{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "2f04eee0-5928-4e74-a754-6dc2e528810c",
   "metadata": {},
   "source": [
    "# YingDamAge"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a3f514a3-772c-4a14-afdf-5a8376851ff4",
   "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": "d95fafdc-643a-40ea-a689-200bd132e90c",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "4adfb4de-cd79-4913-a1af-9e23e9e236c9",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:24:02.211552Z",
     "iopub.status.busy": "2024-03-05T21:24:02.211102Z",
     "iopub.status.idle": "2024-03-05T21:24:03.523239Z",
     "shell.execute_reply": "2024-03-05T21:24:03.522939Z"
    }
   },
   "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": "145082e5-ced4-47ae-88c0-cb69773e3c5a",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "8aa77372-7ed3-4da7-abc9-d30372106139",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:24:03.525076Z",
     "iopub.status.busy": "2024-03-05T21:24:03.524915Z",
     "iopub.status.idle": "2024-03-05T21:24:03.534595Z",
     "shell.execute_reply": "2024-03-05T21:24:03.534346Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class YingDamAge(pyagingModel):\n",
      "    def __init__(self):\n",
      "        super().__init__()\n",
      "\n",
      "    def preprocess(self, x):\n",
      "        return x\n",
      "\n",
      "    def postprocess(self, x):\n",
      "        return x\n",
      "\n"
     ]
    }
   ],
   "source": [
    "def print_entire_class(cls):\n",
    "    source = inspect.getsource(cls)\n",
    "    print(source)\n",
    "\n",
    "print_entire_class(pya.models.YingDamAge)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "78536494-f1d9-44de-8583-c89a310d2307",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:24:03.536067Z",
     "iopub.status.busy": "2024-03-05T21:24:03.535985Z",
     "iopub.status.idle": "2024-03-05T21:24:03.537676Z",
     "shell.execute_reply": "2024-03-05T21:24:03.537459Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.YingDamAge()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "51f8615e-01fa-4aa5-b196-3ee2b35d261c",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "6601da9e-8adc-44ee-9308-75e3cd31b816",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:24:03.539130Z",
     "iopub.status.busy": "2024-03-05T21:24:03.539058Z",
     "iopub.status.idle": "2024-03-05T21:24:03.541106Z",
     "shell.execute_reply": "2024-03-05T21:24:03.540883Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"yingdamage\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: All three clocks use whole-blood DNA-methylation beta values.\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: The models were trained in human Generation Scotland blood samples.\n",
    "model.metadata[\"year\"] = 2024\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Ying, K., Liu, H., Tarkhov, A.E. et al. Causality-enriched epigenetic age uncouples damage and adaptation. Nature Aging 4, 231–246 (2024).\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1038/s43587-023-00557-0\"\n",
    "model.metadata[\"notes\"] = \"Causality-enriched age predictor restricted to damaging age-related CpGs, with feature penalties weighted by EWMR causality scores.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"whole blood\"]  # Paper: The model was trained in whole-blood methylation.\n",
    "model.metadata[\"predicts\"] = [\"damaging epigenetic age\"]  # Paper: DamAge is designed as a biomarker of age-related damaging methylation changes.\n",
    "model.metadata[\"training_target\"] = [\"chronological age\"]  # Paper: All three causality-enriched elastic-net models were trained to predict chronological age.\n",
    "model.metadata[\"unit\"] = [\"years\"]  # Paper: Model selection used mean absolute error in years against chronological age.\n",
    "model.metadata[\"model_type\"] = \"causality-weighted elastic net regression\"  # Paper: Feature-specific elastic-net penalty factors were assigned from each CpG's causality score.\n",
    "model.metadata[\"platform\"] = [\"Illumina 450K\"]  # Paper: Training used Generation Scotland whole-blood methylation at CpGs available to the 450K-based analysis.\n",
    "model.metadata[\"population\"] = \"adults\"  # Paper: Age-related methylation was estimated in 7,036 Generation Scotland participants aged 18–93, and 2,664 blood samples were used for clock training.\n",
