{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "2f04eee0-5928-4e74-a754-6dc2e528810c",
   "metadata": {},
   "source": [
    "# Hannum"
   ]
  },
  {
   "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": "2024-03-05T20:17:31.722332Z",
     "iopub.status.busy": "2024-03-05T20:17:31.721892Z",
     "iopub.status.idle": "2024-03-05T20:17:33.055109Z",
     "shell.execute_reply": "2024-03-05T20:17:33.054815Z"
    }
   },
   "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": "2024-03-05T20:17:33.057028Z",
     "iopub.status.busy": "2024-03-05T20:17:33.056855Z",
     "iopub.status.idle": "2024-03-05T20:17:33.064088Z",
     "shell.execute_reply": "2024-03-05T20:17:33.063821Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class Hannum(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.Hannum)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "78536494-f1d9-44de-8583-c89a310d2307",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T20:17:33.065646Z",
     "iopub.status.busy": "2024-03-05T20:17:33.065563Z",
     "iopub.status.idle": "2024-03-05T20:17:33.067132Z",
     "shell.execute_reply": "2024-03-05T20:17:33.066903Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.Hannum()"
   ]
  },
  {
   "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": "2024-03-05T20:17:33.068611Z",
     "iopub.status.busy": "2024-03-05T20:17:33.068525Z",
     "iopub.status.idle": "2024-03-05T20:17:33.070423Z",
     "shell.execute_reply": "2024-03-05T20:17:33.070185Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"hannum\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: The model uses genome-wide CpG methylation fractions.\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: The cohorts contained 656 human participants.\n",
    "model.metadata[\"year\"] = 2013\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Hannum, G., et al. “Genome-wide methylation profiles reveal quantitative views of human aging rates.” Molecular Cell 49(2), 359–367 (2013).\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1016/j.molcel.2012.10.016\"\n",
    "model.metadata[\"notes\"] = \"Whole-blood elastic-net predictor of chronological age from 71 CpG methylation fractions, derived in a 482-person primary cohort and validated in 174 independent participants.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"whole blood\"]  # Paper: Samples were taken as whole blood.\n",
    "model.metadata[\"predicts\"] = [\"chronological age\"]  # Paper: The model was built to predict participant age.\n",
    "model.metadata[\"training_target\"] = [\"chronological age\"]  # Paper: Age was the response in the predictive aging model.\n",
    "model.metadata[\"unit\"] = [\"years\"]  # Paper: The packaged linear model returns predicted age directly in years with no postprocessing transform.\n",
    "model.metadata[\"model_type\"] = \"elastic net regression\"  # Paper: The predictive model used penalized multivariate regression known as Elastic Net.\n",
    "model.metadata[\"platform\"] = [\"Illumina 450K\"]  # Paper: Whole-blood samples were processed on the Infinium HumanMethylation450 BeadChip.\n",
    "model.metadata[\"population\"] = \"adults\"  # Paper: Two cohorts totaled 656 participants aged 19–101 years, comprising 426 Caucasian and 230 Hispanic individuals.\n",
    "model.metadata[\"journal\"] = \"Molecular Cell\"\n",
    "model.metadata[\"last_author\"] = \"Kang Zhang\"\n",
    "model.metadata[\"n_features\"] = 71\n",
    "model.metadata[\"citations\"] = 4501\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": "2024-03-05T20:17:33.071913Z",
     "iopub.status.busy": "2024-03-05T20:17:33.071827Z",
     "iopub.status.idle": "2024-03-05T20:17:33.397023Z",
     "shell.execute_reply": "2024-03-05T20:17:33.396025Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "supplementary_url = \"https://ars.els-cdn.com/content/image/1-s2.0-S1097276512008933-mmc2.xlsx\"\n",
    "supplementary_file_name = \"coefficients.xlsx\"\n",
    "os.system(f\"curl -o {supplementary_file_name} {supplementary_url}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5035b180-3d1b-4432-8ebe-b9c92bd93a7f",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "793d7b24-b1ef-4dd2-ac26-079f7b67fba7",
   "metadata": {},
   "source": [
    "#### From Excel file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "110a5ded-d25f-4cef-8e84-4f51210dfc26",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T20:17:33.402355Z",
     "iopub.status.busy": "2024-03-05T20:17:33.402007Z",
     "iopub.status.idle": "2024-03-05T20:17:33.538525Z",
     "shell.execute_reply": "2024-03-05T20:17:33.538215Z"
    }
   },
   "outputs": [],
   "source": [
    "df = pd.read_excel('coefficients.xlsx')\n",
    "df['feature'] = df['Marker']\n",
    "df['coefficient'] = df['Coefficient']\n",
    "model.features = df['feature'].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": "2024-03-05T20:17:33.540314Z",
