{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "2f04eee0-5928-4e74-a754-6dc2e528810c",
   "metadata": {},
   "source": [
    "# ZhangMortality"
   ]
  },
  {
   "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": "2024-03-05T21:25:07.956904Z",
     "iopub.status.busy": "2024-03-05T21:25:07.956439Z",
     "iopub.status.idle": "2024-03-05T21:25:09.282393Z",
     "shell.execute_reply": "2024-03-05T21:25:09.282088Z"
    }
   },
   "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": "2024-03-05T21:25:09.284343Z",
     "iopub.status.busy": "2024-03-05T21:25:09.284184Z",
     "iopub.status.idle": "2024-03-05T21:25:09.293562Z",
     "shell.execute_reply": "2024-03-05T21:25:09.293276Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class ZhangMortality(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.ZhangMortality)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "78536494-f1d9-44de-8583-c89a310d2307",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:25:09.295006Z",
     "iopub.status.busy": "2024-03-05T21:25:09.294925Z",
     "iopub.status.idle": "2024-03-05T21:25:09.296661Z",
     "shell.execute_reply": "2024-03-05T21:25:09.296440Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.ZhangMortality()"
   ]
  },
  {
   "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": "2024-03-05T21:25:09.298162Z",
     "iopub.status.busy": "2024-03-05T21:25:09.298063Z",
     "iopub.status.idle": "2024-03-05T21:25:09.300090Z",
     "shell.execute_reply": "2024-03-05T21:25:09.299834Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"zhangmortality\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: The score is based on whole-blood DNA methylation.\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: The ESTHER and KORA cohorts comprise human participants.\n",
    "model.metadata[\"year\"] = 2017\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Zhang, Y., Wilson, R., Heiss, J. et al. DNA methylation signatures in peripheral blood strongly predict all-cause mortality. Nature Communications 8, 14617 (2017).\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1038/ncomms14617\"\n",
    "model.metadata[\"notes\"] = \"Ten-CpG whole-blood mortality risk score. Pyaging implements the paper supplement's continuous LASSO-weighted score exactly (the sum of ten raw beta values multiplied by their published coefficients). The same study also defines a separate simplified 0-10 aberrant-methylation count based on cohort-specific quartile cutoffs.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"whole blood\"]  # Paper: DNAm was quantified in baseline whole blood.\n",
    "model.metadata[\"predicts\"] = [\"mortality risk\"]  # Paper: The implementation returns a continuous weighted methylation score from the ten mortality CpGs.\n",
    "model.metadata[\"training_target\"] = [\"mortality\"]  # Paper: Ten CpGs were selected from mortality-associated loci for an all-cause mortality risk score.\n",
    "model.metadata[\"unit\"] = [\"unitless\"]  # Paper: The pyaging model applies no postprocess and returns the weighted sum directly.\n",
    "model.metadata[\"model_type\"] = \"weighted linear score\"  # Paper: The implementation is a one-layer linear weighted sum of ten methylation beta values.\n",
    "model.metadata[\"platform\"] = [\"Illumina 450K\"]  # Paper: Whole-blood DNAm was measured using the Infinium HumanMethylation450K BeadChip.\n",
    "model.metadata[\"population\"] = \"older adults\"  # Paper: The ESTHER general-population cohort enrolled adults aged 50 to 75 years.\n",
    "model.metadata[\"journal\"] = \"Nature Communications\"\n",
    "model.metadata[\"last_author\"] = \"Hermann Brenner\"\n",
    "model.metadata[\"n_features\"] = 10\n",
    "model.metadata[\"citations\"] = 404\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": "code",
   "execution_count": 5,
   "id": "f1965587-a6ac-47ce-bd7a-bb98ca1d91b5",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:25:09.301539Z",
     "iopub.status.busy": "2024-03-05T21:25:09.301447Z",
     "iopub.status.idle": "2024-03-05T21:25:09.303353Z",
     "shell.execute_reply": "2024-03-05T21:25:09.303096Z"
    }
   },
   "outputs": [],
   "source": [
    "features = [\n",
    "    'cg01612140',\n",
    "    'cg05575921',\n",
    "    'cg06126421',\n",
    "    'cg08362785',\n",
    "    'cg10321156',\n",
    "    'cg14975410',\n",
    "    'cg19572487',\n",
    "    'cg23665802',\n",
    "    'cg24704287',\n",
    "    'cg25983901'\n",
    "]\n",
    "\n",
    "coefficients = [\n",
    "    -0.38253,\n",
    "    -0.92224,\n",
    "    -1.70129,\n",
    "    2.71749,\n",
    "    -0.02073,\n",
    "    -0.04156,\n",
    "    -0.28069,\n",
    "    -0.89440,\n",
    "    -2.98637,\n",
    "    -1.80325,\n",
