{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "2f04eee0-5928-4e74-a754-6dc2e528810c",
   "metadata": {},
   "source": [
    "# PedBE"
   ]
  },
  {
   "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": "2024-03-05T21:22:59.472571Z",
     "iopub.status.busy": "2024-03-05T21:22:59.471909Z",
     "iopub.status.idle": "2024-03-05T21:23:07.530181Z",
     "shell.execute_reply": "2024-03-05T21:23:07.529871Z"
    }
   },
   "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": "2024-03-05T21:23:07.532131Z",
     "iopub.status.busy": "2024-03-05T21:23:07.531963Z",
     "iopub.status.idle": "2024-03-05T21:23:07.543752Z",
     "shell.execute_reply": "2024-03-05T21:23:07.543460Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class PedBE(pyagingModel):\n",
      "    def __init__(self):\n",
      "        super().__init__()\n",
      "\n",
      "    def preprocess(self, x):\n",
      "        return x\n",
      "\n",
      "    def postprocess(self, x):\n",
      "        \"\"\"\n",
      "        Applies an anti-logarithmic linear transformation to a PyTorch tensor.\n",
      "        \"\"\"\n",
      "        adult_age = 20\n",
      "\n",
      "        # Create a mask for negative and non-negative values\n",
      "        mask_negative = x < 0\n",
      "        mask_non_negative = ~mask_negative\n",
      "\n",
      "        # Initialize the result tensor\n",
      "        age_tensor = torch.empty_like(x)\n",
      "\n",
      "        # Exponential transformation for negative values\n",
      "        age_tensor[mask_negative] = (1 + adult_age) * torch.exp(x[mask_negative]) - 1\n",
      "\n",
      "        # Linear transformation for non-negative values\n",
      "        age_tensor[mask_non_negative] = (1 + adult_age) * x[\n",
      "            mask_non_negative\n",
      "        ] + adult_age\n",
      "\n",
      "        return age_tensor\n",
      "\n"
     ]
    }
   ],
   "source": [
    "def print_entire_class(cls):\n",
    "    source = inspect.getsource(cls)\n",
    "    print(source)\n",
    "\n",
    "print_entire_class(pya.models.PedBE)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "78536494-f1d9-44de-8583-c89a310d2307",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:23:07.545288Z",
     "iopub.status.busy": "2024-03-05T21:23:07.545179Z",
     "iopub.status.idle": "2024-03-05T21:23:07.547193Z",
     "shell.execute_reply": "2024-03-05T21:23:07.546706Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.PedBE()"
   ]
  },
  {
   "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": "2024-03-05T21:23:07.548978Z",
     "iopub.status.busy": "2024-03-05T21:23:07.548877Z",
     "iopub.status.idle": "2024-03-05T21:23:07.551163Z",
     "shell.execute_reply": "2024-03-05T21:23:07.550761Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"pedbe\"\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\"] = 2020\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"McEwen, Lisa M., et al. \\\"The PedBE clock accurately estimates DNA methylation age in pediatric buccal cells.\\\" Proceedings of the National Academy of Sciences 117 (2020): 23329–23335.\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1073/pnas.1820843116\"\n",
    "model.metadata[\"notes\"] = \"Pediatric chronological-age estimator developed specifically for noninvasive buccal epithelial-cell samples.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"buccal epithelium\"]  # Paper: The model was developed and tested in buccal epithelial cells.\n",
    "model.metadata[\"predicts\"] = [\"chronological age\"]  # Paper: PedBE estimates DNA methylation age in children.\n",
    "model.metadata[\"training_target\"] = [\"chronological age\"]  # Paper: Elastic-net regression selected CpGs predictive of participant age.\n",
    "model.metadata[\"unit\"] = [\"years\"]  # Paper: Age prediction errors and estimates are reported in years.\n",
    "model.metadata[\"model_type\"] = \"elastic net regression\"  # Paper: The clock was developed using elastic-net penalized regression.\n",
    "model.metadata[\"platform\"] = [\"Illumina 450K\", \"Illumina EPIC\"]  # Paper: The pooled pediatric buccal cohorts included 450K and EPIC methylation profiles.\n",
    "model.metadata[\"population\"] = \"children and adolescents\"  # Paper: The study included 1,721 healthy individuals aged 0 to 20 years.\n",
    "model.metadata[\"journal\"] = \"Proceedings of the National Academy of Sciences of the United States of America\"\n",
    "model.metadata[\"last_author\"] = \"Michael S. Kobor\"\n",
    "model.metadata[\"n_features\"] = 94\n",
    "model.metadata[\"citations\"] = 292\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": "f198b190-7f60-42a0-a23a-a88bbb60fb2f",
   "metadata": {},
   "source": [
    "#### Download GitHub repository"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "4274d190-b549-47b6-9c3e-b2cf90547bec",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:23:07.552952Z",
     "iopub.status.busy": "2024-03-05T21:23:07.552850Z",
     "iopub.status.idle": "2024-03-05T21:23:08.374551Z",
     "shell.execute_reply": "2024-03-05T21:23:08.374032Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "github_url = \"https://github.com/kobor-lab/Public-Scripts\"\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": "2024-03-05T21:23:08.377866Z",
     "iopub.status.busy": "2024-03-05T21:23:08.377678Z",
