82 blood samples for training and independent validation set of 69 blood samples\n",
    "model.metadata[\"journal\"] = \"Genome Biology\"\n",
    "model.metadata[\"last_author\"] = \"Wolfgang Wagner\"\n",
    "model.metadata[\"n_features\"] = 3\n",
    "model.metadata[\"citations\"] = 973\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6f5db821",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "97c175ff",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:14:53.630002Z",
     "iopub.status.busy": "2026-07-04T19:14:53.629937Z",
     "iopub.status.idle": "2026-07-04T19:14:53.946424Z",
     "shell.execute_reply": "2026-07-04T19:14:53.945623Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "supplementary_url = \"https://raw.githubusercontent.com/bio-learn/biolearn/180852e2bab473303cb85da627178b1695ee9d86/biolearn/data/Weidner.csv\"\n",
    "supplementary_file_name = \"Weidner.csv\"\n",
    "os.system(f\"curl -sL -o {supplementary_file_name} {supplementary_url}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d02d3ed4",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "eea1287d",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:14:53.948674Z",
     "iopub.status.busy": "2026-07-04T19:14:53.948497Z",
     "iopub.status.idle": "2026-07-04T19:14:53.956296Z",
     "shell.execute_reply": "2026-07-04T19:14:53.955522Z"
    }
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv('Weidner.csv')\n",
    "model.features = df['CpGmarker'].tolist()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fb85d648",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "7c425874",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:14:53.958418Z",
     "iopub.status.busy": "2026-07-04T19:14:53.958253Z",
     "iopub.status.idle": "2026-07-04T19:14:53.964725Z",
     "shell.execute_reply": "2026-07-04T19:14:53.964251Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor(df['CoefficientTraining'].tolist()).unsqueeze(0).float()\n",
    "intercept = torch.tensor([38.0]).float()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "6ad22e5c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:14:53.966402Z",
     "iopub.status.busy": "2026-07-04T19:14:53.966287Z",
     "iopub.status.idle": "2026-07-04T19:14:53.971793Z",
     "shell.execute_reply": "2026-07-04T19:14:53.971343Z"
    }
   },
   "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": "d86287f3",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "440614a6",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:14:53.973725Z",
     "iopub.status.busy": "2026-07-04T19:14:53.973595Z",
     "iopub.status.idle": "2026-07-04T19:14:53.975627Z",
     "shell.execute_reply": "2026-07-04T19:14:53.975046Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e8393289",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "611995fc",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:14:53.977018Z",
     "iopub.status.busy": "2026-07-04T19:14:53.976914Z",
     "iopub.status.idle": "2026-07-04T19:14:53.978624Z",
     "shell.execute_reply": "2026-07-04T19:14:53.978253Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "9a95009e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:14:53.980136Z",
     "iopub.status.busy": "2026-07-04T19:14:53.980032Z",
     "iopub.status.idle": "2026-07-04T19:14:53.981732Z",
     "shell.execute_reply": "2026-07-04T19:14:53.981275Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2e741416",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "b960b269",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:14:53.982989Z",
     "iopub.status.busy": "2026-07-04T19:14:53.982906Z",
     "iopub.status.idle": "2026-07-04T19:14:54.000670Z",
     "shell.execute_reply": "2026-07-04T19:14:54.000248Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Weidner, Carola I., et al. \"Aging of blood can be tracked by DNA '\n",
      "             'methylation changes at just three CpG sites.\" Genome biology '\n",
      "             '15.2 (2014): R24.',\n",
      " 'clock_name': 'weidner',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1186/gb-2014-15-2-r24',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'Homo sapiens',\n",
      " 'version': None,\n",
      " 'year': 2014}\n",
      "reference_values: None\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: None\n",
      "postprocess_dependencies: None\n",
      "features: ['cg02228185', 'cg25809905', 'cg17861230']\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=3, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: tensor([[-26.4000, -23.7000, 164.7000]])\n",
      "base_model.linear.bias: tensor([38.])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "73775bb5",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "c7c0c320",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:14:54.001912Z",
     "iopub.status.busy": "2026-07-04T19:14:54.001835Z",
     "iopub.status.idle": "2026-07-04T19:14:54.010665Z",
     "shell.execute_reply": "2026-07-04T19:14:54.010206Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[ 70.9916],\n",
       "        [157.0004],\n",
       "        [155.2728],\n",
       "        [ 58.9885],\n",
       "        [ 38.9402],\n",
       "        [143.5184],\n",
       "        [396.4215],\n",
       "        [ 66.8971],\n",
       "        [130.9565],\n",
       "        [-26.1560]], 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": "7a8e340f",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "9890f370",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:14:54.011882Z",
     "iopub.status.busy": "2026-07-04T19:14:54.011804Z",
     "iopub.status.idle": "2026-07-04T19:14:54.016889Z",
     "shell.execute_reply": "2026-07-04T19:14:54.016460Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "910e42e3",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "2ca0b462",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:14:54.018235Z",
     "iopub.status.busy": "2026-07-04T19:14:54.018143Z",
     "iopub.status.idle": "2026-07-04T19:14:54.021578Z",
     "shell.execute_reply": "2026-07-04T19:14:54.021146Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted file: Weidner.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
}