{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "3afe26c6",
   "metadata": {},
   "source": [
    "# DunedinPoAm38"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c56dac27",
   "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": "ace60ef5",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "ffccb098",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:49.069875Z",
     "iopub.status.busy": "2026-07-04T19:51:49.069673Z",
     "iopub.status.idle": "2026-07-04T19:51:51.022943Z",
     "shell.execute_reply": "2026-07-04T19:51:51.022492Z"
    }
   },
   "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": "7f22e588",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "052ed739",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:51.024730Z",
     "iopub.status.busy": "2026-07-04T19:51:51.024525Z",
     "iopub.status.idle": "2026-07-04T19:51:51.027389Z",
     "shell.execute_reply": "2026-07-04T19:51:51.026894Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class DunedinPoAm38(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.DunedinPoAm38)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "86c09545",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:51.028528Z",
     "iopub.status.busy": "2026-07-04T19:51:51.028441Z",
     "iopub.status.idle": "2026-07-04T19:51:51.029926Z",
     "shell.execute_reply": "2026-07-04T19:51:51.029614Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.DunedinPoAm38()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e61817d7",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "f8acc42c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:51.031083Z",
     "iopub.status.busy": "2026-07-04T19:51:51.031006Z",
     "iopub.status.idle": "2026-07-04T19:51:51.033025Z",
     "shell.execute_reply": "2026-07-04T19:51:51.032623Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"dunedinpoam38\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: DunedinPoAm uses blood DNA methylation.\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: The model was developed in members of the human Dunedin Study.\n",
    "model.metadata[\"year\"] = 2020\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Belsky, D.W., Caspi, A., Arseneault, L. et al. Quantification of the pace of biological aging in humans through a blood test, the DunedinPoAm DNA methylation algorithm. eLife 9, e54870 (2020).\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.7554/elife.54870\"\n",
    "model.metadata[\"notes\"] = \"Whole-blood elastic-net estimator of the rate of biological aging, trained at age 38 against a longitudinal 18-biomarker Pace-of-Aging composite measured over ages 26–38.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"whole blood\"]  # Paper: DNA methylation at age 38 was measured in whole blood.\n",
    "model.metadata[\"predicts\"] = [\"pace of aging\"]  # Paper: DunedinPoAm is a rate measure of how fast biological aging is occurring.\n",
    "model.metadata[\"training_target\"] = [\"pace of aging\"]  # Paper: Elastic net was fitted to the Pace-of-Aging composite derived from 18 biomarkers at ages 26, 32 and 38.\n",
    "model.metadata[\"unit\"] = [\"biological years per chronological year\"]  # Paper: A value near 1 represents one year of biological aging per calendar year.\n",
    "model.metadata[\"model_type\"] = \"elastic net regression\"  # Paper: Elastic-net regression was used to derive the methylation algorithm.\n",
    "model.metadata[\"platform\"] = [\"Illumina 450K\"]  # Paper: Feature selection and model fitting used age-38 Dunedin whole-blood methylation measured on the 450K array; EPIC was used for later external application.\n",
    "model.metadata[\"population\"] = \"adults\"  # Paper: The target was developed in 954 members of the same-year Dunedin birth cohort.\n",
    "model.metadata[\"journal\"] = \"eLife\"\n",
    "model.metadata[\"last_author\"] = \"Terrie E. Moffitt\"\n",
    "model.metadata[\"n_features\"] = 46\n",
    "model.metadata[\"citations\"] = 666\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1b09d5f0",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "b5e0115b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:51.034144Z",
     "iopub.status.busy": "2026-07-04T19:51:51.034075Z",
     "iopub.status.idle": "2026-07-04T19:51:51.325931Z",
     "shell.execute_reply": "2026-07-04T19:51:51.325297Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "os.system(f\"curl -sL -o coefficients.csv https://raw.githubusercontent.com/bio-learn/biolearn/180852e2bab473303cb85da627178b1695ee9d86/biolearn/data/DunedinPoAm38.csv\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "247c122d",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "0ffb3b23",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:51.328578Z",
     "iopub.status.busy": "2026-07-04T19:51:51.328383Z",
     "iopub.status.idle": "2026-07-04T19:51:51.336297Z",
     "shell.execute_reply": "2026-07-04T19:51:51.335340Z"
    }
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv('coefficients.csv')\n",
    "mask = df['CpGmarker'].astype(str).str.lower().isin(['intercept', '(intercept)'])\n",
    "intercept_value = float(df.loc[mask, 'CoefficientTraining'].iloc[0]) if mask.any() else 0.0\n",
    "coef_df = df.loc[~mask].reset_index(drop=True)\n",
    "model.features = coef_df['CpGmarker'].tolist()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3c7dd300",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "ea267115",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:51.338817Z",