     "iopub.status.busy": "2024-03-05T20:17:33.540231Z",
     "iopub.status.idle": "2024-03-05T20:17:33.542091Z",
     "shell.execute_reply": "2024-03-05T20:17:33.541845Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor(df['coefficient'].tolist()).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": "2024-03-05T20:17:33.543627Z",
     "iopub.status.busy": "2024-03-05T20:17:33.543521Z",
     "iopub.status.idle": "2024-03-05T20:17:33.545468Z",
     "shell.execute_reply": "2024-03-05T20:17:33.545236Z"
    }
   },
   "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": "2024-03-05T20:17:33.546937Z",
     "iopub.status.busy": "2024-03-05T20:17:33.546846Z",
     "iopub.status.idle": "2024-03-05T20:17:33.548242Z",
     "shell.execute_reply": "2024-03-05T20:17:33.548028Z"
    }
   },
   "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": "2024-03-05T20:17:33.549643Z",
     "iopub.status.busy": "2024-03-05T20:17:33.549572Z",
     "iopub.status.idle": "2024-03-05T20:17:33.551035Z",
     "shell.execute_reply": "2024-03-05T20:17:33.550799Z"
    }
   },
   "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": "2024-03-05T20:17:33.552333Z",
     "iopub.status.busy": "2024-03-05T20:17:33.552263Z",
     "iopub.status.idle": "2024-03-05T20:17:33.553644Z",
     "shell.execute_reply": "2024-03-05T20:17:33.553416Z"
    }
   },
   "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": "2024-03-05T20:17:33.555024Z",
     "iopub.status.busy": "2024-03-05T20:17:33.554949Z",
     "iopub.status.idle": "2024-03-05T20:17:33.557262Z",
     "shell.execute_reply": "2024-03-05T20:17:33.557027Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': ('Hannum, Gregory, et al. \"Genome-wide methylation profiles '\n",
      "              'reveal quantitative views of human aging rates.\" Molecular cell '\n",
      "              '49.2 (2013): 359-367.',),\n",
      " 'clock_name': 'hannum',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1016/j.molcel.2012.10.016',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'Homo sapiens',\n",
      " 'version': None,\n",
      " 'year': 2013}\n",
      "reference_values: None\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: None\n",
      "postprocess_dependencies: None\n",
      "features: ['cg20822990', 'cg22512670', 'cg25410668', 'cg04400972', 'cg16054275', 'cg10501210', 'cg09809672', 'ch.2.30415474F', 'cg22158769', 'cg02085953', 'cg06639320', 'cg22454769', 'cg24079702', 'cg23606718', 'cg22016779', 'cg04474832', 'cg03607117', 'cg07553761', 'cg00481951', 'cg25478614', 'cg25428494', 'cg02650266', 'cg08234504', 'cg23500537', 'cg20052760', 'cg16867657', 'cg22736354', 'cg06493994', 'cg06685111', 'cg00486113']... [Total elements: 71]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=71, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [-15.699999809265137, 1.0499999523162842, 3.869999885559082, 9.619999885559082, -11.100000381469727, -6.460000038146973, -0.7400000095367432, 5.789999961853027, -2.059999942779541, 1.0199999809265137, 8.949999809265137, 4.849999904632568, 2.4800000190734863, 8.350000381469727, 1.7899999618530273, -7.099999904632568, 10.699999809265137, 3.7200000286102295, -2.7200000286102295, 4.010000228881836, -1.809999942779541, 10.199999809265137, -3.1600000858306885, 5.670000076293945, -12.600000381469727, 10.800000190734863, 4.420000076293945, 9.420000076293945, -13.100000381469727, -10.699999809265137]... [Tensor of shape torch.Size([1, 71])]\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": "2024-03-05T20:17:33.558774Z",
     "iopub.status.busy": "2024-03-05T20:17:33.558701Z",
     "iopub.status.idle": "2024-03-05T20:17:33.562205Z",
     "shell.execute_reply": "2024-03-05T20:17:33.561986Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[ 78.6234],\n",
       "        [  7.5513],\n",
       "        [172.7843],\n",
       "        [ 43.1732],\n",
       "        [145.3521],\n",
       "        [ 79.6871],\n",
       "        [ 75.0541],\n",
       "        [ 41.7890],\n",
       "        [-12.6555],\n",
       "        [-78.9716]], 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": "2024-03-05T20:17:33.563720Z",
     "iopub.status.busy": "2024-03-05T20:17:33.563633Z",
     "iopub.status.idle": "2024-03-05T20:17:33.565710Z",
     "shell.execute_reply": "2024-03-05T20:17:33.565467Z"
    }
   },
   "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": "2024-03-05T20:17:33.567125Z",
     "iopub.status.busy": "2024-03-05T20:17:33.567039Z",
     "iopub.status.idle": "2024-03-05T20:17:33.569966Z",
     "shell.execute_reply": "2024-03-05T20:17:33.569731Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted file: coefficients.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": "research",
   "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
}