{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "2e3d5791",
   "metadata": {},
   "source": [
    "# DNAmFILi"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0f244a43",
   "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": "d5b77527",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "2bbbd86d",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:45:47.574508Z",
     "iopub.status.busy": "2026-07-04T19:45:47.574408Z",
     "iopub.status.idle": "2026-07-04T19:45:50.642340Z",
     "shell.execute_reply": "2026-07-04T19:45:50.641856Z"
    }
   },
   "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": "7a073804",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "6e42b7f8",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:45:50.643940Z",
     "iopub.status.busy": "2026-07-04T19:45:50.643760Z",
     "iopub.status.idle": "2026-07-04T19:45:50.646324Z",
     "shell.execute_reply": "2026-07-04T19:45:50.645994Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class DNAmFILi(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.DNAmFILi)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "8aeebf77",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:45:50.647583Z",
     "iopub.status.busy": "2026-07-04T19:45:50.647496Z",
     "iopub.status.idle": "2026-07-04T19:45:50.649118Z",
     "shell.execute_reply": "2026-07-04T19:45:50.648738Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.DNAmFILi()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7bd5a3fe",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "d9318220",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:45:50.650228Z",
     "iopub.status.busy": "2026-07-04T19:45:50.650160Z",
     "iopub.status.idle": "2026-07-04T19:45:50.652007Z",
     "shell.execute_reply": "2026-07-04T19:45:50.651746Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"dnamfili\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: A DNA methylation-based score was derived to predict frailty.\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: A DNA methylation-based score was derived to predict frailty.\n",
    "model.metadata[\"year\"] = 2022\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Li, X. et al. Derivation and validation of an epigenetic frailty risk score in population-based cohorts of older adults. Nature Communications 13, 5269 (2022).\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1038/s41467-022-32893-x\"\n",
    "model.metadata[\"notes\"] = \"Epigenetic frailty risk score (eFRS), a weighted 20-CpG whole-blood DNA-methylation score selected by LASSO from replicated frailty-associated loci.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"whole blood\"]  # Paper: A DNA methylation-based score was derived to predict frailty.\n",
    "model.metadata[\"predicts\"] = [\"frailty risk\"]  # Paper: A DNA methylation-based score was derived to predict frailty.\n",
    "model.metadata[\"training_target\"] = [\"frailty\"]  # Paper: Frailty was defined by a deficit-accumulation frailty index.\n",
    "model.metadata[\"unit\"] = [\"unitless\"]  # Paper: The eFRS was constructed as a weighted CpG score.\n",
    "model.metadata[\"model_type\"] = \"LASSO regression\"  # Paper: LASSO regression selected candidates and constructed eFRS.\n",
    "model.metadata[\"platform\"] = [\"Illumina EPIC\", \"Illumina 450K\"]  # Paper: EPIC was used in subsets I/II; 450K in subset III.\n",
    "model.metadata[\"population\"] = \"older adults\"  # Paper: ESTHER recruited adults aged 50-75; KORA-Age enrolled adults aged at least 65.\n",
    "model.metadata[\"journal\"] = \"Nature Communications\"\n",
    "model.metadata[\"last_author\"] = \"Hermann Brenner\"\n",
    "model.metadata[\"n_features\"] = 20\n",
    "model.metadata[\"citations\"] = 22\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "36999624",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "2e6a270e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:45:50.653306Z",
     "iopub.status.busy": "2026-07-04T19:45:50.653240Z",
     "iopub.status.idle": "2026-07-04T19:45:51.051673Z",
     "shell.execute_reply": "2026-07-04T19:45:51.050989Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "os.system(f\"curl -sL -o DNAmFI_Li_CpGs.rda https://raw.githubusercontent.com/HigginsChenLab/methylCIPHER/19b12296b0d7eb7055a97d068064df635f44ce3e/data/DNAmFI_Li_CpGs.rda\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "3f54f618",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:45:51.053726Z",
     "iopub.status.busy": "2026-07-04T19:45:51.053553Z",
     "iopub.status.idle": "2026-07-04T19:45:51.057119Z",
     "shell.execute_reply": "2026-07-04T19:45:51.056389Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Writing download.r\n"
     ]
    }
   ],
   "source": [
    "%%writefile download.r\n",
    "\n",
    "library(jsonlite)\n",
    "load(\"DNAmFI_Li_CpGs.rda\")\n",
    "write_json(DNAmFI_Li_CpGs, \"coefficients.json\", digits = 10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "ab163ae5",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:45:51.058913Z",
     "iopub.status.busy": "2026-07-04T19:45:51.058786Z",
     "iopub.status.idle": "2026-07-04T19:45:51.521018Z",
     "shell.execute_reply": "2026-07-04T19:45:51.520606Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "os.system(\"Rscript download.r\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1d32160c",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "479b810b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:45:51.522271Z",
     "iopub.status.busy": "2026-07-04T19:45:51.522190Z",
     "iopub.status.idle": "2026-07-04T19:45:51.526269Z",
     "shell.execute_reply": "2026-07-04T19:45:51.525853Z"
