{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "2f04eee0-5928-4e74-a754-6dc2e528810c",
   "metadata": {},
   "source": [
    "# HRSInCHPhenoAge"
   ]
  },
  {
   "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": "2025-04-07T17:51:58.091093Z",
     "iopub.status.busy": "2025-04-07T17:51:58.090949Z",
     "iopub.status.idle": "2025-04-07T17:51:59.474376Z",
     "shell.execute_reply": "2025-04-07T17:51:59.474003Z"
    }
   },
   "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": "2025-04-07T17:51:59.476255Z",
     "iopub.status.busy": "2025-04-07T17:51:59.475975Z",
     "iopub.status.idle": "2025-04-07T17:51:59.484397Z",
     "shell.execute_reply": "2025-04-07T17:51:59.484055Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class HRSInCHPhenoAge(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.HRSInCHPhenoAge)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "78536494-f1d9-44de-8583-c89a310d2307",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:51:59.485911Z",
     "iopub.status.busy": "2025-04-07T17:51:59.485792Z",
     "iopub.status.idle": "2025-04-07T17:51:59.487551Z",
     "shell.execute_reply": "2025-04-07T17:51:59.487294Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.HRSInCHPhenoAge()"
   ]
  },
  {
   "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": "2025-04-07T17:51:59.488947Z",
     "iopub.status.busy": "2025-04-07T17:51:59.488830Z",
     "iopub.status.idle": "2025-04-07T17:51:59.490913Z",
     "shell.execute_reply": "2025-04-07T17:51:59.490638Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"hrsinchphenoage\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: The study constructs clocks from DNA methylation measurements.\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: The analyzed samples and clock are human.\n",
    "model.metadata[\"year\"] = 2022\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Higgins-Chen, Albert T., et al. \\\"A computational solution for bolstering reliability of epigenetic clocks: implications for clinical trials and longitudinal tracking.\\\" Nature Aging 2 (2022): 644–661.\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1038/s43587-022-00248-2\"\n",
    "model.metadata[\"notes\"] = \"CpG-weighted HRS/InCHIANTI retraining of DNAm PhenoAge produced during the PC-clocks work; this implementation is not a principal-component clock.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"whole blood\"]  # Paper: The HRS and InCHIANTI methylation training samples were blood samples.\n",
    "model.metadata[\"predicts\"] = [\"phenotypic age\"]  # Paper: The function returns HRSInChPhenoAge.\n",
    "model.metadata[\"training_target\"] = [\"phenotypic age\"]  # Paper: The retrained model is explicitly identified as PhenoAge.\n",
    "model.metadata[\"unit\"] = [\"years\"]  # Paper: The returned PhenoAge estimate is on an age scale.\n",
    "model.metadata[\"model_type\"] = \"weighted linear score\"  # Paper: The function multiplies beta values by fitted CpG weights and adds an intercept.\n",
    "model.metadata[\"platform\"] = [\"Illumina 450K\", \"Illumina EPIC\"]  # Paper: HRS and InCHIANTI training data span EPIC and 450K methylation arrays.\n",
    "model.metadata[\"population\"] = \"adults\"  # Paper: The function identifies HRS and InCHIANTI as the retraining data.\n",
    "model.metadata[\"journal\"] = \"Nature Aging\"\n",
    "model.metadata[\"last_author\"] = \"Morgan E. Levine\"\n",
    "model.metadata[\"n_features\"] = 959\n",
    "model.metadata[\"citations\"] = 497\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": "fe6c8887-fb81-4f5e-88d8-32fcd6c9d86a",
   "metadata": {},
   "source": [
    "#### Download GitHub repository"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "1db3aa30-541d-4f78-b053-9868ce292ae8",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:51:59.492327Z",
     "iopub.status.busy": "2025-04-07T17:51:59.492225Z",
     "iopub.status.idle": "2025-04-07T17:52:01.855717Z",
     "shell.execute_reply": "2025-04-07T17:52:01.855405Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "github_url = \"https://github.com/MorganLevineLab/methylCIPHER.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": "96782e2a-9084-4e4d-a459-7e98d2ec160c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:52:01.857214Z",
     "iopub.status.busy": "2025-04-07T17:52:01.857096Z",
     "iopub.status.idle": "2025-04-07T17:52:01.861183Z",
     "shell.execute_reply": "2025-04-07T17:52:01.860929Z"
    }
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv('methylCIPHER/data-raw/HRSInChPhenoAge_CpG.csv')\n",
    "df['feature'] = df['CpG']\n",
    "df['coefficient'] = df['Weight']\n",
    "\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": "2025-04-07T17:52:01.862610Z",
     "iopub.status.busy": "2025-04-07T17:52:01.862513Z",
     "iopub.status.idle": "2025-04-07T17:52:01.864494Z",