    "model.metadata[\"journal\"] = \"Nature Aging\"\n",
    "model.metadata[\"last_author\"] = \"Vadim N. Gladyshev\"\n",
    "model.metadata[\"n_features\"] = 1089\n",
    "model.metadata[\"citations\"] = 183\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "74492239-5aae-4026-9d90-6bc9c574c110",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fbacbbc5-7cf1-41bd-81c4-45adde992de6",
   "metadata": {},
   "source": [
    "#### Download directly with curl"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "348e113d-a00a-481d-84ac-e8459a4a5050",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:24:03.542569Z",
     "iopub.status.busy": "2024-03-05T21:24:03.542473Z",
     "iopub.status.idle": "2024-03-05T21:24:03.626893Z",
     "shell.execute_reply": "2024-03-05T21:24:03.626623Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "supplementary_url = \"https://static-content.springer.com/esm/art%3A10.1038%2Fs43587-023-00557-0/MediaObjects/43587_2023_557_MOESM6_ESM.zip\"\n",
    "supplementary_file_name = \"43587_2023_557_MOESM6_ESM.zip\"\n",
    "os.system(f\"curl -o {supplementary_file_name} {supplementary_url}\")\n",
    "os.system(f'unzip {supplementary_file_name}')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5035b180-3d1b-4432-8ebe-b9c92bd93a7f",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1c756bdc-1646-4915-b91d-4da228a02fbc",
   "metadata": {},
   "source": [
    "#### From CSV file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "388283a9-923f-4219-b018-e59cb951ffae",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:24:03.628565Z",
     "iopub.status.busy": "2024-03-05T21:24:03.628461Z",
     "iopub.status.idle": "2024-03-05T21:24:03.632172Z",
     "shell.execute_reply": "2024-03-05T21:24:03.631937Z"
    }
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv('YingDamAge.csv')\n",
    "df['feature'] = df['term']\n",
    "df['coefficient'] = df['estimate']\n",
    "model.features = df['feature'][1:].tolist()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5e3e30f8-4cae-4f82-98cf-927c55eea9df",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "051acf76-075a-44e9-91b4-7fd3a28cfbdf",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:24:03.633688Z",
     "iopub.status.busy": "2024-03-05T21:24:03.633612Z",
     "iopub.status.idle": "2024-03-05T21:24:03.635646Z",
     "shell.execute_reply": "2024-03-05T21:24:03.635397Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor(df['coefficient'][1:].tolist()).unsqueeze(0)\n",
    "intercept = torch.tensor([df['coefficient'][0]])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ad261636-5b00-4979-bb1d-67a851f7aa19",
   "metadata": {},
   "source": [
    "#### Linear model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "d7f43b99-26f2-4622-9a76-316712058877",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:24:03.637102Z",
     "iopub.status.busy": "2024-03-05T21:24:03.637022Z",
     "iopub.status.idle": "2024-03-05T21:24:03.639147Z",
     "shell.execute_reply": "2024-03-05T21:24:03.638925Z"
    }
   },
   "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": "ad8b4c1d-9d57-48b7-9a30-bcfea7b747b1",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "ade0f4c9-2298-4fc3-bb72-d200907dd731",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:24:03.640642Z",
     "iopub.status.busy": "2024-03-05T21:24:03.640563Z",
     "iopub.status.idle": "2024-03-05T21:24:03.642135Z",
     "shell.execute_reply": "2024-03-05T21:24:03.641855Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "af3bcf7b-74a8-4d21-9ccb-4de0c2b0516b",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "7a22fb20-c605-424d-8efb-7620c2c0755c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:24:03.643510Z",
     "iopub.status.busy": "2024-03-05T21:24:03.643435Z",
     "iopub.status.idle": "2024-03-05T21:24:03.644942Z",
     "shell.execute_reply": "2024-03-05T21:24:03.644726Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "ff4a21cb-cf41-44dc-9ed1-95cf8aa15772",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:24:03.646307Z",
     "iopub.status.busy": "2024-03-05T21:24:03.646223Z",
     "iopub.status.idle": "2024-03-05T21:24:03.647719Z",
