{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "2f04eee0-5928-4e74-a754-6dc2e528810c",
   "metadata": {},
   "source": [
    "# ENCen40"
   ]
  },
  {
   "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": "2025-04-07T17:51:27.959555Z",
     "iopub.status.busy": "2025-04-07T17:51:27.959401Z",
     "iopub.status.idle": "2025-04-07T17:51:29.371268Z",
     "shell.execute_reply": "2025-04-07T17:51:29.370912Z"
    }
   },
   "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": "2025-04-07T17:51:29.373042Z",
     "iopub.status.busy": "2025-04-07T17:51:29.372813Z",
     "iopub.status.idle": "2025-04-07T17:51:29.379919Z",
     "shell.execute_reply": "2025-04-07T17:51:29.379636Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class ENCen40(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.ENCen40)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "78536494-f1d9-44de-8583-c89a310d2307",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:51:29.381229Z",
     "iopub.status.busy": "2025-04-07T17:51:29.381147Z",
     "iopub.status.idle": "2025-04-07T17:51:29.382807Z",
     "shell.execute_reply": "2025-04-07T17:51:29.382555Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.ENCen40()"
   ]
  },
  {
   "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": "2025-04-07T17:51:29.384092Z",
     "iopub.status.busy": "2025-04-07T17:51:29.384001Z",
     "iopub.status.idle": "2025-04-07T17:51:29.386007Z",
     "shell.execute_reply": "2025-04-07T17:51:29.385738Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"encen40\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: DNA methylation clocks\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: study individuals\n",
    "model.metadata[\"year\"] = 2023\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Dec, Eric, et al. \\\"Centenarian clocks: epigenetic clocks for validating claims of exceptional longevity.\\\" GeroScience 45 (2023): 1817–1835.\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1007/s11357-023-00731-7\"\n",
    "model.metadata[\"notes\"] = \"Elastic-net DNAm-age clock trained in 7,039 people aged 40–115, including centenarians, to reduce extreme-old-age underestimation.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"whole blood\", \"saliva\", \"buccal epithelium\"]  # Paper: blood, saliva, and buccals cells\n",
    "model.metadata[\"predicts\"] = [\"chronological age\"]  # Paper: DNAm age was defined as predicted age\n",
    "model.metadata[\"training_target\"] = [\"chronological age\"]  # Paper: regress chronological age on the CpG probes\n",
    "model.metadata[\"unit\"] = [\"years\"]  # Paper: individuals aged 40 years or older; predicted age\n",
    "model.metadata[\"model_type\"] = \"elastic net regression\"  # Paper: alpha parameter ... 0.5 (elastic net regression)\n",
    "model.metadata[\"platform\"] = [\"Illumina 450K\", \"Illumina EPIC\"]  # Paper: Infinium 450 K array and the Infinium methylation EPIC beadchip\n",
    "model.metadata[\"population\"] = \"older adults\"  # Paper: Age ≥40: N=7039, age range [40,115]\n",
    "model.metadata[\"journal\"] = \"GeroScience\"\n",
    "model.metadata[\"last_author\"] = \"Steve Horvath\"\n",
    "model.metadata[\"n_features\"] = 559\n",
    "model.metadata[\"citations\"] = 45\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": "1472c242-cf7b-4c26-b28a-dae2dcb69106",
   "metadata": {},
   "source": [
    "#### Download GitHub repository"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "51e8a008-833e-4499-a06f-32638c775821",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:51:29.387406Z",
     "iopub.status.busy": "2025-04-07T17:51:29.387321Z",
     "iopub.status.idle": "2025-04-07T17:51:30.211443Z",
     "shell.execute_reply": "2025-04-07T17:51:30.210909Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "github_url = \"https://github.com/victorychain/Centenarian-Clock.git\"\n",
    "github_folder_name = github_url.split('/')[-1].split('.')[0]\n",
    "os.system(f\"git clone {github_url}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5035b180-3d1b-4432-8ebe-b9c92bd93a7f",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "15f4af76-b93c-438c-b57f-f129d6e9ec99",
   "metadata": {},
   "source": [
    "#### From CSV file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "8a3d5de6-6303-487a-8b4d-e6345792f7be",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:51:30.213455Z",
     "iopub.status.busy": "2025-04-07T17:51:30.213299Z",
     "iopub.status.idle": "2025-04-07T17:51:30.499029Z",
     "shell.execute_reply": "2025-04-07T17:51:30.498648Z"
    }
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv('Centenarian-Clock/clocks/final_clocks.csv', index_col=0).T\n",
    "df = df[df['ENCen40+'] != 0]\n",
    "df = df.reset_index()\n",
    "\n",
    "model.features = df['index'][1:].tolist()"
   ]
  },
  {
   "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": "2025-04-07T17:51:30.500648Z",