     "shell.execute_reply": "2025-04-07T17:52:01.864262Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor(df['coefficient'].tolist()).unsqueeze(0)\n",
    "intercept = torch.tensor([52.8334080])"
   ]
  },
  {
   "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": "2025-04-07T17:52:01.865784Z",
     "iopub.status.busy": "2025-04-07T17:52:01.865698Z",
     "iopub.status.idle": "2025-04-07T17:52:01.867746Z",
     "shell.execute_reply": "2025-04-07T17:52:01.867487Z"
    }
   },
   "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": "2025-04-07T17:52:01.869057Z",
     "iopub.status.busy": "2025-04-07T17:52:01.868972Z",
     "iopub.status.idle": "2025-04-07T17:52:01.870406Z",
     "shell.execute_reply": "2025-04-07T17:52:01.870123Z"
    }
   },
   "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": "2025-04-07T17:52:01.871675Z",
     "iopub.status.busy": "2025-04-07T17:52:01.871592Z",
     "iopub.status.idle": "2025-04-07T17:52:01.872975Z",
     "shell.execute_reply": "2025-04-07T17:52:01.872728Z"
    }
   },
   "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": "2025-04-07T17:52:01.874278Z",
     "iopub.status.busy": "2025-04-07T17:52:01.874177Z",
     "iopub.status.idle": "2025-04-07T17:52:01.875664Z",
     "shell.execute_reply": "2025-04-07T17:52:01.875423Z"
    }
   },
   "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": "2025-04-07T17:52:01.877036Z",
     "iopub.status.busy": "2025-04-07T17:52:01.876945Z",
     "iopub.status.idle": "2025-04-07T17:52:01.880155Z",
     "shell.execute_reply": "2025-04-07T17:52:01.879913Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Higgins-Chen, Albert T., et al. \"A computational solution for '\n",
      "             'bolstering reliability of epigenetic clocks: Implications for '\n",
      "             'clinical trials and longitudinal tracking.\" Nature aging 2.7 '\n",
      "             '(2022): 644-661.',\n",
      " 'clock_name': 'hrsinchphenoage',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1038/s43587-022-00248-2',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'Homo sapiens',\n",
      " 'version': None,\n",
      " 'year': 2022}\n",
      "reference_values: None\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: None\n",
      "postprocess_dependencies: None\n",
      "features: ['cg00025138', 'cg00036347', 'cg00043599', 'cg00049440', 'cg00056497', 'cg00059225', 'cg00066239', 'cg00067518', 'cg00101154', 'cg00135293', 'cg00137209', 'cg00211115', 'cg00238295', 'cg00276799', 'cg00282953', 'cg00312921', 'cg00376639', 'cg00401091', 'cg00417823', 'cg00448560', 'cg00481159', 'cg00495693', 'cg00503840', 'cg00509996', 'cg00551910', 'cg00574958', 'cg00593462', 'cg00602811', 'cg00615241', 'cg00618626']... [Total elements: 959]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=959, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [-12.598388671875, 2.0095407962799072, 3.08774995803833, 1.5167790651321411, 0.20355011522769928, 1.68230140209198, -1.249173879623413, -0.8185797333717346, 0.4907846450805664, 0.5390154123306274, 15.449186325073242, -1.285083293914795, -0.7427912354469299, 1.5232256650924683, 0.5885316729545593, 2.078218936920166, 3.4780304431915283, -10.69495964050293, 2.9323976039886475, -5.428037166595459, 0.2791459858417511, -0.285178542137146, 0.9086608290672302, -0.1606019139289856, 1.7213571071624756, -5.501366138458252, 0.08092798292636871, -2.233879566192627, -1.4966527223587036, -4.973464488983154]... [Tensor of shape torch.Size([1, 959])]\n",
      "base_model.linear.bias: tensor([52.8334])\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": "2025-04-07T17:52:01.881643Z",
     "iopub.status.busy": "2025-04-07T17:52:01.881477Z",
     "iopub.status.idle": "2025-04-07T17:52:01.885640Z",
     "shell.execute_reply": "2025-04-07T17:52:01.885358Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[ 319.0174],\n",
       "        [ -70.3330],\n",
       "        [  49.5369],\n",
       "        [ -66.2511],\n",
       "        [ -99.2095],\n",
       "        [-165.9214],\n",
       "        [ 160.0792],\n",
       "        [ 293.2276],\n",
       "        [ 181.4062],\n",
       "        [-175.9353]], 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": "2025-04-07T17:52:01.886981Z",
     "iopub.status.busy": "2025-04-07T17:52:01.886898Z",
     "iopub.status.idle": "2025-04-07T17:52:01.889863Z",
     "shell.execute_reply": "2025-04-07T17:52:01.889621Z"
    }
   },
   "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": "2025-04-07T17:52:01.891168Z",
     "iopub.status.busy": "2025-04-07T17:52:01.891078Z",
     "iopub.status.idle": "2025-04-07T17:52:01.908268Z",
     "shell.execute_reply": "2025-04-07T17:52:01.907907Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted folder: methylCIPHER\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
}