     "shell.execute_reply": "2024-03-05T21:24:03.647501Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "86e3d6b1-e67e-4f3d-bd39-0ebec5726c3c",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "2168355c-47d9-475d-b816-49f65e74887c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:24:03.649103Z",
     "iopub.status.busy": "2024-03-05T21:24:03.649030Z",
     "iopub.status.idle": "2024-03-05T21:24:03.652086Z",
     "shell.execute_reply": "2024-03-05T21:24:03.651862Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': ('Ying, Kejun, et al. \"Causality-enriched epigenetic age '\n",
      "              'uncouples damage and adaptation.\" Nature Aging (2024): 1-16.',),\n",
      " 'clock_name': 'yingdamage',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1038/s43587-023-00557-0',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'Homo sapiens',\n",
      " 'version': None,\n",
      " 'year': 2024}\n",
      "reference_values: None\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: None\n",
      "postprocess_dependencies: None\n",
      "features: ['cg00003994', 'cg00023464', 'cg00049440', 'cg00052482', 'cg00073543', 'cg00084338', 'cg00115654', 'cg00117599', 'cg00192773', 'cg00228017', 'cg00296038', 'cg00300637', 'cg00310410', 'cg00330279', 'cg00332802', 'cg00346985', 'cg00423487', 'cg00462168', 'cg00488692', 'cg00512563', 'cg00523379', 'cg00534318', 'cg00554993', 'cg00563845', 'cg00603274', 'cg00612299', 'cg00614360', 'cg00645579', 'cg00655552', 'cg00697033']... [Total elements: 1089]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=1089, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [0.1111111119389534, 0.1420900523662567, 0.8157786130905151, -4.8587541580200195, 0.47707557678222656, 0.5002065300941467, 0.39611729979515076, 0.9855431914329529, 0.2023957073688507, 0.35894259810447693, 0.05865344777703285, -1.7170811891555786, 0.6014043688774109, -2.180171012878418, 0.9566295146942139, 0.4613795876502991, 0.8703015446662903, 0.1672862470149994, 0.06815365701913834, 0.15401731431484222, -3.003317356109619, 0.026848409324884415, -7.108214378356934, -5.615413665771484, 0.0425444021821022, 0.48533663153648376, 0.15448161959648132, 0.4560099244117737, -4.907559871673584, 0.8859975337982178]... [Tensor of shape torch.Size([1, 1089])]\n",
      "base_model.linear.bias: tensor([543.4316])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "986d0262-e0c7-4036-b687-dee53ba392fb",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "936b9877-d076-4ced-99aa-e8d4c58c5caf",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:24:03.653676Z",
     "iopub.status.busy": "2024-03-05T21:24:03.653568Z",
     "iopub.status.idle": "2024-03-05T21:24:03.657640Z",
     "shell.execute_reply": "2024-03-05T21:24:03.657364Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[584.9497],\n",
       "        [565.7351],\n",
       "        [780.7145],\n",
       "        [383.1862],\n",
       "        [373.4299],\n",
       "        [484.9948],\n",
       "        [714.8078],\n",
       "        [755.3972],\n",
       "        [452.7687],\n",
       "        [641.0902]], 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": "fe8299d7-9285-4e22-82fd-b664434b4369",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "5ef2fa8d-c80b-4fdd-8555-79c0d541788e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:24:03.659204Z",
     "iopub.status.busy": "2024-03-05T21:24:03.659121Z",
     "iopub.status.idle": "2024-03-05T21:24:03.661508Z",
     "shell.execute_reply": "2024-03-05T21:24:03.661255Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bac6257b-8d08-4a90-8d0b-7f745dc11ac1",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "11aeaa70-44c0-42f9-86d7-740e3849a7a6",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:24:03.662928Z",
     "iopub.status.busy": "2024-03-05T21:24:03.662849Z",
     "iopub.status.idle": "2024-03-05T21:24:03.666229Z",
     "shell.execute_reply": "2024-03-05T21:24:03.666006Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted file: 43587_2023_557_MOESM6_ESM.zip\n",
      "Deleted file: YingCausAge.csv\n",
      "Deleted file: YingDamAge.csv\n",
      "Deleted file: YingAdaptAge.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",
   "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": "3.9.17"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}