{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "b87610a0",
   "metadata": {},
   "source": [
    "# DownSyndrome"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6fe58220",
   "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": "b0d96cab",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "aa5aa921",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:57.220510Z",
     "iopub.status.busy": "2026-07-04T20:00:57.220350Z",
     "iopub.status.idle": "2026-07-04T20:00:59.366749Z",
     "shell.execute_reply": "2026-07-04T20:00:59.366057Z"
    }
   },
   "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": "90356a5e",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "f9cce368",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:59.368742Z",
     "iopub.status.busy": "2026-07-04T20:00:59.368512Z",
     "iopub.status.idle": "2026-07-04T20:00:59.371690Z",
     "shell.execute_reply": "2026-07-04T20:00:59.371260Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class DownSyndrome(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.DownSyndrome)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "4814dc04",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:59.373088Z",
     "iopub.status.busy": "2026-07-04T20:00:59.373002Z",
     "iopub.status.idle": "2026-07-04T20:00:59.374745Z",
     "shell.execute_reply": "2026-07-04T20:00:59.374314Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.DownSyndrome()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fdd0be16",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "fa67b5a8",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:59.376003Z",
     "iopub.status.busy": "2026-07-04T20:00:59.375916Z",
     "iopub.status.idle": "2026-07-04T20:00:59.378026Z",
     "shell.execute_reply": "2026-07-04T20:00:59.377603Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"downsyndrome\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: genome-wide DNA methylation data\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: 196 DS and 439 non-DS newborns\n",
    "model.metadata[\"year\"] = 2021\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Muskens, Ivo S., et al. \\\"The genome-wide impact of trisomy 21 on DNA methylation and its implications for hematopoiesis.\\\" Nature Communications 12 (2021): 821.\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1038/s41467-021-21064-z\"\n",
    "model.metadata[\"notes\"] = \"Implementation-derived Down-syndrome-associated methylation projection score: pyaging computes a zero-intercept weighted sum of 652 neonatal blood-spot beta values using the paper's autosomal EWAS beta_overall effect estimates. The paper presents an EWAS, not a trained or validated Down syndrome classifier.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"neonatal blood spots\"]  # Paper: newborn blood samples\n",
    "model.metadata[\"predicts\"] = [\"Down syndrome methylation score\"]  # Paper: The output is the sum of methylation beta values weighted by beta_overall EWAS estimates.\n",
    "model.metadata[\"training_target\"] = [\"not applicable\"]  # Paper: The EWAS compares 196 newborns with Down syndrome and 439 without Down syndrome.\n",
    "model.metadata[\"unit\"] = [\"unitless\"]  # Paper: Methylation beta values and beta_overall weights are summed without calibration.\n",
    "model.metadata[\"model_type\"] = \"weighted linear score\"  # Paper: weights = beta_overall; intercept = 0.0\n",
    "model.metadata[\"platform\"] = [\"Illumina EPIC\"]  # Paper: Illumina Infinium MethylationEPIC Beadchip\n",
    "model.metadata[\"population\"] = \"newborns\"  # Paper: 196 DS and 439 non-DS newborns\n",
    "model.metadata[\"journal\"] = \"Nature Communications\"\n",
    "model.metadata[\"last_author\"] = \"Adam J. de Smith\"\n",
    "model.metadata[\"n_features\"] = 652\n",
    "model.metadata[\"citations\"] = 62\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b6431b55",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "dbd81250",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:59.379354Z",
     "iopub.status.busy": "2026-07-04T20:00:59.379267Z",
     "iopub.status.idle": "2026-07-04T20:00:59.626967Z",
     "shell.execute_reply": "2026-07-04T20:00:59.626471Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "os.system(f\"curl -sL -o downsyndrome.xlsx https://static-content.springer.com/esm/art%3A10.1038%2Fs41467-021-21064-z/MediaObjects/41467_2021_21064_MOESM6_ESM.xlsx\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "15e64390",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "6f7a291f",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:59.628313Z",
     "iopub.status.busy": "2026-07-04T20:00:59.628209Z",
     "iopub.status.idle": "2026-07-04T20:00:59.840432Z",
     "shell.execute_reply": "2026-07-04T20:00:59.839503Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/lucascamillo/pyaging/.venv/lib/python3.13/site-packages/openpyxl/worksheet/_reader.py:329: UserWarning: Unknown extension is not supported and will be removed\n",
      "  warn(msg)\n"
     ]
    }
   ],
   "source": [
    "df = pd.read_excel('downsyndrome.xlsx', sheet_name='EWAS_autosomes', skiprows=2)\n",
    "model.features = df['CpG'].tolist()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "52f591e0",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "813b5c2c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:59.842194Z",
