{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "45dd50f8",
   "metadata": {},
   "source": [
    "# CompIL6"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6df251e6",
   "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": "2a87a779",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "e186a2b1",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:11.018016Z",
     "iopub.status.busy": "2026-07-04T19:34:11.017767Z",
     "iopub.status.idle": "2026-07-04T19:34:14.056505Z",
     "shell.execute_reply": "2026-07-04T19:34:14.056083Z"
    }
   },
   "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": "7a6f12f2",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "ab2e35f1",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:14.058255Z",
     "iopub.status.busy": "2026-07-04T19:34:14.058068Z",
     "iopub.status.idle": "2026-07-04T19:34:14.060929Z",
     "shell.execute_reply": "2026-07-04T19:34:14.060519Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class CompIL6(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.CompIL6)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "d8b1b2e2",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:14.062015Z",
     "iopub.status.busy": "2026-07-04T19:34:14.061930Z",
     "iopub.status.idle": "2026-07-04T19:34:14.063652Z",
     "shell.execute_reply": "2026-07-04T19:34:14.063282Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.CompIL6()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "24ddaba4",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "a5c9683f",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:14.064840Z",
     "iopub.status.busy": "2026-07-04T19:34:14.064770Z",
     "iopub.status.idle": "2026-07-04T19:34:14.066911Z",
     "shell.execute_reply": "2026-07-04T19:34:14.066494Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"compil6\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: A DNA-methylation predictor of IL-6 was developed from CpG methylation levels.\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: The training cohort comprised Lothian Birth Cohort 1936 participants.\n",
    "model.metadata[\"year\"] = 2021\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Stevenson, A. J., et al. “Creating and Validating a DNA Methylation-Based Proxy for Interleukin-6.” The Journals of Gerontology: Series A 76(12): 2284–2292 (2021).\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1093/gerona/glab046\"\n",
    "model.metadata[\"notes\"] = \"Thirty-five-CpG whole-blood proxy score for persistent IL-6-related inflammatory burden, fitted against covariate-adjusted normalized plasma IL-6.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"whole blood\"]  # Paper: DNA extracted from whole blood supplied the methylation predictors.\n",
    "model.metadata[\"predicts\"] = [\"interleukin-6\"]  # Paper: The 35-CpG weighted sum was generated as a DNAm proxy for IL-6.\n",
    "model.metadata[\"training_target\"] = [\"interleukin-6\"]  # Paper: IL-6 NPX was inverse normalized and adjusted for age, sex, genetic principal components, and Olink plate; standardized residuals entered penalized regression.\n",
    "model.metadata[\"unit\"] = [\"unitless\"]  # Paper: The proxy is computed by multiplying beta values by coefficients and summing into one score.\n",
    "model.metadata[\"model_type\"] = \"elastic net regression\"  # Paper: The elastic net model used glmnet with 12-fold cross-validation and alpha 0.5.\n",
    "model.metadata[\"platform\"] = [\"Illumina 450K\"]  # Paper: Training whole-blood DNA was analyzed on the Illumina 450K BeadChip.\n",
    "model.metadata[\"population\"] = \"older adults\"  # Paper: The predictor was developed in 875 LBC1936 older adults with mean age 70.\n",
    "model.metadata[\"journal\"] = \"The Journals of Gerontology: Series A\"\n",
    "model.metadata[\"last_author\"] = \"Riccardo E. Marioni\"\n",
    "model.metadata[\"n_features\"] = 35\n",
    "model.metadata[\"citations\"] = 55\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8e694012",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "89bbc4f4",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:14.068166Z",
     "iopub.status.busy": "2026-07-04T19:34:14.068091Z",
     "iopub.status.idle": "2026-07-04T19:34:14.321523Z",
     "shell.execute_reply": "2026-07-04T19:34:14.320849Z"
    }
   },
   "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/CompIL6.csv\"\n",
    "supplementary_file_name = \"coefficients.csv\"\n",
    "os.system(f\"curl -sL -o {supplementary_file_name} {supplementary_url}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "55f18405",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "b58c5283",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:14.323210Z",
     "iopub.status.busy": "2026-07-04T19:34:14.323083Z",
     "iopub.status.idle": "2026-07-04T19:34:14.332127Z",
     "shell.execute_reply": "2026-07-04T19:34:14.331594Z"
    }
   },
   "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": "3aeba73f",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "c7ced5d7",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:14.333838Z",
     "iopub.status.busy": "2026-07-04T19:34:14.333709Z",
     "iopub.status.idle": "2026-07-04T19:34:14.340415Z",