    }
   },
   "outputs": [],
   "source": [
    "coef_df = pd.DataFrame(json.load(open('coefficients.json')))\n",
    "model.features = coef_df['CpG'].tolist()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d06e7cda",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "1774f835",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:45:51.527432Z",
     "iopub.status.busy": "2026-07-04T19:45:51.527356Z",
     "iopub.status.idle": "2026-07-04T19:45:51.533006Z",
     "shell.execute_reply": "2026-07-04T19:45:51.532638Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor(coef_df['Beta'].tolist()).unsqueeze(0).float()\n",
    "intercept = torch.tensor([0.204]).float()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "a951fb9f",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:45:51.534190Z",
     "iopub.status.busy": "2026-07-04T19:45:51.534123Z",
     "iopub.status.idle": "2026-07-04T19:45:51.538773Z",
     "shell.execute_reply": "2026-07-04T19:45:51.538400Z"
    }
   },
   "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": "8ccf6acb",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "2d2677c2",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:45:51.539944Z",
     "iopub.status.busy": "2026-07-04T19:45:51.539875Z",
     "iopub.status.idle": "2026-07-04T19:45:51.541371Z",
     "shell.execute_reply": "2026-07-04T19:45:51.541006Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c486bab2",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "9c926dd2",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:45:51.542477Z",
     "iopub.status.busy": "2026-07-04T19:45:51.542412Z",
     "iopub.status.idle": "2026-07-04T19:45:51.543840Z",
     "shell.execute_reply": "2026-07-04T19:45:51.543558Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "a1f90561",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:45:51.544959Z",
     "iopub.status.busy": "2026-07-04T19:45:51.544886Z",
     "iopub.status.idle": "2026-07-04T19:45:51.546374Z",
     "shell.execute_reply": "2026-07-04T19:45:51.545997Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4aafda21",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "5a84f932",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:45:51.547447Z",
     "iopub.status.busy": "2026-07-04T19:45:51.547387Z",
     "iopub.status.idle": "2026-07-04T19:45:51.564412Z",
     "shell.execute_reply": "2026-07-04T19:45:51.564001Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Li, Xiaoyu, et al. \"A DNA methylation-based epigenetic frailty '\n",
      "             'score in older adults.\" Nature Communications 13.1 (2022): 5269.',\n",
      " 'clock_name': 'dnamfili',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1038/s41467-022-32893-x',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'Homo sapiens',\n",
      " 'version': None,\n",
      " 'year': 2022}\n",
      "reference_values: None\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: None\n",
      "postprocess_dependencies: None\n",
      "features: ['cg00921350',\n",
      " 'cg01234420',\n",
      " 'cg02867102',\n",
      " 'cg03725309',\n",
      " 'cg04955914',\n",
      " 'cg07312601',\n",
      " 'cg07349348',\n",
      " 'cg08463758',\n",
      " 'cg10408430',\n",
      " 'cg11700584',\n",
      " 'cg12510708',\n",
      " 'cg13570972',\n",
      " 'cg15058210',\n",
      " 'cg15380836',\n",
      " 'cg17860366',\n",
      " 'cg17971578',\n",
      " 'cg18791730',\n",
      " 'cg19267254',\n",
      " 'cg21656937',\n",
      " 'cg23458887']\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=20, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: tensor([[-0.2090, -0.1000, -0.0160, -0.2930, -0.1460, -0.0840,  0.1580,  0.1370,\n",
      "          0.2480, -0.1010, -0.0490,  0.0640, -0.0570, -0.1800, -0.1440,  0.3150,\n",
      "         -0.0750, -0.1760, -0.0250, -0.0770]])\n",
      "base_model.linear.bias: tensor([0.2040])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2667b5ca",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "9d682d4b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:45:51.565564Z",
     "iopub.status.busy": "2026-07-04T19:45:51.565496Z",
     "iopub.status.idle": "2026-07-04T19:45:51.573993Z",
     "shell.execute_reply": "2026-07-04T19:45:51.573612Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[-1.3837],\n",
       "        [-0.2305],\n",
       "        [-0.8730],\n",
       "        [ 0.7649],\n",
       "        [ 0.6257],\n",
       "        [ 0.3401],\n",
       "        [ 0.5390],\n",
       "        [-1.0176],\n",
       "        [ 0.3744],\n",
       "        [ 0.9479]], dtype=torch.float64, grad_fn=<AddmmBackward0>)"
      ]
     },
     "execution_count": 15,
     "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": "70cf6b12",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "d26521ad",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:45:51.575268Z",
     "iopub.status.busy": "2026-07-04T19:45:51.575192Z",
     "iopub.status.idle": "2026-07-04T19:45:51.579918Z",
     "shell.execute_reply": "2026-07-04T19:45:51.579503Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fd9eb3d9",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "09207c59",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:45:51.581202Z",
     "iopub.status.busy": "2026-07-04T19:45:51.581134Z",
     "iopub.status.idle": "2026-07-04T19:45:51.584736Z",
     "shell.execute_reply": "2026-07-04T19:45:51.584264Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted file: download.r\n",
      "Deleted file: DNAmFI_Li_CpGs.rda\n",
      "Deleted file: coefficients.json\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
}