     "iopub.status.idle": "2024-03-05T21:23:08.384082Z",
     "shell.execute_reply": "2024-03-05T21:23:08.383667Z"
    }
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv('Public-Scripts/datcoefInteresting94.csv')\n",
    "df['feature'] = df['ID']\n",
    "df['coefficient'] = df['Coef']\n",
    "\n",
    "model.features = df['feature'][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": "2024-03-05T21:23:08.386513Z",
     "iopub.status.busy": "2024-03-05T21:23:08.386357Z",
     "iopub.status.idle": "2024-03-05T21:23:08.389361Z",
     "shell.execute_reply": "2024-03-05T21:23:08.388947Z"
    }
   },
   "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": "2024-03-05T21:23:08.391644Z",
     "iopub.status.busy": "2024-03-05T21:23:08.391500Z",
     "iopub.status.idle": "2024-03-05T21:23:08.394629Z",
     "shell.execute_reply": "2024-03-05T21:23:08.394230Z"
    }
   },
   "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": "2024-03-05T21:23:08.396857Z",
     "iopub.status.busy": "2024-03-05T21:23:08.396715Z",
     "iopub.status.idle": "2024-03-05T21:23:08.398669Z",
     "shell.execute_reply": "2024-03-05T21:23:08.398344Z"
    }
   },
   "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": "2024-03-05T21:23:08.400633Z",
     "iopub.status.busy": "2024-03-05T21:23:08.400512Z",
     "iopub.status.idle": "2024-03-05T21:23:08.402307Z",
     "shell.execute_reply": "2024-03-05T21:23:08.402009Z"
    }
   },
   "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": "2024-03-05T21:23:08.404008Z",
     "iopub.status.busy": "2024-03-05T21:23:08.403894Z",
     "iopub.status.idle": "2024-03-05T21:23:08.405684Z",
     "shell.execute_reply": "2024-03-05T21:23:08.405384Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = 'anti_log_linear'\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": "2024-03-05T21:23:08.407437Z",
     "iopub.status.busy": "2024-03-05T21:23:08.407323Z",
     "iopub.status.idle": "2024-03-05T21:23:08.410733Z",
     "shell.execute_reply": "2024-03-05T21:23:08.410407Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'McEwen, Lisa M., et al. \"The PedBE clock accurately estimates '\n",
      "             'DNA methylation age in pediatric buccal cells.\" Proceedings of '\n",
      "             'the National Academy of Sciences 117.38 (2020): 23329-23335.',\n",
      " 'clock_name': 'pedbe',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1073/pnas.1820843116',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'Homo sapiens',\n",
      " 'version': None,\n",
      " 'year': 2019}\n",
      "reference_values: None\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: 'anti_log_linear'\n",
      "postprocess_dependencies: None\n",
      "features: ['cg00059225', 'cg00085493', 'cg00095976', 'cg00609333', 'cg01287592', 'cg01704999', 'cg02209075', 'cg02310103', 'cg02426178', 'cg02821342', 'cg02980055', 'cg03020208', 'cg03466124', 'cg03473016', 'cg03493146', 'cg03555227', 'cg04221461', 'cg04452203', 'cg04937184', 'cg04948475', 'cg05024939', 'cg05271255', 'cg05923197', 'cg05928290', 'cg06048436', 'cg06144905', 'cg06198384', 'cg06416491', 'cg06430061', 'cg06455149']... [Total elements: 94]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=94, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [0.021960020065307617, -0.10039610415697098, 0.007872418500483036, 0.022823642939329147, -0.055414702743291855, -0.09757450968027115, 0.13820089399814606, -0.08401073515415192, -0.3583613932132721, -0.13026674091815948, -0.1387656182050705, 0.21038542687892914, -0.022311074659228325, 0.00015541094762738794, -0.1624089926481247, 0.6385841369628906, 0.03457474708557129, -0.026989279314875603, -0.05423707515001297, -0.0008215174311771989, 0.14885476231575012, -0.1249200701713562, 0.039291542023420334, 0.15890249609947205, -0.1548999398946762, 0.31524088978767395, 0.003525394480675459, -0.19241906702518463, -0.017204945906996727, 0.08637607842683792]... [Tensor of shape torch.Size([1, 94])]\n",
      "base_model.linear.bias: tensor([-2.0973])\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": "2024-03-05T21:23:08.412500Z",
     "iopub.status.busy": "2024-03-05T21:23:08.412403Z",
     "iopub.status.idle": "2024-03-05T21:23:08.416297Z",
     "shell.execute_reply": "2024-03-05T21:23:08.416029Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[-0.8260],\n",
       "        [-0.4025],\n",
       "        [ 2.6240],\n",
       "        [-0.3707],\n",
       "        [-0.8111],\n",
       "        [-0.4591],\n",
       "        [16.2847],\n",
       "        [ 8.2621],\n",
       "        [ 2.4227],\n",
       "        [ 4.0783]], dtype=torch.float64, grad_fn=<IndexPutBackward0>)"
      ]
     },
     "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": "2024-03-05T21:23:08.417959Z",
     "iopub.status.busy": "2024-03-05T21:23:08.417848Z",
     "iopub.status.idle": "2024-03-05T21:23:08.421051Z",
     "shell.execute_reply": "2024-03-05T21:23:08.420790Z"
    }
   },
   "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": "2024-03-05T21:23:08.422543Z",
     "iopub.status.busy": "2024-03-05T21:23:08.422459Z",
     "iopub.status.idle": "2024-03-05T21:23:08.428060Z",
     "shell.execute_reply": "2024-03-05T21:23:08.427839Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted folder: Public-Scripts\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
}