     "shell.execute_reply": "2026-07-04T19:34:14.340057Z"
    }
   },
   "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": "865a0a8b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:14.342025Z",
     "iopub.status.busy": "2026-07-04T19:34:14.341944Z",
     "iopub.status.idle": "2026-07-04T19:34:14.347150Z",
     "shell.execute_reply": "2026-07-04T19:34:14.346791Z"
    }
   },
   "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": "2f4a9c28",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "13c91d76",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:14.348491Z",
     "iopub.status.busy": "2026-07-04T19:34:14.348416Z",
     "iopub.status.idle": "2026-07-04T19:34:14.350239Z",
     "shell.execute_reply": "2026-07-04T19:34:14.349790Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1d094df1",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "35a710fa",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:14.351513Z",
     "iopub.status.busy": "2026-07-04T19:34:14.351434Z",
     "iopub.status.idle": "2026-07-04T19:34:14.353262Z",
     "shell.execute_reply": "2026-07-04T19:34:14.352840Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "c2885a53",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:14.354410Z",
     "iopub.status.busy": "2026-07-04T19:34:14.354339Z",
     "iopub.status.idle": "2026-07-04T19:34:14.356028Z",
     "shell.execute_reply": "2026-07-04T19:34:14.355627Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e03bd9ff",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "bbfcc7aa",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:14.357213Z",
     "iopub.status.busy": "2026-07-04T19:34:14.357146Z",
     "iopub.status.idle": "2026-07-04T19:34:14.370170Z",
     "shell.execute_reply": "2026-07-04T19:34:14.369691Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Stevenson, Anna J., et al. \"Creating and validating a DNA '\n",
      "             'methylation-based proxy for interleukin-6.\" The Journals of '\n",
      "             'Gerontology: Series A 76.12 (2021): 2284-2292.',\n",
      " 'clock_name': 'compil6',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1093/gerona/glab046',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'Homo sapiens',\n",
      " 'version': None,\n",
      " 'year': 2021}\n",
      "reference_values: None\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: None\n",
      "postprocess_dependencies: None\n",
      "features: ['cg26144437', 'cg03076319', 'cg05575921', 'cg21368161', 'cg04642923', 'cg21123519', 'cg04583842', 'cg16357224', 'cg24455236', 'cg25323809', 'cg03885055', 'cg17412005', 'cg19638572', 'cg04921989', 'cg14965639', 'cg04381957', 'cg20789595', 'cg24935598', 'cg26230601', 'cg16508480', 'cg12503394', 'cg18925601', 'cg19584649', 'cg03245734', 'cg04366687', 'cg14044707', 'cg25250132', 'cg04468741', 'cg23729763', 'cg10195814']... [Total elements: 35]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=35, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [0.05400000140070915, 0.3799999952316284, -0.14000000059604645, 0.11999999731779099, 0.25, 0.004999999888241291, 0.00019999999494757503, 0.003599999938160181, 0.06400000303983688, 0.1899999976158142, -0.44999998807907104, -0.08799999952316284, 0.36000001430511475, 0.0860000029206276, -0.10999999940395355, -0.01899999938905239, -0.3100000023841858, 0.09099999815225601, -0.10999999940395355, 0.028999999165534973, 0.0010999999940395355, -0.017999999225139618, 0.08100000023841858, 0.020999999716877937, 0.0820000022649765, 0.007499999832361937, 0.23999999463558197, 0.02500000037252903, 0.10000000149011612, 0.06300000101327896]... [Tensor of shape torch.Size([1, 35])]\n",
      "base_model.linear.bias: tensor([0.])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2c60f25e",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "a4306b82",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:14.371479Z",
     "iopub.status.busy": "2026-07-04T19:34:14.371392Z",
     "iopub.status.idle": "2026-07-04T19:34:14.386277Z",
     "shell.execute_reply": "2026-07-04T19:34:14.385777Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[-1.3984],\n",
       "        [ 0.5055],\n",
       "        [-1.2893],\n",
       "        [ 0.7687],\n",
       "        [ 1.4874],\n",
       "        [ 1.2169],\n",
       "        [-0.0179],\n",
       "        [ 0.4686],\n",
       "        [ 1.8998],\n",
       "        [-1.8617]], 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": "89025fd8",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "d45fc9cb",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:14.387585Z",
     "iopub.status.busy": "2026-07-04T19:34:14.387487Z",
     "iopub.status.idle": "2026-07-04T19:34:14.392445Z",
     "shell.execute_reply": "2026-07-04T19:34:14.392006Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "69f9096f",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "160a3ba7",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:14.393713Z",
     "iopub.status.busy": "2026-07-04T19:34:14.393641Z",
     "iopub.status.idle": "2026-07-04T19:34:14.397496Z",
     "shell.execute_reply": "2026-07-04T19:34:14.397024Z"
    }
   },
   "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
}