    "]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5035b180-3d1b-4432-8ebe-b9c92bd93a7f",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "77face1a-b58f-4f8f-9fe8-1f12037be99a",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:25:09.304769Z",
     "iopub.status.busy": "2024-03-05T21:25:09.304680Z",
     "iopub.status.idle": "2024-03-05T21:25:09.306154Z",
     "shell.execute_reply": "2024-03-05T21:25:09.305938Z"
    }
   },
   "outputs": [],
   "source": [
    "model.features = features"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ee6d8fa0-4767-4c45-9717-eb1c95e2ddc0",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "e09b3463-4fd4-41b1-ac21-e63ddd223fe0",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:25:09.307564Z",
     "iopub.status.busy": "2024-03-05T21:25:09.307482Z",
     "iopub.status.idle": "2024-03-05T21:25:09.309314Z",
     "shell.execute_reply": "2024-03-05T21:25:09.309089Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor(coefficients).unsqueeze(0)\n",
    "intercept = torch.tensor([0.0])"
   ]
  },
  {
   "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": "2024-03-05T21:25:09.310733Z",
     "iopub.status.busy": "2024-03-05T21:25:09.310662Z",
     "iopub.status.idle": "2024-03-05T21:25:09.312660Z",
     "shell.execute_reply": "2024-03-05T21:25:09.312432Z"
    }
   },
   "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": "2024-03-05T21:25:09.314121Z",
     "iopub.status.busy": "2024-03-05T21:25:09.314044Z",
     "iopub.status.idle": "2024-03-05T21:25:09.315651Z",
     "shell.execute_reply": "2024-03-05T21:25:09.315448Z"
    }
   },
   "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": "2024-03-05T21:25:09.317059Z",
     "iopub.status.busy": "2024-03-05T21:25:09.316985Z",
     "iopub.status.idle": "2024-03-05T21:25:09.318518Z",
     "shell.execute_reply": "2024-03-05T21:25:09.318276Z"
    }
   },
   "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": "2024-03-05T21:25:09.319853Z",
     "iopub.status.busy": "2024-03-05T21:25:09.319775Z",
     "iopub.status.idle": "2024-03-05T21:25:09.321301Z",
     "shell.execute_reply": "2024-03-05T21:25:09.321077Z"
    }
   },
   "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": "2024-03-05T21:25:09.322743Z",
     "iopub.status.busy": "2024-03-05T21:25:09.322648Z",
     "iopub.status.idle": "2024-03-05T21:25:09.325705Z",
     "shell.execute_reply": "2024-03-05T21:25:09.325440Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Zhang, Yan, et al. \"DNA methylation signatures in peripheral '\n",
      "             'blood strongly predict all-cause mortality.\" Nature '\n",
      "             'communications 8.1 (2017): 14617.',\n",
      " 'clock_name': 'zhangmortality',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1038/ncomms14617',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'Homo sapiens',\n",
      " 'version': None,\n",
      " 'year': 2017}\n",
      "reference_values: None\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: None\n",
      "postprocess_dependencies: None\n",
      "features: ['cg01612140',\n",
      " 'cg05575921',\n",
      " 'cg06126421',\n",
      " 'cg08362785',\n",
      " 'cg10321156',\n",
      " 'cg14975410',\n",
      " 'cg19572487',\n",
      " 'cg23665802',\n",
      " 'cg24704287',\n",
      " 'cg25983901']\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=10, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: tensor([[-0.3825, -0.9222, -1.7013,  2.7175, -0.0207, -0.0416, -0.2807, -0.8944,\n",
      "         -2.9864, -1.8032]])\n",
      "base_model.linear.bias: tensor([0.])\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": "2024-03-05T21:25:09.327232Z",
     "iopub.status.busy": "2024-03-05T21:25:09.327153Z",
     "iopub.status.idle": "2024-03-05T21:25:09.331310Z",
     "shell.execute_reply": "2024-03-05T21:25:09.331080Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[ -0.4323],\n",
       "        [ -7.2390],\n",
       "        [ -4.4894],\n",
       "        [ -0.7974],\n",
       "        [  2.5606],\n",
       "        [ -0.6228],\n",
       "        [ -4.8378],\n",
       "        [ -6.7516],\n",
       "        [-10.8399],\n",
       "        [ -3.3397]], 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": "2024-03-05T21:25:09.332785Z",
     "iopub.status.busy": "2024-03-05T21:25:09.332705Z",
     "iopub.status.idle": "2024-03-05T21:25:09.335406Z",
     "shell.execute_reply": "2024-03-05T21:25:09.335158Z"
    }
   },
   "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": "2024-03-05T21:25:09.336853Z",
     "iopub.status.busy": "2024-03-05T21:25:09.336775Z",
     "iopub.status.idle": "2024-03-05T21:25:09.339468Z",
     "shell.execute_reply": "2024-03-05T21:25:09.339242Z"
    }
   },
   "outputs": [],
   "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
}