{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "8d5655aa",
   "metadata": {},
   "source": [
    "# EnsembleAgeHumanMouse"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "abb20db3",
   "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": "94d11f61",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "28ef9e62",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:33.693286Z",
     "iopub.status.busy": "2026-07-04T19:34:33.693156Z",
     "iopub.status.idle": "2026-07-04T19:34:35.684479Z",
     "shell.execute_reply": "2026-07-04T19:34:35.683969Z"
    }
   },
   "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": "2755a48c",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "596726bb",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:35.686158Z",
     "iopub.status.busy": "2026-07-04T19:34:35.685940Z",
     "iopub.status.idle": "2026-07-04T19:34:35.688944Z",
     "shell.execute_reply": "2026-07-04T19:34:35.688592Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class EnsembleAgeHumanMouse(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.EnsembleAgeHumanMouse)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "f91115e8",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:35.690204Z",
     "iopub.status.busy": "2026-07-04T19:34:35.690132Z",
     "iopub.status.idle": "2026-07-04T19:34:35.691885Z",
     "shell.execute_reply": "2026-07-04T19:34:35.691540Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.EnsembleAgeHumanMouse()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fc745769",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "d9229f62",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:35.693133Z",
     "iopub.status.busy": "2026-07-04T19:34:35.693046Z",
     "iopub.status.idle": "2026-07-04T19:34:35.695208Z",
     "shell.execute_reply": "2026-07-04T19:34:35.694828Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"ensembleagehumanmouse\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: EnsembleAge integrates predictions from multiple penalized models.\n",
    "model.metadata[\"species\"] = \"Homo sapiens and Mus musculus\"  # Paper: A merged human-mouse dataset enabled cross-species predictions.\n",
    "model.metadata[\"year\"] = 2025\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Haghani, A. et al. EnsembleAge: enhancing epigenetic age assessment with a multi-clock framework. GeroScience 48, 2873-2886 (2025).\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1007/s11357-025-01808-1\"\n",
    "model.metadata[\"notes\"] = \"Cross-species static EnsembleAge model trained on merged human and mouse methylation data; age is normalized by species maximum lifespan.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"multi-tissue\", \"whole blood\"]  # Paper: The human dataset consisted of 81 blood samples; mouse data covered various tissues.\n",
    "model.metadata[\"predicts\"] = [\"relative age\"]  # Paper: EnsembleAge integrates predictions from multiple penalized models.\n",
    "model.metadata[\"training_target\"] = [\"relative age\"]  # Paper: Age was normalized by maximum species lifespan.\n",
    "model.metadata[\"unit\"] = [\"relative age\"]  # Paper: HumanMouse clocks predict relative age (age/maximum species lifespan).\n",
    "model.metadata[\"model_type\"] = \"elastic net regression\"  # Paper: The clocks were trained using ridge, lasso, and elastic net regression.\n",
    "model.metadata[\"platform\"] = [\"mammalian methylation array\"]  # Paper: The DNA methylation data used in this study were generated using either the Mammal40k or Mammal320k BeadChip platforms.\n",
    "model.metadata[\"population\"] = \"humans and mice\"  # Paper: Mouse and human methylation data were combined for cross-species predictions.\n",
    "model.metadata[\"journal\"] = \"GeroScience\"\n",
    "model.metadata[\"last_author\"] = \"Steve Horvath\"\n",
    "model.metadata[\"n_features\"] = 100\n",
    "model.metadata[\"citations\"] = 3\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "34c8c0c7",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "8c43a8a1",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:35.696570Z",
     "iopub.status.busy": "2026-07-04T19:34:35.696488Z",
     "iopub.status.idle": "2026-07-04T19:34:35.858102Z",
     "shell.execute_reply": "2026-07-04T19:34:35.857414Z"
    }
   },
   "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/EnsembleAge/EnsembleAge_HumanMouse_HumanMouse_coefs.csv\"\n",
    "supplementary_file_name = \"coefficients.csv\"\n",
    "os.system(f\"curl -sL -o {supplementary_file_name} {supplementary_url}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "719af326",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "64a4fac2",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:35.859936Z",
     "iopub.status.busy": "2026-07-04T19:34:35.859806Z",
     "iopub.status.idle": "2026-07-04T19:34:35.866906Z",
     "shell.execute_reply": "2026-07-04T19:34:35.866283Z"
    }
   },