     "iopub.status.busy": "2025-04-07T17:51:30.500558Z",
     "iopub.status.idle": "2025-04-07T17:51:30.502758Z",
     "shell.execute_reply": "2025-04-07T17:51:30.502486Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor(df['ENCen40+'][1:].tolist()).unsqueeze(0).float()\n",
    "intercept = torch.tensor([df['ENCen40+'][0]]).float()"
   ]
  },
  {
   "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": "2025-04-07T17:51:30.504113Z",
     "iopub.status.busy": "2025-04-07T17:51:30.504020Z",
     "iopub.status.idle": "2025-04-07T17:51:30.506065Z",
     "shell.execute_reply": "2025-04-07T17:51:30.505785Z"
    }
   },
   "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": "2025-04-07T17:51:30.507416Z",
     "iopub.status.busy": "2025-04-07T17:51:30.507335Z",
     "iopub.status.idle": "2025-04-07T17:51:30.508816Z",
     "shell.execute_reply": "2025-04-07T17:51:30.508554Z"
    }
   },
   "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": "2025-04-07T17:51:30.510078Z",
     "iopub.status.busy": "2025-04-07T17:51:30.509989Z",
     "iopub.status.idle": "2025-04-07T17:51:30.511481Z",
     "shell.execute_reply": "2025-04-07T17:51:30.511235Z"
    }
   },
   "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": "2025-04-07T17:51:30.512719Z",
     "iopub.status.busy": "2025-04-07T17:51:30.512626Z",
     "iopub.status.idle": "2025-04-07T17:51:30.514088Z",
     "shell.execute_reply": "2025-04-07T17:51:30.513850Z"
    }
   },
   "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": "2025-04-07T17:51:30.515334Z",
     "iopub.status.busy": "2025-04-07T17:51:30.515251Z",
     "iopub.status.idle": "2025-04-07T17:51:30.518525Z",
     "shell.execute_reply": "2025-04-07T17:51:30.518301Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Dec, Eric, et al. \"Centenarian clocks: epigenetic clocks for '\n",
      "             'validating claims of exceptional longevity.\" GeroScience (2023): '\n",
      "             '1-19.',\n",
      " 'clock_name': 'encen40',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1007/s11357-023-00731-7',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'Homo sapiens',\n",
      " 'version': None,\n",
      " 'year': 2023}\n",
      "reference_values: None\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: None\n",
      "postprocess_dependencies: None\n",
      "features: ['cg06437747', 'cg12140144', 'cg17804348', 'cg18025409', 'cg17489312', 'cg15952725', 'cg20822990', 'cg09195271', 'cg18107827', 'cg14333454', 'cg08169949', 'cg25410668', 'cg15554401', 'cg04299080', 'cg12065799', 'cg23093580', 'cg07388493', 'cg13806070', 'cg03664992', 'cg12671744', 'cg26881761', 'cg06784991', 'cg14614643', 'cg06836772', 'cg13786801', 'cg10628205', 'cg12079303', 'cg21912203', 'cg24871743', 'cg09118625']... [Total elements: 559]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=559, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [-2.098886489868164, 2.474569320678711, 0.13260692358016968, 1.0926762819290161, 2.006046772003174, -4.083102703094482, -5.88031530380249, 0.3561629354953766, -0.08976617455482483, 0.7154412865638733, 0.35456162691116333, 3.4960098266601562, 2.4149603843688965, -0.35807767510414124, -0.29285097122192383, -0.7337096929550171, -1.02739679813385, 3.951477289199829, 1.4296942949295044, -0.4479224681854248, -0.12719875574111938, 2.4558544158935547, -0.19818300008773804, -0.5594075322151184, -0.8976538181304932, -0.8460569381713867, -4.011434555053711, 2.74596905708313, 3.6343932151794434, 0.11721660196781158]... [Tensor of shape torch.Size([1, 559])]\n",
      "base_model.linear.bias: tensor([33.3240])\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": "2025-04-07T17:51:30.519903Z",
     "iopub.status.busy": "2025-04-07T17:51:30.519790Z",
     "iopub.status.idle": "2025-04-07T17:51:30.523577Z",
     "shell.execute_reply": "2025-04-07T17:51:30.523315Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[ 53.0407],\n",
       "        [109.0838],\n",
       "        [  9.5339],\n",
       "        [ 91.3573],\n",
       "        [ -9.1270],\n",
       "        [100.4752],\n",
       "        [ 43.2027],\n",
       "        [ 84.4988],\n",
       "        [-64.7365],\n",
       "        [110.1437]], 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": "2025-04-07T17:51:30.524882Z",
     "iopub.status.busy": "2025-04-07T17:51:30.524798Z",
     "iopub.status.idle": "2025-04-07T17:51:30.527390Z",
     "shell.execute_reply": "2025-04-07T17:51:30.527097Z"
    }
   },
   "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": "2025-04-07T17:51:30.528690Z",
     "iopub.status.busy": "2025-04-07T17:51:30.528605Z",
     "iopub.status.idle": "2025-04-07T17:51:30.535583Z",
     "shell.execute_reply": "2025-04-07T17:51:30.535294Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted folder: Centenarian-Clock\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": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}