     "iopub.status.busy": "2026-07-04T20:00:59.842084Z",
     "iopub.status.idle": "2026-07-04T20:00:59.844716Z",
     "shell.execute_reply": "2026-07-04T20:00:59.844210Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor(df['beta_overall'].tolist()).unsqueeze(0).float()\n",
    "intercept = torch.tensor([0.0]).float()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "d870db88",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:59.845954Z",
     "iopub.status.busy": "2026-07-04T20:00:59.845852Z",
     "iopub.status.idle": "2026-07-04T20:00:59.848349Z",
     "shell.execute_reply": "2026-07-04T20:00:59.847820Z"
    }
   },
   "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": "84481b74",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "5419366e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:59.849670Z",
     "iopub.status.busy": "2026-07-04T20:00:59.849567Z",
     "iopub.status.idle": "2026-07-04T20:00:59.851319Z",
     "shell.execute_reply": "2026-07-04T20:00:59.850989Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "49e4fdec",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "e98f49e7",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:59.852678Z",
     "iopub.status.busy": "2026-07-04T20:00:59.852577Z",
     "iopub.status.idle": "2026-07-04T20:00:59.854085Z",
     "shell.execute_reply": "2026-07-04T20:00:59.853713Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "f6b7f345",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:59.855360Z",
     "iopub.status.busy": "2026-07-04T20:00:59.855268Z",
     "iopub.status.idle": "2026-07-04T20:00:59.857362Z",
     "shell.execute_reply": "2026-07-04T20:00:59.856978Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a437e727",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "3d681f34",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:59.858587Z",
     "iopub.status.busy": "2026-07-04T20:00:59.858504Z",
     "iopub.status.idle": "2026-07-04T20:00:59.861609Z",
     "shell.execute_reply": "2026-07-04T20:00:59.861231Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Muskens, Ivo S., et al. \"Germline aberrant methylation '\n",
      "             'associated with Down syndrome and its impact on childhood acute '\n",
      "             'lymphoblastic leukemia risk.\" Nature Communications 12.1 (2021): '\n",
      "             '821.',\n",
      " 'clock_name': 'downsyndrome',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1038/s41467-021-21064-z',\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: ['cg07741821', 'cg02993069', 'cg12477880', 'cg08882472', 'cg24942416', 'cg07841633', 'cg00994804', 'cg11218872', 'cg02451831', 'cg13382072', 'cg24020235', 'cg17239923', 'cg19030331', 'cg03142697', 'cg24999883', 'cg12679760', 'cg23719650', 'cg11972401', 'cg23565347', 'cg19765472', 'cg04599341', 'cg16831070', 'cg06758350', 'cg11151981', 'cg08620751', 'cg08849601', 'cg02680932', 'cg22539182', 'cg11075561', 'cg04131721']... [Total elements: 652]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=652, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [-0.28867992758750916, 0.19754931330680847, 0.38263070583343506, 0.15737323462963104, -0.17506907880306244, -0.3285122215747833, 0.38840898871421814, -0.12085756659507751, -0.15854349732398987, 0.179888516664505, 0.18759849667549133, 0.23218844830989838, 0.16510215401649475, 0.3955685794353485, -0.0671553760766983, 0.18286938965320587, -0.10707408934831619, 0.05787608027458191, -0.09203432500362396, 0.2067182958126068, 0.19878044724464417, -0.061179906129837036, 0.28260132670402527, -0.062310606241226196, 0.1342443823814392, -0.07032307982444763, -0.07384317368268967, -0.14031463861465454, -0.22928495705127716, -0.0856233760714531]... [Tensor of shape torch.Size([1, 652])]\n",
      "base_model.linear.bias: tensor([0.])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "512347b2",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "ae50d83b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:59.862812Z",
     "iopub.status.busy": "2026-07-04T20:00:59.862726Z",
     "iopub.status.idle": "2026-07-04T20:00:59.866987Z",
     "shell.execute_reply": "2026-07-04T20:00:59.866594Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[-4.8313],\n",
       "        [-1.6036],\n",
       "        [ 4.0192],\n",
       "        [-1.2427],\n",
       "        [ 1.9975],\n",
       "        [-1.7729],\n",
       "        [ 0.8015],\n",
       "        [-1.8500],\n",
       "        [ 1.6546],\n",
       "        [ 0.3752]], 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": "cd022878",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "fbc36ccc",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:59.868554Z",
     "iopub.status.busy": "2026-07-04T20:00:59.868472Z",
     "iopub.status.idle": "2026-07-04T20:00:59.871908Z",
     "shell.execute_reply": "2026-07-04T20:00:59.871419Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2b66ba55",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "2aa157b8",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:59.873229Z",
     "iopub.status.busy": "2026-07-04T20:00:59.873151Z",
     "iopub.status.idle": "2026-07-04T20:00:59.877137Z",
     "shell.execute_reply": "2026-07-04T20:00:59.876655Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted file: downsyndrome.xlsx\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
}