   "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": "f9c9a8bd",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "1cf7ab25",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:35.868665Z",
     "iopub.status.busy": "2026-07-04T19:34:35.868545Z",
     "iopub.status.idle": "2026-07-04T19:34:35.871508Z",
     "shell.execute_reply": "2026-07-04T19:34:35.870926Z"
    }
   },
   "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": "3751b4b1",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:35.872890Z",
     "iopub.status.busy": "2026-07-04T19:34:35.872771Z",
     "iopub.status.idle": "2026-07-04T19:34:35.875542Z",
     "shell.execute_reply": "2026-07-04T19:34:35.875007Z"
    }
   },
   "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": "49bf5598",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "060b4e0f",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:35.877338Z",
     "iopub.status.busy": "2026-07-04T19:34:35.877196Z",
     "iopub.status.idle": "2026-07-04T19:34:35.879255Z",
     "shell.execute_reply": "2026-07-04T19:34:35.878789Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "610ac906",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "12e51c7a",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:35.880548Z",
     "iopub.status.busy": "2026-07-04T19:34:35.880453Z",
     "iopub.status.idle": "2026-07-04T19:34:35.882040Z",
     "shell.execute_reply": "2026-07-04T19:34:35.881604Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "f372fd5b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:35.883419Z",
     "iopub.status.busy": "2026-07-04T19:34:35.883334Z",
     "iopub.status.idle": "2026-07-04T19:34:35.885256Z",
     "shell.execute_reply": "2026-07-04T19:34:35.884855Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8125ae04",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "43a20bfb",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:35.886553Z",
     "iopub.status.busy": "2026-07-04T19:34:35.886472Z",
     "iopub.status.idle": "2026-07-04T19:34:35.890121Z",
     "shell.execute_reply": "2026-07-04T19:34:35.889695Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Haghani, Amin, et al. \"EnsembleAge: an ensemble of epigenetic '\n",
      "             'clocks for robust age estimation.\" GeroScience (2025).',\n",
      " 'clock_name': 'ensembleagehumanmouse',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1007/s11357-025-01808-1',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'Homo sapiens',\n",
      " 'version': None,\n",
      " 'year': 2025}\n",
      "reference_values: None\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: None\n",
      "postprocess_dependencies: None\n",
      "features: ['cg00001364', 'cg00001582', 'cg00003994', 'cg00005112', 'cg00051782', 'cg00060304', 'cg00066554', 'cg00067884', 'cg00073543', 'cg00079224', 'cg00084577', 'cg00091964', 'cg00096922', 'cg00109076', 'cg00109300', 'cg00116234', 'cg00146676', 'cg00158333', 'cg00159243', 'cg00167491', 'cg00187380', 'cg00211337', 'cg00216659', 'cg00247020', 'cg00271154', 'cg00272971', 'cg00297075', 'cg00314427', 'cg00323965', 'cg00331096']... [Total elements: 2252]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=2252, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.02849973551928997, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.27547580003738403, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]... [Tensor of shape torch.Size([1, 2252])]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "base_model.linear.bias: tensor([-0.5651])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6a0e8621",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "4d2655ef",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:35.891852Z",
     "iopub.status.busy": "2026-07-04T19:34:35.891743Z",
     "iopub.status.idle": "2026-07-04T19:34:35.896802Z",
     "shell.execute_reply": "2026-07-04T19:34:35.896477Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[-1.0967],\n",
       "        [ 0.8136],\n",
       "        [-3.3391],\n",
       "        [-0.1142],\n",
       "        [-1.4556],\n",
       "        [ 2.6708],\n",
       "        [-3.5248],\n",
       "        [-2.2007],\n",
       "        [-4.3380],\n",
       "        [-1.6859]], 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": "004e34f8",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "5249b193",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:35.898442Z",
     "iopub.status.busy": "2026-07-04T19:34:35.898349Z",
     "iopub.status.idle": "2026-07-04T19:34:35.902267Z",
     "shell.execute_reply": "2026-07-04T19:34:35.901826Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c4016af5",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "933ba5a7",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:35.903562Z",
     "iopub.status.busy": "2026-07-04T19:34:35.903479Z",
     "iopub.status.idle": "2026-07-04T19:34:35.907178Z",
     "shell.execute_reply": "2026-07-04T19:34:35.906731Z"
    }
   },
   "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
}