     "iopub.status.busy": "2026-07-04T19:51:51.338610Z",
     "iopub.status.idle": "2026-07-04T19:51:51.342005Z",
     "shell.execute_reply": "2026-07-04T19:51:51.341198Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor(coef_df['CoefficientTraining'].tolist()).unsqueeze(0).float()\n",
    "intercept = torch.tensor([intercept_value]).float()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "7bc4f1ef",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:51.343916Z",
     "iopub.status.busy": "2026-07-04T19:51:51.343750Z",
     "iopub.status.idle": "2026-07-04T19:51:51.346700Z",
     "shell.execute_reply": "2026-07-04T19:51:51.346151Z"
    }
   },
   "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": "d70fc713",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "5b6afea1",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:51.348488Z",
     "iopub.status.busy": "2026-07-04T19:51:51.348346Z",
     "iopub.status.idle": "2026-07-04T19:51:51.350333Z",
     "shell.execute_reply": "2026-07-04T19:51:51.349761Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ccaaa9b4",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "4f106911",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:51.352278Z",
     "iopub.status.busy": "2026-07-04T19:51:51.352139Z",
     "iopub.status.idle": "2026-07-04T19:51:51.354172Z",
     "shell.execute_reply": "2026-07-04T19:51:51.353586Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "018e94b7",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:51.355855Z",
     "iopub.status.busy": "2026-07-04T19:51:51.355720Z",
     "iopub.status.idle": "2026-07-04T19:51:51.357805Z",
     "shell.execute_reply": "2026-07-04T19:51:51.357221Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7500ab2b",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "2554719c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:51.359348Z",
     "iopub.status.busy": "2026-07-04T19:51:51.359226Z",
     "iopub.status.idle": "2026-07-04T19:51:51.363894Z",
     "shell.execute_reply": "2026-07-04T19:51:51.363440Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Belsky, Daniel W., et al. \"Quantification of the pace of '\n",
      "             'biological aging in humans through a blood test, the DunedinPoAm '\n",
      "             'DNA methylation algorithm.\" eLife 9 (2020): e54870.',\n",
      " 'clock_name': 'dunedinpoam38',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.7554/eLife.54870',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'Homo sapiens',\n",
      " 'version': None,\n",
      " 'year': 2020}\n",
      "reference_values: None\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: None\n",
      "postprocess_dependencies: None\n",
      "features: ['cg02582848', 'cg03730474', 'cg03922834', 'cg04480708', 'cg05227215', 'cg05513157', 'cg05575921', 'cg06133392', 'cg07045089', 'cg07185119', 'cg07986378', 'cg08376310', 'cg09349128', 'cg09404119', 'cg10727171', 'cg10919522', 'cg11574055', 'cg11674508', 'cg11897887', 'cg13074055', 'cg13121699', 'cg14485633', 'cg14775114', 'cg15018359', 'cg19422687', 'cg19510038', 'cg19743820', 'cg20451986', 'cg21079030', 'cg21370522']... [Total elements: 46]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=46, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [0.16865555942058563, -0.030930202454328537, 0.10762208700180054, 0.32811808586120605, 0.20570090413093567, -0.19139723479747772, -0.2568254768848419, -0.013769027777016163, 0.002585785463452339, 0.007155308965593576, -0.3933064937591553, 0.0372597873210907, -0.6891953945159912, 0.010446280241012573, -0.014004146680235863, -0.32410237193107605, 0.06089318171143532, 0.07774978131055832, 0.0017560641281306744, -0.0569249764084816, -0.05277020111680031, 0.030463986098766327, -0.1716403365135193, -0.19539450109004974, 0.2227468192577362, -0.16681736707687378, -0.10328859090805054, 0.01552193146198988, 0.008607408963143826, 0.1834435760974884]... [Tensor of shape torch.Size([1, 46])]\n",
      "base_model.linear.bias: tensor([-0.0693])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7912cf69",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "b4cdd204",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:51.365454Z",
     "iopub.status.busy": "2026-07-04T19:51:51.365348Z",
     "iopub.status.idle": "2026-07-04T19:51:51.370117Z",
     "shell.execute_reply": "2026-07-04T19:51:51.369506Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[ 2.5557],\n",
       "        [ 1.7208],\n",
       "        [ 1.9728],\n",
       "        [ 0.4137],\n",
       "        [-1.7117],\n",
       "        [-1.8462],\n",
       "        [-2.8839],\n",
       "        [-2.1433],\n",
       "        [-0.0711],\n",
       "        [-1.1731]], 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": "d8b09202",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "f7d23e7b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:51.372012Z",
     "iopub.status.busy": "2026-07-04T19:51:51.371857Z",
     "iopub.status.idle": "2026-07-04T19:51:51.375788Z",
     "shell.execute_reply": "2026-07-04T19:51:51.375344Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e5eccd9a",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "c55c1ce2",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:51.377229Z",
     "iopub.status.busy": "2026-07-04T19:51:51.377132Z",
     "iopub.status.idle": "2026-07-04T19:51:51.381019Z",
     "shell.execute_reply": "2026-07-04T19:51:51.380617Z"
    }
   },
   "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
}